From 67b886d290052dbf2bcfc876a5ae41a5fe461edf Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Thu, 21 Mar 2019 15:09:56 -0500 Subject: dma-buf: Remove leftover [un]map_atomic comments The map_atomic/unmap_atomic callbacks have been removed, remove the related comments. Fixes: f664a5269542 ("dma-buf: remove kmap_atomic interface") Signed-off-by: Andrew F. Davis Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20190321200957.16938-1-afd@ti.com --- include/linux/dma-buf.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 58725f890b5b..e4a8dab2bc54 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,11 +39,6 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @map_atomic: [optional] maps a page from the buffer into kernel address - * space, users may not block until the subsequent unmap call. - * This callback must not sleep. - * @unmap_atomic: [optional] unmaps a atomically mapped page from the buffer. - * This Callback must not sleep. * @map: [optional] maps a page from the buffer into kernel address space. * @unmap: [optional] unmaps a page from the buffer. * @vmap: [optional] creates a virtual mapping for the buffer into kernel -- cgit v1.2.3 From d5ae7712b7ffbb435e8f3d98f2123eff4734c77f Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Thu, 21 Mar 2019 15:09:57 -0500 Subject: dma-buf: Update [un]map documentation to match the other functions Other function have inline documentation, a couple still have theirs at the top of the structure, update the docs and move them inline. Signed-off-by: Andrew F. Davis Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20190321200957.16938-2-afd@ti.com --- include/linux/dma-buf.h | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index e4a8dab2bc54..a0bd071466fc 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,8 +39,6 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @map: [optional] maps a page from the buffer into kernel address space. - * @unmap: [optional] unmaps a page from the buffer. * @vmap: [optional] creates a virtual mapping for the buffer into kernel * address space. Same restrictions as for vmap and friends apply. * @vunmap: [optional] unmaps a vmap from the buffer @@ -200,8 +198,6 @@ struct dma_buf_ops { * to be restarted. */ int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); - void *(*map)(struct dma_buf *, unsigned long); - void (*unmap)(struct dma_buf *, unsigned long, void *); /** * @mmap: @@ -240,6 +236,31 @@ struct dma_buf_ops { */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); + /** + * @map: + * + * Maps a page from the buffer into kernel address space. The page is + * specified by offset into the buffer in PAGE_SIZE units. + * + * This callback is optional. + * + * Returns: + * + * Virtual address pointer where requested page can be accessed. NULL + * on error or when this function is unimplemented by the exporter. + */ + void *(*map)(struct dma_buf *, unsigned long); + + /** + * @unmap: + * + * Unmaps a page from the buffer. Page offset and address pointer should + * be the same as the one passed to and returned by matching call to map. + * + * This callback is optional. + */ + void (*unmap)(struct dma_buf *, unsigned long, void *); + void *(*vmap)(struct dma_buf *); void (*vunmap)(struct dma_buf *, void *vaddr); }; -- cgit v1.2.3 From 09ed79d6d75f06cc963a78f25463251b0a758dc7 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 7 May 2019 10:01:47 -0700 Subject: percpu_ref: introduce PERCPU_REF_ALLOW_REINIT flag In most cases percpu reference counters are not switched to the percpu mode after they reach the atomic mode. Some obvious exceptions are reference counters which are initialized into the atomic mode (using PERCPU_REF_INIT_ATOMIC and PERCPU_REF_INIT_DEAD flags), and there are few other exceptions. But in most cases there is no way back, and once the reference counter is switched to the atomic mode, there is no reason to wait for percpu_ref_exit() to release the percpu memory. Of course, the size of a single counter is not so big, but because it can pin the whole percpu block in memory, the memory footprint can be noticeable (e.g. on my 32 CPUs machine a percpu block is 8Mb large). To make releasing of the percpu memory as early as possible, let's introduce the PERCPU_REF_ALLOW_REINIT flag with the following semantics: it has to be set in order to switch a percpu reference counter to the percpu mode after the initialization. PERCPU_REF_INIT_ATOMIC and PERCPU_REF_INIT_DEAD flags will implicitly assume PERCPU_REF_ALLOW_REINIT. This patch doesn't introduce any functional change to avoid any regressions. It will be done later in the patchset after adjusting all call sites, which are reviving percpu counters. Signed-off-by: Roman Gushchin Acked-by: Tejun Heo Signed-off-by: Dennis Zhou --- include/linux/percpu-refcount.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b297cd1cd4f1..0f0240af8520 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -75,14 +75,21 @@ enum { * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. + * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with - * percpu_ref_reinit() before used. Implies INIT_ATOMIC. + * percpu_ref_reinit() before used. Implies INIT_ATOMIC and + * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, + + /* + * Allow switching from atomic mode to percpu mode. + */ + PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref { -- cgit v1.2.3 From 7d9ab9b6adffd9c474c1274acb5f6208f9a09cf3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 7 May 2019 10:01:50 -0700 Subject: percpu_ref: release percpu memory early without PERCPU_REF_ALLOW_REINIT Release percpu memory after finishing the switch to the atomic mode if only PERCPU_REF_ALLOW_REINIT isn't set. Signed-off-by: Roman Gushchin Acked-by: Tejun Heo Signed-off-by: Dennis Zhou --- include/linux/percpu-refcount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 0f0240af8520..7aef0abc194a 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -102,6 +102,7 @@ struct percpu_ref { percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; + bool allow_reinit:1; struct rcu_head rcu; }; -- cgit v1.2.3 From ec9964b4803300fb86f8e8fd9b421e59f7a71dc5 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 13 May 2019 09:56:34 +0200 Subject: Platform: OLPC: Move EC-specific functionality out from x86 Move the olpc-ec driver away from the X86 OLPC platform so that it could be used by the ARM based laptops too. Notably, the driver for the OLPC battery, which is also used on the ARM models, builds on this driver's interface. It is actually plaform independent: the OLPC EC commands with their argument and responses are mostly the same despite the delivery mechanism is different. Signed-off-by: Lubomir Rintel Acked-by: Pavel Machek Signed-off-by: Andy Shevchenko --- include/linux/olpc-ec.h | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index 79bdc6328c52..7fa3d27f7fee 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -16,14 +16,28 @@ #define EC_SCI_QUERY 0x84 #define EC_EXT_SCI_QUERY 0x85 +/* SCI source values */ +#define EC_SCI_SRC_EMPTY 0x00 +#define EC_SCI_SRC_GAME 0x01 +#define EC_SCI_SRC_BATTERY 0x02 +#define EC_SCI_SRC_BATSOC 0x04 +#define EC_SCI_SRC_BATERR 0x08 +#define EC_SCI_SRC_EBOOK 0x10 /* XO-1 only */ +#define EC_SCI_SRC_WLAN 0x20 /* XO-1 only */ +#define EC_SCI_SRC_ACPWR 0x40 +#define EC_SCI_SRC_BATCRIT 0x80 +#define EC_SCI_SRC_GPWAKE 0x100 /* XO-1.5 only */ +#define EC_SCI_SRC_ALL 0x1FF + struct platform_device; struct olpc_ec_driver { - int (*probe)(struct platform_device *); int (*suspend)(struct platform_device *); int (*resume)(struct platform_device *); int (*ec_cmd)(u8, u8 *, size_t, u8 *, size_t, void *); + + bool wakeup_available; }; #ifdef CONFIG_OLPC @@ -33,11 +47,27 @@ extern void olpc_ec_driver_register(struct olpc_ec_driver *drv, void *arg); extern int olpc_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen); +extern void olpc_ec_wakeup_set(u16 value); +extern void olpc_ec_wakeup_clear(u16 value); + +extern int olpc_ec_mask_write(u16 bits); +extern int olpc_ec_sci_query(u16 *sci_value); + +extern bool olpc_ec_wakeup_available(void); + #else static inline int olpc_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen) { return -ENODEV; } +static inline void olpc_ec_wakeup_set(u16 value) { } +static inline void olpc_ec_wakeup_clear(u16 value) { } + +static inline bool olpc_ec_wakeup_available(void) +{ + return false; +} + #endif /* CONFIG_OLPC */ #endif /* _LINUX_OLPC_EC_H */ -- cgit v1.2.3 From 8097548f3af9ec990169574ad9d874052b78bff8 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 13 May 2019 09:56:36 +0200 Subject: Platform: OLPC: Use BIT() and GENMASK() for event masks Just a cosmetic tidy-up. Signed-off-by: Lubomir Rintel Reviewed-by: Andy Shevchenko Signed-off-by: Andy Shevchenko --- include/linux/olpc-ec.h | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index 7fa3d27f7fee..f7b6a7eda232 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -2,6 +2,8 @@ #ifndef _LINUX_OLPC_EC_H #define _LINUX_OLPC_EC_H +#include + /* XO-1 EC commands */ #define EC_FIRMWARE_REV 0x08 #define EC_WRITE_SCI_MASK 0x1b @@ -17,17 +19,16 @@ #define EC_EXT_SCI_QUERY 0x85 /* SCI source values */ -#define EC_SCI_SRC_EMPTY 0x00 -#define EC_SCI_SRC_GAME 0x01 -#define EC_SCI_SRC_BATTERY 0x02 -#define EC_SCI_SRC_BATSOC 0x04 -#define EC_SCI_SRC_BATERR 0x08 -#define EC_SCI_SRC_EBOOK 0x10 /* XO-1 only */ -#define EC_SCI_SRC_WLAN 0x20 /* XO-1 only */ -#define EC_SCI_SRC_ACPWR 0x40 -#define EC_SCI_SRC_BATCRIT 0x80 -#define EC_SCI_SRC_GPWAKE 0x100 /* XO-1.5 only */ -#define EC_SCI_SRC_ALL 0x1FF +#define EC_SCI_SRC_GAME BIT(0) +#define EC_SCI_SRC_BATTERY BIT(1) +#define EC_SCI_SRC_BATSOC BIT(2) +#define EC_SCI_SRC_BATERR BIT(3) +#define EC_SCI_SRC_EBOOK BIT(4) /* XO-1 only */ +#define EC_SCI_SRC_WLAN BIT(5) /* XO-1 only */ +#define EC_SCI_SRC_ACPWR BIT(6) +#define EC_SCI_SRC_BATCRIT BIT(7) +#define EC_SCI_SRC_GPWAKE BIT(8) /* XO-1.5 only */ +#define EC_SCI_SRC_ALL GENMASK(8, 0) struct platform_device; -- cgit v1.2.3 From 0c3d931b3ab9efeea4948b5373c62095449d0101 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 13 May 2019 09:56:37 +0200 Subject: Platform: OLPC: Add XO-1.75 EC driver It's based off the driver from the OLPC kernel sources. Somewhat modernized and cleaned up, for better or worse. Modified to plug into the olpc-ec driver infrastructure (so that battery interface and debugfs could be reused) and the SPI slave framework. Signed-off-by: Lubomir Rintel Reviewed-by: Andy Shevchenko Signed-off-by: Andy Shevchenko --- include/linux/olpc-ec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index f7b6a7eda232..c4602364e909 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -41,7 +41,7 @@ struct olpc_ec_driver { bool wakeup_available; }; -#ifdef CONFIG_OLPC +#ifdef CONFIG_OLPC_EC extern void olpc_ec_driver_register(struct olpc_ec_driver *drv, void *arg); @@ -69,6 +69,6 @@ static inline bool olpc_ec_wakeup_available(void) return false; } -#endif /* CONFIG_OLPC */ +#endif /* CONFIG_OLPC_EC */ #endif /* _LINUX_OLPC_EC_H */ -- cgit v1.2.3 From 9a0f780958bbcb85604636fa340e2a1efaa4f432 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 13 May 2019 13:39:51 +0200 Subject: dmaengine: sudmac: remove unused driver SUDMAC driver was introduced in v3.10 but was never integrated for use by any platform. As it is unused remove it. Signed-off-by: Simon Horman Acked-by: Yoshihiro Shimoda Signed-off-by: Vinod Koul --- include/linux/sudmac.h | 52 -------------------------------------------------- 1 file changed, 52 deletions(-) delete mode 100644 include/linux/sudmac.h (limited to 'include/linux') diff --git a/include/linux/sudmac.h b/include/linux/sudmac.h deleted file mode 100644 index 377b8a5788fa..000000000000 --- a/include/linux/sudmac.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Header for the SUDMAC driver - * - * Copyright (C) 2013 Renesas Solutions Corp. - * - * This is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - */ -#ifndef SUDMAC_H -#define SUDMAC_H - -#include -#include -#include - -/* Used by slave DMA clients to request DMA to/from a specific peripheral */ -struct sudmac_slave { - struct shdma_slave shdma_slave; /* Set by the platform */ -}; - -/* - * Supplied by platforms to specify, how a DMA channel has to be configured for - * a certain peripheral - */ -struct sudmac_slave_config { - int slave_id; -}; - -struct sudmac_channel { - unsigned long offset; - unsigned long config; - unsigned long wait; /* The configuable range is 0 to 3 */ - unsigned long dint_end_bit; -}; - -struct sudmac_pdata { - const struct sudmac_slave_config *slave; - int slave_num; - const struct sudmac_channel *channel; - int channel_num; -}; - -/* Definitions for the sudmac_channel.config */ -#define SUDMAC_TX_BUFFER_MODE BIT(0) -#define SUDMAC_RX_END_MODE BIT(1) - -/* Definitions for the sudmac_channel.dint_end_bit */ -#define SUDMAC_DMA_BIT_CH0 BIT(0) -#define SUDMAC_DMA_BIT_CH1 BIT(1) - -#endif -- cgit v1.2.3 From 7e5f7bb08b8cefd3a7e8961861f47fe1f0e830d4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 May 2019 13:44:57 +0100 Subject: unexport simple_dname() Signed-off-by: Al Viro --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f14e587c5d5d..361305ddd75e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -291,7 +291,6 @@ static inline unsigned d_count(const struct dentry *dentry) */ extern __printf(4, 5) char *dynamic_dname(struct dentry *, char *, int, const char *, ...); -extern char *simple_dname(struct dentry *, char *, int); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); -- cgit v1.2.3 From f13e143e7444bffc53f5c2904aeed76646da69d6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 3 Jul 2018 16:42:26 +0200 Subject: dma-buf: start caching of sg_table objects v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To allow a smooth transition from pinning buffer objects to dynamic invalidation we first start to cache the sg_table for an attachment. v2: keep closer to the DRM implementation Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.kernel.org/patch/10943053/ --- include/linux/dma-buf.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index a0bd071466fc..8a327566d7f4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -44,6 +44,15 @@ struct dma_buf_attachment; * @vunmap: [optional] unmaps a vmap from the buffer */ struct dma_buf_ops { + /** + * @cache_sgt_mapping: + * + * If true the framework will cache the first mapping made for each + * attachment. This avoids creating mappings for attachments multiple + * times. + */ + bool cache_sgt_mapping; + /** * @attach: * @@ -323,6 +332,8 @@ struct dma_buf { * @dmabuf: buffer for this attachment. * @dev: device attached to the buffer. * @node: list of dma_buf_attachment. + * @sgt: cached mapping. + * @dir: direction of cached mapping. * @priv: exporter specific attachment data. * * This structure holds the attachment information between the dma_buf buffer @@ -338,6 +349,8 @@ struct dma_buf_attachment { struct dma_buf *dmabuf; struct device *dev; struct list_head node; + struct sg_table *sgt; + enum dma_data_direction dir; void *priv; }; -- cgit v1.2.3 From fbb5d0353c62d10c3699ec844d2d015a762952d7 Mon Sep 17 00:00:00 2001 From: Uma Shankar Date: Thu, 16 May 2019 19:40:06 +0530 Subject: drm: Add HDR source metadata property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a blob property to get HDR metadata information from userspace. This will be send as part of AVI Infoframe to panel. It also implements get() and set() functions for HDR output metadata property.The blob data is received from userspace and saved in connector state, the same is returned as blob in get property call to userspace. v2: Rebase and modified the metadata structure elements as per Ville's POC changes. v3: No Change v4: Addressed Shashank's review comments v5: Rebase. v6: Addressed Brian Starkey's review comments, defined new structure with header for dynamic metadata scalability. Merge get/set property functions for metadata in this patch. v7: Addressed Jonas Karlman review comments and defined separate structure for infoframe to better align with CTA 861.G spec. Added Shashank's RB. v8: Addressed Ville's review comments. Moved sink metadata structure out of uapi headers as suggested by Jonas Karlman. v9: Rebase and addressed Jonas Karlman review comments. v10: Addressed Ville's review comments, dropped the metdata_changed state variable as its not needed anymore. Signed-off-by: Uma Shankar Reviewed-by: Shashank Sharma Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/1558015817-12025-2-git-send-email-uma.shankar@intel.com --- include/linux/hdmi.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 927ad6451105..6780476dcbff 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -152,6 +152,16 @@ enum hdmi_content_type { HDMI_CONTENT_TYPE_GAME, }; +enum hdmi_metadata_type { + HDMI_STATIC_METADATA_TYPE1 = 1, +}; + +enum hdmi_eotf { + HDMI_EOTF_TRADITIONAL_GAMMA_SDR, + HDMI_EOTF_TRADITIONAL_GAMMA_HDR, + HDMI_EOTF_SMPTE_ST2084, +}; + struct hdmi_avi_infoframe { enum hdmi_infoframe_type type; unsigned char version; @@ -320,6 +330,22 @@ struct hdmi_vendor_infoframe { unsigned int s3d_ext_data; }; +/* HDR Metadata as per 861.G spec */ +struct hdr_static_metadata { + __u8 eotf; + __u8 metadata_type; + __u16 max_cll; + __u16 max_fall; + __u16 min_cll; +}; + +struct hdr_sink_metadata { + __u32 metadata_type; + union { + struct hdr_static_metadata hdmi_type1; + }; +}; + int hdmi_vendor_infoframe_init(struct hdmi_vendor_infoframe *frame); ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame, void *buffer, size_t size); -- cgit v1.2.3 From 2cdbfd66a82969770ce1a7032fb1e2155a08cee8 Mon Sep 17 00:00:00 2001 From: Uma Shankar Date: Thu, 16 May 2019 19:40:09 +0530 Subject: drm: Enable HDR infoframe support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enable Dynamic Range and Mastering Infoframe for HDR content, which is defined in CEA 861.3 spec. The metadata will be computed based on blending policy in userspace compositors and passed as a connector property blob to driver. The same will be sent as infoframe to panel which support HDR. Added the const version of infoframe for DRM metadata for HDR. v2: Rebase and added Ville's POC changes. v3: No Change v4: Addressed Shashank's review comments and merged the patch making drm infoframe function arguments as constant. v5: Rebase v6: Fixed checkpatch warnings with --strict option. Addressed Shashank's review comments and added his RB. v7: Addressed Brian Starkey's review comments. Merged 2 patches into one. v8: Addressed Jonas Karlman review comments. v9: Addressed Jonas Karlman review comments. v10: Addressed Ville's review comments. v11: Added BUILD_BUG_ON and sizeof instead of magic numbers as per Ville's comments. Signed-off-by: Uma Shankar Reviewed-by: Shashank Sharma Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/1558015817-12025-5-git-send-email-uma.shankar@intel.com --- include/linux/hdmi.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 6780476dcbff..bcf3c6c3499e 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -47,6 +47,7 @@ enum hdmi_infoframe_type { HDMI_INFOFRAME_TYPE_AVI = 0x82, HDMI_INFOFRAME_TYPE_SPD = 0x83, HDMI_INFOFRAME_TYPE_AUDIO = 0x84, + HDMI_INFOFRAME_TYPE_DRM = 0x87, }; #define HDMI_IEEE_OUI 0x000c03 @@ -55,6 +56,7 @@ enum hdmi_infoframe_type { #define HDMI_AVI_INFOFRAME_SIZE 13 #define HDMI_SPD_INFOFRAME_SIZE 25 #define HDMI_AUDIO_INFOFRAME_SIZE 10 +#define HDMI_DRM_INFOFRAME_SIZE 26 #define HDMI_INFOFRAME_SIZE(type) \ (HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE) @@ -185,12 +187,37 @@ struct hdmi_avi_infoframe { unsigned short right_bar; }; +/* DRM Infoframe as per CTA 861.G spec */ +struct hdmi_drm_infoframe { + enum hdmi_infoframe_type type; + unsigned char version; + unsigned char length; + enum hdmi_eotf eotf; + enum hdmi_metadata_type metadata_type; + struct { + u16 x, y; + } display_primaries[3]; + struct { + u16 x, y; + } white_point; + u16 max_display_mastering_luminance; + u16 min_display_mastering_luminance; + u16 max_cll; + u16 max_fall; +}; + int hdmi_avi_infoframe_init(struct hdmi_avi_infoframe *frame); ssize_t hdmi_avi_infoframe_pack(struct hdmi_avi_infoframe *frame, void *buffer, size_t size); ssize_t hdmi_avi_infoframe_pack_only(const struct hdmi_avi_infoframe *frame, void *buffer, size_t size); int hdmi_avi_infoframe_check(struct hdmi_avi_infoframe *frame); +int hdmi_drm_infoframe_init(struct hdmi_drm_infoframe *frame); +ssize_t hdmi_drm_infoframe_pack(struct hdmi_drm_infoframe *frame, void *buffer, + size_t size); +ssize_t hdmi_drm_infoframe_pack_only(const struct hdmi_drm_infoframe *frame, + void *buffer, size_t size); +int hdmi_drm_infoframe_check(struct hdmi_drm_infoframe *frame); enum hdmi_spd_sdi { HDMI_SPD_SDI_UNKNOWN, @@ -381,6 +408,7 @@ union hdmi_infoframe { struct hdmi_spd_infoframe spd; union hdmi_vendor_any_infoframe vendor; struct hdmi_audio_infoframe audio; + struct hdmi_drm_infoframe drm; }; ssize_t hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, -- cgit v1.2.3 From b5e3eed1eeb363c148e2935d9d3c12c30a280de6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 16 May 2019 19:40:12 +0530 Subject: drm: Add HLG EOTF MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ADD HLG EOTF to the list of EOTF transfer functions supported. Hybrid Log-Gamma (HLG) is a high dynamic range (HDR) standard. HLG defines a nonlinear transfer function in which the lower half of the signal values use a gamma curve and the upper half of the signal values use a logarithmic curve. v2: Rebase v3: Fixed a warning message v4: Addressed Shashank's review comments v5: Addressed Jonas Karlman's review comment and dropped the i915 tag from header. Signed-off-by: Ville Syrjälä Signed-off-by: Uma Shankar Reviewed-by: Shashank Sharma Link: https://patchwork.freedesktop.org/patch/msgid/1558015817-12025-8-git-send-email-uma.shankar@intel.com --- include/linux/hdmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index bcf3c6c3499e..ee55ba589cdc 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -162,6 +162,7 @@ enum hdmi_eotf { HDMI_EOTF_TRADITIONAL_GAMMA_SDR, HDMI_EOTF_TRADITIONAL_GAMMA_HDR, HDMI_EOTF_SMPTE_ST2084, + HDMI_EOTF_BT_2100_HLG, }; struct hdmi_avi_infoframe { -- cgit v1.2.3 From c08e7e4c8a6f04e01d16117eb4a0077059ec2cd4 Mon Sep 17 00:00:00 2001 From: Guillaume La Roque Date: Tue, 14 May 2019 10:26:48 +0200 Subject: pinctrl: generic: add new 'drive-strength-microamp' property support Add drive-strength-microamp property support to allow drive strength in uA Signed-off-by: Guillaume La Roque Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 6c0680641108..72d06d6a3099 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -55,6 +55,8 @@ * push-pull mode, the argument is ignored. * @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current * passed as argument. The argument is in mA. + * @PIN_CONFIG_DRIVE_STRENGTH_UA: the pin will sink or source at most the current + * passed as argument. The argument is in uA. * @PIN_CONFIG_INPUT_DEBOUNCE: this will configure the pin to debounce mode, * which means it will wait for signals to settle when reading inputs. The * argument gives the debounce time in usecs. Setting the @@ -112,6 +114,7 @@ enum pin_config_param { PIN_CONFIG_DRIVE_OPEN_SOURCE, PIN_CONFIG_DRIVE_PUSH_PULL, PIN_CONFIG_DRIVE_STRENGTH, + PIN_CONFIG_DRIVE_STRENGTH_UA, PIN_CONFIG_INPUT_DEBOUNCE, PIN_CONFIG_INPUT_ENABLE, PIN_CONFIG_INPUT_SCHMITT, -- cgit v1.2.3 From 036f394dd77f8117346874151793ec38967d843f Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Wed, 22 May 2019 17:29:24 +0200 Subject: pinctrl: Enable device link creation for pin control A pin controller may want to create a link between itself and its clients to be sure of suspend/resume call ordering. Introduce link_consumers field in pinctrl_desc structure to let pinctrl core knows that controller expect to create a link. Signed-off-by: Benjamin Gaignard [Renamed create_link to link_consumers] Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinctrl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 8f5dbb84547a..2744113f1024 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -125,6 +125,10 @@ struct pinctrl_ops { * the hardware description * @custom_conf_items: Information how to print @params in debugfs, must be * the same size as the @custom_params, i.e. @num_custom_params + * @link_consumers: If true create a device link between pinctrl and its + * consumers (i.e. the devices requesting pin control states). This is + * sometimes necessary to ascertain the right suspend/resume order for + * example. */ struct pinctrl_desc { const char *name; @@ -139,6 +143,7 @@ struct pinctrl_desc { const struct pinconf_generic_params *custom_params; const struct pin_config_item *custom_conf_items; #endif + bool link_consumers; }; /* External interface to pin controller */ -- cgit v1.2.3 From 59fcdce425b7c947ccea03a16e393af9bb4d6262 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 23 May 2019 17:05:59 -0700 Subject: clk: Remove ifdef for COMMON_CLK in clk-provider.h This ifdef has been there since the beginning of this file, but it doesn't really seem to serve any purpose besides obfuscating the struct definitions and #defines here from compilation units that include it. Let's always expose these function prototypes and struct definitions so that code can inspect clk providers without needing to have CONFIG_COMMON_CLK enabled. Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index bb6118f79784..3bced2ec9f26 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -9,8 +9,6 @@ #include #include -#ifdef CONFIG_COMMON_CLK - /* * flags used across common struct clk. these flags should only affect the * top-level framework. custom flags for dealing with hardware specifics @@ -1019,5 +1017,4 @@ static inline int of_clk_detect_critical(struct device_node *np, int index, void clk_gate_restore_context(struct clk_hw *hw); -#endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3 From 30d5a945743cd05ec5c847f2e38c2fbda5e00944 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 23 May 2019 17:11:57 -0700 Subject: clk: Unexport __clk_of_table This symbol doesn't need to be exported to clk providers anymore. Originally, it was hidden inside clk.c, but then OMAP needed to get access to it in commit 819b4861c18d ("CLK: ti: add init support for clock IP blocks"), but eventually that code also changed in commit c08ee14cc663 ("clk: ti: change clock init to use generic of_clk_init") and we were left with this exported. Move this back into clk.c so that it isn't exposed anymore. Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 3bced2ec9f26..9ba000e3a50d 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -865,8 +865,6 @@ static inline long divider_ro_round_rate(struct clk_hw *hw, unsigned long rate, */ unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate); -struct of_device_id; - struct clk_onecell_data { struct clk **clks; unsigned int clk_num; @@ -877,8 +875,6 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -extern struct of_device_id __clk_of_table; - #define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) /* -- cgit v1.2.3 From 1f58bb18f6f28d1df0b7144d90bc90ee5672416d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 May 2019 13:44:57 +0100 Subject: mount_pseudo(): drop 'name' argument, switch to d_make_root() Once upon a time we used to set ->d_name of e.g. pipefs root so that d_path() on pipes would work. These days it's completely pointless - dentries of pipes are not even connected to pipefs root. However, mount_pseudo() had set the root dentry name (passed as the second argument) and callers kept inventing names to pass to it. Including those that didn't *have* any non-root dentries to start with... All of that had been pointless for about 8 years now; it's time to get rid of that cargo-culting... Signed-off-by: Al Viro --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f7fdfe93e25d..b06251dd429f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2257,18 +2257,18 @@ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); -extern struct dentry *mount_pseudo_xattr(struct file_system_type *, char *, +extern struct dentry *mount_pseudo_xattr(struct file_system_type *, const struct super_operations *ops, const struct xattr_handler **xattr, const struct dentry_operations *dops, unsigned long); static inline struct dentry * -mount_pseudo(struct file_system_type *fs_type, char *name, +mount_pseudo(struct file_system_type *fs_type, const struct super_operations *ops, const struct dentry_operations *dops, unsigned long magic) { - return mount_pseudo_xattr(fs_type, name, ops, NULL, dops, magic); + return mount_pseudo_xattr(fs_type, ops, NULL, dops, magic); } /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -- cgit v1.2.3 From bb7b6b2bbdb827e68cd506c8f5e3ba13215cccb2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Mar 2019 16:38:28 +0000 Subject: vfs: Kill mount_ns() Kill mount_ns() as it has been replaced by vfs_get_super() in the new mount API. Signed-off-by: David Howells cc: linux-fsdevel@vger.kernel.org Signed-off-by: Al Viro --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b06251dd429f..790342cf4df9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2206,9 +2206,6 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -extern struct dentry *mount_ns(struct file_system_type *fs_type, - int flags, void *data, void *ns, struct user_namespace *user_ns, - int (*fill_super)(struct super_block *, void *, int)); #ifdef CONFIG_BLOCK extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, -- cgit v1.2.3 From c80fa7c8301c10ad10d997b9e86b4aeac5923b3e Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Mar 2019 16:38:23 +0000 Subject: vfs: Provide sb->s_iflags settings in fs_context struct Provide a field in the fs_context struct through which bits in the sb->s_iflags superblock field can be set. Signed-off-by: David Howells cc: linux-fsdevel@vger.kernel.org --- include/linux/fs_context.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 1f966670c8dc..c995b852ba40 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -103,6 +103,7 @@ struct fs_context { void *s_fs_info; /* Proposed s_fs_info */ unsigned int sb_flags; /* Proposed superblock flags (SB_*) */ unsigned int sb_flags_mask; /* Superblock flags that were changed */ + unsigned int s_iflags; /* OR'd with sb->s_iflags */ unsigned int lsm_flags; /* Information flags from the fs to the LSM */ enum fs_context_purpose purpose:8; enum fs_context_phase phase:8; /* The phase the context is in */ -- cgit v1.2.3 From 31d6d5ce53400d6dc58e29ddd8dc184b3ba89d66 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Mar 2019 16:38:23 +0000 Subject: vfs: Provide a mount_pseudo-replacement for the new mount API Provide a function, init_pseudo(), that provides a common infrastructure for converting pseudo-filesystems that can never be mountable. [AV: once all users of mount_pseudo_xattr() get converted, it will be folded into pseudo_fs_get_tree()] Signed-off-by: David Howells cc: linux-fsdevel@vger.kernel.org --- include/linux/pseudo_fs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/pseudo_fs.h (limited to 'include/linux') diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h new file mode 100644 index 000000000000..eceda1d1407a --- /dev/null +++ b/include/linux/pseudo_fs.h @@ -0,0 +1,16 @@ +#ifndef __LINUX_PSEUDO_FS__ +#define __LINUX_PSEUDO_FS__ + +#include + +struct pseudo_fs_context { + const struct super_operations *ops; + const struct xattr_handler **xattr; + const struct dentry_operations *dops; + unsigned long magic; +}; + +struct pseudo_fs_context *init_pseudo(struct fs_context *fc, + unsigned long magic); + +#endif -- cgit v1.2.3 From 8d9e46d80777b484f8f0945c317ad618224d7811 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 11 May 2019 11:43:59 -0400 Subject: fold mount_pseudo_xattr() into pseudo_fs_get_tree() ... now that all other callers are gone Signed-off-by: Al Viro --- include/linux/fs.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 790342cf4df9..d625acabbfcf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2254,19 +2254,6 @@ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); -extern struct dentry *mount_pseudo_xattr(struct file_system_type *, - const struct super_operations *ops, - const struct xattr_handler **xattr, - const struct dentry_operations *dops, - unsigned long); - -static inline struct dentry * -mount_pseudo(struct file_system_type *fs_type, - const struct super_operations *ops, - const struct dentry_operations *dops, unsigned long magic) -{ - return mount_pseudo_xattr(fs_type, ops, NULL, dops, magic); -} /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ -- cgit v1.2.3 From 023d066a0d0a87696c04b0de2ceae53063d0b655 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Mar 2019 16:38:28 +0000 Subject: vfs: Kill sget_userns() Kill sget_userns(), folding it into sget() as that's the only remaining user. Signed-off-by: David Howells cc: linux-fsdevel@vger.kernel.org --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d625acabbfcf..71421856ff2c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2245,11 +2245,6 @@ void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); -struct super_block *sget_userns(struct file_system_type *type, - int (*test)(struct super_block *,void *), - int (*set)(struct super_block *,void *), - int flags, struct user_namespace *user_ns, - void *data); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), -- cgit v1.2.3 From 7375dca1647fa978310f2d706ddbff537f72110b Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 20 May 2019 09:26:24 -0400 Subject: ftrace: Make enable and update parameters bool when applicable The code modification functions have "enable" and "update" variables that are sometimes "int" but used as "bool". Remove the ambiguity and make them "bool" when they are only used for true or false values. Link: http://lkml.kernel.org/r/e1429923d9eda92a3cf5ee9e33c7eacce539781d.1558115654.git.naveen.n.rao@linux.vnet.ibm.com Reported-by: "Naveen N. Rao" Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 25e2995d4a4c..8a8cb3c401b2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -427,8 +427,8 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter); iter = ftrace_rec_iter_next(iter)) -int ftrace_update_record(struct dyn_ftrace *rec, int enable); -int ftrace_test_record(struct dyn_ftrace *rec, int enable); +int ftrace_update_record(struct dyn_ftrace *rec, bool enable); +int ftrace_test_record(struct dyn_ftrace *rec, bool enable); void ftrace_run_stop_machine(int command); unsigned long ftrace_location(unsigned long ip); unsigned long ftrace_location_range(unsigned long start, unsigned long end); -- cgit v1.2.3 From 2d8d8fac3b4eab035dcd0068e1f5a746a697fbb3 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 15 May 2019 14:38:06 +0900 Subject: x86/uaccess: Allow access_ok() in irq context if pagefault_disabled WARN_ON_IN_IRQ() assumes that the access_ok() and following user memory access can sleep. But this assumption is not always correct; when the pagefault is disabled, following memory access will just returns -EFAULT and never sleep. Add pagefault_disabled() check in WARN_ON_ONCE() so that it can ignore the case we call it with disabling pagefault. For this purpose, this modified pagefault_disabled() as an inline function. Link: http://lkml.kernel.org/r/155789868664.26965.7932665824135793317.stgit@devnote2 Acked-by: Ingo Molnar Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/uaccess.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 2b70130af585..5a43ef7db492 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -203,7 +203,10 @@ static inline void pagefault_enable(void) /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ -#define pagefault_disabled() (current->pagefault_disabled != 0) +static inline bool pagefault_disabled(void) +{ + return current->pagefault_disabled != 0; +} /* * The pagefault handler is in general disabled by pagefault_disable() or -- cgit v1.2.3 From 3d7081822f7f9eab867d9bcc8fd635208ec438e0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 15 May 2019 14:38:18 +0900 Subject: uaccess: Add non-pagefault user-space read functions Add probe_user_read(), strncpy_from_unsafe_user() and strnlen_unsafe_user() which allows caller to access user-space in IRQ context. Current probe_kernel_read() and strncpy_from_unsafe() are not available for user-space memory, because it sets KERNEL_DS while accessing data. On some arch, user address space and kernel address space can be co-exist, but others can not. In that case, setting KERNEL_DS means given address is treated as a kernel address space. Also strnlen_user() is only available from user context since it can sleep if pagefault is enabled. To access user-space memory without pagefault, we need these new functions which sets USER_DS while accessing the data. Link: http://lkml.kernel.org/r/155789869802.26965.4940338412595759063.stgit@devnote2 Acked-by: Ingo Molnar Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/uaccess.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 5a43ef7db492..9c435c3f2105 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -242,6 +242,17 @@ static inline unsigned long __copy_from_user_inatomic_nocache(void *to, extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); +/* + * probe_user_read(): safely attempt to read from a location in user space + * @dst: pointer to the buffer that shall take the data + * @src: address to read from + * @size: size of the data chunk + * + * Safely read from address @src to the buffer at @dst. If a kernel fault + * happens, handle that and return -EFAULT. + */ +extern long probe_user_read(void *dst, const void __user *src, size_t size); + /* * probe_kernel_write(): safely attempt to write to a location * @dst: address to write to @@ -255,6 +266,9 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); +extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, + long count); +extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); /** * probe_kernel_address(): safely attempt to read from a location -- cgit v1.2.3 From 87a90956eeab260a469a51897bfda27b28adf67d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 22 May 2019 17:27:44 +0900 Subject: uaccess: Add a prototype of non-static __probe_user_read() Declare a prototype of non-static __probe_user_read() as same as __probe_kernel_read() at uaccess.h. Reported-by: kbuild test robot Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/uaccess.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 9c435c3f2105..34a038563d97 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -252,6 +252,7 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size); * happens, handle that and return -EFAULT. */ extern long probe_user_read(void *dst, const void __user *src, size_t size); +extern long __probe_user_read(void *dst, const void __user *src, size_t size); /* * probe_kernel_write(): safely attempt to write to a location -- cgit v1.2.3 From f5151311c3f37f6edc85b2253ccf6d3e2a4c4c26 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 20 May 2019 19:32:14 +0800 Subject: dmaengine: Add matching device node validation in __dma_request_channel() When user try to request one DMA channel by __dma_request_channel(), it won't validate if it is the correct DMA device to request, that will lead each DMA engine driver to validate the correct device node in their filter function if it is necessary. Thus we can add the matching device node validation in the DMA engine core, to remove all of device node validation in the drivers. Tested-by: Peter Ujfalusi Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index d49ec5c31944..504085b2bf21 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1314,7 +1314,8 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, - dma_filter_fn fn, void *fn_param); + dma_filter_fn fn, void *fn_param, + struct device_node *np); struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); struct dma_chan *dma_request_chan(struct device *dev, const char *name); @@ -1339,7 +1340,9 @@ static inline void dma_issue_pending_all(void) { } static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, - dma_filter_fn fn, void *fn_param) + dma_filter_fn fn, + void *fn_param, + struct device_node *np) { return NULL; } @@ -1411,7 +1414,8 @@ void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); struct dma_chan *dma_get_any_slave_channel(struct dma_device *device); -#define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) +#define dma_request_channel(mask, x, y) \ + __dma_request_channel(&(mask), x, y, NULL) #define dma_request_slave_channel_compat(mask, x, y, dev, name) \ __dma_request_slave_channel_compat(&(mask), x, y, dev, name) @@ -1429,6 +1433,6 @@ static inline struct dma_chan if (!fn || !fn_param) return NULL; - return __dma_request_channel(mask, fn, fn_param); + return __dma_request_channel(mask, fn, fn_param, NULL); } #endif /* DMAENGINE_H */ -- cgit v1.2.3 From 990c0b53bf6599a9c9c7df1529dde681dee6cf64 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 20 May 2019 19:32:16 +0800 Subject: dmaengine: imx-sdma: Let the core do the device node validation Let the DMA engine core do the device node validation instead of drivers. Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-imx.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h index 9daea8d42a10..7d964e787299 100644 --- a/include/linux/platform_data/dma-imx.h +++ b/include/linux/platform_data/dma-imx.h @@ -55,7 +55,6 @@ struct imx_dma_data { int dma_request2; /* secondary DMA request line */ enum sdma_peripheral_type peripheral_type; int priority; - struct device_node *of_node; }; static inline int imx_dma_is_ipu(struct dma_chan *chan) -- cgit v1.2.3 From d27ac2e02bf256d4e824e7c1e1e1afa2b96cefcc Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 27 May 2019 09:55:16 +0300 Subject: include: fpga: adi-axi-common.h: add common regs & defs header The AXI HDL cores provided for Analog Devices reference designs all share some common base registers (e.g. version register at address 0x00). To reduce duplication for this, a common header is added to define these registers as well as bitfields & macros to work with these registers. Signed-off-by: Alexandru Ardelean Signed-off-by: Vinod Koul --- include/linux/fpga/adi-axi-common.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/fpga/adi-axi-common.h (limited to 'include/linux') diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h new file mode 100644 index 000000000000..7fc95d5c95bb --- /dev/null +++ b/include/linux/fpga/adi-axi-common.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Analog Devices AXI common registers & definitions + * + * Copyright 2019 Analog Devices Inc. + * + * https://wiki.analog.com/resources/fpga/docs/axi_ip + * https://wiki.analog.com/resources/fpga/docs/hdl/regmap + */ + +#ifndef ADI_AXI_COMMON_H_ +#define ADI_AXI_COMMON_H_ + +#define ADI_AXI_REG_VERSION 0x0000 + +#define ADI_AXI_PCORE_VER(major, minor, patch) \ + (((major) << 16) | ((minor) << 8) | (patch)) + +#endif /* ADI_AXI_COMMON_H_ */ -- cgit v1.2.3 From 153969fd952d81ab8f57574f9be1a90b0a0fa791 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 21 May 2019 03:38:25 +0200 Subject: ARM: versatile: Drop CLCD platform data The Versatile family no longer makes any use of the CLCD platform data, we have moved over all users to the DRM driver that has built-in handling of the displays. Delete the old auxdata. Signed-off-by: Linus Walleij --- include/linux/platform_data/video-clcd-versatile.h | 28 ---------------------- 1 file changed, 28 deletions(-) delete mode 100644 include/linux/platform_data/video-clcd-versatile.h (limited to 'include/linux') diff --git a/include/linux/platform_data/video-clcd-versatile.h b/include/linux/platform_data/video-clcd-versatile.h deleted file mode 100644 index 305ebaec3afd..000000000000 --- a/include/linux/platform_data/video-clcd-versatile.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PLAT_CLCD_H -#define PLAT_CLCD_H - -#ifdef CONFIG_PLAT_VERSATILE_CLCD -struct clcd_panel *versatile_clcd_get_panel(const char *); -int versatile_clcd_setup_dma(struct clcd_fb *, unsigned long); -int versatile_clcd_mmap_dma(struct clcd_fb *, struct vm_area_struct *); -void versatile_clcd_remove_dma(struct clcd_fb *); -#else -static inline struct clcd_panel *versatile_clcd_get_panel(const char *s) -{ - return NULL; -} -static inline int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize) -{ - return -ENODEV; -} -static inline int versatile_clcd_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vm) -{ - return -ENODEV; -} -static inline void versatile_clcd_remove_dma(struct clcd_fb *fb) -{ -} -#endif - -#endif -- cgit v1.2.3 From 2b2f7def058a5386838ef4dba70a860285f79e66 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 27 May 2019 04:51:53 -0700 Subject: bus: ti-sysc: Add support for missing clockdomain handling We need to let ti-sysc driver manage clockdomain autoidle for the duration of of reset, enable and idle. And we need to do it before we enable the clock and after we disable it. Currently we are still relying on platform callbacks indirectly managing clockdomain autoidle. But I noticed that for device tree only probed drivers it now happens only after we enabling the clocks and before we disable the clocks, while it should be the other way around. So far I have not noticed any issues with this though. Let's add new ti_sysc_clkdm_deny_idle() and ti_sysc_clkdm_allow_idle() functions for ti-sysc driver to use to manage clockdomains directly via platform data callbacks. Note that we can implement the clockdomain functions in pdata-quirks.c as for probing devices without "ti,hwmods" custom property we don't need to use the other platform data callbacks. Let's do this in one patch as there's is still an unlikely chance we may need to apply this as a fix for v5.2 for dropping legacy platform data for some devices. We also do have the option of adding back the platform data if needed in case of trouble. Tested-by: Keerthy Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 9256c0305968..6626fd31e309 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -19,6 +19,7 @@ enum ti_sysc_module_type { struct ti_sysc_cookie { void *data; + void *clkdm; }; /** @@ -125,9 +126,16 @@ struct ti_sysc_module_data { }; struct device; +struct clk; struct ti_sysc_platform_data { struct of_dev_auxdata *auxdata; + int (*init_clockdomain)(struct device *dev, struct clk *fck, + struct clk *ick, struct ti_sysc_cookie *cookie); + void (*clkdm_deny_idle)(struct device *dev, + const struct ti_sysc_cookie *cookie); + void (*clkdm_allow_idle)(struct device *dev, + const struct ti_sysc_cookie *cookie); int (*init_module)(struct device *dev, const struct ti_sysc_module_data *data, struct ti_sysc_cookie *cookie); -- cgit v1.2.3 From e0db94fe87dacd72be0699adcc29e321db7f1689 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 27 May 2019 04:51:53 -0700 Subject: bus: ti-sysc: Make OCP reset work for sysstatus and sysconfig reset bits We've had minimal OCP softreset support in ti-sysc interconnect target module driver only used for MCAN driver so far. But it turns out that MCAN has the sysstatus register resetdone bit inverted compared to most other modules. Let's make OCP softreset work for other typical cases with reset status in sysstatus or sysconfig register so we can use the new functions for sysc_enable_module() and sysc_disable_module() without "ti,hwmods" property in the following patches. Tested-by: Keerthy Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 6626fd31e309..8822e99ff813 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -47,6 +47,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSS_QUIRK_RESETDONE_INVERTED BIT(14) #define SYSC_QUIRK_SWSUP_MSTANDBY BIT(13) #define SYSC_QUIRK_SWSUP_SIDLE_ACT BIT(12) #define SYSC_QUIRK_SWSUP_SIDLE BIT(11) -- cgit v1.2.3 From 229b4e0728e0a6ddca2645e73696d5b104fbbbfb Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 14 May 2019 22:47:24 +0800 Subject: Documentation: PCI: convert pci.txt to reST Convert plain text documentation to reStructuredText format and add it to Sphinx TOC tree. No essential content change. Move the description of struct pci_driver and struct pci_device_id into in-source comments. Signed-off-by: Changbin Du [bhelgaas: fix kernel-doc warnings related to moving descriptions to linux/pci.h, fix "space tab" whitespace errors in mod_devicetable.h] Signed-off-by: Bjorn Helgaas Reviewed-by: Mauro Carvalho Chehab --- include/linux/mod_devicetable.h | 29 ++++++++++++++++++++----- include/linux/pci.h | 48 ++++++++++++++++++++++++++++++++++++++++- 2 files changed, 71 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 448621c32e4d..664c0fb1d53d 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -16,6 +16,25 @@ typedef unsigned long kernel_ulong_t; #define PCI_ANY_ID (~0) +/** + * struct pci_device_id - PCI device ID structure + * @vendor: Vendor ID to match (or PCI_ANY_ID) + * @device: Device ID to match (or PCI_ANY_ID) + * @subvendor: Subsystem vendor ID to match (or PCI_ANY_ID) + * @subdevice: Subsystem device ID to match (or PCI_ANY_ID) + * @class: Device class, subclass, and "interface" to match. + * See Appendix D of the PCI Local Bus Spec or + * include/linux/pci_ids.h for a full list of classes. + * Most drivers do not need to specify class/class_mask + * as vendor/device is normally sufficient. + * @class_mask: Limit which sub-fields of the class field are compared. + * See drivers/scsi/sym53c8xx_2/ for example of usage. + * @driver_data: Data private to the driver. + * Most drivers don't need to use driver_data field. + * Best practice is to use driver_data as an index + * into a static list of equivalent device types, + * instead of using it as a pointer. + */ struct pci_device_id { __u32 vendor, device; /* Vendor and device ID or PCI_ANY_ID*/ __u32 subvendor, subdevice; /* Subsystem ID's or PCI_ANY_ID */ @@ -257,17 +276,17 @@ struct pcmcia_device_id { __u16 match_flags; __u16 manf_id; - __u16 card_id; + __u16 card_id; - __u8 func_id; + __u8 func_id; /* for real multi-function devices */ - __u8 function; + __u8 function; /* for pseudo multi-function devices */ - __u8 device_no; + __u8 device_no; - __u32 prod_id_hash[4]; + __u32 prod_id_hash[4]; /* not matched against in kernelspace */ const char * prod_id[4]; diff --git a/include/linux/pci.h b/include/linux/pci.h index 4a5a84d7bdd4..b74b2a4e6df2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -151,6 +151,8 @@ static inline const char *pci_power_name(pci_power_t state) #define PCI_PM_BUS_WAIT 50 /** + * typedef pci_channel_state_t + * * The pci_channel state describes connectivity between the CPU and * the PCI device. If some PCI bus between here and the PCI device * has crashed or locked up, this info is reflected here. @@ -775,6 +777,50 @@ struct pci_error_handlers { struct module; + +/** + * struct pci_driver - PCI driver structure + * @node: List of driver structures. + * @name: Driver name. + * @id_table: Pointer to table of device IDs the driver is + * interested in. Most drivers should export this + * table using MODULE_DEVICE_TABLE(pci,...). + * @probe: This probing function gets called (during execution + * of pci_register_driver() for already existing + * devices or later if a new device gets inserted) for + * all PCI devices which match the ID table and are not + * "owned" by the other drivers yet. This function gets + * passed a "struct pci_dev \*" for each device whose + * entry in the ID table matches the device. The probe + * function returns zero when the driver chooses to + * take "ownership" of the device or an error code + * (negative number) otherwise. + * The probe function always gets called from process + * context, so it can sleep. + * @remove: The remove() function gets called whenever a device + * being handled by this driver is removed (either during + * deregistration of the driver or when it's manually + * pulled out of a hot-pluggable slot). + * The remove function always gets called from process + * context, so it can sleep. + * @suspend: Put device into low power state. + * @suspend_late: Put device into low power state. + * @resume_early: Wake device from low power state. + * @resume: Wake device from low power state. + * (Please see Documentation/power/pci.txt for descriptions + * of PCI Power Management and the related functions.) + * @shutdown: Hook into reboot_notifier_list (kernel/sys.c). + * Intended to stop any idling DMA operations. + * Useful for enabling wake-on-lan (NIC) or changing + * the power state of a device before reboot. + * e.g. drivers/net/e100.c. + * @sriov_configure: Optional driver callback to allow configuration of + * number of VFs to enable via sysfs "sriov_numvfs" file. + * @err_handler: See Documentation/PCI/pci-error-recovery.rst + * @groups: Sysfs attribute groups. + * @driver: Driver model structure. + * @dynids: List of dynamically added device IDs. + */ struct pci_driver { struct list_head node; const char *name; @@ -2206,7 +2252,7 @@ static inline u8 pci_vpd_srdt_tag(const u8 *srdt) /** * pci_vpd_info_field_size - Extracts the information field length - * @lrdt: Pointer to the beginning of an information field header + * @info_field: Pointer to the beginning of an information field header * * Returns the extracted information field length. */ -- cgit v1.2.3 From 87e5e6dab6c2a21fab2620f37786276d202e2ce0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 14 May 2019 16:02:22 -0600 Subject: uio: make import_iovec()/compat_import_iovec() return bytes on success Currently these functions return < 0 on error, and 0 for success. Change that so that we return < 0 on error, but number of bytes for success. Some callers already treat the return value that way, others need a slight tweak. Signed-off-by: Jens Axboe --- include/linux/uio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 2d0131ad4604..a61ceb6575ab 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -279,13 +279,13 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); -int import_iovec(int type, const struct iovec __user * uvector, +ssize_t import_iovec(int type, const struct iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, struct iovec **iov, struct iov_iter *i); #ifdef CONFIG_COMPAT struct compat_iovec; -int compat_import_iovec(int type, const struct compat_iovec __user * uvector, +ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, struct iovec **iov, struct iov_iter *i); #endif -- cgit v1.2.3 From 5213d7efc8ec26ed8938dce75427eff9275a62d9 Mon Sep 17 00:00:00 2001 From: Ruslan Babayev Date: Tue, 28 May 2019 16:02:32 -0700 Subject: i2c: acpi: export i2c_acpi_find_adapter_by_handle This allows drivers to lookup i2c adapters on ACPI based systems similar to of_get_i2c_adapter_by_node() with DT based systems. Signed-off-by: Ruslan Babayev Reviewed-by: Andrew Lunn Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 1308126fc384..e982b8913b73 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -14,6 +14,7 @@ #ifndef _LINUX_I2C_H #define _LINUX_I2C_H +#include /* for acpi_handle */ #include #include /* for struct device */ #include /* for completion */ @@ -981,6 +982,7 @@ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); +struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) @@ -996,6 +998,10 @@ static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, { return NULL; } +static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) +{ + return NULL; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From a09db883e5d938b525a86a4630fc04f98ff1063d Mon Sep 17 00:00:00 2001 From: Uma Shankar Date: Tue, 4 Jun 2019 16:47:02 +0530 Subject: drm: Fix docbook warnings in hdr metadata helper structures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following warnings: ./include/drm/drm_mode_config.h:841: warning: Incorrect use of kernel-doc format: * hdr_output_metadata_property: Connector property containing hdr ./include/drm/drm_mode_config.h:918: warning: Function parameter or member 'hdr_output_metadata_property' not described in 'drm_mode_config' ./include/drm/drm_connector.h:1251: warning: Function parameter or member 'hdr_output_metadata' not described in 'drm_connector' ./include/drm/drm_connector.h:1251: warning: Function parameter or member 'hdr_sink_metadata' not described in 'drm_connector' Also adds some property documentation for HDR Metadata Connector Property in connector property create function. v2: Fixed Sean Paul's review comments. v3: Fixed Daniel Vetter's review comments, added the UAPI structure definition section in kernel docs. v4: Fixed Daniel Vetter's review comments. v5: Added structure member references as per Daniel's suggestion. Cc: Shashank Sharma Cc: Ville Syrjä Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Sean Paul Cc: David Airlie Cc: Daniel Vetter Cc: Bartlomiej Zolnierkiewicz Cc: "Ville Syrjä" Cc: Hans Verkuil Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Reviewed-by: Sean Paul (v1) Signed-off-by: Uma Shankar [danvet: Fix up markup: () for functions, & for structs. Style guide also recommends to prepend struct for structures.] Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/1559647022-7336-1-git-send-email-uma.shankar@intel.com --- include/linux/hdmi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index ee55ba589cdc..9918a6c910c5 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -367,8 +367,19 @@ struct hdr_static_metadata { __u16 min_cll; }; +/** + * struct hdr_sink_metadata - HDR sink metadata + * + * Metadata Information read from Sink's EDID + */ struct hdr_sink_metadata { + /** + * @metadata_type: Static_Metadata_Descriptor_ID. + */ __u32 metadata_type; + /** + * @hdmi_type1: HDR Metadata Infoframe. + */ union { struct hdr_static_metadata hdmi_type1; }; @@ -398,6 +409,7 @@ union hdmi_vendor_any_infoframe { * @spd: spd infoframe * @vendor: union of all vendor infoframes * @audio: audio infoframe + * @drm: Dynamic Range and Mastering infoframe * * This is used by the generic pack function. This works since all infoframes * have the same header which also indicates which type of infoframe should be -- cgit v1.2.3 From 1e390478cfb527e34c9ab89ba57212cb05c33c51 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 5 Jun 2019 10:46:05 +0200 Subject: gpu: host1x: Increase maximum DMA segment size Recent versions of the DMA API debug code have started to warn about violations of the maximum DMA segment size. This is because the segment size defaults to 64 KiB, which can easily be exceeded in large buffer allocations such as used in DRM/KMS for framebuffers. Technically the Tegra SMMU and ARM SMMU don't have a maximum segment size (they map individual pages irrespective of whether they are contiguous or not), so the choice of 4 MiB is a bit arbitrary here. The maximum segment size is a 32-bit unsigned integer, though, so we can't set it to the correct maximum size, which would be the size of the aperture. Signed-off-by: Thierry Reding --- include/linux/host1x.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 89110d896d72..aef6e2f73802 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -310,6 +310,8 @@ struct host1x_device { struct list_head clients; bool registered; + + struct device_dma_parameters dma_parms; }; static inline struct host1x_device *to_host1x_device(struct device *dev) -- cgit v1.2.3 From 2076e5c0451ca943ff8ecc6def7239c84c77e070 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Mon, 6 May 2019 16:29:38 -0700 Subject: mm/hmm: update HMM documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update the HMM documentation to reflect the latest API and make a few minor wording changes. Cc: John Hubbard Cc: Ira Weiny Cc: Dan Williams Cc: Arnd Bergmann Cc: Balbir Singh Cc: Dan Carpenter Cc: Matthew Wilcox Cc: Souptick Joarder Cc: Andrew Morton Signed-off-by: Ralph Campbell Reviewed-by: Jérôme Glisse Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 044a36d7c3f8..740bb00853f5 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -418,9 +418,10 @@ struct hmm_mirror_ops { * * @mirror: pointer to struct hmm_mirror * - * This is called when the mm_struct is being released. - * The callback should make sure no references to the mirror occur - * after the callback returns. + * This is called when the mm_struct is being released. The callback + * must ensure that all access to any pages obtained from this mirror + * is halted before the callback returns. All future access should + * fault. */ void (*release)(struct hmm_mirror *mirror); -- cgit v1.2.3 From 085ea25064a9169eba5f2ed6484c111ab0f3ee79 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Mon, 6 May 2019 16:29:39 -0700 Subject: mm/hmm: clean up some coding style and comments MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no functional changes, just some coding style clean ups and minor comment changes. Cc: John Hubbard Cc: Ira Weiny Cc: Dan Williams Cc: Arnd Bergmann Cc: Balbir Singh Cc: Dan Carpenter Cc: Matthew Wilcox Cc: Souptick Joarder Cc: Andrew Morton Signed-off-by: Ralph Campbell Reviewed-by: Jérôme Glisse Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 71 +++++++++++++++++++++++++++-------------------------- 1 file changed, 36 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 740bb00853f5..7007123842ba 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -21,8 +21,8 @@ * * HMM address space mirroring API: * - * Use HMM address space mirroring if you want to mirror range of the CPU page - * table of a process into a device page table. Here, "mirror" means "keep + * Use HMM address space mirroring if you want to mirror a range of the CPU + * page tables of a process into a device page table. Here, "mirror" means "keep * synchronized". Prerequisites: the device must provide the ability to write- * protect its page tables (at PAGE_SIZE granularity), and must be able to * recover from the resulting potential page faults. @@ -105,10 +105,11 @@ struct hmm { * HMM_PFN_WRITE: CPU page table has write permission set * HMM_PFN_DEVICE_PRIVATE: private device memory (ZONE_DEVICE) * - * The driver provide a flags array, if driver valid bit for an entry is bit - * 3 ie (entry & (1 << 3)) is true if entry is valid then driver must provide + * The driver provides a flags array for mapping page protections to device + * PTE bits. If the driver valid bit for an entry is bit 3, + * i.e., (entry & (1 << 3)), then the driver must provide * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3. - * Same logic apply to all flags. This is same idea as vm_page_prot in vma + * Same logic apply to all flags. This is the same idea as vm_page_prot in vma * except that this is per device driver rather than per architecture. */ enum hmm_pfn_flag_e { @@ -129,13 +130,13 @@ enum hmm_pfn_flag_e { * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. * - * Driver provide entry value for none entry, error entry and special entry, - * driver can alias (ie use same value for error and special for instance). It - * should not alias none and error or special. + * Driver provides values for none entry, error entry, and special entry. + * Driver can alias (i.e., use same value) error and special, but + * it should not alias none with error or special. * * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, - * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table + * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry, * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one */ enum hmm_pfn_value_e { @@ -158,6 +159,7 @@ enum hmm_pfn_value_e { * @values: pfn value for some special case (none, special, error, ...) * @default_flags: default flags for the range (write, read, ... see hmm doc) * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter + * @page_shift: device virtual address shift value (should be >= PAGE_SHIFT) * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT) * @valid: pfns array did not change since it has been fill by an HMM function */ @@ -180,7 +182,7 @@ struct hmm_range { /* * hmm_range_page_shift() - return the page shift for the range * @range: range being queried - * Returns: page shift (page size = 1 << page shift) for the range + * Return: page shift (page size = 1 << page shift) for the range */ static inline unsigned hmm_range_page_shift(const struct hmm_range *range) { @@ -190,7 +192,7 @@ static inline unsigned hmm_range_page_shift(const struct hmm_range *range) /* * hmm_range_page_size() - return the page size for the range * @range: range being queried - * Returns: page size for the range in bytes + * Return: page size for the range in bytes */ static inline unsigned long hmm_range_page_size(const struct hmm_range *range) { @@ -201,7 +203,7 @@ static inline unsigned long hmm_range_page_size(const struct hmm_range *range) * hmm_range_wait_until_valid() - wait for range to be valid * @range: range affected by invalidation to wait on * @timeout: time out for wait in ms (ie abort wait after that period of time) - * Returns: true if the range is valid, false otherwise. + * Return: true if the range is valid, false otherwise. */ static inline bool hmm_range_wait_until_valid(struct hmm_range *range, unsigned long timeout) @@ -222,7 +224,7 @@ static inline bool hmm_range_wait_until_valid(struct hmm_range *range, /* * hmm_range_valid() - test if a range is valid or not * @range: range - * Returns: true if the range is valid, false otherwise. + * Return: true if the range is valid, false otherwise. */ static inline bool hmm_range_valid(struct hmm_range *range) { @@ -233,7 +235,7 @@ static inline bool hmm_range_valid(struct hmm_range *range) * hmm_device_entry_to_page() - return struct page pointed to by a device entry * @range: range use to decode device entry value * @entry: device entry value to get corresponding struct page from - * Returns: struct page pointer if entry is a valid, NULL otherwise + * Return: struct page pointer if entry is a valid, NULL otherwise * * If the device entry is valid (ie valid flag set) then return the struct page * matching the entry value. Otherwise return NULL. @@ -256,7 +258,7 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang * hmm_device_entry_to_pfn() - return pfn value store in a device entry * @range: range use to decode device entry value * @entry: device entry to extract pfn from - * Returns: pfn value if device entry is valid, -1UL otherwise + * Return: pfn value if device entry is valid, -1UL otherwise */ static inline unsigned long hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn) @@ -276,7 +278,7 @@ hmm_device_entry_to_pfn(const struct hmm_range *range, uint64_t pfn) * hmm_device_entry_from_page() - create a valid device entry for a page * @range: range use to encode HMM pfn value * @page: page for which to create the device entry - * Returns: valid device entry for the page + * Return: valid device entry for the page */ static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range, struct page *page) @@ -289,7 +291,7 @@ static inline uint64_t hmm_device_entry_from_page(const struct hmm_range *range, * hmm_device_entry_from_pfn() - create a valid device entry value from pfn * @range: range use to encode HMM pfn value * @pfn: pfn value for which to create the device entry - * Returns: valid device entry for the pfn + * Return: valid device entry for the pfn */ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, unsigned long pfn) @@ -394,7 +396,7 @@ enum hmm_update_event { }; /* - * struct hmm_update - HMM update informations for callback + * struct hmm_update - HMM update information for callback * * @start: virtual start address of the range to update * @end: virtual end address of the range to update @@ -428,8 +430,8 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update: update informations (see struct hmm_update) - * Returns: -EAGAIN if update.blockable false and callback need to + * @update: update information (see struct hmm_update) + * Return: -EAGAIN if update.blockable false and callback need to * block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU @@ -468,13 +470,13 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror); /* * hmm_mirror_mm_is_alive() - test if mm is still alive * @mirror: the HMM mm mirror for which we want to lock the mmap_sem - * Returns: false if the mm is dead, true otherwise + * Return: false if the mm is dead, true otherwise * - * This is an optimization it will not accurately always return -EINVAL if the - * mm is dead ie there can be false negative (process is being kill but HMM is - * not yet inform of that). It is only intented to be use to optimize out case - * where driver is about to do something time consuming and it would be better - * to skip it if the mm is dead. + * This is an optimization, it will not always accurately return false if the + * mm is dead; i.e., there can be false negatives (process is being killed but + * HMM is not yet informed of that). It is only intended to be used to optimize + * out cases where the driver is about to do something time consuming and it + * would be better to skip it if the mm is dead. */ static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror) { @@ -489,7 +491,6 @@ static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror) return true; } - /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ @@ -562,7 +563,7 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block) ret = hmm_range_fault(range, block); if (ret <= 0) { if (ret == -EBUSY || !ret) { - /* Same as above drop mmap_sem to match old API. */ + /* Same as above, drop mmap_sem to match old API. */ up_read(&range->vma->vm_mm->mmap_sem); ret = -EBUSY; } else if (ret == -EAGAIN) @@ -629,7 +630,7 @@ struct hmm_devmem_ops { * @page: pointer to struct page backing virtual address (unreliable) * @flags: FAULT_FLAG_* (see include/linux/mm.h) * @pmdp: page middle directory - * Returns: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR + * Return: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR * on error * * The callback occurs whenever there is a CPU page fault or GUP on a @@ -637,14 +638,14 @@ struct hmm_devmem_ops { * page back to regular memory (CPU accessible). * * The device driver is free to migrate more than one page from the - * fault() callback as an optimization. However if device decide to - * migrate more than one page it must always priotirize the faulting + * fault() callback as an optimization. However if the device decides + * to migrate more than one page it must always priotirize the faulting * address over the others. * - * The struct page pointer is only given as an hint to allow quick + * The struct page pointer is only given as a hint to allow quick * lookup of internal device driver data. A concurrent migration - * might have already free that page and the virtual address might - * not longer be back by it. So it should not be modified by the + * might have already freed that page and the virtual address might + * no longer be backed by it. So it should not be modified by the * callback. * * Note that mmap semaphore is held in read mode at least when this @@ -671,7 +672,7 @@ struct hmm_devmem_ops { * @ref: per CPU refcount * @page_fault: callback when CPU fault on an unaddressable device page * - * This an helper structure for device drivers that do not wish to implement + * This is a helper structure for device drivers that do not wish to implement * the gory details related to hotplugging new memoy and allocating struct * pages. * -- cgit v1.2.3 From 6d7c3cde93c1d9ac0b37f78ec3f2ff052159a242 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 22 May 2019 16:52:52 -0300 Subject: mm/hmm: fix use after free with struct hmm in the mmu notifiers mmu_notifier_unregister_no_release() is not a fence and the mmu_notifier system will continue to reference hmm->mn until the srcu grace period expires. Resulting in use after free races like this: CPU0 CPU1 __mmu_notifier_invalidate_range_start() srcu_read_lock hlist_for_each () // mn == hmm->mn hmm_mirror_unregister() hmm_put() hmm_free() mmu_notifier_unregister_no_release() hlist_del_init_rcu(hmm-mn->list) mn->ops->invalidate_range_start(mn, range); mm_get_hmm() mm->hmm = NULL; kfree(hmm) mutex_lock(&hmm->lock); Use SRCU to kfree the hmm memory so that the notifiers can rely on hmm existing. Get the now-safe hmm struct through container_of and directly check kref_get_unless_zero to lock it against free. Signed-off-by: Jason Gunthorpe Reviewed-by: Ira Weiny Reviewed-by: John Hubbard Reviewed-by: Ralph Campbell Reviewed-by: Christoph Hellwig Tested-by: Philip Yang --- include/linux/hmm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 7007123842ba..cb01cf1fa3c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -93,6 +93,7 @@ struct hmm { struct mmu_notifier mmu_notifier; struct rw_semaphore mirrors_sem; wait_queue_head_t wq; + struct rcu_head rcu; long notifiers; bool dead; }; -- cgit v1.2.3 From f652e66fcca07e59f207bcca27c5566193feabd5 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 9 Jun 2019 23:43:13 +0900 Subject: pinctrl: add include guard to pinctrl-state.h Signed-off-by: Masahiro Yamada Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinctrl-state.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinctrl-state.h b/include/linux/pinctrl/pinctrl-state.h index a0e785815a64..635d97e9285e 100644 --- a/include/linux/pinctrl/pinctrl-state.h +++ b/include/linux/pinctrl/pinctrl-state.h @@ -3,6 +3,9 @@ * Standard pin control state definitions */ +#ifndef __LINUX_PINCTRL_PINCTRL_STATE_H +#define __LINUX_PINCTRL_PINCTRL_STATE_H + /** * @PINCTRL_STATE_DEFAULT: the state the pinctrl handle shall be put * into as default, usually this means the pins are up and ready to @@ -31,3 +34,5 @@ #define PINCTRL_STATE_INIT "init" #define PINCTRL_STATE_IDLE "idle" #define PINCTRL_STATE_SLEEP "sleep" + +#endif /* __LINUX_PINCTRL_PINCTRL_STATE_H */ -- cgit v1.2.3 From e63d79d1ffcd2201a2dbff1d7a1184b8f3ec74cf Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Tue, 4 Jun 2019 15:29:22 +0200 Subject: dmaengine: Add Synopsys eDMA IP core driver Add Synopsys PCIe Endpoint eDMA IP core driver to kernel. This IP is generally distributed with Synopsys PCIe Endpoint IP (depends of the use and licensing agreement). This core driver, initializes and configures the eDMA IP using vma-helpers functions and dma-engine subsystem. This driver can be compile as built-in or external module in kernel. To enable this driver just select DW_EDMA option in kernel configuration, however it requires and selects automatically DMA_ENGINE and DMA_VIRTUAL_CHANNELS option too. In order to transfer data from point A to B as fast as possible this IP requires a dedicated memory space containing linked list of elements. All elements of this linked list are continuous and each one describes a data transfer (source and destination addresses, length and a control variable). For the sake of simplicity, lets assume a memory space for channel write 0 which allows about 42 elements. +---------+ | Desc #0 |-+ +---------+ | V +----------+ | Chunk #0 |-+ | CB = 1 | | +----------+ +-----+ +-----------+ +-----+ +----------+ +->| Burst #0 |->| ... |->| Burst #41 |->| llp | | +----------+ +-----+ +-----------+ +-----+ V +----------+ | Chunk #1 |-+ | CB = 0 | | +-----------+ +-----+ +-----------+ +-----+ +----------+ +->| Burst #42 |->| ... |->| Burst #83 |->| llp | | +-----------+ +-----+ +-----------+ +-----+ V +----------+ | Chunk #2 |-+ | CB = 1 | | +-----------+ +-----+ +------------+ +-----+ +----------+ +->| Burst #84 |->| ... |->| Burst #125 |->| llp | | +-----------+ +-----+ +------------+ +-----+ V +----------+ | Chunk #3 |-+ | CB = 0 | | +------------+ +-----+ +------------+ +-----+ +----------+ +->| Burst #126 |->| ... |->| Burst #129 |->| llp | +------------+ +-----+ +------------+ +-----+ Legend: - Linked list, also know as Chunk - Linked list element*, also know as Burst *CB*, also know as Change Bit, it's a control bit (and typically is toggled) that allows to easily identify and differentiate between the current linked list and the previous or the next one. - LLP, is a special element that indicates the end of the linked list element stream also informs that the next CB should be toggle On every last Burst of the Chunk (Burst #41, Burst #83, Burst #125 or even Burst #129) is set some flags on their control variable (RIE and LIE bits) that will trigger the send of "done" interruption. On the interruptions callback, is decided whether to recycle the linked list memory space by writing a new set of Bursts elements (if still exists Chunks to transfer) or is considered completed (if there is no Chunks available to transfer). On scatter-gather transfer mode, the client will submit a scatter-gather list of n (on this case 130) elements, that will be divide in multiple Chunks, each Chunk will have (on this case 42) a limited number of Bursts and after transferring all Bursts, an interrupt will be triggered, which will allow to recycle the all linked list dedicated memory again with the new information relative to the next Chunk and respective Burst associated and repeat the whole cycle again. On cyclic transfer mode, the client will submit a buffer pointer, length of it and number of repetitions, in this case each burst will correspond directly to each repetition. Each Burst can describes a data transfer from point A(source) to point B(destination) with a length that can be from 1 byte up to 4 GB. Since dedicated the memory space where the linked list will reside is limited, the whole n burst elements will be organized in several Chunks, that will be used later to recycle the dedicated memory space to initiate a new sequence of data transfers. The whole transfer is considered has completed when it was transferred all bursts. Currently this IP has a set well-known register map, which includes support for legacy and unroll modes. Legacy mode is version of this register map that has multiplexer register that allows to switch registers between all write and read channels and the unroll modes repeats all write and read channels registers with an offset between them. This register map is called v0. The IP team is creating a new register map more suitable to the latest PCIe features, that very likely will change the map register, which this version will be called v1. As soon as this new version is released by the IP team the support for this version in be included on this driver. According to the logic, patches 1, 2 and 3 should be squashed into 1 unique patch, but for the sake of simplicity of review, it was divided in this 3 patches files. Signed-off-by: Gustavo Pimentel Cc: Vinod Koul Cc: Dan Williams Cc: Andy Shevchenko Cc: Russell King Cc: Joao Pinto Signed-off-by: Vinod Koul --- include/linux/dma/edma.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/dma/edma.h (limited to 'include/linux') diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h new file mode 100644 index 000000000000..cab6e18773da --- /dev/null +++ b/include/linux/dma/edma.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018-2019 Synopsys, Inc. and/or its affiliates. + * Synopsys DesignWare eDMA core driver + * + * Author: Gustavo Pimentel + */ + +#ifndef _DW_EDMA_H +#define _DW_EDMA_H + +#include +#include + +struct dw_edma; + +/** + * struct dw_edma_chip - representation of DesignWare eDMA controller hardware + * @dev: struct device of the eDMA controller + * @id: instance ID + * @irq: irq line + * @dw: struct dw_edma that is filed by dw_edma_probe() + */ +struct dw_edma_chip { + struct device *dev; + int id; + int irq; + struct dw_edma *dw; +}; + +/* Export to the platform drivers */ +#if IS_ENABLED(CONFIG_DW_EDMA) +int dw_edma_probe(struct dw_edma_chip *chip); +int dw_edma_remove(struct dw_edma_chip *chip); +#else +static inline int dw_edma_probe(struct dw_edma_chip *chip) +{ + return -ENODEV; +} + +static inline int dw_edma_remove(struct dw_edma_chip *chip) +{ + return 0; +} +#endif /* CONFIG_DW_EDMA */ + +#endif /* _DW_EDMA_H */ -- cgit v1.2.3 From 1f418f46503d72594bbe6407d97fd2ae1ce15ee6 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Tue, 4 Jun 2019 15:29:25 +0200 Subject: PCI: Add Synopsys endpoint EDDA Device ID Create and add Synopsys Endpoint EDDA Device ID to PCI ID list, since this ID is now being use on two different drivers (pci_endpoint_test.ko and dw-edma-pcie.ko). Signed-off-by: Gustavo Pimentel Acked-by: Bjorn Helgaas Cc: Kishon Vijay Abraham I Cc: Bjorn Helgaas Cc: Lorenzo Pieralisi Cc: Joao Pinto Signed-off-by: Vinod Koul --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 70e86148cb1e..4aad69fc4d6b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2366,6 +2366,7 @@ #define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3 0xabcd #define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3_AXI 0xabce #define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB31 0xabcf +#define PCI_DEVICE_ID_SYNOPSYS_EDDA 0xedda #define PCI_VENDOR_ID_USR 0x16ec -- cgit v1.2.3 From 4e23be473e3063a9d3bc06bb0aee89885fffab0e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 10 Jun 2019 04:48:05 -0700 Subject: bus: ti-sysc: Add support for module specific reset quirks Some older interconnect target modules need module internal clock toggling quirks to reset properly. We've been doing this in the platform code earlier, but need to be able to it directly in the ti-sysc driver when we no longer rely on on the platform code. Let's add reset handling for 1-wire, i2c and watchdog. Later on we can add more modules like msdi and dss as they get tested. For dra7 pcie, we should be able to just use the rstctrl reset driver when available. Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 8822e99ff813..0c587d4fc718 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -47,6 +47,9 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_HDQ1W BIT(17) +#define SYSC_MODULE_QUIRK_I2C BIT(16) +#define SYSC_MODULE_QUIRK_WDT BIT(15) #define SYSS_QUIRK_RESETDONE_INVERTED BIT(14) #define SYSC_QUIRK_SWSUP_MSTANDBY BIT(13) #define SYSC_QUIRK_SWSUP_SIDLE_ACT BIT(12) -- cgit v1.2.3 From e36acfe6c86d13eec62321e1e86a1ce287e52e7d Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 23 May 2019 09:41:19 -0300 Subject: mm/hmm: Use hmm_mirror not mm as an argument for hmm_range_register Ralph observes that hmm_range_register() can only be called by a driver while a mirror is registered. Make this clear in the API by passing in the mirror structure as a parameter. This also simplifies understanding the lifetime model for struct hmm, as the hmm pointer must be valid as part of a registered mirror so all we need in hmm_register_range() is a simple kref_get. Suggested-by: Ralph Campbell Signed-off-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: Ralph Campbell Reviewed-by: Ira Weiny Reviewed-by: Christoph Hellwig Tested-by: Philip Yang --- include/linux/hmm.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index cb01cf1fa3c0..1fba6979adf4 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -496,7 +496,7 @@ static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror) * Please see Documentation/vm/hmm.rst for how to use the range API. */ int hmm_range_register(struct hmm_range *range, - struct mm_struct *mm, + struct hmm_mirror *mirror, unsigned long start, unsigned long end, unsigned page_shift); @@ -532,7 +532,8 @@ static inline bool hmm_vma_range_done(struct hmm_range *range) } /* This is a temporary helper to avoid merge conflict between trees. */ -static inline int hmm_vma_fault(struct hmm_range *range, bool block) +static inline int hmm_vma_fault(struct hmm_mirror *mirror, + struct hmm_range *range, bool block) { long ret; @@ -545,7 +546,7 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block) range->default_flags = 0; range->pfn_flags_mask = -1UL; - ret = hmm_range_register(range, range->vma->vm_mm, + ret = hmm_range_register(range, mirror, range->start, range->end, PAGE_SHIFT); if (ret) -- cgit v1.2.3 From c8a53b2db0aec40d8b217936e1b7f3d840c50390 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 23 May 2019 10:36:46 -0300 Subject: mm/hmm: Hold a mmgrab from hmm to mm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So long as a struct hmm pointer exists, so should the struct mm it is linked too. Hold the mmgrab() as soon as a hmm is created, and mmdrop() it once the hmm refcount goes to zero. Since mmdrop() (ie a 0 kref on struct mm) is now impossible with a !NULL mm->hmm delete the hmm_hmm_destroy(). Signed-off-by: Jason Gunthorpe Reviewed-by: Jérôme Glisse Reviewed-by: John Hubbard Reviewed-by: Ralph Campbell Reviewed-by: Ira Weiny Reviewed-by: Christoph Hellwig Tested-by: Philip Yang --- include/linux/hmm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 1fba6979adf4..1d97b6d62c5b 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -577,14 +577,11 @@ static inline int hmm_vma_fault(struct hmm_mirror *mirror, } /* Below are for HMM internal use only! Not to be used by device driver! */ -void hmm_mm_destroy(struct mm_struct *mm); - static inline void hmm_mm_init(struct mm_struct *mm) { mm->hmm = NULL; } #else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -- cgit v1.2.3 From 78b99577b3934e3e787fe0c52aa1b59442c8bbb5 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jun 2019 00:09:53 +0900 Subject: pinctrl: remove unused pin_is_valid() This function was used by pin_request() to pointlessly double-check the pin validity, and it was the only user ever. Since commit d2f6a1c6fb0e ("pinctrl: remove double pin validity check."), no one has ever used it. Signed-off-by: Masahiro Yamada Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinctrl.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 2744113f1024..36a79fe7b84f 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -172,7 +172,6 @@ extern struct pinctrl_dev *devm_pinctrl_register(struct device *dev, extern void devm_pinctrl_unregister(struct device *dev, struct pinctrl_dev *pctldev); -extern bool pin_is_valid(struct pinctrl_dev *pctldev, int pin); extern void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range); extern void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev, @@ -203,15 +202,6 @@ struct pinctrl_dev *of_pinctrl_get(struct device_node *np) extern const char *pinctrl_dev_get_name(struct pinctrl_dev *pctldev); extern const char *pinctrl_dev_get_devname(struct pinctrl_dev *pctldev); extern void *pinctrl_dev_get_drvdata(struct pinctrl_dev *pctldev); -#else - -struct pinctrl_dev; - -/* Sufficiently stupid default functions when pinctrl is not in use */ -static inline bool pin_is_valid(struct pinctrl_dev *pctldev, int pin) -{ - return pin >= 0; -} #endif /* !CONFIG_PINCTRL */ -- cgit v1.2.3 From 0b673b6486998061b0489b09447ebe8452da0146 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 8 May 2019 11:46:34 -0700 Subject: firmware: arm_scmi: fetch and store sensor scale In preparation for dealing with scales within the SCMI HWMON driver, fetch and store the sensor unit scale into the scmi_sensor_info structure. In order to simplify computations for upper layer, take care of sign extending the scale to a full 8-bit signed value. Reviewed-by: Guenter Roeck Signed-off-by: Florian Fainelli [sudeep.holla: update bitfield values as per specification] Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 3105055c00a7..9ff2e9357e9a 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -144,6 +144,7 @@ struct scmi_power_ops { struct scmi_sensor_info { u32 id; u8 type; + s8 scale; char name[SCMI_MAX_STR_SIZE]; }; -- cgit v1.2.3 From 81f4458c9c6998fcd37c427d16d76d4dba65d015 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Tue, 28 May 2019 16:10:24 +0300 Subject: firmware: ti_sci: extend clock identifiers from u8 to u32 Future SoCs are going to have more than 255 device clocks in certain cases, and thus the API must be extended to support this. The support is done in backwards compatible extension, in which the new u32 clock identifier fields are only used if the existing u8 size clock identifier is set as 255. In all the other cases, the existing u8 clock identifier is used. As the size of the messages sent / received is not verified for existing devices / old firmware, increasing the size of the messages from the end is also fine. Due to this reason, depending on ABI version isn't necessary either. Acked-by: Santosh Shilimkar Signed-off-by: Tero Kristo --- include/linux/soc/ti/ti_sci_protocol.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 568722a041bf..406e6717d252 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -166,29 +166,29 @@ struct ti_sci_dev_ops { * managed by driver for that purpose. */ struct ti_sci_clk_ops { - int (*get_clock)(const struct ti_sci_handle *handle, u32 did, u8 cid, + int (*get_clock)(const struct ti_sci_handle *handle, u32 did, u32 cid, bool needs_ssc, bool can_change_freq, bool enable_input_term); - int (*idle_clock)(const struct ti_sci_handle *handle, u32 did, u8 cid); - int (*put_clock)(const struct ti_sci_handle *handle, u32 did, u8 cid); - int (*is_auto)(const struct ti_sci_handle *handle, u32 did, u8 cid, + int (*idle_clock)(const struct ti_sci_handle *handle, u32 did, u32 cid); + int (*put_clock)(const struct ti_sci_handle *handle, u32 did, u32 cid); + int (*is_auto)(const struct ti_sci_handle *handle, u32 did, u32 cid, bool *req_state); - int (*is_on)(const struct ti_sci_handle *handle, u32 did, u8 cid, + int (*is_on)(const struct ti_sci_handle *handle, u32 did, u32 cid, bool *req_state, bool *current_state); - int (*is_off)(const struct ti_sci_handle *handle, u32 did, u8 cid, + int (*is_off)(const struct ti_sci_handle *handle, u32 did, u32 cid, bool *req_state, bool *current_state); - int (*set_parent)(const struct ti_sci_handle *handle, u32 did, u8 cid, - u8 parent_id); - int (*get_parent)(const struct ti_sci_handle *handle, u32 did, u8 cid, - u8 *parent_id); + int (*set_parent)(const struct ti_sci_handle *handle, u32 did, u32 cid, + u32 parent_id); + int (*get_parent)(const struct ti_sci_handle *handle, u32 did, u32 cid, + u32 *parent_id); int (*get_num_parents)(const struct ti_sci_handle *handle, u32 did, - u8 cid, u8 *num_parents); + u32 cid, u32 *num_parents); int (*get_best_match_freq)(const struct ti_sci_handle *handle, u32 did, - u8 cid, u64 min_freq, u64 target_freq, + u32 cid, u64 min_freq, u64 target_freq, u64 max_freq, u64 *match_freq); - int (*set_freq)(const struct ti_sci_handle *handle, u32 did, u8 cid, + int (*set_freq)(const struct ti_sci_handle *handle, u32 did, u32 cid, u64 min_freq, u64 target_freq, u64 max_freq); - int (*get_freq)(const struct ti_sci_handle *handle, u32 did, u8 cid, + int (*get_freq)(const struct ti_sci_handle *handle, u32 did, u32 cid, u64 *current_freq); }; -- cgit v1.2.3 From 5740671e596bdc3986a5391997de194300970201 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 12 Jun 2019 14:28:30 +0100 Subject: dma-fence/reservation: Markup rcu protected access for DEBUG_MUTEXES MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Mark the access to reservation_object.fence as being protected to silence sparse. Signed-off-by: Chris Wilson Reviewed-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20190612132830.31221-1-chris@chris-wilson.co.uk --- include/linux/reservation.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/reservation.h b/include/linux/reservation.h index ee750765cc94..644a22dbe53b 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -216,8 +216,12 @@ reservation_object_unlock(struct reservation_object *obj) { #ifdef CONFIG_DEBUG_MUTEXES /* Test shared fence slot reservation */ - if (obj->fence) - obj->fence->shared_max = obj->fence->shared_count; + if (rcu_access_pointer(obj->fence)) { + struct reservation_object_list *fence = + reservation_object_get_list(obj); + + fence->shared_max = fence->shared_count; + } #endif ww_mutex_unlock(&obj->lock); } -- cgit v1.2.3 From d664c43958e0d9e0b34e23b6f8a8f4cf8ec61a2e Mon Sep 17 00:00:00 2001 From: Enrico Weigelt Date: Wed, 12 Jun 2019 23:59:36 +0200 Subject: gpio: Fix build warnings on undefined struct pinctrl_dev This fixes the warnings: * include/linux/gpio.h:254:11: warning: 'struct pinctrl_dev' declared inside parameter list will not be visible outside of this definition or declaration * include/linux/gpio/driver.h:602:11: warning: 'struct pinctrl_dev' declared inside parameter list will not be visible outside of this definition or declaration Fixes: 78b99577b393 ("pinctrl: remove unused pin_is_valid()") Reported-by: kbuild test robot Signed-off-by: Enrico Weigelt Signed-off-by: Linus Walleij --- include/linux/gpio.h | 1 + include/linux/gpio/driver.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 39745b8bdd65..40915b461f18 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -106,6 +106,7 @@ void devm_gpio_free(struct device *dev, unsigned int gpio); struct device; struct gpio_chip; +struct pinctrl_dev; static inline bool gpio_is_valid(int number) { diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index a1d273c96016..b58b27c11355 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -590,6 +590,8 @@ void gpiochip_remove_pin_ranges(struct gpio_chip *chip); #else +struct pinctrl_dev; + static inline int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, -- cgit v1.2.3 From 68608b5e5063dd12942f1118286c6f595d0c4a05 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 10 Jun 2019 12:18:56 +0300 Subject: firmware: ti_sci: Add resource management APIs for ringacc, psi-l and udma Configuration of NAVSS resource, like rings, UDMAP channels, flows and PSI-L thread management need to be done via TISCI. Add the needed structures and functions for NAVSS resource configuration of the following: Rings from Ring Accelerator PSI-L thread management UDMAP tchan, rchan and rflow configuration. Signed-off-by: Peter Ujfalusi Reviewed-by: Lokesh Vutla Signed-off-by: Tero Kristo Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/ti_sci_protocol.h | 215 +++++++++++++++++++++++++++++++++ 1 file changed, 215 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 568722a041bf..4fd9bff5806b 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -241,6 +241,218 @@ struct ti_sci_rm_irq_ops { u16 global_event, u8 vint_status_bit); }; +/* RA config.addr_lo parameter is valid for RM ring configure TI_SCI message */ +#define TI_SCI_MSG_VALUE_RM_RING_ADDR_LO_VALID BIT(0) +/* RA config.addr_hi parameter is valid for RM ring configure TI_SCI message */ +#define TI_SCI_MSG_VALUE_RM_RING_ADDR_HI_VALID BIT(1) + /* RA config.count parameter is valid for RM ring configure TI_SCI message */ +#define TI_SCI_MSG_VALUE_RM_RING_COUNT_VALID BIT(2) +/* RA config.mode parameter is valid for RM ring configure TI_SCI message */ +#define TI_SCI_MSG_VALUE_RM_RING_MODE_VALID BIT(3) +/* RA config.size parameter is valid for RM ring configure TI_SCI message */ +#define TI_SCI_MSG_VALUE_RM_RING_SIZE_VALID BIT(4) +/* RA config.order_id parameter is valid for RM ring configure TISCI message */ +#define TI_SCI_MSG_VALUE_RM_RING_ORDER_ID_VALID BIT(5) + +#define TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER \ + (TI_SCI_MSG_VALUE_RM_RING_ADDR_LO_VALID | \ + TI_SCI_MSG_VALUE_RM_RING_ADDR_HI_VALID | \ + TI_SCI_MSG_VALUE_RM_RING_COUNT_VALID | \ + TI_SCI_MSG_VALUE_RM_RING_MODE_VALID | \ + TI_SCI_MSG_VALUE_RM_RING_SIZE_VALID) + +/** + * struct ti_sci_rm_ringacc_ops - Ring Accelerator Management operations + * @config: configure the SoC Navigator Subsystem Ring Accelerator ring + * @get_config: get the SoC Navigator Subsystem Ring Accelerator ring + * configuration + */ +struct ti_sci_rm_ringacc_ops { + int (*config)(const struct ti_sci_handle *handle, + u32 valid_params, u16 nav_id, u16 index, + u32 addr_lo, u32 addr_hi, u32 count, u8 mode, + u8 size, u8 order_id + ); + int (*get_config)(const struct ti_sci_handle *handle, + u32 nav_id, u32 index, u8 *mode, + u32 *addr_lo, u32 *addr_hi, u32 *count, + u8 *size, u8 *order_id); +}; + +/** + * struct ti_sci_rm_psil_ops - PSI-L thread operations + * @pair: pair PSI-L source thread to a destination thread. + * If the src_thread is mapped to UDMA tchan, the corresponding channel's + * TCHAN_THRD_ID register is updated. + * If the dst_thread is mapped to UDMA rchan, the corresponding channel's + * RCHAN_THRD_ID register is updated. + * @unpair: unpair PSI-L source thread from a destination thread. + * If the src_thread is mapped to UDMA tchan, the corresponding channel's + * TCHAN_THRD_ID register is cleared. + * If the dst_thread is mapped to UDMA rchan, the corresponding channel's + * RCHAN_THRD_ID register is cleared. + */ +struct ti_sci_rm_psil_ops { + int (*pair)(const struct ti_sci_handle *handle, u32 nav_id, + u32 src_thread, u32 dst_thread); + int (*unpair)(const struct ti_sci_handle *handle, u32 nav_id, + u32 src_thread, u32 dst_thread); +}; + +/* UDMAP channel types */ +#define TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR 2 +#define TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR_SB 3 /* RX only */ +#define TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_PBRR 10 +#define TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_PBVR 11 +#define TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR 12 +#define TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBVR 13 + +#define TI_SCI_RM_UDMAP_RX_FLOW_DESC_HOST 0 +#define TI_SCI_RM_UDMAP_RX_FLOW_DESC_MONO 2 + +#define TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES 1 +#define TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_128_BYTES 2 +#define TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES 3 + +/* UDMAP TX/RX channel valid_params common declarations */ +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID BIT(0) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_VALID BIT(1) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID BIT(2) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID BIT(3) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID BIT(4) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_PRIORITY_VALID BIT(5) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_QOS_VALID BIT(6) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_ORDER_ID_VALID BIT(7) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_SCHED_PRIORITY_VALID BIT(8) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_BURST_SIZE_VALID BIT(14) + +/** + * Configures a Navigator Subsystem UDMAP transmit channel + * + * Configures a Navigator Subsystem UDMAP transmit channel registers. + * See @ti_sci_msg_rm_udmap_tx_ch_cfg_req + */ +struct ti_sci_msg_rm_udmap_tx_ch_cfg { + u32 valid_params; +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_EINFO_VALID BIT(9) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_PSWORDS_VALID BIT(10) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID BIT(11) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_CREDIT_COUNT_VALID BIT(12) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FDEPTH_VALID BIT(13) + u16 nav_id; + u16 index; + u8 tx_pause_on_err; + u8 tx_filt_einfo; + u8 tx_filt_pswords; + u8 tx_atype; + u8 tx_chan_type; + u8 tx_supr_tdpkt; + u16 tx_fetch_size; + u8 tx_credit_count; + u16 txcq_qnum; + u8 tx_priority; + u8 tx_qos; + u8 tx_orderid; + u16 fdepth; + u8 tx_sched_priority; + u8 tx_burst_size; +}; + +/** + * Configures a Navigator Subsystem UDMAP receive channel + * + * Configures a Navigator Subsystem UDMAP receive channel registers. + * See @ti_sci_msg_rm_udmap_rx_ch_cfg_req + */ +struct ti_sci_msg_rm_udmap_rx_ch_cfg { + u32 valid_params; +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID BIT(9) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID BIT(10) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_IGNORE_SHORT_VALID BIT(11) +#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_IGNORE_LONG_VALID BIT(12) + u16 nav_id; + u16 index; + u16 rx_fetch_size; + u16 rxcq_qnum; + u8 rx_priority; + u8 rx_qos; + u8 rx_orderid; + u8 rx_sched_priority; + u16 flowid_start; + u16 flowid_cnt; + u8 rx_pause_on_err; + u8 rx_atype; + u8 rx_chan_type; + u8 rx_ignore_short; + u8 rx_ignore_long; + u8 rx_burst_size; +}; + +/** + * Configures a Navigator Subsystem UDMAP receive flow + * + * Configures a Navigator Subsystem UDMAP receive flow's registers. + * See @tis_ci_msg_rm_udmap_flow_cfg_req + */ +struct ti_sci_msg_rm_udmap_flow_cfg { + u32 valid_params; +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_EINFO_PRESENT_VALID BIT(0) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PSINFO_PRESENT_VALID BIT(1) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_ERROR_HANDLING_VALID BIT(2) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DESC_TYPE_VALID BIT(3) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SOP_OFFSET_VALID BIT(4) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID BIT(5) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_VALID BIT(6) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_VALID BIT(7) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_VALID BIT(8) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_VALID BIT(9) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_SEL_VALID BIT(10) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_SEL_VALID BIT(11) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_SEL_VALID BIT(12) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_SEL_VALID BIT(13) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID BIT(14) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID BIT(15) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID BIT(16) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID BIT(17) +#define TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PS_LOCATION_VALID BIT(18) + u16 nav_id; + u16 flow_index; + u8 rx_einfo_present; + u8 rx_psinfo_present; + u8 rx_error_handling; + u8 rx_desc_type; + u16 rx_sop_offset; + u16 rx_dest_qnum; + u8 rx_src_tag_hi; + u8 rx_src_tag_lo; + u8 rx_dest_tag_hi; + u8 rx_dest_tag_lo; + u8 rx_src_tag_hi_sel; + u8 rx_src_tag_lo_sel; + u8 rx_dest_tag_hi_sel; + u8 rx_dest_tag_lo_sel; + u16 rx_fdq0_sz0_qnum; + u16 rx_fdq1_qnum; + u16 rx_fdq2_qnum; + u16 rx_fdq3_qnum; + u8 rx_ps_location; +}; + +/** + * struct ti_sci_rm_udmap_ops - UDMA Management operations + * @tx_ch_cfg: configure SoC Navigator Subsystem UDMA transmit channel. + * @rx_ch_cfg: configure SoC Navigator Subsystem UDMA receive channel. + * @rx_flow_cfg1: configure SoC Navigator Subsystem UDMA receive flow. + */ +struct ti_sci_rm_udmap_ops { + int (*tx_ch_cfg)(const struct ti_sci_handle *handle, + const struct ti_sci_msg_rm_udmap_tx_ch_cfg *params); + int (*rx_ch_cfg)(const struct ti_sci_handle *handle, + const struct ti_sci_msg_rm_udmap_rx_ch_cfg *params); + int (*rx_flow_cfg)(const struct ti_sci_handle *handle, + const struct ti_sci_msg_rm_udmap_flow_cfg *params); +}; + /** * struct ti_sci_ops - Function support for TI SCI * @dev_ops: Device specific operations @@ -254,6 +466,9 @@ struct ti_sci_ops { struct ti_sci_clk_ops clk_ops; struct ti_sci_rm_core_ops rm_core_ops; struct ti_sci_rm_irq_ops rm_irq_ops; + struct ti_sci_rm_ringacc_ops rm_ring_ops; + struct ti_sci_rm_psil_ops rm_psil_ops; + struct ti_sci_rm_udmap_ops rm_udmap_ops; }; /** -- cgit v1.2.3 From 1e407f337f4015c8ffc56e7cfd70e06b2e9fc9da Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Wed, 5 Jun 2019 17:33:34 -0500 Subject: firmware: ti_sci: Add support for processor control Texas Instrument's System Control Interface (TI-SCI) Message Protocol is used in Texas Instrument's System on Chip (SoC) such as those in K3 family AM654 SoC to communicate between various compute processors with a central system controller entity. The system controller provides various services including the control of other compute processors within the SoC. Extend the TI-SCI protocol support to add various TI-SCI commands to invoke services associated with power and reset control, and boot vector management of the various compute processors from the Linux kernel. Signed-off-by: Suman Anna Signed-off-by: Tero Kristo Signed-off-by: Santosh Shilimkar --- include/linux/soc/ti/ti_sci_protocol.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 4fd9bff5806b..7b3762f68df9 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -453,12 +453,42 @@ struct ti_sci_rm_udmap_ops { const struct ti_sci_msg_rm_udmap_flow_cfg *params); }; +/** + * struct ti_sci_proc_ops - Processor Control operations + * @request: Request to control a physical processor. The requesting host + * should be in the processor access list + * @release: Relinquish a physical processor control + * @handover: Handover a physical processor control to another host + * in the permitted list + * @set_config: Set base configuration of a processor + * @set_control: Setup limited control flags in specific cases + * @get_status: Get the state of physical processor + * + * NOTE: The following paramteres are generic in nature for all these ops, + * -handle: Pointer to TI SCI handle as retrieved by *ti_sci_get_handle + * -pid: Processor ID + * -hid: Host ID + */ +struct ti_sci_proc_ops { + int (*request)(const struct ti_sci_handle *handle, u8 pid); + int (*release)(const struct ti_sci_handle *handle, u8 pid); + int (*handover)(const struct ti_sci_handle *handle, u8 pid, u8 hid); + int (*set_config)(const struct ti_sci_handle *handle, u8 pid, + u64 boot_vector, u32 cfg_set, u32 cfg_clr); + int (*set_control)(const struct ti_sci_handle *handle, u8 pid, + u32 ctrl_set, u32 ctrl_clr); + int (*get_status)(const struct ti_sci_handle *handle, u8 pid, + u64 *boot_vector, u32 *cfg_flags, u32 *ctrl_flags, + u32 *status_flags); +}; + /** * struct ti_sci_ops - Function support for TI SCI * @dev_ops: Device specific operations * @clk_ops: Clock specific operations * @rm_core_ops: Resource management core operations. * @rm_irq_ops: IRQ management specific operations + * @proc_ops: Processor Control specific operations */ struct ti_sci_ops { struct ti_sci_core_ops core_ops; @@ -469,6 +499,7 @@ struct ti_sci_ops { struct ti_sci_rm_ringacc_ops rm_ring_ops; struct ti_sci_rm_psil_ops rm_psil_ops; struct ti_sci_rm_udmap_ops rm_udmap_ops; + struct ti_sci_proc_ops proc_ops; }; /** -- cgit v1.2.3 From 18c8c0954d15105b02f7d2f556b9eafae426871f Mon Sep 17 00:00:00 2001 From: Wesley Sheng Date: Tue, 30 Apr 2019 18:04:29 +0800 Subject: NTB: correct ntb_dev_ops and ntb_dev comment typos The comment for ntb_dev_ops and ntb_dev incorrectly referred to ntb_ctx_ops and ntb_device. Signed-off-by: Wesley Sheng Reviewed-by: Logan Gunthorpe Signed-off-by: Jon Mason --- include/linux/ntb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 56a92e3ae3ae..604abc883741 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -205,7 +205,7 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) } /** - * struct ntb_ctx_ops - ntb device operations + * struct ntb_dev_ops - ntb device operations * @port_number: See ntb_port_number(). * @peer_port_count: See ntb_peer_port_count(). * @peer_port_number: See ntb_peer_port_number(). @@ -404,7 +404,7 @@ struct ntb_client { #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** - * struct ntb_device - ntb device + * struct ntb_dev - ntb device * @dev: Linux device object. * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. -- cgit v1.2.3 From d7cc609fb679e11dc2b00cbe6c50cbd37ec4bfa2 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 23 May 2019 16:30:51 -0600 Subject: PCI/MSI: Support allocating virtual MSI interrupts For NTB devices, we want to be able to trigger MSI interrupts through a memory window. In these cases we may want to use more interrupts than the NTB PCI device has available in its MSI-X table. We allow for this by creating a new 'virtual' interrupt. These interrupts are allocated as usual but are not programmed into the MSI-X table (as there may not be space for them). The MSI address and data will then handled through an NTB MSI library introduced later in this series. Signed-off-by: Logan Gunthorpe Acked-by: Bjorn Helgaas Signed-off-by: Jon Mason --- include/linux/msi.h | 8 ++++++++ include/linux/pci.h | 9 +++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index d48e919d55ae..8ad679e9d9c0 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -64,6 +64,10 @@ struct ti_sci_inta_msi_desc { * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor * + * @write_msi_msg: Callback that may be called when the MSI message + * address or data changes + * @write_msi_msg_data: Data parameter for the callback. + * * @masked: [PCI MSI/X] Mask bits * @is_msix: [PCI MSI/X] True if MSI-X * @multiple: [PCI MSI/X] log2 num of messages allocated @@ -90,6 +94,9 @@ struct msi_desc { const void *iommu_cookie; #endif + void (*write_msi_msg)(struct msi_desc *entry, void *data); + void *write_msi_msg_data; + union { /* PCI MSI/X specific data */ struct { @@ -100,6 +107,7 @@ struct msi_desc { u8 multi_cap : 3; u8 maskbit : 1; u8 is_64 : 1; + u8 is_virtual : 1; u16 entry_nr; unsigned default_irq; } msi_attrib; diff --git a/include/linux/pci.h b/include/linux/pci.h index 4a5a84d7bdd4..19b5c27c6f63 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1362,6 +1362,15 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, #define PCI_IRQ_MSI (1 << 1) /* Allow MSI interrupts */ #define PCI_IRQ_MSIX (1 << 2) /* Allow MSI-X interrupts */ #define PCI_IRQ_AFFINITY (1 << 3) /* Auto-assign affinity */ + +/* + * Virtual interrupts allow for more interrupts to be allocated + * than the device has interrupts for. These are not programmed + * into the device's MSI-X table and must be handled by some + * other driver means. + */ +#define PCI_IRQ_VIRTUAL (1 << 4) + #define PCI_IRQ_ALL_TYPES \ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) -- cgit v1.2.3 From 246a42c51bc5dd247629f86c87d5e1b7628343c4 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 23 May 2019 16:30:53 -0600 Subject: NTB: Introduce helper functions to calculate logical port number This patch introduces the "Logical Port Number" which is similar to the "Port Number" in that it enumerates the ports in the system. The original (or Physical) "Port Number" can be any number used by the hardware to uniquely identify a port in the system. The "Logical Port Number" enumerates all ports in the system from 0 to the number of ports minus one. For example a system with 5 ports might have the following port numbers which would be enumerated thusly: Port Number: 1 2 5 7 116 Logical Port Number: 0 1 2 3 4 The logical port number is useful when calculating which resources to use for which peers. So we thus define two helper functions: ntb_logical_port_number() and ntb_peer_logical_port_number() which provide the "Logical Port Number" for the local port and any peer respectively. Signed-off-by: Logan Gunthorpe Cc: Dave Jiang Cc: Allen Hubbe Cc: Serge Semin Signed-off-by: Jon Mason --- include/linux/ntb.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 52 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 604abc883741..2fadd0352683 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -616,7 +616,6 @@ static inline int ntb_port_number(struct ntb_dev *ntb) return ntb->ops->port_number(ntb); } - /** * ntb_peer_port_count() - get the number of peer device ports * @ntb: NTB device context. @@ -653,6 +652,58 @@ static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) return ntb->ops->peer_port_number(ntb, pidx); } +/** + * ntb_logical_port_number() - get the logical port number of the local port + * @ntb: NTB device context. + * + * The Logical Port Number is defined to be a unique number for each + * port starting from zero through to the number of ports minus one. + * This is in contrast to the Port Number where each port can be assigned + * any unique physical number by the hardware. + * + * The logical port number is useful for calculating the resource indexes + * used by peers. + * + * Return: the logical port number or negative value indicating an error + */ +static inline int ntb_logical_port_number(struct ntb_dev *ntb) +{ + int lport = ntb_port_number(ntb); + int pidx; + + if (lport < 0) + return lport; + + for (pidx = 0; pidx < ntb_peer_port_count(ntb); pidx++) + if (lport <= ntb_peer_port_number(ntb, pidx)) + return pidx; + + return pidx; +} + +/** + * ntb_peer_logical_port_number() - get the logical peer port by given index + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * The Logical Port Number is defined to be a unique number for each + * port starting from zero through to the number of ports minus one. + * This is in contrast to the Port Number where each port can be assigned + * any unique physical number by the hardware. + * + * The logical port number is useful for calculating the resource indexes + * used by peers. + * + * Return: the peer's logical port number or negative value indicating an error + */ +static inline int ntb_peer_logical_port_number(struct ntb_dev *ntb, int pidx) +{ + if (ntb_peer_port_number(ntb, pidx) < ntb_port_number(ntb)) + return pidx; + else + return pidx + 1; +} + /** * ntb_peer_port_idx() - get the peer device port index by given port number * @ntb: NTB device context. -- cgit v1.2.3 From 5f1b1f065c791de71017502ed3ba46779e231d9b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 23 May 2019 16:30:54 -0600 Subject: NTB: Introduce functions to calculate multi-port resource index When using multi-ports each port uses resources (dbs, msgs, mws, etc) on every other port. Creating a mapping for these resources such that each port has a corresponding resource on every other port is a bit tricky. Introduce the ntb_peer_resource_idx() function for this purpose. It returns the peer resource number that will correspond with the local peer index on the remote peer. Also, introduce ntb_peer_highest_mw_idx() which will use ntb_peer_resource_idx() but return the MW index starting with the highest index and working down. Signed-off-by: Logan Gunthorpe Cc: Dave Jiang Cc: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 2fadd0352683..bed421b9579b 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -1557,4 +1557,74 @@ static inline int ntb_peer_msg_write(struct ntb_dev *ntb, int pidx, int midx, return ntb->ops->peer_msg_write(ntb, pidx, midx, msg); } +/** + * ntb_peer_resource_idx() - get a resource index for a given peer idx + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * When constructing a graph of peers, each remote peer must use a different + * resource index (mw, doorbell, etc) to communicate with each other + * peer. + * + * In a two peer system, this function should always return 0 such that + * resource 0 points to the remote peer on both ports. + * + * In a 5 peer system, this function will return the following matrix + * + * pidx \ port 0 1 2 3 4 + * 0 0 0 1 2 3 + * 1 0 1 1 2 3 + * 2 0 1 2 2 3 + * 3 0 1 2 3 3 + * + * For example, if this function is used to program peer's memory + * windows, port 0 will program MW 0 on all it's peers to point to itself. + * port 1 will program MW 0 in port 0 to point to itself and MW 1 on all + * other ports. etc. + * + * For the legacy two host case, ntb_port_number() and ntb_peer_port_number() + * both return zero and therefore this function will always return zero. + * So MW 0 on each host would be programmed to point to the other host. + * + * Return: the resource index to use for that peer. + */ +static inline int ntb_peer_resource_idx(struct ntb_dev *ntb, int pidx) +{ + int local_port, peer_port; + + if (pidx >= ntb_peer_port_count(ntb)) + return -EINVAL; + + local_port = ntb_logical_port_number(ntb); + peer_port = ntb_peer_logical_port_number(ntb, pidx); + + if (peer_port < local_port) + return local_port - 1; + else + return local_port; +} + +/** + * ntb_peer_highest_mw_idx() - get a memory window index for a given peer idx + * using the highest index memory windows first + * + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * Like ntb_peer_resource_idx(), except it returns indexes starting with + * last memory window index. + * + * Return: the resource index to use for that peer. + */ +static inline int ntb_peer_highest_mw_idx(struct ntb_dev *ntb, int pidx) +{ + int ret; + + ret = ntb_peer_resource_idx(ntb, pidx); + if (ret < 0) + return ret; + + return ntb_mw_count(ntb, pidx) - ret - 1; +} + #endif -- cgit v1.2.3 From 26b3a37b928457ba2cd98eaf6d7b0feca5a30fa6 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 23 May 2019 16:30:56 -0600 Subject: NTB: Introduce MSI library The NTB MSI library allows passing MSI interrupts across a memory window. This offers similar functionality to doorbells or messages except will often have much better latency and the client can potentially use significantly more remote interrupts than typical hardware provides for doorbells. (Which can be important in high-multiport setups.) The library utilizes one memory window per peer and uses the highest index memory windows. Before any ntb_msi function may be used, the user must call ntb_msi_init(). It may then setup and tear down the memory windows when the link state changes using ntb_msi_setup_mws() and ntb_msi_clear_mws(). The peer which receives the interrupt must call ntb_msim_request_irq() to assign the interrupt handler (this function is functionally similar to devm_request_irq()) and the returned descriptor must be transferred to the peer which can use it to trigger the interrupt. The triggering peer, once having received the descriptor, can trigger the interrupt by calling ntb_msi_peer_trigger(). Signed-off-by: Logan Gunthorpe Cc: Dave Jiang Cc: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index bed421b9579b..8c13538aeffe 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -58,9 +58,11 @@ #include #include +#include struct ntb_client; struct ntb_dev; +struct ntb_msi; struct pci_dev; /** @@ -426,6 +428,10 @@ struct ntb_dev { spinlock_t ctx_lock; /* block unregister until device is fully released */ struct completion released; + +#ifdef CONFIG_NTB_MSI + struct ntb_msi *msi; +#endif }; #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) @@ -1627,4 +1633,71 @@ static inline int ntb_peer_highest_mw_idx(struct ntb_dev *ntb, int pidx) return ntb_mw_count(ntb, pidx) - ret - 1; } +struct ntb_msi_desc { + u32 addr_offset; + u32 data; +}; + +#ifdef CONFIG_NTB_MSI + +int ntb_msi_init(struct ntb_dev *ntb, void (*desc_changed)(void *ctx)); +int ntb_msi_setup_mws(struct ntb_dev *ntb); +void ntb_msi_clear_mws(struct ntb_dev *ntb); +int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler, + irq_handler_t thread_fn, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc); +void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, void *dev_id); +int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc); +int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc, + phys_addr_t *msi_addr); + +#else /* not CONFIG_NTB_MSI */ + +static inline int ntb_msi_init(struct ntb_dev *ntb, + void (*desc_changed)(void *ctx)) +{ + return -EOPNOTSUPP; +} +static inline int ntb_msi_setup_mws(struct ntb_dev *ntb) +{ + return -EOPNOTSUPP; +} +static inline void ntb_msi_clear_mws(struct ntb_dev *ntb) {} +static inline int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, + irq_handler_t handler, + irq_handler_t thread_fn, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc) +{ + return -EOPNOTSUPP; +} +static inline void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, + void *dev_id) {} +static inline int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc) +{ + return -EOPNOTSUPP; +} +static inline int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc, + phys_addr_t *msi_addr) +{ + return -EOPNOTSUPP; + +} + +#endif /* CONFIG_NTB_MSI */ + +static inline int ntbm_msi_request_irq(struct ntb_dev *ntb, + irq_handler_t handler, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc) +{ + return ntbm_msi_request_threaded_irq(ntb, handler, NULL, name, + dev_id, msi_desc); +} + #endif -- cgit v1.2.3 From de76cda215d56256ffcda7ffa538b70f9fb301a7 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Tue, 4 Jun 2019 18:24:43 +0200 Subject: PCI: Decode PCIe 32 GT/s link speed PCIe r5.0, sec 7.5.3.18, defines a new 32.0 GT/s bit in the Supported Link Speeds Vector of Link Capabilities 2. Decode this new speed. This does not affect the speed of the link, which should be negotiated automatically by the hardware; it only adds decoding when showing the speed to the user. Previously, reading the speed of a link operating at this speed showed "Unknown speed" instead of "32.0 GT/s". Link: https://lore.kernel.org/lkml/92365e3caf0fc559f9ab14bcd053bfc92d4f661c.1559664969.git.gustavo.pimentel@synopsys.com Signed-off-by: Gustavo Pimentel [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4a5a84d7bdd4..2173e6b75579 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -258,6 +258,7 @@ enum pci_bus_speed { PCIE_SPEED_5_0GT = 0x15, PCIE_SPEED_8_0GT = 0x16, PCIE_SPEED_16_0GT = 0x17, + PCIE_SPEED_32_0GT = 0x18, PCI_SPEED_UNKNOWN = 0xff, }; -- cgit v1.2.3 From bb2bb903042517b8fb17b2bc21e00512f2dcac01 Mon Sep 17 00:00:00 2001 From: Greg Hackmann Date: Thu, 13 Jun 2019 15:34:07 -0700 Subject: dma-buf: add DMA_BUF_SET_NAME ioctls This patch adds complimentary DMA_BUF_SET_NAME ioctls, which lets userspace processes attach a free-form name to each buffer. This information can be extremely helpful for tracking and accounting shared buffers. For example, on Android, we know what each buffer will be used for at allocation time: GL, multimedia, camera, etc. The userspace allocator can use DMA_BUF_SET_NAME to associate that information with the buffer, so we can later give developers a breakdown of how much memory they're allocating for graphics, camera, etc. Signed-off-by: Greg Hackmann Signed-off-by: Chenbo Feng Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20190613223408.139221-3-fengc@google.com --- include/linux/dma-buf.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8a327566d7f4..01ad5b942a6f 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -280,10 +280,12 @@ struct dma_buf_ops { * @file: file pointer used for sharing buffers across, and for refcounting. * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. - * @lock: used internally to serialize list manipulation, attach/detach and vmap/unmap + * @lock: used internally to serialize list manipulation, attach/detach and + * vmap/unmap, and accesses to name * @vmapping_counter: used internally to refcnt the vmaps * @vmap_ptr: the current vmap ptr if vmapping_counter > 0 * @exp_name: name of the exporter; useful for debugging. + * @name: userspace-provided name; useful for accounting and debugging. * @owner: pointer to exporter module; used for refcounting when exporter is a * kernel module. * @list_node: node for dma_buf accounting and debugging. @@ -311,6 +313,7 @@ struct dma_buf { unsigned vmapping_counter; void *vmap_ptr; const char *exp_name; + const char *name; struct module *owner; struct list_head list_node; void *priv; -- cgit v1.2.3 From 151f4e2bdc7a04020ae5c533896fb91a16e1f501 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 13 Jun 2019 07:10:36 -0300 Subject: docs: power: convert docs to ReST and rename to *.rst Convert the PM documents to ReST, in order to allow them to build with Sphinx. The conversion is actually: - add blank lines and indentation in order to identify paragraphs; - fix tables markups; - add some lists markups; - mark literal blocks; - adjust title markups. At its new index.rst, let's add a :orphan: while this is not linked to the main index.rst file, in order to avoid build warnings. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Bjorn Helgaas Acked-by: Mark Brown Acked-by: Srivatsa S. Bhat (VMware) --- include/linux/interrupt.h | 2 +- include/linux/pci.h | 2 +- include/linux/pm.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c7eef32e7739..5b8328a99b2a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -52,7 +52,7 @@ * irq line disabled until the threaded handler has been run. * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend. Does not guarantee * that this interrupt will wake the system from a suspended - * state. See Documentation/power/suspend-and-interrupts.txt + * state. See Documentation/power/suspend-and-interrupts.rst * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device diff --git a/include/linux/pci.h b/include/linux/pci.h index b74b2a4e6df2..3d9a167ca5c3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -807,7 +807,7 @@ struct module; * @suspend_late: Put device into low power state. * @resume_early: Wake device from low power state. * @resume: Wake device from low power state. - * (Please see Documentation/power/pci.txt for descriptions + * (Please see Documentation/power/pci.rst for descriptions * of PCI Power Management and the related functions.) * @shutdown: Hook into reboot_notifier_list (kernel/sys.c). * Intended to stop any idling DMA operations. diff --git a/include/linux/pm.h b/include/linux/pm.h index 66c19a65a514..c14ad8bc1a41 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -284,7 +284,7 @@ typedef struct pm_message { * actions to be performed by a device driver's callbacks generally depend on * the platform and subsystem the device belongs to. * - * Refer to Documentation/power/runtime_pm.txt for more information about the + * Refer to Documentation/power/runtime_pm.rst for more information about the * role of the @runtime_suspend(), @runtime_resume() and @runtime_idle() * callbacks in device runtime power management. */ -- cgit v1.2.3 From e1714daad7cf8fe4d6dd91adcfbbdd0604b0210d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 3 Jun 2019 10:25:31 +0200 Subject: i2c: headers: don't use 'dev' as adapter variable It is not a struct device, so 'dev' is confusing. Use 'adap', the most common name. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e982b8913b73..6bd199cfe61f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -703,14 +703,14 @@ struct i2c_adapter { }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -static inline void *i2c_get_adapdata(const struct i2c_adapter *dev) +static inline void *i2c_get_adapdata(const struct i2c_adapter *adap) { - return dev_get_drvdata(&dev->dev); + return dev_get_drvdata(&adap->dev); } -static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data) +static inline void i2c_set_adapdata(struct i2c_adapter *adap, void *data) { - dev_set_drvdata(&dev->dev, data); + dev_set_drvdata(&adap->dev, data); } static inline struct i2c_adapter * -- cgit v1.2.3 From d68222d4d6647611be5a32c80a53a145e7c80ce9 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 3 Jun 2019 10:25:32 +0200 Subject: i2c: headers: always have a named variable in arguments Much better to read and understand. Naming for i2c_adapter is not consistent (yet), so use the name which is also used in core code. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 39 ++++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 6bd199cfe61f..14e04fb4f46f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -40,7 +40,8 @@ struct i2c_device_identity; union i2c_smbus_data; struct i2c_board_info; enum i2c_slave_event; -typedef int (*i2c_slave_cb_t)(struct i2c_client *, enum i2c_slave_event, u8 *); +typedef int (*i2c_slave_cb_t)(struct i2c_client *client, + enum i2c_slave_event event, u8 *val); struct module; struct property_entry; @@ -257,16 +258,16 @@ struct i2c_driver { unsigned int class; /* Standard driver model interfaces */ - int (*probe)(struct i2c_client *, const struct i2c_device_id *); - int (*remove)(struct i2c_client *); + int (*probe)(struct i2c_client *client, const struct i2c_device_id *id); + int (*remove)(struct i2c_client *client); /* New driver model interface to aid the seamless removal of the * current probe()'s, more commonly unused than used second parameter. */ - int (*probe_new)(struct i2c_client *); + int (*probe_new)(struct i2c_client *client); /* driver model interfaces that don't relate to enumeration */ - void (*shutdown)(struct i2c_client *); + void (*shutdown)(struct i2c_client *client); /* Alert callback, for example for the SMBus alert protocol. * The format and meaning of the data value depends on the protocol. @@ -275,7 +276,7 @@ struct i2c_driver { * For the SMBus Host Notify protocol, the data corresponds to the * 16-bit payload data reported by the slave device acting as master. */ - void (*alert)(struct i2c_client *, enum i2c_alert_protocol protocol, + void (*alert)(struct i2c_client *client, enum i2c_alert_protocol protocol, unsigned int data); /* a ioctl like command that can be used to perform specific functions @@ -287,7 +288,7 @@ struct i2c_driver { const struct i2c_device_id *id_table; /* Device detection callback for automatic device creation */ - int (*detect)(struct i2c_client *, struct i2c_board_info *); + int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; struct list_head clients; @@ -447,10 +448,10 @@ extern struct i2c_client * i2c_new_probed_device(struct i2c_adapter *adap, struct i2c_board_info *info, unsigned short const *addr_list, - int (*probe)(struct i2c_adapter *, unsigned short addr)); + int (*probe)(struct i2c_adapter *adap, unsigned short addr)); /* Common custom probe functions */ -extern int i2c_probe_func_quick_read(struct i2c_adapter *, unsigned short addr); +extern int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); /* For devices that use several addresses, use i2c_new_dummy() to make * client handles for the extra addresses. @@ -466,7 +467,7 @@ i2c_new_secondary_device(struct i2c_client *client, const char *name, u16 default_addr); -extern void i2c_unregister_device(struct i2c_client *); +extern void i2c_unregister_device(struct i2c_client *client); #endif /* I2C */ /* Mainboard arch_initcall() code should register all its I2C devices. @@ -551,9 +552,9 @@ struct i2c_algorithm { * The main operations are wrapped by i2c_lock_bus and i2c_unlock_bus. */ struct i2c_lock_operations { - void (*lock_bus)(struct i2c_adapter *, unsigned int flags); - int (*trylock_bus)(struct i2c_adapter *, unsigned int flags); - void (*unlock_bus)(struct i2c_adapter *, unsigned int flags); + void (*lock_bus)(struct i2c_adapter *adapter, unsigned int flags); + int (*trylock_bus)(struct i2c_adapter *adapter, unsigned int flags); + void (*unlock_bus)(struct i2c_adapter *adapter, unsigned int flags); }; /** @@ -726,7 +727,7 @@ i2c_parent_is_i2c_adapter(const struct i2c_adapter *adapter) return NULL; } -int i2c_for_each_dev(void *data, int (*fn)(struct device *, void *)); +int i2c_for_each_dev(void *data, int (*fn)(struct device *dev, void *data)); /* Adapter locking functions, exported for shared pin cases */ #define I2C_LOCK_ROOT_ADAPTER BIT(0) @@ -832,12 +833,12 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) /* administration... */ #if IS_ENABLED(CONFIG_I2C) -extern int i2c_add_adapter(struct i2c_adapter *); -extern void i2c_del_adapter(struct i2c_adapter *); -extern int i2c_add_numbered_adapter(struct i2c_adapter *); +extern int i2c_add_adapter(struct i2c_adapter *adap); +extern void i2c_del_adapter(struct i2c_adapter *adap); +extern int i2c_add_numbered_adapter(struct i2c_adapter *adap); -extern int i2c_register_driver(struct module *, struct i2c_driver *); -extern void i2c_del_driver(struct i2c_driver *); +extern int i2c_register_driver(struct module *owner, struct i2c_driver *driver); +extern void i2c_del_driver(struct i2c_driver *driver); /* use a define to avoid include chaining to get THIS_MODULE */ #define i2c_add_driver(driver) \ -- cgit v1.2.3 From 2caea56f569ac361fc854f6bf2fe94b70514c917 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 3 Jun 2019 10:25:34 +0200 Subject: i2c: headers: update docs about I2C_CLIENT_* Update kerneldoc for i2c client flags because they increased over time. Also, move them to a position where they can be more easily found. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 14e04fb4f46f..9853fae9b505 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -298,8 +298,7 @@ struct i2c_driver { /** * struct i2c_client - represent an I2C slave device - * @flags: I2C_CLIENT_TEN indicates the device uses a ten bit chip address; - * I2C_CLIENT_PEC indicates it uses SMBus Packet Error Checking + * @flags: see I2C_CLIENT_* for possible flags * @addr: Address used on the I2C bus connected to the parent adapter. * @name: Indicates the type of the device, usually a chip name that's * generic enough to hide second-sourcing and compatible revisions. @@ -317,6 +316,15 @@ struct i2c_driver { */ struct i2c_client { unsigned short flags; /* div., see below */ +#define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ +#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ + /* Must equal I2C_M_TEN below */ +#define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ +#define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ +#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ +#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ + /* Must match I2C_M_STOP|IGNORE_NAK */ + unsigned short addr; /* chip address - NOTE: 7bit */ /* addresses are stored in the */ /* _LOWER_ 7 bits */ @@ -803,16 +811,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) i2c_unlock_bus(adap, I2C_LOCK_ROOT_ADAPTER); } -/*flags for the client struct: */ -#define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ -#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ - /* Must equal I2C_M_TEN below */ -#define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ -#define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ -#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ -#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ - /* Must match I2C_M_STOP|IGNORE_NAK */ - /* i2c adapter classes (bitmask) */ #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ #define I2C_CLASS_DDC (1<<3) /* DDC bus on graphics adapters */ -- cgit v1.2.3 From 76cc9f0efd952d376e93e79b1f19fd6fdb8291bc Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 3 Jun 2019 10:25:35 +0200 Subject: i2c: headers: reformat header comment and update copyright Let's stick to coding style. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 9853fae9b505..d8f9060179d0 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1,16 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/* ------------------------------------------------------------------------- */ -/* */ -/* i2c.h - definitions for the i2c-bus interface */ -/* */ -/* ------------------------------------------------------------------------- */ -/* Copyright (C) 1995-2000 Simon G. Vogl - +/* + * i2c.h - definitions for the Linux i2c bus interface + * Copyright (C) 1995-2000 Simon G. Vogl + * Copyright (C) 2013-2019 Wolfram Sang + * + * With some changes from Kyösti Mälkki and + * Frodo Looijaard */ -/* ------------------------------------------------------------------------- */ - -/* With some changes from Kyösti Mälkki and - Frodo Looijaard */ #ifndef _LINUX_I2C_H #define _LINUX_I2C_H -- cgit v1.2.3 From 013e868bc9465452c7b667830712ab57de236d08 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 15 May 2019 15:38:47 +0530 Subject: mfd: lp87565: Add support for 4-phase LP87561 combination Add support for 4-phase LP87561 combination. Data Sheet: https://www.ti.com/lit/ds/symlink/lp87561-q1.pdf Signed-off-by: Keerthy Signed-off-by: Lee Jones --- include/linux/mfd/lp87565.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h index d0c91ba65525..976447607ea2 100644 --- a/include/linux/mfd/lp87565.h +++ b/include/linux/mfd/lp87565.h @@ -17,6 +17,7 @@ enum lp87565_device_type { LP87565_DEVICE_TYPE_UNKNOWN = 0, + LP87565_DEVICE_TYPE_LP87561_Q1, LP87565_DEVICE_TYPE_LP87565_Q1, }; @@ -249,6 +250,7 @@ enum LP87565_regulator_id { LP87565_BUCK_3, LP87565_BUCK_10, LP87565_BUCK_23, + LP87565_BUCK_3210, }; /** -- cgit v1.2.3 From e7488e58c7cfe4be0c52db68622a0397bb75258e Mon Sep 17 00:00:00 2001 From: Yurii Pavlovskyi Date: Tue, 14 May 2019 20:59:01 +0200 Subject: platform/x86: wmi: Add function to get _UID of WMI device Add a new function to acpi.h / wmi.c that returns _UID of the ACPI WMI device. For example, it returns "ATK" for the following declaration in DSDT: Device (ATKD) { Name (_HID, "PNP0C14" /* Windows Management Instrumentation Device */) // _HID: Hardware ID Name (_UID, "ATK") // _UID: Unique ID .. Generally, it is possible that multiple PNP0C14 ACPI devices are present in the system as mentioned in the commit message of commit bff431e49ff5 ("ACPI: WMI: Add ACPI-WMI mapping driver"). Therefore the _UID is returned for a specific ACPI device that declares the given GUID, to which it is also mapped by other methods of wmi module. Signed-off-by: Yurii Pavlovskyi Signed-off-by: Andy Shevchenko --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 98440df7fe42..d867a9a904f9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -380,6 +380,7 @@ extern acpi_status wmi_install_notify_handler(const char *guid, extern acpi_status wmi_remove_notify_handler(const char *guid); extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out); extern bool wmi_has_guid(const char *guid); +extern char *wmi_get_acpi_device_uid(const char *guid); #endif /* CONFIG_ACPI_WMI */ -- cgit v1.2.3 From e0668f28888184f6c633110a37386f2d4a6fa00e Mon Sep 17 00:00:00 2001 From: Yurii Pavlovskyi Date: Tue, 14 May 2019 21:00:31 +0200 Subject: platform/x86: asus-wmi: Improve DSTS WMI method ID detection The DSTS method detection mistakenly selects DCTS instead of DSTS if nothing is returned when the method ID is not defined in WMNB. As a result, the control of keyboard backlight is not functional for TUF Gaming series laptops. Implement detection based on _UID of the WMI device instead. There is evidence that DCTS is handled by ACPI WMI devices that have _UID ASUSWMI, whereas none of the devices without ASUSWMI respond to DCTS and DSTS is used instead [1]. DSDT examples: FX505GM (_UID ATK): Method (WMNB, 3, Serialized) { ... If ((Local0 == 0x53545344)) { ... Return (Zero) } ... // No return } K54C (_UID ATK): Method (WMNB, 3, Serialized) { ... If ((Local0 == 0x53545344)) { ... Return (0x02) } ... Return (0xFFFFFFFE) } [1] Link: https://lkml.org/lkml/2019/4/11/322 Signed-off-by: Yurii Pavlovskyi Suggested-by: Daniel Drake Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index bfba245636a7..0668f76df921 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -18,8 +18,8 @@ #define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ #define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ #define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ -#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ -#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ +#define ASUS_WMI_METHODID_DCTS 0x53544344 /* Device status (DCTS) */ +#define ASUS_WMI_METHODID_DSTS 0x53545344 /* Device status (DSTS) */ #define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ #define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ #define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ -- cgit v1.2.3 From b096f626a6827ad2ced5ebdbdc04e62422d463f6 Mon Sep 17 00:00:00 2001 From: Yurii Pavlovskyi Date: Tue, 14 May 2019 21:07:05 +0200 Subject: platform/x86: asus-wmi: Switch fan boost mode The WMI exposes a write-only device ID where up to three fan modes can be switched on some laptops (TUF Gaming FX505GM). There is a hotkey combination Fn-F5 that does have a fan icon, which is designed to toggle between fan modes. The DSTS of the device ID returns information about the presence of this capability and the presence of each of the two additional fan modes as a bitmask (0x01 - overboost present, 0x02 - silent present) [1]. Add a SysFS entry that reads the last written value and updates value in WMI on write and a hotkey handler that toggles the modes taking into account their availability according to DSTS. Modes: * 0x00 - normal or balanced, * 0x01 - overboost, increased fan RPM, * 0x02 - silent, decreased fan RPM [1] Link: https://lkml.org/lkml/2019/4/12/110 Signed-off-by: Yurii Pavlovskyi Suggested-by: Daniel Drake Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 0668f76df921..8551156b8dca 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -57,6 +57,7 @@ #define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 #define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ #define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 +#define ASUS_WMI_DEVID_FAN_MODE 0x00110018 /* Misc */ #define ASUS_WMI_DEVID_CAMERA 0x00060013 -- cgit v1.2.3 From a48e23385fcf397e69e2a75d72a81c545ec8bec2 Mon Sep 17 00:00:00 2001 From: Mattias Jacobsson <2pi@mok.nu> Date: Mon, 27 May 2019 18:21:29 +0200 Subject: platform/x86: wmi: add context pointer field to struct wmi_device_id When using wmi_install_notify_handler() to initialize a WMI handler a data pointer can be supplied which will be passed on to the notification handler. No similar feature exist when handling WMI events via struct wmi_driver. Add a context field pointer to struct wmi_device_id and add a function find_guid_context() to retrieve that context pointer. Signed-off-by: Mattias Jacobsson <2pi@mok.nu> Signed-off-by: Andy Shevchenko --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 448621c32e4d..09366859aac2 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -798,6 +798,7 @@ struct tee_client_device_id { */ struct wmi_device_id { const char guid_string[UUID_STRING_LEN+1]; + const void *context; }; #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From 440c4983de262f78033ec58f6abcd199a664327d Mon Sep 17 00:00:00 2001 From: Mattias Jacobsson <2pi@mok.nu> Date: Mon, 27 May 2019 18:21:30 +0200 Subject: platform/x86: wmi: add context argument to the probe function The struct wmi_device_id has a context pointer field, forward this pointer as an argument to the probe function in struct wmi_driver. Update existing users of the same probe function to accept this new context argument. Signed-off-by: Mattias Jacobsson <2pi@mok.nu> Signed-off-by: Andy Shevchenko --- include/linux/wmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 592f81afecbb..1e84c474a993 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -44,7 +44,7 @@ struct wmi_driver { struct device_driver driver; const struct wmi_device_id *id_table; - int (*probe)(struct wmi_device *wdev); + int (*probe)(struct wmi_device *wdev, const void *context); int (*remove)(struct wmi_device *wdev); void (*notify)(struct wmi_device *device, union acpi_object *data); long (*filter_callback)(struct wmi_device *wdev, unsigned int cmd, -- cgit v1.2.3 From 99600fd47eafd20b9ba6e04562bb2fcc48475344 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 22 Apr 2019 07:15:05 +0800 Subject: clk: Add CLK_HW_INIT_* macros using .parent_hws With the new clk parenting code, struct clk_init_data was expanded to include .parent_hws, for clk drivers to directly list parents by pointing to their respective struct clk_hw's. Add macros that can take either one single struct clk_hw *, or an array of them, for drivers to use. A special CLK_HW_INIT_HWS macro is included, which takes an array of struct clk_hw *, but sets .num_parents to 1. This variant is to allow the reuse of the array, instead of having a compound literal allocated for each clk sharing the same parent. Signed-off-by: Chen-Yu Tsai --- include/linux/clk-provider.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index bb6118f79784..70aad5cefea7 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -904,6 +904,29 @@ extern struct of_device_id __clk_of_table; .ops = _ops, \ }) +#define CLK_HW_INIT_HW(_name, _parent, _ops, _flags) \ + (&(struct clk_init_data) { \ + .flags = _flags, \ + .name = _name, \ + .parent_hws = (const struct clk_hw*[]) { _parent }, \ + .num_parents = 1, \ + .ops = _ops, \ + }) + +/* + * This macro is intended for drivers to be able to share the otherwise + * individual struct clk_hw[] compound literals created by the compiler + * when using CLK_HW_INIT_HW. It does NOT support multiple parents. + */ +#define CLK_HW_INIT_HWS(_name, _parent, _ops, _flags) \ + (&(struct clk_init_data) { \ + .flags = _flags, \ + .name = _name, \ + .parent_hws = _parent, \ + .num_parents = 1, \ + .ops = _ops, \ + }) + #define CLK_HW_INIT_PARENTS(_name, _parents, _ops, _flags) \ (&(struct clk_init_data) { \ .flags = _flags, \ @@ -913,6 +936,15 @@ extern struct of_device_id __clk_of_table; .ops = _ops, \ }) +#define CLK_HW_INIT_PARENTS_HW(_name, _parents, _ops, _flags) \ + (&(struct clk_init_data) { \ + .flags = _flags, \ + .name = _name, \ + .parent_hws = _parents, \ + .num_parents = ARRAY_SIZE(_parents), \ + .ops = _ops, \ + }) + #define CLK_HW_INIT_NO_PARENT(_name, _ops, _flags) \ (&(struct clk_init_data) { \ .flags = _flags, \ -- cgit v1.2.3 From 2d6b4f33e637bf51c50c536966a19e94a59f3212 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 3 May 2019 11:49:03 +0800 Subject: clk: Add CLK_HW_INIT_FW_NAME macro using .fw_name in .parent_data With the new clk parenting code, clk_init_data was expanded to include .parent_data, for clk drivers that have parents referenced using a combination of device tree clock-names, clock indices, and/or clk_hw pointers. Add a CLK_HW_INIT macro for specifying a single parent from the device tree using .fw_name in struct clk_parent_data. Signed-off-by: Chen-Yu Tsai --- include/linux/clk-provider.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 70aad5cefea7..b19063512a29 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -927,6 +927,17 @@ extern struct of_device_id __clk_of_table; .ops = _ops, \ }) +#define CLK_HW_INIT_FW_NAME(_name, _parent, _ops, _flags) \ + (&(struct clk_init_data) { \ + .flags = _flags, \ + .name = _name, \ + .parent_data = (const struct clk_parent_data[]) { \ + { .fw_name = _parent }, \ + }, \ + .num_parents = 1, \ + .ops = _ops, \ + }) + #define CLK_HW_INIT_PARENTS(_name, _parents, _ops, _flags) \ (&(struct clk_init_data) { \ .flags = _flags, \ -- cgit v1.2.3 From 13933109dff0a5abbfc3980304c6c21c90829810 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 22 Apr 2019 07:17:50 +0800 Subject: clk: Add CLK_HW_INIT_PARENT_DATA macro using .parent_data With the new clk parenting code, struct clk_init_data was expanded to include .parent_data, for clk drivers that have parents referenced using a combination of device tree clock-names, clock indices, and/or struct clk_hw pointers. Add a new macro that can take a list of struct clk_parent_data for drivers to use. Signed-off-by: Chen-Yu Tsai --- include/linux/clk-provider.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index b19063512a29..0fd14c4874d6 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -956,6 +956,15 @@ extern struct of_device_id __clk_of_table; .ops = _ops, \ }) +#define CLK_HW_INIT_PARENTS_DATA(_name, _parents, _ops, _flags) \ + (&(struct clk_init_data) { \ + .flags = _flags, \ + .name = _name, \ + .parent_data = _parents, \ + .num_parents = ARRAY_SIZE(_parents), \ + .ops = _ops, \ + }) + #define CLK_HW_INIT_NO_PARENT(_name, _ops, _flags) \ (&(struct clk_init_data) { \ .flags = _flags, \ -- cgit v1.2.3 From d7b15114aba956ca395ec5cc28f68fe861ffc208 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 22 Apr 2019 07:19:46 +0800 Subject: clk: fixed-factor: Add CLK_FIXED_FACTOR_HW which takes clk_hw pointer as parent With the new clk parenting code, clk_init_data was expanded to include .parent_hws, for clk drivers to directly reference parents by clk_hw. Add a new macro, CLK_FIXED_FACTOR_HW, that can take a struct clk_hw pointer, instead of a string, as its parent. Signed-off-by: Chen-Yu Tsai --- include/linux/clk-provider.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 0fd14c4874d6..c85e9f3809f2 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -985,6 +985,17 @@ extern struct of_device_id __clk_of_table; _flags), \ } +#define CLK_FIXED_FACTOR_HW(_struct, _name, _parent, \ + _div, _mult, _flags) \ + struct clk_fixed_factor _struct = { \ + .div = _div, \ + .mult = _mult, \ + .hw.init = CLK_HW_INIT_HW(_name, \ + _parent, \ + &clk_fixed_factor_ops, \ + _flags), \ + } + #ifdef CONFIG_OF int of_clk_add_provider(struct device_node *np, struct clk *(*clk_src_get)(struct of_phandle_args *args, -- cgit v1.2.3 From 1bef004e2680511ecbb6b5db3954fba430501ecb Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 6 May 2019 10:43:16 +0800 Subject: clk: fixed-factor: Add CLK_FIXED_FACTOR_HWS which takes list of struct clk_hw * With the new clk parenting code, clk_init_data was expanded to include .parent_hws, for clk drivers to directly reference parents by clk_hw. Add a new macro, CLK_FIXED_FACTOR_HWS, that can take an array of pointers to struct clk_hw, instead of a string, as its parent. Taking an array instead of a direct pointer allows the reuse of the array for multiple clks, rather than having one compound literal with the same contents allocated for each clk declaration. Signed-off-by: Chen-Yu Tsai --- include/linux/clk-provider.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c85e9f3809f2..146a6859969e 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -996,6 +996,21 @@ extern struct of_device_id __clk_of_table; _flags), \ } +/* + * This macro allows the driver to reuse the _parent array for multiple + * fixed factor clk declarations. + */ +#define CLK_FIXED_FACTOR_HWS(_struct, _name, _parent, \ + _div, _mult, _flags) \ + struct clk_fixed_factor _struct = { \ + .div = _div, \ + .mult = _mult, \ + .hw.init = CLK_HW_INIT_HWS(_name, \ + _parent, \ + &clk_fixed_factor_ops, \ + _flags), \ + } + #ifdef CONFIG_OF int of_clk_add_provider(struct device_node *np, struct clk *(*clk_src_get)(struct of_phandle_args *args, -- cgit v1.2.3 From 8b13a48b891c7c855e9f3a401d91391a946f4ca7 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 3 May 2019 11:58:20 +0800 Subject: clk: fixed-factor: Add CLK_FIXED_FACTOR_FW_NAME for DT clock-names parent With the new clk parenting code, clk_init_data was expanded to include .parent_data, for clk drivers to specify parents using a combination of device tree clock-names, pointers to struct clk_hw, device tree clocks, and/or fallback global clock names. Add a new macro, CLK_FIXED_FACTOR_FW_NAME, that takes a string to match a clock-names entry in the device tree to specify the clock parent. Signed-off-by: Chen-Yu Tsai --- include/linux/clk-provider.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 146a6859969e..e5c44f6dd897 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1011,6 +1011,17 @@ extern struct of_device_id __clk_of_table; _flags), \ } +#define CLK_FIXED_FACTOR_FW_NAME(_struct, _name, _parent, \ + _div, _mult, _flags) \ + struct clk_fixed_factor _struct = { \ + .div = _div, \ + .mult = _mult, \ + .hw.init = CLK_HW_INIT_FW_NAME(_name, \ + _parent, \ + &clk_fixed_factor_ops, \ + _flags), \ + } + #ifdef CONFIG_OF int of_clk_add_provider(struct device_node *np, struct clk *(*clk_src_get)(struct of_phandle_args *args, -- cgit v1.2.3 From 4eb293487d05a69862a4907ee944aa271ed49a4c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 13 Jun 2019 10:55:32 +0900 Subject: pinctrl: make pinconf.h self-contained This header uses 'bool', but it does not include any header by itself. So, it could cause unknown type name error, depending on the header include order, although probably has been included by someone else. Include to make it self-contained. Signed-off-by: Masahiro Yamada Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index 93c9dd133e9d..9bebc3554809 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -14,6 +14,8 @@ #ifdef CONFIG_PINCONF +#include + struct pinctrl_dev; struct seq_file; -- cgit v1.2.3 From 29875a52915e09abb9703722054f6443cb492ccc Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 12 Oct 2018 17:06:06 +0200 Subject: mm: Add an apply_to_pfn_range interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is basically apply_to_page_range with added functionality: Allocating missing parts of the page table becomes optional, which means that the function can be guaranteed not to error if allocation is disabled. Also passing of the closure struct and callback function becomes different and more in line with how things are done elsewhere. Finally we keep apply_to_page_range as a wrapper around apply_to_pfn_range The reason for not using the page-walk code is that we want to perform the page-walk on vmas pointing to an address space without requiring the mmap_sem to be held rather than on vmas belonging to a process with the mmap_sem held. Notable changes since RFC: Don't export apply_to_pfn range. Cc: Andrew Morton Cc: Matthew Wilcox Cc: Will Deacon Cc: Peter Zijlstra Cc: Rik van Riel Cc: Minchan Kim Cc: Michal Hocko Cc: Huang Ying Cc: Souptick Joarder Cc: "Jérôme Glisse" Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Thomas Hellstrom Reviewed-by: Ralph Campbell #v1 --- include/linux/mm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0e8834ac32b7..3d06ce2a64af 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2675,6 +2675,16 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); +struct pfn_range_apply; +typedef int (*pter_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, + struct pfn_range_apply *closure); +struct pfn_range_apply { + struct mm_struct *mm; + pter_fn_t ptefn; + unsigned int alloc; +}; +extern int apply_to_pfn_range(struct pfn_range_apply *closure, + unsigned long address, unsigned long size); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); -- cgit v1.2.3 From 4fe51e9e7902b5724b618dadd9527b1bbf2b55cc Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 19 Mar 2019 13:12:30 +0100 Subject: mm: Add write-protect and clean utilities for address space ranges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add two utilities to a) write-protect and b) clean all ptes pointing into a range of an address space. The utilities are intended to aid in tracking dirty pages (either driver-allocated system memory or pci device memory). The write-protect utility should be used in conjunction with page_mkwrite() and pfn_mkwrite() to trigger write page-faults on page accesses. Typically one would want to use this on sparse accesses into large memory regions. The clean utility should be used to utilize hardware dirtying functionality and avoid the overhead of page-faults, typically on large accesses into small memory regions. The added file "as_dirty_helpers.c" is initially listed as maintained by VMware under our DRM driver. If somebody would like it elsewhere, that's of course no problem. Notable changes since RFC: - Added comments to help avoid the usage of these function for VMAs it's not intended for. We also do advisory checks on the vm_flags and warn on illegal usage. - Perform the pte modifications the same way softdirty does. - Add mmu_notifier range invalidation calls. - Add a config option so that this code is not unconditionally included. - Tell the mmu_gather code about pending tlb flushes. Cc: Andrew Morton Cc: Matthew Wilcox Cc: Will Deacon Cc: Peter Zijlstra Cc: Rik van Riel Cc: Minchan Kim Cc: Michal Hocko Cc: Huang Ying Cc: Souptick Joarder Cc: "Jérôme Glisse" Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Thomas Hellstrom Reviewed-by: Ralph Campbell #v1 --- include/linux/mm.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3d06ce2a64af..a0bc2a82917e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2685,7 +2685,14 @@ struct pfn_range_apply { }; extern int apply_to_pfn_range(struct pfn_range_apply *closure, unsigned long address, unsigned long size); - +unsigned long apply_as_wrprotect(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr); +unsigned long apply_as_clean(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr, + pgoff_t bitmap_pgoff, + unsigned long *bitmap, + pgoff_t *start, + pgoff_t *end); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); -- cgit v1.2.3 From 378a60406415bd20ec6e845a3d6883d460656537 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 23 May 2019 11:17:22 -0300 Subject: mm/hmm: Remove duplicate condition test before wait_event_timeout The wait_event_timeout macro already tests the condition as its first action, so there is no reason to open code another version of this, all that does is skip the might_sleep() debugging in common cases, which is not helpful. Further, based on prior patches, we can now simplify the required condition test: - If range is valid memory then so is range->hmm - If hmm_release() has run then range->valid is set to false at the same time as dead, so no reason to check both. - A valid hmm has a valid hmm->mm. Allowing the return value of wait_event_timeout() (along with its internal barriers) to compute the result of the function. Signed-off-by: Jason Gunthorpe Reviewed-by: Ralph Campbell Reviewed-by: John Hubbard Reviewed-by: Ira Weiny Reviewed-by: Christoph Hellwig Tested-by: Philip Yang --- include/linux/hmm.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 1d97b6d62c5b..26e7c477490c 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -209,17 +209,8 @@ static inline unsigned long hmm_range_page_size(const struct hmm_range *range) static inline bool hmm_range_wait_until_valid(struct hmm_range *range, unsigned long timeout) { - /* Check if mm is dead ? */ - if (range->hmm == NULL || range->hmm->dead || range->hmm->mm == NULL) { - range->valid = false; - return false; - } - if (range->valid) - return true; - wait_event_timeout(range->hmm->wq, range->valid || range->hmm->dead, - msecs_to_jiffies(timeout)); - /* Return current valid status just in case we get lucky */ - return range->valid; + return wait_event_timeout(range->hmm->wq, range->valid, + msecs_to_jiffies(timeout)) != 0; } /* -- cgit v1.2.3 From 47f245985a4f3e270b1e4f28aa49f4c939527981 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 23 May 2019 11:08:28 -0300 Subject: mm/hmm: Hold on to the mmget for the lifetime of the range Range functions like hmm_range_snapshot() and hmm_range_fault() call find_vma, which requires hodling the mmget() and the mmap_sem for the mm. Make this simpler for the callers by holding the mmget() inside the range for the lifetime of the range. Other functions that accept a range should only be called if the range is registered. This has the side effect of directly preventing hmm_release() from happening while a range is registered. That means range->dead cannot be false during the lifetime of the range, so remove dead and hmm_mirror_mm_is_alive() entirely. Signed-off-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: Ralph Campbell Reviewed-by: Christoph Hellwig Tested-by: Philip Yang --- include/linux/hmm.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 26e7c477490c..bf013e965257 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -82,7 +82,6 @@ * @mirrors_sem: read/write semaphore protecting the mirrors list * @wq: wait queue for user waiting on a range invalidation * @notifiers: count of active mmu notifiers - * @dead: is the mm dead ? */ struct hmm { struct mm_struct *mm; @@ -95,7 +94,6 @@ struct hmm { wait_queue_head_t wq; struct rcu_head rcu; long notifiers; - bool dead; }; /* @@ -459,30 +457,6 @@ struct hmm_mirror { int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); void hmm_mirror_unregister(struct hmm_mirror *mirror); -/* - * hmm_mirror_mm_is_alive() - test if mm is still alive - * @mirror: the HMM mm mirror for which we want to lock the mmap_sem - * Return: false if the mm is dead, true otherwise - * - * This is an optimization, it will not always accurately return false if the - * mm is dead; i.e., there can be false negatives (process is being killed but - * HMM is not yet informed of that). It is only intended to be used to optimize - * out cases where the driver is about to do something time consuming and it - * would be better to skip it if the mm is dead. - */ -static inline bool hmm_mirror_mm_is_alive(struct hmm_mirror *mirror) -{ - struct mm_struct *mm; - - if (!mirror || !mirror->hmm) - return false; - mm = READ_ONCE(mirror->hmm->mm); - if (mirror->hmm->dead || !mm) - return false; - - return true; -} - /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -- cgit v1.2.3 From a78cf9657ba5426f54aa93a067c10d097944c082 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sat, 15 Jun 2019 10:23:57 +1000 Subject: PCI/ACPI: Evaluate PCI Boot Configuration _DSM Evaluate _DSM Function #5, the "PCI Boot Configuration" function. If the result is 0, the OS should preserve any resource assignments made by the firmware. Link: https://lore.kernel.org/r/20190615002359.29577-2-benh@kernel.crashing.org Signed-off-by: Benjamin Herrenschmidt [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas --- include/linux/pci-acpi.h | 7 ++++--- include/linux/pci.h | 2 ++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 8082b612f561..62b7fdcc661c 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -107,9 +107,10 @@ static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } #endif extern const guid_t pci_acpi_dsm_guid; -#define DEVICE_LABEL_DSM 0x07 -#define RESET_DELAY_DSM 0x08 -#define FUNCTION_DELAY_DSM 0x09 +#define IGNORE_PCI_BOOT_CONFIG_DSM 0x05 +#define DEVICE_LABEL_DSM 0x07 +#define RESET_DELAY_DSM 0x08 +#define FUNCTION_DELAY_DSM 0x09 #else /* CONFIG_ACPI */ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } diff --git a/include/linux/pci.h b/include/linux/pci.h index 4a5a84d7bdd4..5e2b309363a3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -505,6 +505,8 @@ struct pci_host_bridge { unsigned int native_shpc_hotplug:1; /* OS may use SHPC hotplug */ unsigned int native_pme:1; /* OS may use PCIe PME */ unsigned int native_ltr:1; /* OS may use PCIe LTR */ + unsigned int preserve_config:1; /* Preserve FW resource setup */ + /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, const struct resource *res, -- cgit v1.2.3 From d308dfbf62eff897d71968d764f21a78678ee0a5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 18 Jun 2019 12:58:33 +0200 Subject: i2c: mux/i801: Switch to use descriptor passing This switches the i801 GPIO mux to use GPIO descriptors for handling the GPIO lines. The previous hack which was reaching inside the GPIO chips etc cannot live on. We pass descriptors along with the GPIO mux device at creation instead. The GPIO mux was only used by way of platform data with a platform device from one place in the kernel: the i801 i2c bus driver. Let's just associate the GPIO descriptor table with the actual device like everyone else and dynamically create a descriptor table passed along with the GPIO i2c mux. This enables simplification of the GPIO i2c mux driver to use only the descriptor API and the OF probe path gets simplified in the process. The i801 driver was registering the GPIO i2c mux with PLATFORM_DEVID_AUTO which would make it hard to predict the device name and assign the descriptor table properly, but this seems to be a mistake to begin with: all of the GPIO mux devices are hardcoded to look up GPIO lines from the "gpio_ich" GPIO chip. If there are more than one mux, there is certainly more than one gpio chip as well, and then we have more serious problems. Switch to PLATFORM_DEVID_NONE instead. There can be only one. Cc: Mika Westerberg Cc: Andy Shevchenko Cc: Peter Rosin Cc: Jean Delvare Signed-off-by: Serge Semin Signed-off-by: Linus Walleij Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg [Removed a newline, suggested by Andy. /Peter] Signed-off-by: Peter Rosin --- include/linux/platform_data/i2c-mux-gpio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/i2c-mux-gpio.h b/include/linux/platform_data/i2c-mux-gpio.h index 4406108201fe..28f288eed652 100644 --- a/include/linux/platform_data/i2c-mux-gpio.h +++ b/include/linux/platform_data/i2c-mux-gpio.h @@ -22,10 +22,6 @@ * position * @n_values: Number of multiplexer positions (busses to instantiate) * @classes: Optional I2C auto-detection classes - * @gpio_chip: Optional GPIO chip name; if set, GPIO pin numbers are given - * relative to the base GPIO number of that chip - * @gpios: Array of GPIO numbers used to control MUX - * @n_gpios: Number of GPIOs used to control MUX * @idle: Bitmask to write to MUX when idle or GPIO_I2CMUX_NO_IDLE if not used */ struct i2c_mux_gpio_platform_data { @@ -34,9 +30,6 @@ struct i2c_mux_gpio_platform_data { const unsigned *values; int n_values; const unsigned *classes; - char *gpio_chip; - const unsigned *gpios; - int n_gpios; unsigned idle; }; -- cgit v1.2.3 From 62de37da9f382455b983f2f92b10012109005278 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 20 Jun 2019 15:26:29 +0300 Subject: mtd: spi-nor: intel-spi: Convert to use SPDX identifier This gets rid of the license boilerplate duplicated in each file. No functional changes intended. Signed-off-by: Mika Westerberg Signed-off-by: Tudor Ambarus --- include/linux/platform_data/intel-spi.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h index 942b0c3f8f08..001f377fb5ef 100644 --- a/include/linux/platform_data/intel-spi.h +++ b/include/linux/platform_data/intel-spi.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Intel PCH/PCU SPI flash driver. * * Copyright (C) 2016, Intel Corporation * Author: Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef INTEL_SPI_PDATA_H -- cgit v1.2.3 From e67d4dfc9ff19dbe74b29617cf2592ccc50c3920 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Wed, 12 Jun 2019 01:44:04 -0700 Subject: power: supply: Add HWMON compatibility layer Add code implementing HWMON adapter/compatibility layer to allow expositing various sensors present on power supply devices via HWMON subsystem. This is done in order to allow userspace to use single ABI/library(libsensors) to access/manipulate all of the sensors of the system. Signed-off-by: Andrey Smirnov Reviewed-by: Guenter Roeck Tested-by: Chris Healy Cc: Chris Healy Cc: Cory Tusar Cc: Lucas Stach Cc: Fabio Estevam Cc: Guenter Roeck Cc: Sebastian Reichel Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index d9c0c094f8a0..d5b15e039f4f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -481,4 +481,17 @@ static inline bool power_supply_is_watt_property(enum power_supply_property psp) return 0; } +#ifdef CONFIG_POWER_SUPPLY_HWMON +int power_supply_add_hwmon_sysfs(struct power_supply *psy); +void power_supply_remove_hwmon_sysfs(struct power_supply *psy); +#else +static inline int power_supply_add_hwmon_sysfs(struct power_supply *psy) +{ + return 0; +} + +static inline +void power_supply_remove_hwmon_sysfs(struct power_supply *psy) {} +#endif + #endif /* __LINUX_POWER_SUPPLY_H__ */ -- cgit v1.2.3 From 38b37d631aec80da0c65ac03a7ef680b468c7857 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 7 Jun 2019 12:49:11 +0200 Subject: module: allow arch overrides for .exit section names Some archs like ARM store unwind information for .exit.text in sections with unusual names. As this unwind information refers to .exit.text, it must not be loaded when .exit.text is not loaded (when CONFIG_MODULE_UNLOAD is unset); otherwise, loading a module can fail due to relocation failures. Signed-off-by: Matthias Schiffer Signed-off-by: Jessica Yu --- include/linux/moduleloader.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 31013c2effd3..5229c18025e9 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -29,6 +29,11 @@ void *module_alloc(unsigned long size); /* Free memory returned from module_alloc. */ void module_memfree(void *module_region); +/* Determines if the section name is an exit section (that is only used during + * module unloading) + */ +bool module_exit_section(const char *name); + /* * Apply the given relocation to the (simplified) ELF. Return -error * or 0. -- cgit v1.2.3 From 38ca87c6f1e514686d4a385246d1afe1e1f2e482 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Tue, 11 Jun 2019 18:52:46 +0300 Subject: RDMA/mlx5: Introduce and implement new IB_WR_REG_MR_INTEGRITY work request This new WR will be used to perform PI (protection information) handover using the new API. Using the new API, the user will post a single WR that will internally perform all the needed actions to complete PI operation. This new WR will use a memory region that was allocated as IB_MR_TYPE_INTEGRITY and was mapped using ib_map_mr_sg_pi to perform the registration. In the old API, in order to perform a signature handover operation, each ULP should perform the following: 1. Map and register the data buffers. 2. Map and register the protection buffers. 3. Post a special reg WR to configure the signature handover operation layout. 4. Invalidate the signature memory key. 5. Invalidate protection buffers memory key. 6. Invalidate data buffers memory key. In the new API, the mapping of both data and protection buffers is performed using a single call to ib_map_mr_sg_pi function. Also the registration of the buffers and the configuration of the signature operation layout is done by a single new work request called IB_WR_REG_MR_INTEGRITY. This patch implements this operation for mlx5 devices that are capable to offload data integrity generation/validation while performing the actual buffer transfer. This patch will not remove the old signature API that is used by the iSER initiator and target drivers. This will be done in the future. In the internal implementation, for each IB_WR_REG_MR_INTEGRITY work request, we are using a single UMR operation to register both data and protection buffers using KLM's. Afterwards, another UMR operation will describe the strided block format. These will be followed by 2 SET_PSV operations to set the memory/wire domains initial signature parameters passed by the user. In the end of the whole transaction, only the signature memory key (the one that exposed for the RDMA operation) will be invalidated. Signed-off-by: Max Gurtovoy Signed-off-by: Israel Rukshin Reviewed-by: Sagi Grimberg Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/qp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 3ba4edbd17a6..08e43cd9e742 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -37,7 +37,8 @@ #include #define MLX5_INVALID_LKEY 0x100 -#define MLX5_SIG_WQE_SIZE (MLX5_SEND_WQE_BB * 5) +/* UMR (3 WQE_BB's) + SIG (3 WQE_BB's) + PSV (mem) + PSV (wire) */ +#define MLX5_SIG_WQE_SIZE (MLX5_SEND_WQE_BB * 8) #define MLX5_DIF_SIZE 8 #define MLX5_STRIDE_BLOCK_OP 0x400 #define MLX5_CPY_GRD_MASK 0xc0 -- cgit v1.2.3 From ec6516bfbaf72e7c81811162b6de96322e32a027 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 13 Jun 2019 10:55:31 +0900 Subject: pinctrl: remove unneeded #ifdef around declarations What is the point in surrounding the whole of declarations with ifdef like this? #ifdef CONFIG_FOO int foo(void); #endif If CONFIG_FOO is not defined, all callers of foo() will fail with implicit declaration errors since the top Makefile adds -Werror-implicit-function-declaration to KBUILD_CFLAGS. This breaks the build earlier when you are doing something wrong. That's it. Anyway, it will fail to link since the definition of foo() is not compiled. In summary, these ifdef are unneeded. Signed-off-by: Masahiro Yamada Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 20 ++++++-------------- include/linux/pinctrl/pinconf.h | 4 ---- include/linux/pinctrl/pinctrl.h | 4 ---- include/linux/pinctrl/pinmux.h | 4 ---- 4 files changed, 6 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 72d06d6a3099..673828a52294 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -12,6 +12,12 @@ #ifndef __LINUX_PINCTRL_PINCONF_GENERIC_H #define __LINUX_PINCTRL_PINCONF_GENERIC_H +#include +#include + +struct pinctrl_dev; +struct pinctrl_map; + /** * enum pin_config_param - possible pin configuration parameters * @PIN_CONFIG_BIAS_BUS_HOLD: the pin will be set to weakly latch so that it @@ -159,9 +165,6 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param return PIN_CONF_PACKED(param, argument); } -#ifdef CONFIG_GENERIC_PINCONF - -#ifdef CONFIG_DEBUG_FS #define PCONFDUMP(a, b, c, d) { \ .param = a, .display = b, .format = c, .has_arg = d \ } @@ -172,14 +175,6 @@ struct pin_config_item { const char * const format; bool has_arg; }; -#endif /* CONFIG_DEBUG_FS */ - -#ifdef CONFIG_OF - -#include -#include -struct pinctrl_dev; -struct pinctrl_map; struct pinconf_generic_params { const char * const property; @@ -224,8 +219,5 @@ static inline int pinconf_generic_dt_node_to_map_all( return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps, PIN_MAP_TYPE_INVALID); } -#endif - -#endif /* CONFIG_GENERIC_PINCONF */ #endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */ diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index 9bebc3554809..513883dcc5a9 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -12,8 +12,6 @@ #ifndef __LINUX_PINCTRL_PINCONF_H #define __LINUX_PINCTRL_PINCONF_H -#ifdef CONFIG_PINCONF - #include struct pinctrl_dev; @@ -67,6 +65,4 @@ struct pinconf_ops { unsigned long config); }; -#endif - #endif /* __LINUX_PINCTRL_PINCONF_H */ diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 36a79fe7b84f..27738164daa7 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -12,8 +12,6 @@ #ifndef __LINUX_PINCTRL_PINCTRL_H #define __LINUX_PINCTRL_PINCTRL_H -#ifdef CONFIG_PINCTRL - #include #include #include @@ -203,6 +201,4 @@ extern const char *pinctrl_dev_get_name(struct pinctrl_dev *pctldev); extern const char *pinctrl_dev_get_devname(struct pinctrl_dev *pctldev); extern void *pinctrl_dev_get_drvdata(struct pinctrl_dev *pctldev); -#endif /* !CONFIG_PINCTRL */ - #endif /* __LINUX_PINCTRL_PINCTRL_H */ diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h index ace60d775b20..566a5fe8eab5 100644 --- a/include/linux/pinctrl/pinmux.h +++ b/include/linux/pinctrl/pinmux.h @@ -16,8 +16,6 @@ #include #include -#ifdef CONFIG_PINMUX - struct pinctrl_dev; /** @@ -85,6 +83,4 @@ struct pinmux_ops { bool strict; }; -#endif /* CONFIG_PINMUX */ - #endif /* __LINUX_PINCTRL_PINMUX_H */ -- cgit v1.2.3 From 2f25528e4edddc6eddd42c8d41c9c9e341c8b9da Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Wed, 19 Jun 2019 11:39:25 +0200 Subject: clk: Add clk_bulk_get_optional() function clk_bulk_get_optional() allows to get a group of clocks where one or more is optional. For a not available clock, e.g. not specifed in the clock consumer node in DT, its respective struct clk pointer will be NULL. This allows for operating on a group of returned clocks (struct clk_bulk_data array) with existing clk_bulk* APIs. Signed-off-by: Sylwester Nawrocki Signed-off-by: Stephen Boyd --- include/linux/clk.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index f689fc58d7be..1b50e7d1675c 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -332,6 +332,19 @@ int __must_check clk_bulk_get(struct device *dev, int num_clks, */ int __must_check clk_bulk_get_all(struct device *dev, struct clk_bulk_data **clks); + +/** + * clk_bulk_get_optional - lookup and obtain a number of references to clock producer + * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Behaves the same as clk_bulk_get() except where there is no clock producer. + * In this case, instead of returning -ENOENT, the function returns 0 and + * NULL for a clk for which a clock producer could not be determined. + */ +int __must_check clk_bulk_get_optional(struct device *dev, int num_clks, + struct clk_bulk_data *clks); /** * devm_clk_bulk_get - managed get multiple clk consumers * @dev: device for clock "consumer" @@ -718,6 +731,12 @@ static inline int __must_check clk_bulk_get(struct device *dev, int num_clks, return 0; } +static inline int __must_check clk_bulk_get_optional(struct device *dev, + int num_clks, struct clk_bulk_data *clks) +{ + return 0; +} + static inline int __must_check clk_bulk_get_all(struct device *dev, struct clk_bulk_data **clks) { -- cgit v1.2.3 From 9bd5ef0bd8743700d9adffb6fbb1baa346575457 Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Wed, 19 Jun 2019 11:39:26 +0200 Subject: clk: Add devm_clk_bulk_get_optional() function Add managed version of the clk_bulk_get_optional() helper function. Signed-off-by: Sylwester Nawrocki [sboyd@kernel.org: Mark __devm_clk_bulk_get() static] Signed-off-by: Stephen Boyd --- include/linux/clk.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 1b50e7d1675c..5e7b2dd84965 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -359,6 +359,28 @@ int __must_check clk_bulk_get_optional(struct device *dev, int num_clks, */ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); +/** + * devm_clk_bulk_get_optional - managed get multiple optional consumer clocks + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * Behaves the same as devm_clk_bulk_get() except where there is no clock + * producer. In this case, instead of returning -ENOENT, the function returns + * NULL for given clk. It is assumed all clocks in clk_bulk_data are optional. + * + * Returns 0 if all clocks specified in clk_bulk_data table are obtained + * successfully or for any clk there was no clk provider available, otherwise + * returns valid IS_ERR() condition containing errno. + * The implementation uses @dev and @clk_bulk_data.id to determine the + * clock consumer, and thereby the clock producer. + * The clock returned is stored in each @clk_bulk_data.clk field. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_bulk_get should not be called from within interrupt context. + */ +int __must_check devm_clk_bulk_get_optional(struct device *dev, int num_clks, + struct clk_bulk_data *clks); /** * devm_clk_bulk_get_all - managed get multiple clk consumers * @dev: device for clock "consumer" @@ -760,6 +782,12 @@ static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clk return 0; } +static inline int __must_check devm_clk_bulk_get_optional(struct device *dev, + int num_clks, struct clk_bulk_data *clks) +{ + return 0; +} + static inline int __must_check devm_clk_bulk_get_all(struct device *dev, struct clk_bulk_data **clks) { -- cgit v1.2.3 From 550113d4e9f5c7b62be760fc01178c9e0139c1f4 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 24 Jun 2019 19:04:02 +0200 Subject: i2c: add newly exported functions to the header, too Nobody (including me) noticed that these functions were exported but not added to the header :/ Fixes: 7159dbdae3c5 ("i2c: core: improve return value handling of i2c_new_device and i2c_new_dummy") Signed-off-by: Wolfram Sang Reviewed-by: Bartosz Golaszewski Reviewed-by: Kieran Bingham Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index d8f9060179d0..fa5552c2307b 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -442,6 +442,9 @@ struct i2c_board_info { extern struct i2c_client * i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info); +extern struct i2c_client * +i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info); + /* If you don't know the exact address of an I2C device, use this variant * instead, which can probe for device presence in a list of possible * addresses. The "probe" callback function is optional. If it is provided, @@ -463,6 +466,9 @@ extern int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short ad extern struct i2c_client * i2c_new_dummy(struct i2c_adapter *adap, u16 address); +extern struct i2c_client * +i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address); + extern struct i2c_client * devm_i2c_new_dummy_device(struct device *dev, struct i2c_adapter *adap, u16 address); -- cgit v1.2.3 From 2a6a7aacd4e557a4c7007f8858bcc9654b098fea Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 3 Jun 2019 10:24:32 +0300 Subject: mfd: regulator: clk: Split rohm-bd718x7.h Split the bd718x7.h to ROHM common and bd718x7 specific parts so that we do not need to add same things in every new ROHM PMIC header. Please note that this change requires changes also in bd718x7 sub-device drivers for regulators and clk. Signed-off-by: Matti Vaittinen Acked-by: Mark Brown Acked-by: Stephen Boyd Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd718x7.h | 22 ++++++++-------------- include/linux/mfd/rohm-generic.h | 20 ++++++++++++++++++++ 2 files changed, 28 insertions(+), 14 deletions(-) create mode 100644 include/linux/mfd/rohm-generic.h (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index fd194bfc836f..7f2dbde402a1 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -4,14 +4,9 @@ #ifndef __LINUX_MFD_BD718XX_H__ #define __LINUX_MFD_BD718XX_H__ +#include #include -enum { - BD718XX_TYPE_BD71837 = 0, - BD718XX_TYPE_BD71847, - BD718XX_TYPE_AMOUNT -}; - enum { BD718XX_BUCK1 = 0, BD718XX_BUCK2, @@ -321,18 +316,17 @@ enum { BD718XX_PWRBTN_LONG_PRESS_15S }; -struct bd718xx_clk; - struct bd718xx { - unsigned int chip_type; - struct device *dev; - struct regmap *regmap; - unsigned long int id; + /* + * Please keep this as the first member here as some + * drivers (clk) supporting more than one chip may only know this + * generic struct 'struct rohm_regmap_dev' and assume it is + * the first chunk of parent device's private data. + */ + struct rohm_regmap_dev chip; int chip_irq; struct regmap_irq_chip_data *irq_data; - - struct bd718xx_clk *clk; }; #endif /* __LINUX_MFD_BD718XX_H__ */ diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h new file mode 100644 index 000000000000..bff15ac26f2c --- /dev/null +++ b/include/linux/mfd/rohm-generic.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2018 ROHM Semiconductors */ + +#ifndef __LINUX_MFD_ROHM_H__ +#define __LINUX_MFD_ROHM_H__ + +enum { + ROHM_CHIP_TYPE_BD71837 = 0, + ROHM_CHIP_TYPE_BD71847, + ROHM_CHIP_TYPE_BD70528, + ROHM_CHIP_TYPE_AMOUNT +}; + +struct rohm_regmap_dev { + unsigned int chip_type; + struct device *dev; + struct regmap *regmap; +}; + +#endif -- cgit v1.2.3 From 21b7c58fc1943f3aa8c18a994ab9bed4ae5aa72d Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 3 Jun 2019 10:25:08 +0300 Subject: mfd: bd70528: Support ROHM bd70528 PMIC core ROHM BD70528MWV is an ultra-low quiescent current general purpose single-chip power management IC for battery-powered portable devices. Add MFD core which enables chip access for following subdevices: - regulators/LED drivers - battery-charger - gpios - 32.768kHz clk - RTC - watchdog Signed-off-by: Matti Vaittinen Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd70528.h | 408 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 408 insertions(+) create mode 100644 include/linux/mfd/rohm-bd70528.h (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h new file mode 100644 index 000000000000..1013e60c5b25 --- /dev/null +++ b/include/linux/mfd/rohm-bd70528.h @@ -0,0 +1,408 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2018 ROHM Semiconductors */ + +#ifndef __LINUX_MFD_BD70528_H__ +#define __LINUX_MFD_BD70528_H__ + +#include +#include +#include +#include + +enum { + BD70528_BUCK1, + BD70528_BUCK2, + BD70528_BUCK3, + BD70528_LDO1, + BD70528_LDO2, + BD70528_LDO3, + BD70528_LED1, + BD70528_LED2, +}; + +struct bd70528_data { + struct rohm_regmap_dev chip; + struct mutex rtc_timer_lock; +}; + +#define BD70528_BUCK_VOLTS 17 +#define BD70528_BUCK_VOLTS 17 +#define BD70528_BUCK_VOLTS 17 +#define BD70528_LDO_VOLTS 0x20 + +#define BD70528_REG_BUCK1_EN 0x0F +#define BD70528_REG_BUCK1_VOLT 0x15 +#define BD70528_REG_BUCK2_EN 0x10 +#define BD70528_REG_BUCK2_VOLT 0x16 +#define BD70528_REG_BUCK3_EN 0x11 +#define BD70528_REG_BUCK3_VOLT 0x17 +#define BD70528_REG_LDO1_EN 0x1b +#define BD70528_REG_LDO1_VOLT 0x1e +#define BD70528_REG_LDO2_EN 0x1c +#define BD70528_REG_LDO2_VOLT 0x1f +#define BD70528_REG_LDO3_EN 0x1d +#define BD70528_REG_LDO3_VOLT 0x20 +#define BD70528_REG_LED_CTRL 0x2b +#define BD70528_REG_LED_VOLT 0x29 +#define BD70528_REG_LED_EN 0x2a + +/* main irq registers */ +#define BD70528_REG_INT_MAIN 0x7E +#define BD70528_REG_INT_MAIN_MASK 0x74 + +/* 'sub irq' registers */ +#define BD70528_REG_INT_SHDN 0x7F +#define BD70528_REG_INT_PWR_FLT 0x80 +#define BD70528_REG_INT_VR_FLT 0x81 +#define BD70528_REG_INT_MISC 0x82 +#define BD70528_REG_INT_BAT1 0x83 +#define BD70528_REG_INT_BAT2 0x84 +#define BD70528_REG_INT_RTC 0x85 +#define BD70528_REG_INT_GPIO 0x86 +#define BD70528_REG_INT_OP_FAIL 0x87 + +#define BD70528_REG_INT_SHDN_MASK 0x75 +#define BD70528_REG_INT_PWR_FLT_MASK 0x76 +#define BD70528_REG_INT_VR_FLT_MASK 0x77 +#define BD70528_REG_INT_MISC_MASK 0x78 +#define BD70528_REG_INT_BAT1_MASK 0x79 +#define BD70528_REG_INT_BAT2_MASK 0x7a +#define BD70528_REG_INT_RTC_MASK 0x7b +#define BD70528_REG_INT_GPIO_MASK 0x7c +#define BD70528_REG_INT_OP_FAIL_MASK 0x7d + +/* Reset related 'magic' registers */ +#define BD70528_REG_SHIPMODE 0x03 +#define BD70528_REG_HWRESET 0x04 +#define BD70528_REG_WARMRESET 0x05 +#define BD70528_REG_STANDBY 0x06 + +/* GPIO registers */ +#define BD70528_REG_GPIO_STATE 0x8F + +#define BD70528_REG_GPIO1_IN 0x4d +#define BD70528_REG_GPIO2_IN 0x4f +#define BD70528_REG_GPIO3_IN 0x51 +#define BD70528_REG_GPIO4_IN 0x53 +#define BD70528_REG_GPIO1_OUT 0x4e +#define BD70528_REG_GPIO2_OUT 0x50 +#define BD70528_REG_GPIO3_OUT 0x52 +#define BD70528_REG_GPIO4_OUT 0x54 + +/* clk control */ + +#define BD70528_REG_CLK_OUT 0x2c + +/* RTC */ + +#define BD70528_REG_RTC_COUNT_H 0x2d +#define BD70528_REG_RTC_COUNT_L 0x2e +#define BD70528_REG_RTC_SEC 0x2f +#define BD70528_REG_RTC_MINUTE 0x30 +#define BD70528_REG_RTC_HOUR 0x31 +#define BD70528_REG_RTC_WEEK 0x32 +#define BD70528_REG_RTC_DAY 0x33 +#define BD70528_REG_RTC_MONTH 0x34 +#define BD70528_REG_RTC_YEAR 0x35 + +#define BD70528_REG_RTC_ALM_SEC 0x36 +#define BD70528_REG_RTC_ALM_START BD70528_REG_RTC_ALM_SEC +#define BD70528_REG_RTC_ALM_MINUTE 0x37 +#define BD70528_REG_RTC_ALM_HOUR 0x38 +#define BD70528_REG_RTC_ALM_WEEK 0x39 +#define BD70528_REG_RTC_ALM_DAY 0x3a +#define BD70528_REG_RTC_ALM_MONTH 0x3b +#define BD70528_REG_RTC_ALM_YEAR 0x3c +#define BD70528_REG_RTC_ALM_MASK 0x3d +#define BD70528_REG_RTC_ALM_REPEAT 0x3e +#define BD70528_REG_RTC_START BD70528_REG_RTC_SEC + +#define BD70528_REG_RTC_WAKE_SEC 0x43 +#define BD70528_REG_RTC_WAKE_START BD70528_REG_RTC_WAKE_SEC +#define BD70528_REG_RTC_WAKE_MIN 0x44 +#define BD70528_REG_RTC_WAKE_HOUR 0x45 +#define BD70528_REG_RTC_WAKE_CTRL 0x46 + +#define BD70528_REG_ELAPSED_TIMER_EN 0x42 +#define BD70528_REG_WAKE_EN 0x46 + +/* WDT registers */ +#define BD70528_REG_WDT_CTRL 0x4A +#define BD70528_REG_WDT_HOUR 0x49 +#define BD70528_REG_WDT_MINUTE 0x48 +#define BD70528_REG_WDT_SEC 0x47 + +/* Charger / Battery */ +#define BD70528_REG_CHG_CURR_STAT 0x59 +#define BD70528_REG_CHG_BAT_STAT 0x57 +#define BD70528_REG_CHG_BAT_TEMP 0x58 +#define BD70528_REG_CHG_IN_STAT 0x56 +#define BD70528_REG_CHG_DCIN_ILIM 0x5d +#define BD70528_REG_CHG_CHG_CURR_WARM 0x61 +#define BD70528_REG_CHG_CHG_CURR_COLD 0x62 + +/* Masks for main IRQ register bits */ +enum { + BD70528_INT_SHDN, +#define BD70528_INT_SHDN_MASK BIT(BD70528_INT_SHDN) + BD70528_INT_PWR_FLT, +#define BD70528_INT_PWR_FLT_MASK BIT(BD70528_INT_PWR_FLT) + BD70528_INT_VR_FLT, +#define BD70528_INT_VR_FLT_MASK BIT(BD70528_INT_VR_FLT) + BD70528_INT_MISC, +#define BD70528_INT_MISC_MASK BIT(BD70528_INT_MISC) + BD70528_INT_BAT1, +#define BD70528_INT_BAT1_MASK BIT(BD70528_INT_BAT1) + BD70528_INT_RTC, +#define BD70528_INT_RTC_MASK BIT(BD70528_INT_RTC) + BD70528_INT_GPIO, +#define BD70528_INT_GPIO_MASK BIT(BD70528_INT_GPIO) + BD70528_INT_OP_FAIL, +#define BD70528_INT_OP_FAIL_MASK BIT(BD70528_INT_OP_FAIL) +}; + +/* IRQs */ +enum { + /* Shutdown register IRQs */ + BD70528_INT_LONGPUSH, + BD70528_INT_WDT, + BD70528_INT_HWRESET, + BD70528_INT_RSTB_FAULT, + BD70528_INT_VBAT_UVLO, + BD70528_INT_TSD, + BD70528_INT_RSTIN, + /* Power failure register IRQs */ + BD70528_INT_BUCK1_FAULT, + BD70528_INT_BUCK2_FAULT, + BD70528_INT_BUCK3_FAULT, + BD70528_INT_LDO1_FAULT, + BD70528_INT_LDO2_FAULT, + BD70528_INT_LDO3_FAULT, + BD70528_INT_LED1_FAULT, + BD70528_INT_LED2_FAULT, + /* VR FAULT register IRQs */ + BD70528_INT_BUCK1_OCP, + BD70528_INT_BUCK2_OCP, + BD70528_INT_BUCK3_OCP, + BD70528_INT_LED1_OCP, + BD70528_INT_LED2_OCP, + BD70528_INT_BUCK1_FULLON, + BD70528_INT_BUCK2_FULLON, + /* PMU register interrupts */ + BD70528_INT_SHORTPUSH, + BD70528_INT_AUTO_WAKEUP, + BD70528_INT_STATE_CHANGE, + /* Charger 1 register IRQs */ + BD70528_INT_BAT_OV_RES, + BD70528_INT_BAT_OV_DET, + BD70528_INT_DBAT_DET, + BD70528_INT_BATTSD_COLD_RES, + BD70528_INT_BATTSD_COLD_DET, + BD70528_INT_BATTSD_HOT_RES, + BD70528_INT_BATTSD_HOT_DET, + BD70528_INT_CHG_TSD, + /* Charger 2 register IRQs */ + BD70528_INT_BAT_RMV, + BD70528_INT_BAT_DET, + BD70528_INT_DCIN2_OV_RES, + BD70528_INT_DCIN2_OV_DET, + BD70528_INT_DCIN2_RMV, + BD70528_INT_DCIN2_DET, + BD70528_INT_DCIN1_RMV, + BD70528_INT_DCIN1_DET, + /* RTC register IRQs */ + BD70528_INT_RTC_ALARM, + BD70528_INT_ELPS_TIM, + /* GPIO register IRQs */ + BD70528_INT_GPIO0, + BD70528_INT_GPIO1, + BD70528_INT_GPIO2, + BD70528_INT_GPIO3, + /* Invalid operation register IRQs */ + BD70528_INT_BUCK1_DVS_OPFAIL, + BD70528_INT_BUCK2_DVS_OPFAIL, + BD70528_INT_BUCK3_DVS_OPFAIL, + BD70528_INT_LED1_VOLT_OPFAIL, + BD70528_INT_LED2_VOLT_OPFAIL, +}; + +/* Masks */ +#define BD70528_INT_LONGPUSH_MASK 0x1 +#define BD70528_INT_WDT_MASK 0x2 +#define BD70528_INT_HWRESET_MASK 0x4 +#define BD70528_INT_RSTB_FAULT_MASK 0x8 +#define BD70528_INT_VBAT_UVLO_MASK 0x10 +#define BD70528_INT_TSD_MASK 0x20 +#define BD70528_INT_RSTIN_MASK 0x40 + +#define BD70528_INT_BUCK1_FAULT_MASK 0x1 +#define BD70528_INT_BUCK2_FAULT_MASK 0x2 +#define BD70528_INT_BUCK3_FAULT_MASK 0x4 +#define BD70528_INT_LDO1_FAULT_MASK 0x8 +#define BD70528_INT_LDO2_FAULT_MASK 0x10 +#define BD70528_INT_LDO3_FAULT_MASK 0x20 +#define BD70528_INT_LED1_FAULT_MASK 0x40 +#define BD70528_INT_LED2_FAULT_MASK 0x80 + +#define BD70528_INT_BUCK1_OCP_MASK 0x1 +#define BD70528_INT_BUCK2_OCP_MASK 0x2 +#define BD70528_INT_BUCK3_OCP_MASK 0x4 +#define BD70528_INT_LED1_OCP_MASK 0x8 +#define BD70528_INT_LED2_OCP_MASK 0x10 +#define BD70528_INT_BUCK1_FULLON_MASK 0x20 +#define BD70528_INT_BUCK2_FULLON_MASK 0x40 + +#define BD70528_INT_SHORTPUSH_MASK 0x1 +#define BD70528_INT_AUTO_WAKEUP_MASK 0x2 +#define BD70528_INT_STATE_CHANGE_MASK 0x10 + +#define BD70528_INT_BAT_OV_RES_MASK 0x1 +#define BD70528_INT_BAT_OV_DET_MASK 0x2 +#define BD70528_INT_DBAT_DET_MASK 0x4 +#define BD70528_INT_BATTSD_COLD_RES_MASK 0x8 +#define BD70528_INT_BATTSD_COLD_DET_MASK 0x10 +#define BD70528_INT_BATTSD_HOT_RES_MASK 0x20 +#define BD70528_INT_BATTSD_HOT_DET_MASK 0x40 +#define BD70528_INT_CHG_TSD_MASK 0x80 + +#define BD70528_INT_BAT_RMV_MASK 0x1 +#define BD70528_INT_BAT_DET_MASK 0x2 +#define BD70528_INT_DCIN2_OV_RES_MASK 0x4 +#define BD70528_INT_DCIN2_OV_DET_MASK 0x8 +#define BD70528_INT_DCIN2_RMV_MASK 0x10 +#define BD70528_INT_DCIN2_DET_MASK 0x20 +#define BD70528_INT_DCIN1_RMV_MASK 0x40 +#define BD70528_INT_DCIN1_DET_MASK 0x80 + +#define BD70528_INT_RTC_ALARM_MASK 0x1 +#define BD70528_INT_ELPS_TIM_MASK 0x2 + +#define BD70528_INT_GPIO0_MASK 0x1 +#define BD70528_INT_GPIO1_MASK 0x2 +#define BD70528_INT_GPIO2_MASK 0x4 +#define BD70528_INT_GPIO3_MASK 0x8 + +#define BD70528_INT_BUCK1_DVS_OPFAIL_MASK 0x1 +#define BD70528_INT_BUCK2_DVS_OPFAIL_MASK 0x2 +#define BD70528_INT_BUCK3_DVS_OPFAIL_MASK 0x4 +#define BD70528_INT_LED1_VOLT_OPFAIL_MASK 0x10 +#define BD70528_INT_LED2_VOLT_OPFAIL_MASK 0x20 + +#define BD70528_DEBOUNCE_MASK 0x3 + +#define BD70528_DEBOUNCE_DISABLE 0 +#define BD70528_DEBOUNCE_15MS 1 +#define BD70528_DEBOUNCE_30MS 2 +#define BD70528_DEBOUNCE_50MS 3 + +#define BD70528_GPIO_DRIVE_MASK 0x2 +#define BD70528_GPIO_PUSH_PULL 0x0 +#define BD70528_GPIO_OPEN_DRAIN 0x2 + +#define BD70528_GPIO_OUT_EN_MASK 0x80 +#define BD70528_GPIO_OUT_ENABLE 0x80 +#define BD70528_GPIO_OUT_DISABLE 0x0 + +#define BD70528_GPIO_OUT_HI 0x1 +#define BD70528_GPIO_OUT_LO 0x0 +#define BD70528_GPIO_OUT_MASK 0x1 + +#define BD70528_GPIO_IN_STATE_BASE 1 + +#define BD70528_CLK_OUT_EN_MASK 0x1 + +/* RTC masks to mask out reserved bits */ + +#define BD70528_MASK_RTC_SEC 0x7f +#define BD70528_MASK_RTC_MINUTE 0x7f +#define BD70528_MASK_RTC_HOUR_24H 0x80 +#define BD70528_MASK_RTC_HOUR_PM 0x20 +#define BD70528_MASK_RTC_HOUR 0x1f +#define BD70528_MASK_RTC_DAY 0x3f +#define BD70528_MASK_RTC_WEEK 0x07 +#define BD70528_MASK_RTC_MONTH 0x1f +#define BD70528_MASK_RTC_YEAR 0xff +#define BD70528_MASK_RTC_COUNT_L 0x7f + +#define BD70528_MASK_ELAPSED_TIMER_EN 0x1 +/* Mask second, min and hour fields + * HW would support ALM irq for over 24h + * (by setting day, month and year too) + * but as we wish to keep this same as for + * wake-up we limit ALM to 24H and only + * unmask sec, min and hour + */ +#define BD70528_MASK_ALM_EN 0x7 +#define BD70528_MASK_WAKE_EN 0x1 + +/* WDT masks */ +#define BD70528_MASK_WDT_EN 0x1 +#define BD70528_MASK_WDT_HOUR 0x1 +#define BD70528_MASK_WDT_MINUTE 0x7f +#define BD70528_MASK_WDT_SEC 0x7f + +#define BD70528_WDT_STATE_BIT 0x1 +#define BD70528_ELAPSED_STATE_BIT 0x2 +#define BD70528_WAKE_STATE_BIT 0x4 + +/* Charger masks */ +#define BD70528_MASK_CHG_STAT 0x7f +#define BD70528_MASK_CHG_BAT_TIMER 0x20 +#define BD70528_MASK_CHG_BAT_OVERVOLT 0x10 +#define BD70528_MASK_CHG_BAT_DETECT 0x1 +#define BD70528_MASK_CHG_DCIN1_UVLO 0x1 +#define BD70528_MASK_CHG_DCIN_ILIM 0x3f +#define BD70528_MASK_CHG_CHG_CURR 0x1f +#define BD70528_MASK_CHG_TRICKLE_CURR 0x10 + +/* + * Note, external battery register is the lonely rider at + * address 0xc5. See how to stuff that in the regmap + */ +#define BD70528_MAX_REGISTER 0x94 + +/* Buck control masks */ +#define BD70528_MASK_RUN_EN 0x4 +#define BD70528_MASK_STBY_EN 0x2 +#define BD70528_MASK_IDLE_EN 0x1 +#define BD70528_MASK_LED1_EN 0x1 +#define BD70528_MASK_LED2_EN 0x10 + +#define BD70528_MASK_BUCK_VOLT 0xf +#define BD70528_MASK_LDO_VOLT 0x1f +#define BD70528_MASK_LED1_VOLT 0x1 +#define BD70528_MASK_LED2_VOLT 0x10 + +/* Misc irq masks */ +#define BD70528_INT_MASK_SHORT_PUSH 1 +#define BD70528_INT_MASK_AUTO_WAKE 2 +#define BD70528_INT_MASK_POWER_STATE 4 + +#define BD70528_MASK_BUCK_RAMP 0x10 +#define BD70528_SIFT_BUCK_RAMP 4 + +#if IS_ENABLED(CONFIG_BD70528_WATCHDOG) + +int bd70528_wdt_set(struct rohm_regmap_dev *data, int enable, int *old_state); +void bd70528_wdt_lock(struct rohm_regmap_dev *data); +void bd70528_wdt_unlock(struct rohm_regmap_dev *data); + +#else /* CONFIG_BD70528_WATCHDOG */ + +static inline int bd70528_wdt_set(struct rohm_regmap_dev *data, int enable, + int *old_state) +{ + return 0; +} + +static inline void bd70528_wdt_lock(struct rohm_regmap_dev *data) +{ +} + +static inline void bd70528_wdt_unlock(struct rohm_regmap_dev *data) +{ +} + +#endif /* CONFIG_BD70528_WATCHDOG */ + +#endif /* __LINUX_MFD_BD70528_H__ */ -- cgit v1.2.3 From 6bbe6f5732faeabb4bb583726ec2d7f9739532bd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 18 Jun 2019 18:05:28 -0300 Subject: docs: thermal: convert to ReST Rename the thermal documentation files to ReST, add an index for them and adjust in order to produce a nice html output via the Sphinx build system. At its new index.rst, let's add a :orphan: while this is not linked to the main index.rst file, in order to avoid build warnings. Signed-off-by: Mauro Carvalho Chehab Acked-by: Zhang Rui Signed-off-by: Zhang Rui --- include/linux/thermal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 15a4ca5d7099..681047f8cc05 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -251,7 +251,7 @@ struct thermal_bind_params { * platform characterization. This value is relative to the * rest of the weights so a cooling device whose weight is * double that of another cooling device is twice as - * effective. See Documentation/thermal/sysfs-api.txt for more + * effective. See Documentation/thermal/sysfs-api.rst for more * information. */ int weight; @@ -259,7 +259,7 @@ struct thermal_bind_params { /* * This is a bit mask that gives the binding relation between this * thermal zone and cdev, for a particular trip point. - * See Documentation/thermal/sysfs-api.txt for more information. + * See Documentation/thermal/sysfs-api.rst for more information. */ int trip_mask; -- cgit v1.2.3 From 586c1b4125b3c7bf5b482fcafab5d568b8a3c285 Mon Sep 17 00:00:00 2001 From: Tony Xie Date: Fri, 21 Jun 2019 06:32:54 -0400 Subject: mfd: rk808: Add RK817 and RK809 support The RK809 and RK817 are a Power Management IC (PMIC) for multimedia and handheld devices. They contains the following components: - Regulators - RTC - Clocking Both RK809 and RK817 chips are using a similar register map, so we can reuse the RTC and Clocking functionality. Most of regulators have a some implementation also. Signed-off-by: Tony Xie Acked-by: Stephen Boyd Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 172 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index d3156594674c..0fd9eedf3c20 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -382,6 +382,7 @@ enum rk805_reg { #define SWITCH1_EN BIT(5) #define DEV_OFF_RST BIT(3) #define DEV_OFF BIT(0) +#define RTC_STOP BIT(0) #define VB_LO_ACT BIT(4) #define VB_LO_SEL_3500MV (7 << 0) @@ -396,6 +397,175 @@ enum rk805_reg { #define SLEEP_FUN (0x1 << 2) #define RK8XX_ID_MSK 0xfff0 #define FPWM_MODE BIT(7) +enum rk817_reg_id { + RK817_ID_DCDC1 = 0, + RK817_ID_DCDC2, + RK817_ID_DCDC3, + RK817_ID_DCDC4, + RK817_ID_LDO1, + RK817_ID_LDO2, + RK817_ID_LDO3, + RK817_ID_LDO4, + RK817_ID_LDO5, + RK817_ID_LDO6, + RK817_ID_LDO7, + RK817_ID_LDO8, + RK817_ID_LDO9, + RK817_ID_BOOST, + RK817_ID_BOOST_OTG_SW, + RK817_NUM_REGULATORS +}; + +enum rk809_reg_id { + RK809_ID_DCDC5 = RK817_ID_BOOST, + RK809_ID_SW1, + RK809_ID_SW2, + RK809_NUM_REGULATORS +}; + +#define RK817_SECONDS_REG 0x00 +#define RK817_MINUTES_REG 0x01 +#define RK817_HOURS_REG 0x02 +#define RK817_DAYS_REG 0x03 +#define RK817_MONTHS_REG 0x04 +#define RK817_YEARS_REG 0x05 +#define RK817_WEEKS_REG 0x06 +#define RK817_ALARM_SECONDS_REG 0x07 +#define RK817_ALARM_MINUTES_REG 0x08 +#define RK817_ALARM_HOURS_REG 0x09 +#define RK817_ALARM_DAYS_REG 0x0a +#define RK817_ALARM_MONTHS_REG 0x0b +#define RK817_ALARM_YEARS_REG 0x0c +#define RK817_RTC_CTRL_REG 0xd +#define RK817_RTC_STATUS_REG 0xe +#define RK817_RTC_INT_REG 0xf +#define RK817_RTC_COMP_LSB_REG 0x10 +#define RK817_RTC_COMP_MSB_REG 0x11 + +#define RK817_POWER_EN_REG(i) (0xb1 + (i)) +#define RK817_POWER_SLP_EN_REG(i) (0xb5 + (i)) + +#define RK817_POWER_CONFIG (0xb9) + +#define RK817_BUCK_CONFIG_REG(i) (0xba + (i) * 3) + +#define RK817_BUCK1_ON_VSEL_REG 0xBB +#define RK817_BUCK1_SLP_VSEL_REG 0xBC + +#define RK817_BUCK2_CONFIG_REG 0xBD +#define RK817_BUCK2_ON_VSEL_REG 0xBE +#define RK817_BUCK2_SLP_VSEL_REG 0xBF + +#define RK817_BUCK3_CONFIG_REG 0xC0 +#define RK817_BUCK3_ON_VSEL_REG 0xC1 +#define RK817_BUCK3_SLP_VSEL_REG 0xC2 + +#define RK817_BUCK4_CONFIG_REG 0xC3 +#define RK817_BUCK4_ON_VSEL_REG 0xC4 +#define RK817_BUCK4_SLP_VSEL_REG 0xC5 + +#define RK817_LDO_ON_VSEL_REG(idx) (0xcc + (idx) * 2) +#define RK817_BOOST_OTG_CFG (0xde) + +#define RK817_ID_MSB 0xed +#define RK817_ID_LSB 0xee + +#define RK817_SYS_STS 0xf0 +#define RK817_SYS_CFG(i) (0xf1 + (i)) + +#define RK817_ON_SOURCE_REG 0xf5 +#define RK817_OFF_SOURCE_REG 0xf6 + +/* INTERRUPT REGISTER */ +#define RK817_INT_STS_REG0 0xf8 +#define RK817_INT_STS_MSK_REG0 0xf9 +#define RK817_INT_STS_REG1 0xfa +#define RK817_INT_STS_MSK_REG1 0xfb +#define RK817_INT_STS_REG2 0xfc +#define RK817_INT_STS_MSK_REG2 0xfd +#define RK817_GPIO_INT_CFG 0xfe + +/* IRQ Definitions */ +#define RK817_IRQ_PWRON_FALL 0 +#define RK817_IRQ_PWRON_RISE 1 +#define RK817_IRQ_PWRON 2 +#define RK817_IRQ_PWMON_LP 3 +#define RK817_IRQ_HOTDIE 4 +#define RK817_IRQ_RTC_ALARM 5 +#define RK817_IRQ_RTC_PERIOD 6 +#define RK817_IRQ_VB_LO 7 +#define RK817_IRQ_PLUG_IN 8 +#define RK817_IRQ_PLUG_OUT 9 +#define RK817_IRQ_CHRG_TERM 10 +#define RK817_IRQ_CHRG_TIME 11 +#define RK817_IRQ_CHRG_TS 12 +#define RK817_IRQ_USB_OV 13 +#define RK817_IRQ_CHRG_IN_CLMP 14 +#define RK817_IRQ_BAT_DIS_ILIM 15 +#define RK817_IRQ_GATE_GPIO 16 +#define RK817_IRQ_TS_GPIO 17 +#define RK817_IRQ_CODEC_PD 18 +#define RK817_IRQ_CODEC_PO 19 +#define RK817_IRQ_CLASSD_MUTE_DONE 20 +#define RK817_IRQ_CLASSD_OCP 21 +#define RK817_IRQ_BAT_OVP 22 +#define RK817_IRQ_CHRG_BAT_HI 23 +#define RK817_IRQ_END (RK817_IRQ_CHRG_BAT_HI + 1) + +/* + * rtc_ctrl 0xd + * same as 808, except bit4 + */ +#define RK817_RTC_CTRL_RSV4 BIT(4) + +/* power config 0xb9 */ +#define RK817_BUCK3_FB_RES_MSK BIT(6) +#define RK817_BUCK3_FB_RES_INTER BIT(6) +#define RK817_BUCK3_FB_RES_EXT 0 + +/* buck config 0xba */ +#define RK817_RAMP_RATE_OFFSET 6 +#define RK817_RAMP_RATE_MASK (0x3 << RK817_RAMP_RATE_OFFSET) +#define RK817_RAMP_RATE_3MV_PER_US (0x0 << RK817_RAMP_RATE_OFFSET) +#define RK817_RAMP_RATE_6_3MV_PER_US (0x1 << RK817_RAMP_RATE_OFFSET) +#define RK817_RAMP_RATE_12_5MV_PER_US (0x2 << RK817_RAMP_RATE_OFFSET) +#define RK817_RAMP_RATE_25MV_PER_US (0x3 << RK817_RAMP_RATE_OFFSET) + +/* sys_cfg1 0xf2 */ +#define RK817_HOTDIE_TEMP_MSK (0x3 << 4) +#define RK817_HOTDIE_85 (0x0 << 4) +#define RK817_HOTDIE_95 (0x1 << 4) +#define RK817_HOTDIE_105 (0x2 << 4) +#define RK817_HOTDIE_115 (0x3 << 4) + +#define RK817_TSD_TEMP_MSK BIT(6) +#define RK817_TSD_140 0 +#define RK817_TSD_160 BIT(6) + +#define RK817_CLK32KOUT2_EN BIT(7) + +/* sys_cfg3 0xf4 */ +#define RK817_SLPPIN_FUNC_MSK (0x3 << 3) +#define SLPPIN_NULL_FUN (0x0 << 3) +#define SLPPIN_SLP_FUN (0x1 << 3) +#define SLPPIN_DN_FUN (0x2 << 3) +#define SLPPIN_RST_FUN (0x3 << 3) + +#define RK817_RST_FUNC_MSK (0x3 << 6) +#define RK817_RST_FUNC_SFT (6) +#define RK817_RST_FUNC_CNT (3) +#define RK817_RST_FUNC_DEV (0) /* reset the dev */ +#define RK817_RST_FUNC_REG (0x1 << 6) /* reset the reg only */ + +#define RK817_SLPPOL_MSK BIT(5) +#define RK817_SLPPOL_H BIT(5) +#define RK817_SLPPOL_L (0) + +/* gpio&int 0xfe */ +#define RK817_INT_POL_MSK BIT(1) +#define RK817_INT_POL_H BIT(1) +#define RK817_INT_POL_L 0 +#define RK809_BUCK5_CONFIG(i) (RK817_BOOST_OTG_CFG + (i) * 1) enum { BUCK_ILMIN_50MA, @@ -443,6 +613,8 @@ enum { enum { RK805_ID = 0x8050, RK808_ID = 0x0000, + RK809_ID = 0x8090, + RK817_ID = 0x8170, RK818_ID = 0x8181, }; -- cgit v1.2.3 From e444f6d68c07bc01a3a3d5905409dbe1ca391d26 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Wed, 26 Jun 2019 14:29:18 +0200 Subject: regulator: rk808: Add RK809 and RK817 support. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for the rk809 and rk817 regulator driver. Their specifications are as follows： 1. The RK809 and RK809 consist of 5 DCDCs, 9 LDOs and have the same registers for these components except dcdc5. 2. The dcdc5 is a boost dcdc for RK817 and is a buck for RK809. 3. The RK817 has one switch but The Rk809 has two. The output voltages are configurable and are meant to supply power to the main processor and other components. Signed-off-by: Tony Xie Acked-by: Mark Brown [rebased on top of 5.2-rc1] Signed-off-by: Heiko Stuebner Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 0fd9eedf3c20..2a9cd01691b2 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -396,7 +396,10 @@ enum rk805_reg { #define SHUTDOWN_FUN (0x2 << 2) #define SLEEP_FUN (0x1 << 2) #define RK8XX_ID_MSK 0xfff0 +#define PWM_MODE_MSK BIT(7) #define FPWM_MODE BIT(7) +#define AUTO_PWM_MODE 0 + enum rk817_reg_id { RK817_ID_DCDC1 = 0, RK817_ID_DCDC2, -- cgit v1.2.3 From 5a136b4ae327e7f6be9c984a010df8d7ea5a4f83 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 7 Jun 2019 12:10:33 -0300 Subject: mm/hmm: Fix error flows in hmm_invalidate_range_start If the trylock on the hmm->mirrors_sem fails the function will return without decrementing the notifiers that were previously incremented. Since the caller will not call invalidate_range_end() on EAGAIN this will result in notifiers becoming permanently incremented and deadlock. If the sync_cpu_device_pagetables() required blocking the function will not return EAGAIN even though the device continues to touch the pages. This is a violation of the mmu notifier contract. Switch, and rename, the ranges_lock to a spin lock so we can reliably obtain it without blocking during error unwind. The error unwind is necessary since the notifiers count must be held incremented across the call to sync_cpu_device_pagetables() as we cannot allow the range to become marked valid by a parallel invalidate_start/end() pair while doing sync_cpu_device_pagetables(). Signed-off-by: Jason Gunthorpe Reviewed-by: Ralph Campbell Reviewed-by: Christoph Hellwig Tested-by: Philip Yang --- include/linux/hmm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index bf013e965257..0fa8ea34ccef 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -86,7 +86,7 @@ struct hmm { struct mm_struct *mm; struct kref kref; - struct mutex lock; + spinlock_t ranges_lock; struct list_head ranges; struct list_head mirrors; struct mmu_notifier mmu_notifier; -- cgit v1.2.3 From 4844ef80305d0180051d0787cd91c63573255dc2 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Tue, 25 Jun 2019 13:27:42 +0530 Subject: mtd: cfi_cmdset_0002: Add support for polling status register HyperFlash devices are compliant with CFI AMD/Fujitsu Extended Command Set (0x0002) for flash operations, therefore drivers/mtd/chips/cfi_cmdset_0002.c can be used as is. But these devices do not support DQ polling method of determining chip ready/good status. These flashes provide Status Register whose bits can be polled to know status of flash operation. Cypress HyperFlash datasheet here[1], talks about CFI Amd/Fujitsu Extended Query version 1.5. Bit 0 of "Software Features supported" field of CFI Primary Vendor-Specific Extended Query table indicates presence/absence of status register and Bit 1 indicates whether or not DQ polling is supported. Using these bits, its possible to determine whether flash supports DQ polling or need to use Status Register. Add support for polling Status Register to know device ready/status of erase/write operations when DQ polling is not supported. Print error messages on erase/program failure by looking at related Status Register bits. [1] https://www.cypress.com/file/213346/download Signed-off-by: Vignesh Raghavendra Reviewed-by: Tokunori Ikegami Signed-off-by: Miquel Raynal --- include/linux/mtd/cfi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index cbf77168658c..7fdbc1ff6527 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -233,6 +233,13 @@ struct cfi_pri_amdstd { uint8_t VppMin; uint8_t VppMax; uint8_t TopBottom; + /* Below field are added from version 1.5 */ + uint8_t ProgramSuspend; + uint8_t UnlockBypass; + uint8_t SecureSiliconSector; + uint8_t SoftwareFeatures; +#define CFI_POLL_STATUS_REG BIT(0) +#define CFI_POLL_DQ BIT(1) } __packed; /* Vendor-Specific PRI for Atmel chips (command set 0x0002) */ -- cgit v1.2.3 From dcc7d3446a0fa19bd7e8074920b8f9ef3b7ec00c Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Tue, 25 Jun 2019 13:27:44 +0530 Subject: mtd: Add support for HyperBus memory devices Cypress' HyperBus is Low Signal Count, High Performance Double Data Rate Bus interface between a host system master and one or more slave interfaces. HyperBus is used to connect microprocessor, microcontroller, or ASIC devices with random access NOR flash memory (called HyperFlash) or self refresh DRAM (called HyperRAM). Its a 8-bit data bus (DQ[7:0]) with Read-Write Data Strobe (RWDS) signal and either Single-ended clock(3.0V parts) or Differential clock (1.8V parts). It uses ChipSelect lines to select b/w multiple slaves. At bus level, it follows a separate protocol described in HyperBus specification[1]. HyperFlash follows CFI AMD/Fujitsu Extended Command Set (0x0002) similar to that of existing parallel NORs. Since HyperBus is x8 DDR bus, its equivalent to x16 parallel NOR flash with respect to bits per clock cycle. But HyperBus operates at >166MHz frequencies. HyperRAM provides direct random read/write access to flash memory array. But, HyperBus memory controllers seem to abstract implementation details and expose a simple MMIO interface to access connected flash. Add support for registering HyperFlash devices with MTD framework. MTD maps framework along with CFI chip support framework are used to support communicating with flash. Framework is modelled along the lines of spi-nor framework. HyperBus memory controller (HBMC) drivers calls hyperbus_register_device() to register a single HyperFlash device. HyperFlash core parses MMIO access information from DT, sets up the map_info struct, probes CFI flash and registers it with MTD framework. Some HBMC masters need calibration/training sequence[3] to be carried out, in order for DLL inside the controller to lock, by reading a known string/pattern. This is done by repeatedly reading CFI Query Identification String. Calibration needs to be done before trying to detect flash as part of CFI flash probe. HyperRAM is not supported at the moment. HyperBus specification can be found at[1] HyperFlash datasheet can be found at[2] [1] https://www.cypress.com/file/213356/download [2] https://www.cypress.com/file/213346/download [3] http://www.ti.com/lit/ug/spruid7b/spruid7b.pdf Table 12-5741. HyperFlash Access Sequence Signed-off-by: Vignesh Raghavendra Signed-off-by: Miquel Raynal --- include/linux/mtd/hyperbus.h | 84 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 include/linux/mtd/hyperbus.h (limited to 'include/linux') diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h new file mode 100644 index 000000000000..2dfe65964f6e --- /dev/null +++ b/include/linux/mtd/hyperbus.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ + */ + +#ifndef __LINUX_MTD_HYPERBUS_H__ +#define __LINUX_MTD_HYPERBUS_H__ + +#include + +enum hyperbus_memtype { + HYPERFLASH, + HYPERRAM, +}; + +/** + * struct hyperbus_device - struct representing HyperBus slave device + * @map: map_info struct for accessing MMIO HyperBus flash memory + * @np: pointer to HyperBus slave device node + * @mtd: pointer to MTD struct + * @ctlr: pointer to HyperBus controller struct + * @memtype: type of memory device: HyperFlash or HyperRAM + */ + +struct hyperbus_device { + struct map_info map; + struct device_node *np; + struct mtd_info *mtd; + struct hyperbus_ctlr *ctlr; + enum hyperbus_memtype memtype; +}; + +/** + * struct hyperbus_ops - struct representing custom HyperBus operations + * @read16: read 16 bit of data from flash in a single burst. Used to read + * from non default address space, such as ID/CFI space + * @write16: write 16 bit of data to flash in a single burst. Used to + * send cmd to flash or write single 16 bit word at a time. + * @copy_from: copy data from flash memory + * @copy_to: copy data to flash memory + * @calibrate: calibrate HyperBus controller + */ + +struct hyperbus_ops { + u16 (*read16)(struct hyperbus_device *hbdev, unsigned long addr); + void (*write16)(struct hyperbus_device *hbdev, + unsigned long addr, u16 val); + void (*copy_from)(struct hyperbus_device *hbdev, void *to, + unsigned long from, ssize_t len); + void (*copy_to)(struct hyperbus_device *dev, unsigned long to, + const void *from, ssize_t len); + int (*calibrate)(struct hyperbus_device *dev); +}; + +/** + * struct hyperbus_ctlr - struct representing HyperBus controller + * @dev: pointer to HyperBus controller device + * @calibrated: flag to indicate ctlr calibration sequence is complete + * @ops: HyperBus controller ops + */ +struct hyperbus_ctlr { + struct device *dev; + bool calibrated; + + const struct hyperbus_ops *ops; +}; + +/** + * hyperbus_register_device - probe and register a HyperBus slave memory device + * @hbdev: hyperbus_device struct with dev, np and ctlr field populated + * + * Return: 0 for success, others for failure. + */ +int hyperbus_register_device(struct hyperbus_device *hbdev); + +/** + * hyperbus_unregister_device - deregister HyperBus slave memory device + * @hbdev: hyperbus_device to be unregistered + * + * Return: 0 for success, others for failure. + */ +int hyperbus_unregister_device(struct hyperbus_device *hbdev); + +#endif /* __LINUX_MTD_HYPERBUS_H__ */ -- cgit v1.2.3 From 855eff216a97afa4a2233b792cb3c812b5ebd876 Mon Sep 17 00:00:00 2001 From: Jonathan Bakker Date: Fri, 26 Apr 2019 17:06:34 +0200 Subject: mtd: onenand: Add support for 8Gb datasize onenand MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Used in several S5PV210-based Galaxy S devices, among them SGH-T959V, SGH-T959P, SGH-T839, and SPH-D700. Signed-off-by: Jonathan Bakker Signed-off-by: Paweł Chmiel Signed-off-by: Miquel Raynal --- include/linux/mtd/onenand_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/onenand_regs.h b/include/linux/mtd/onenand_regs.h index d60130f88eed..9640d707cbf8 100644 --- a/include/linux/mtd/onenand_regs.h +++ b/include/linux/mtd/onenand_regs.h @@ -80,6 +80,7 @@ #define ONENAND_DEVICE_DENSITY_1Gb (0x003) #define ONENAND_DEVICE_DENSITY_2Gb (0x004) #define ONENAND_DEVICE_DENSITY_4Gb (0x005) +#define ONENAND_DEVICE_DENSITY_8Gb (0x006) /* * Version ID Register F002h (R) -- cgit v1.2.3 From 14a82ea7e1682645d942d9fb41fcb6126fd1645e Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Tue, 21 May 2019 09:06:30 +0200 Subject: mtd: rawnand: export NAND operation tracer The NAND core has a NAND operation tracing function, but it can only be used by drivers using the generic option parser from the NAND core. Export the tracing function as a static inline function in rawnand.h so that drivers implementing exec_op directly do not have to write their own operation tracing. Signed-off-by: Sascha Hauer Reviewed-by: Miquel Raynal Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index dbfffa5bec7b..f5bb6f11c36b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -877,6 +877,42 @@ int nand_op_parser_exec_op(struct nand_chip *chip, const struct nand_op_parser *parser, const struct nand_operation *op, bool check_only); +static inline void nand_op_trace(const char *prefix, + const struct nand_op_instr *instr) +{ +#if IS_ENABLED(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG) + switch (instr->type) { + case NAND_OP_CMD_INSTR: + pr_debug("%sCMD [0x%02x]\n", prefix, + instr->ctx.cmd.opcode); + break; + case NAND_OP_ADDR_INSTR: + pr_debug("%sADDR [%d cyc: %*ph]\n", prefix, + instr->ctx.addr.naddrs, + instr->ctx.addr.naddrs < 64 ? + instr->ctx.addr.naddrs : 64, + instr->ctx.addr.addrs); + break; + case NAND_OP_DATA_IN_INSTR: + pr_debug("%sDATA_IN [%d B%s]\n", prefix, + instr->ctx.data.len, + instr->ctx.data.force_8bit ? + ", force 8-bit" : ""); + break; + case NAND_OP_DATA_OUT_INSTR: + pr_debug("%sDATA_OUT [%d B%s]\n", prefix, + instr->ctx.data.len, + instr->ctx.data.force_8bit ? + ", force 8-bit" : ""); + break; + case NAND_OP_WAITRDY_INSTR: + pr_debug("%sWAITRDY [max %d ms]\n", prefix, + instr->ctx.waitrdy.timeout_ms); + break; + } +#endif +} + /** * struct nand_controller_ops - Controller operations * -- cgit v1.2.3 From e0ddaab76802d3179013f4864535043e2aea6c69 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Tue, 21 May 2019 09:06:41 +0200 Subject: dmaengine: mxs: Add header file to be shared with gpmi nand driver The mxs dma driver can do PIO transfers. A pointer to the PIO words to transfer is passed in the struct scatterlist * argument of dmaengine_prep_slave_sg(). It's quite ugly and non obvious to cast u32 * to struct scatterlist * each time when calling dmaengine_prep_slave_sg(), so add a static inline wrapper function to be called by the user along with a description what is going on. Signed-off-by: Sascha Hauer Acked-by: Vinod Koul Signed-off-by: Miquel Raynal --- include/linux/dma/mxs-dma.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/dma/mxs-dma.h (limited to 'include/linux') diff --git a/include/linux/dma/mxs-dma.h b/include/linux/dma/mxs-dma.h new file mode 100644 index 000000000000..092b2a7b92ac --- /dev/null +++ b/include/linux/dma/mxs-dma.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MXS_DMA_H_ +#define _MXS_DMA_H_ + +#include + +/* + * The mxs dmaengine can do PIO transfers. We pass a pointer to the PIO words + * in the second argument to dmaengine_prep_slave_sg when the direction is + * set to DMA_TRANS_NONE. To make this clear and to prevent users from doing + * the error prone casting we have this wrapper function + */ +static inline struct dma_async_tx_descriptor *mxs_dmaengine_prep_pio( + struct dma_chan *chan, u32 *pio, unsigned int npio, + enum dma_transfer_direction dir, unsigned long flags) +{ + return dmaengine_prep_slave_sg(chan, (struct scatterlist *)pio, npio, + dir, flags); +} + +#endif /* _MXS_DMA_H_ */ -- cgit v1.2.3 From ceeeb99cd821a2f7493e1e0e1eca5afc7a205213 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Tue, 21 May 2019 09:06:42 +0200 Subject: dmaengine: mxs: rename custom flag The mxs dma driver uses the flags parameter in dmaengine_prep_slave_sg() for custom flags, but still uses the dmaengine specific names of the flags. Do a little bit better and at least give the flag a custom name. Signed-off-by: Sascha Hauer Acked-by: Vinod Koul Signed-off-by: Miquel Raynal --- include/linux/dma/mxs-dma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma/mxs-dma.h b/include/linux/dma/mxs-dma.h index 092b2a7b92ac..4a33f2c8a682 100644 --- a/include/linux/dma/mxs-dma.h +++ b/include/linux/dma/mxs-dma.h @@ -4,6 +4,8 @@ #include +#define MXS_DMA_CTRL_WAIT4END BIT(31) + /* * The mxs dmaengine can do PIO transfers. We pass a pointer to the PIO words * in the second argument to dmaengine_prep_slave_sg when the direction is -- cgit v1.2.3 From ef347c0cfd619a9251e5a2f9ff72e33650a9bccb Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Tue, 21 May 2019 09:06:43 +0200 Subject: mtd: rawnand: gpmi: Implement exec_op The gpmi driver performance suffers from NAND operations being split in multiple small DMA transfers. This has been forced by the NAND layer in the former days, but now with exec_op we can use the controller as intended. With this patch gpmi_nfc_exec_op becomes the main entry point to NAND operations. Here all instructions are collected and chained as separate DMA transfers. In the end whole chain is fired and waited to be finished. gpmi_nfc_exec_op only does the hardware operations, bad block marker swapping and buffer scrambling is done by the callers. It's worth noting that the nand_*_op functions always take the buffer lengths for the data that the NAND chip actually transfers. When doing BCH we have to calculate the net data size from the raw data size in some places. This patch has been tested with 2048/64 and 2048/128 byte NAND on i.MX6q. mtd_oobtest, mtd_subpagetest and mtd_speedtest run without errors. nandbiterrs, nandpagetest and nandsubpagetest userspace tests from mtdutils run without errors and UBIFS can successfully be mounted. Signed-off-by: Sascha Hauer Signed-off-by: Miquel Raynal --- include/linux/dma/mxs-dma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma/mxs-dma.h b/include/linux/dma/mxs-dma.h index 4a33f2c8a682..069d9f5a609e 100644 --- a/include/linux/dma/mxs-dma.h +++ b/include/linux/dma/mxs-dma.h @@ -5,6 +5,7 @@ #include #define MXS_DMA_CTRL_WAIT4END BIT(31) +#define MXS_DMA_CTRL_WAIT4RDY BIT(30) /* * The mxs dmaengine can do PIO transfers. We pass a pointer to the PIO words -- cgit v1.2.3 From bded033062396e67ffbb3111084cf7ea202473d5 Mon Sep 17 00:00:00 2001 From: Jeff Kletsky Date: Wed, 22 May 2019 15:05:53 -0700 Subject: mtd: spinand: Define macros for page-read ops with three-byte addresses The GigaDevice GD5F1GQ4UFxxG SPI NAND utilizes three-byte addresses for its page-read ops. http://www.gigadevice.com/datasheet/gd5f1gq4xfxxg/ Signed-off-by: Jeff Kletsky Reviewed-by: Frieder Schrempf Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 507f7e289bd1..8aa39ac41e8e 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -68,30 +68,60 @@ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 1)) +#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(fast, addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + #define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 2)) +#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 2)) + #define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 4)) +#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 4)) + #define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ SPI_MEM_OP_ADDR(2, addr, 2), \ SPI_MEM_OP_DUMMY(ndummy, 2), \ SPI_MEM_OP_DATA_IN(len, buf, 2)) +#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ + SPI_MEM_OP_ADDR(3, addr, 2), \ + SPI_MEM_OP_DUMMY(ndummy, 2), \ + SPI_MEM_OP_DATA_IN(len, buf, 2)) + #define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ SPI_MEM_OP_ADDR(2, addr, 4), \ SPI_MEM_OP_DUMMY(ndummy, 4), \ SPI_MEM_OP_DATA_IN(len, buf, 4)) +#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ + SPI_MEM_OP_ADDR(3, addr, 4), \ + SPI_MEM_OP_DUMMY(ndummy, 4), \ + SPI_MEM_OP_DATA_IN(len, buf, 4)) + #define SPINAND_PROG_EXEC_OP(addr) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1), \ SPI_MEM_OP_ADDR(3, addr, 1), \ -- cgit v1.2.3 From 878844908e563a2f02b977bacd221c288e681c47 Mon Sep 17 00:00:00 2001 From: Jeff Kletsky Date: Wed, 22 May 2019 15:05:54 -0700 Subject: mtd: spinand: Add support for two-byte device IDs The GigaDevice GD5F1GQ4UFxxG SPI NAND utilizes two-byte device IDs. http://www.gigadevice.com/datasheet/gd5f1gq4xfxxg/ Signed-off-by: Jeff Kletsky Reviewed-by: Frieder Schrempf Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 8aa39ac41e8e..fbc0423bb4ae 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -290,7 +290,7 @@ struct spinand_ecc_info { */ struct spinand_info { const char *model; - u8 devid; + u16 devid; u32 flags; struct nand_memory_organization memorg; struct nand_ecc_req eccreq; @@ -452,7 +452,7 @@ static inline void spinand_set_of_node(struct spinand_device *spinand, int spinand_match_and_init(struct spinand_device *dev, const struct spinand_info *table, - unsigned int table_size, u8 devid); + unsigned int table_size, u16 devid); int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val); int spinand_select_target(struct spinand_device *spinand, unsigned int target); -- cgit v1.2.3 From 9f897bfdd89f5f08a12fa263a7f57fbf8ad9292f Mon Sep 17 00:00:00 2001 From: Kamal Dasu Date: Thu, 16 May 2019 12:41:46 -0400 Subject: mtd: Add flag to indicate panic_write Added a flag to indicate a panic_write so that low level drivers can use it to take required action where applicable, to ensure oops data gets written to assigned mtd device. Signed-off-by: Kamal Dasu Signed-off-by: Miquel Raynal --- include/linux/mtd/mtd.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 936a3fdb48b5..4ca8c1c845fb 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -316,6 +316,12 @@ struct mtd_info { int (*_get_device) (struct mtd_info *mtd); void (*_put_device) (struct mtd_info *mtd); + /* + * flag indicates a panic write, low level drivers can take appropriate + * action if required to ensure writes go through + */ + bool oops_panic_write; + struct notifier_block reboot_notifier; /* default mode before reboot */ /* ECC status information */ -- cgit v1.2.3 From 3552691616c940a7c4125c2678ba816653cd725e Mon Sep 17 00:00:00 2001 From: Jeff Kletsky Date: Tue, 18 Jun 2019 10:08:05 -0700 Subject: mtd: spinand: Add initial support for Paragon PN26G0xA Add initial support for Paragon Technology PN26G01Axxxxx and PN26G02Axxxxx SPI NAND Datasheets available at http://www.xtxtech.com/upfile/2016082517274590.pdf http://www.xtxtech.com/upfile/2016082517282329.pdf Signed-off-by: Jeff Kletsky Reviewed-by: Frieder Schrempf Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index fbc0423bb4ae..4ea558bd3c46 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -227,6 +227,7 @@ struct spinand_manufacturer { extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; +extern const struct spinand_manufacturer paragon_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; -- cgit v1.2.3 From a4496d52b3430cb3c4c16d03cdd5f4ee97ad1241 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Tue, 7 May 2019 11:52:47 +0200 Subject: power: supply: add input power and voltage limit properties For thermal management strategy you might be interested on limit the input power for a power supply. We already have current limit but basically what we probably want is to limit power. So, introduce the input_power_limit property. Although the common use case is limit the input power, in some specific cases it is the voltage that is problematic (i.e some regulators have different efficiencies at higher voltage resulting in more heat). So introduce also the input_voltage_limit property. This happens in one Chromebook and is used on the Pixel C's thermal management strategy to effectively limit the input power to 5V 3A when the screen is on. When the screen is on, the display, the CPU, and the GPU all contribute more heat to the system than while the screen is off, and we made a tradeoff to throttle the charger in order to give more of the thermal budget to those other components. So there's nothing fundamentally broken about the hardware that would cause the Pixel C to malfunction if we were charging at 9V or 12V instead of 5V when the screen is on, i.e. if userspace doesn't change this. What would happen is that you wouldn't meet Google's skin temperature targets on the system if the charger was allowed to run at 9V or 12V with the screen on. For folks hacking on Pixel Cs (which is now outside of Google's official support window for Android) and customizing their own kernel and userspace this would be acceptable, but we wanted to expose this feature in the power supply properties because the feature does exist in the Emedded Controller firmware of the Pixel C and all of Google's Chromebooks with USB-C made since 2015 in case someone running an up to date kernel wanted to limit the charging power for thermal or other reasons. This patch exposes a new property, similar to input current limit, to re-configure the maximum voltage from the external supply at runtime based on system-level knowledge or user input. Signed-off-by: Enric Balletbo i Serra Reviewed-by: Guenter Roeck Acked-by: Adam Thomson Reviewed-by: Benson Leung Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index d5b15e039f4f..cbb708b57b11 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -129,6 +129,8 @@ enum power_supply_property { POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD, /* in percents! */ POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD, /* in percents! */ POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, + POWER_SUPPLY_PROP_INPUT_VOLTAGE_LIMIT, + POWER_SUPPLY_PROP_INPUT_POWER_LIMIT, POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN, POWER_SUPPLY_PROP_ENERGY_EMPTY_DESIGN, POWER_SUPPLY_PROP_ENERGY_FULL, -- cgit v1.2.3 From b1a17513a2d60f9e933016bed04d0eeb8651a915 Mon Sep 17 00:00:00 2001 From: Clement Leger Date: Mon, 17 Jun 2019 14:57:30 +0200 Subject: remoteproc: add vendor resources handling In order to allow rproc backend to handle vendor resources such as in OpenAMP, add a handle_rsc hook. This hook allow the rproc backends to handle vendor resources as they like. The hook will be called only for vendor resources and should return RSC_HANDLED on successful resource handling, RSC_IGNORED if resource was ignored, or a negative value on error. Signed-off-by: Clement Leger Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 04d04709f2bd..16ad66683ad0 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -100,7 +100,9 @@ struct fw_rsc_hdr { * the remote processor will be writing logs. * @RSC_VDEV: declare support for a virtio device, and serve as its * virtio header. - * @RSC_LAST: just keep this one at the end + * @RSC_LAST: just keep this one at the end of standard resources + * @RSC_VENDOR_START: start of the vendor specific resource types range + * @RSC_VENDOR_END: end of the vendor specific resource types range * * For more details regarding a specific resource type, please see its * dedicated structure below. @@ -111,11 +113,13 @@ struct fw_rsc_hdr { * please update it as needed. */ enum fw_resource_type { - RSC_CARVEOUT = 0, - RSC_DEVMEM = 1, - RSC_TRACE = 2, - RSC_VDEV = 3, - RSC_LAST = 4, + RSC_CARVEOUT = 0, + RSC_DEVMEM = 1, + RSC_TRACE = 2, + RSC_VDEV = 3, + RSC_LAST = 4, + RSC_VENDOR_START = 128, + RSC_VENDOR_END = 512, }; #define FW_RSC_ADDR_ANY (-1) @@ -339,6 +343,16 @@ struct rproc_mem_entry { struct firmware; +/** + * enum rsc_handling_status - return status of rproc_ops handle_rsc hook + * @RSC_HANDLED: resource was handled + * @RSC_IGNORED: resource was ignored + */ +enum rsc_handling_status { + RSC_HANDLED = 0, + RSC_IGNORED = 1, +}; + /** * struct rproc_ops - platform-specific device handlers * @start: power on the device and boot it @@ -346,6 +360,10 @@ struct firmware; * @kick: kick a virtqueue (virtqueue id given as a parameter) * @da_to_va: optional platform hook to perform address translations * @parse_fw: parse firmware to extract information (e.g. resource table) + * @handle_rsc: optional platform hook to handle vendor resources. Should return + * RSC_HANDLED if resource was handled, RSC_IGNORED if not handled and a + * negative value on error + * @load_rsc_table: load resource table from firmware image * @find_loaded_rsc_table: find the loaded resouce table * @load: load firmware to memory, where the remote processor * expects to find it @@ -358,6 +376,8 @@ struct rproc_ops { void (*kick)(struct rproc *rproc, int vqid); void * (*da_to_va)(struct rproc *rproc, u64 da, int len); int (*parse_fw)(struct rproc *rproc, const struct firmware *fw); + int (*handle_rsc)(struct rproc *rproc, u32 rsc_type, void *rsc, + int offset, int avail); struct resource_table *(*find_loaded_rsc_table)( struct rproc *rproc, const struct firmware *fw); int (*load)(struct rproc *rproc, const struct firmware *fw); -- cgit v1.2.3 From 360aa640a59f269b784848c0b2d6d462952750d9 Mon Sep 17 00:00:00 2001 From: Fabien Dessenne Date: Thu, 7 Mar 2019 16:58:23 +0100 Subject: hwspinlock: add the 'in_atomic' API Add the 'in_atomic' mode which can be called from an atomic context. This mode relies on the existing 'raw' mode (no lock, no preemption/irq disabling) with the difference that the timeout is not based on jiffies (jiffies won't increase when irq are disabled) but handled with busy-waiting udelay() calls. Signed-off-by: Fabien Dessenne Signed-off-by: Bjorn Andersson --- include/linux/hwspinlock.h | 61 +++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 0afe693be5f4..bfe7c1f1ac6d 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -14,9 +14,10 @@ #include /* hwspinlock mode argument */ -#define HWLOCK_IRQSTATE 0x01 /* Disable interrupts, save state */ -#define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */ -#define HWLOCK_RAW 0x03 +#define HWLOCK_IRQSTATE 0x01 /* Disable interrupts, save state */ +#define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */ +#define HWLOCK_RAW 0x03 +#define HWLOCK_IN_ATOMIC 0x04 /* Called while in atomic context */ struct device; struct device_node; @@ -222,6 +223,23 @@ static inline int hwspin_trylock_raw(struct hwspinlock *hwlock) return __hwspin_trylock(hwlock, HWLOCK_RAW, NULL); } +/** + * hwspin_trylock_in_atomic() - attempt to lock a specific hwspinlock + * @hwlock: an hwspinlock which we want to trylock + * + * This function attempts to lock an hwspinlock, and will immediately fail + * if the hwspinlock is already taken. + * + * This function shall be called only from an atomic context. + * + * Returns 0 if we successfully locked the hwspinlock, -EBUSY if + * the hwspinlock was already taken, and -EINVAL if @hwlock is invalid. + */ +static inline int hwspin_trylock_in_atomic(struct hwspinlock *hwlock) +{ + return __hwspin_trylock(hwlock, HWLOCK_IN_ATOMIC, NULL); +} + /** * hwspin_trylock() - attempt to lock a specific hwspinlock * @hwlock: an hwspinlock which we want to trylock @@ -312,6 +330,28 @@ int hwspin_lock_timeout_raw(struct hwspinlock *hwlock, unsigned int to) return __hwspin_lock_timeout(hwlock, to, HWLOCK_RAW, NULL); } +/** + * hwspin_lock_timeout_in_atomic() - lock an hwspinlock with timeout limit + * @hwlock: the hwspinlock to be locked + * @to: timeout value in msecs + * + * This function locks the underlying @hwlock. If the @hwlock + * is already taken, the function will busy loop waiting for it to + * be released, but give up when @timeout msecs have elapsed. + * + * This function shall be called only from an atomic context and the timeout + * value shall not exceed a few msecs. + * + * Returns 0 when the @hwlock was successfully taken, and an appropriate + * error code otherwise (most notably an -ETIMEDOUT if the @hwlock is still + * busy after @timeout msecs). The function will never sleep. + */ +static inline +int hwspin_lock_timeout_in_atomic(struct hwspinlock *hwlock, unsigned int to) +{ + return __hwspin_lock_timeout(hwlock, to, HWLOCK_IN_ATOMIC, NULL); +} + /** * hwspin_lock_timeout() - lock an hwspinlock with timeout limit * @hwlock: the hwspinlock to be locked @@ -386,6 +426,21 @@ static inline void hwspin_unlock_raw(struct hwspinlock *hwlock) __hwspin_unlock(hwlock, HWLOCK_RAW, NULL); } +/** + * hwspin_unlock_in_atomic() - unlock hwspinlock + * @hwlock: a previously-acquired hwspinlock which we want to unlock + * + * This function will unlock a specific hwspinlock. + * + * @hwlock must be already locked (e.g. by hwspin_trylock()) before calling + * this function: it is a bug to call unlock on a @hwlock that is already + * unlocked. + */ +static inline void hwspin_unlock_in_atomic(struct hwspinlock *hwlock) +{ + __hwspin_unlock(hwlock, HWLOCK_IN_ATOMIC, NULL); +} + /** * hwspin_unlock() - unlock hwspinlock * @hwlock: a previously-acquired hwspinlock which we want to unlock -- cgit v1.2.3 From 0828c1001399d5c5fcab547ef7b0a29c78d4bdf6 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Sun, 30 Jun 2019 00:14:52 -0700 Subject: Input: elan_i2c - export the device id whitelist Elan_i2c and hid-quirks work in conjunction to decide which devices each driver will handle. Elan_i2c has a whitelist of devices that should be consumed by hid-quirks so that there is one master list of devices to handoff between the drivers. Put the ids in a header file so that hid-quirks can consume it instead of duplicating the list. Signed-off-by: Jeffrey Hugo Acked-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov --- include/linux/input/elan-i2c-ids.h | 76 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 include/linux/input/elan-i2c-ids.h (limited to 'include/linux') diff --git a/include/linux/input/elan-i2c-ids.h b/include/linux/input/elan-i2c-ids.h new file mode 100644 index 000000000000..ceabb01a6a7d --- /dev/null +++ b/include/linux/input/elan-i2c-ids.h @@ -0,0 +1,76 @@ +/* + * Elan I2C/SMBus Touchpad device whitelist + * + * Copyright (c) 2013 ELAN Microelectronics Corp. + * + * Author: æ維 (Duson Lin) + * Author: KT Liao + * Version: 1.6.3 + * + * Based on cyapa driver: + * copyright (c) 2011-2012 Cypress Semiconductor, Inc. + * copyright (c) 2011-2012 Google, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * Trademarks are the property of their respective owners. + */ + +#ifndef __ELAN_I2C_IDS_H +#define __ELAN_I2C_IDS_H + +#include + +static const struct acpi_device_id elan_acpi_id[] = { + { "ELAN0000", 0 }, + { "ELAN0100", 0 }, + { "ELAN0600", 0 }, + { "ELAN0601", 0 }, + { "ELAN0602", 0 }, + { "ELAN0603", 0 }, + { "ELAN0604", 0 }, + { "ELAN0605", 0 }, + { "ELAN0606", 0 }, + { "ELAN0607", 0 }, + { "ELAN0608", 0 }, + { "ELAN0609", 0 }, + { "ELAN060B", 0 }, + { "ELAN060C", 0 }, + { "ELAN060F", 0 }, + { "ELAN0610", 0 }, + { "ELAN0611", 0 }, + { "ELAN0612", 0 }, + { "ELAN0615", 0 }, + { "ELAN0616", 0 }, + { "ELAN0617", 0 }, + { "ELAN0618", 0 }, + { "ELAN0619", 0 }, + { "ELAN061A", 0 }, + { "ELAN061B", 0 }, + { "ELAN061C", 0 }, + { "ELAN061D", 0 }, + { "ELAN061E", 0 }, + { "ELAN061F", 0 }, + { "ELAN0620", 0 }, + { "ELAN0621", 0 }, + { "ELAN0622", 0 }, + { "ELAN0623", 0 }, + { "ELAN0624", 0 }, + { "ELAN0625", 0 }, + { "ELAN0626", 0 }, + { "ELAN0627", 0 }, + { "ELAN0628", 0 }, + { "ELAN0629", 0 }, + { "ELAN062A", 0 }, + { "ELAN062B", 0 }, + { "ELAN062C", 0 }, + { "ELAN062D", 0 }, + { "ELAN0631", 0 }, + { "ELAN0632", 0 }, + { "ELAN1000", 0 }, + { } +}; + +#endif /* __ELAN_I2C_IDS_H */ -- cgit v1.2.3 From 498b98e939007f8bb65094dfa229e84b6bf30e62 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 21 Jun 2019 18:21:45 -0700 Subject: soc: qcom: mdt_loader: Support loading non-split images In some software releases the firmware images are not split up with each loadable segment in it's own file. Check the size of the loaded firmware to see if it still contains each segment to be loaded, before falling back to the split-out segments. Acked-by: Andy Gross Reviewed-by: Jeffrey Hugo Signed-off-by: Bjorn Andersson --- include/linux/soc/qcom/mdt_loader.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index 944b06aefb0f..e600baec6825 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -21,4 +21,6 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base); +void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len); + #endif -- cgit v1.2.3 From 6987fd42239ad43937166dace2ed8fb260b14d25 Mon Sep 17 00:00:00 2001 From: Otto Sabart Date: Mon, 20 May 2019 10:06:26 +0100 Subject: mfd: madera: Fix bad reference to pinctrl.txt file The pinctrl.txt file was converted into reStructuredText and moved into driver-api folder. This patch updates the broken reference. Fixes: 5a9b73832e9e ("pinctrl.txt: move it to the driver-api book") Signed-off-by: Otto Sabart Signed-off-by: Charles Keepax Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Lee Jones --- include/linux/mfd/madera/pdata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h index 8dc852402dbb..dd00ab824e5b 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -34,7 +34,8 @@ struct madera_codec_pdata; * @micvdd: Substruct of pdata for the MICVDD regulator * @irq_flags: Mode for primary IRQ (defaults to active low) * @gpio_base: Base GPIO number - * @gpio_configs: Array of GPIO configurations (See Documentation/pinctrl.txt) + * @gpio_configs: Array of GPIO configurations (See + * Documentation/driver-api/pinctl.rst) * @n_gpio_configs: Number of entries in gpio_configs * @gpsw: General purpose switch mode setting. Depends on the external * hardware connected to the switch. (See the SW1_MODE field -- cgit v1.2.3 From 1ef921b6d1b68887be22f02dabc6ae73c112dce4 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 30 May 2019 15:39:52 +0100 Subject: mfd: madera: Add Madera core support for CS47L15 This patch adds all the core support and defines for the Cirrus Logic CS47L15 smart audio CODEC. Registers or fields are named MADERA_* if it is part of the common hardware platform and does not conflict with any other Madera codecs. It is named CS47L15_* if it is unique to CS47L15 and conflicts with definitions on other codecs. Signed-off-by: Richard Fitzgerald Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 2 ++ include/linux/mfd/madera/registers.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index 4d5d51a9c8a6..98dd3cb5e84d 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -27,11 +27,13 @@ enum madera_type { CS47L90 = 3, CS47L91 = 4, WM1840 = 7, + CS47L15 = 8, }; #define MADERA_MAX_CORE_SUPPLIES 2 #define MADERA_MAX_GPIOS 40 +#define CS47L15_NUM_GPIOS 15 #define CS47L35_NUM_GPIOS 16 #define CS47L85_NUM_GPIOS 40 #define CS47L90_NUM_GPIOS 38 diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h index 977e06101711..5b054d511c6a 100644 --- a/include/linux/mfd/madera/registers.h +++ b/include/linux/mfd/madera/registers.h @@ -244,6 +244,8 @@ #define MADERA_IN6R_CONTROL 0x33C #define MADERA_ADC_DIGITAL_VOLUME_6R 0x33D #define MADERA_DMIC6R_CONTROL 0x33E +#define CS47L15_ADC_INT_BIAS 0x3A8 +#define CS47L15_PGA_BIAS_SEL 0x3C4 #define MADERA_OUTPUT_ENABLES_1 0x400 #define MADERA_OUTPUT_STATUS_1 0x401 #define MADERA_RAW_OUTPUT_STATUS_1 0x406 @@ -1202,6 +1204,8 @@ #define MADERA_GPIO1_CTRL_2 0x1701 #define MADERA_GPIO2_CTRL_1 0x1702 #define MADERA_GPIO2_CTRL_2 0x1703 +#define MADERA_GPIO15_CTRL_1 0x171C +#define MADERA_GPIO15_CTRL_2 0x171D #define MADERA_GPIO16_CTRL_1 0x171E #define MADERA_GPIO16_CTRL_2 0x171F #define MADERA_GPIO38_CTRL_1 0x174A @@ -1232,6 +1236,7 @@ #define MADERA_IRQ2_CTRL 0x1A82 #define MADERA_INTERRUPT_RAW_STATUS_1 0x1AA0 #define MADERA_WSEQ_SEQUENCE_1 0x3000 +#define MADERA_WSEQ_SEQUENCE_225 0x31C0 #define MADERA_WSEQ_SEQUENCE_252 0x31F6 #define CS47L35_OTP_HPDET_CAL_1 0x31F8 #define CS47L35_OTP_HPDET_CAL_2 0x31FA -- cgit v1.2.3 From 297939901f382f16ab78a8073cdfb2a6279bb654 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 30 May 2019 15:39:53 +0100 Subject: mfd: madera: Add Madera core support for CS47L92 This patch adds all the core support and defines for the Cirrus Logic CS42L92, CS47L92 and CS47L93 smart audio CODECs. Registers or fields are named MADERA_* if it is part of the common hardware platform and does not conflict with any other Madera codecs. It is named CS47L15_* if it is unique to CS47L15 and conflicts with definitions on other codecs. Signed-off-by: Stuart Henderson Signed-off-by: Richard Fitzgerald Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 4 + include/linux/mfd/madera/registers.h | 195 +++++++++++++++++++++++++++++++++++ 2 files changed, 199 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index 98dd3cb5e84d..7b87f9a02ecc 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -26,8 +26,11 @@ enum madera_type { CS47L85 = 2, CS47L90 = 3, CS47L91 = 4, + CS47L92 = 5, + CS47L93 = 6, WM1840 = 7, CS47L15 = 8, + CS42L92 = 9, }; #define MADERA_MAX_CORE_SUPPLIES 2 @@ -37,6 +40,7 @@ enum madera_type { #define CS47L35_NUM_GPIOS 16 #define CS47L85_NUM_GPIOS 40 #define CS47L90_NUM_GPIOS 38 +#define CS47L92_NUM_GPIOS 16 #define MADERA_MAX_MICBIAS 4 diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h index 5b054d511c6a..6439c0282ac6 100644 --- a/include/linux/mfd/madera/registers.h +++ b/include/linux/mfd/madera/registers.h @@ -77,9 +77,15 @@ #define MADERA_FLL1_CONTROL_5 0x175 #define MADERA_FLL1_CONTROL_6 0x176 #define MADERA_FLL1_LOOP_FILTER_TEST_1 0x177 +#define CS47L92_FLL1_CONTROL_7 0x177 #define MADERA_FLL1_NCO_TEST_0 0x178 +#define CS47L92_FLL1_CONTROL_8 0x178 #define MADERA_FLL1_CONTROL_7 0x179 +#define CS47L92_FLL1_CONTROL_9 0x179 #define MADERA_FLL1_EFS_2 0x17A +#define CS47L92_FLL1_CONTROL_10 0x17A +#define MADERA_FLL1_CONTROL_11 0x17B +#define MADERA_FLL1_DIGITAL_TEST_1 0x17D #define CS47L35_FLL1_SYNCHRONISER_1 0x17F #define CS47L35_FLL1_SYNCHRONISER_2 0x180 #define CS47L35_FLL1_SYNCHRONISER_3 0x181 @@ -98,6 +104,7 @@ #define MADERA_FLL1_SYNCHRONISER_7 0x187 #define MADERA_FLL1_SPREAD_SPECTRUM 0x189 #define MADERA_FLL1_GPIO_CLOCK 0x18A +#define CS47L92_FLL1_GPIO_CLOCK 0x18E #define MADERA_FLL2_CONTROL_1 0x191 #define MADERA_FLL2_CONTROL_2 0x192 #define MADERA_FLL2_CONTROL_3 0x193 @@ -105,9 +112,15 @@ #define MADERA_FLL2_CONTROL_5 0x195 #define MADERA_FLL2_CONTROL_6 0x196 #define MADERA_FLL2_LOOP_FILTER_TEST_1 0x197 +#define CS47L92_FLL2_CONTROL_7 0x197 #define MADERA_FLL2_NCO_TEST_0 0x198 +#define CS47L92_FLL2_CONTROL_8 0x198 #define MADERA_FLL2_CONTROL_7 0x199 +#define CS47L92_FLL2_CONTROL_9 0x199 #define MADERA_FLL2_EFS_2 0x19A +#define CS47L92_FLL2_CONTROL_10 0x19A +#define MADERA_FLL2_CONTROL_11 0x19B +#define MADERA_FLL2_DIGITAL_TEST_1 0x19D #define MADERA_FLL2_SYNCHRONISER_1 0x1A1 #define MADERA_FLL2_SYNCHRONISER_2 0x1A2 #define MADERA_FLL2_SYNCHRONISER_3 0x1A3 @@ -117,6 +130,7 @@ #define MADERA_FLL2_SYNCHRONISER_7 0x1A7 #define MADERA_FLL2_SPREAD_SPECTRUM 0x1A9 #define MADERA_FLL2_GPIO_CLOCK 0x1AA +#define CS47L92_FLL2_GPIO_CLOCK 0x1AE #define MADERA_FLL3_CONTROL_1 0x1B1 #define MADERA_FLL3_CONTROL_2 0x1B2 #define MADERA_FLL3_CONTROL_3 0x1B3 @@ -267,6 +281,7 @@ #define MADERA_NOISE_GATE_SELECT_2R 0x41F #define MADERA_OUTPUT_PATH_CONFIG_3L 0x420 #define MADERA_DAC_DIGITAL_VOLUME_3L 0x421 +#define MADERA_OUTPUT_PATH_CONFIG_3 0x422 #define MADERA_NOISE_GATE_SELECT_3L 0x423 #define MADERA_OUTPUT_PATH_CONFIG_3R 0x424 #define MADERA_DAC_DIGITAL_VOLUME_3R 0x425 @@ -369,8 +384,20 @@ #define MADERA_AIF3_FRAME_CTRL_2 0x588 #define MADERA_AIF3_FRAME_CTRL_3 0x589 #define MADERA_AIF3_FRAME_CTRL_4 0x58A +#define MADERA_AIF3_FRAME_CTRL_5 0x58B +#define MADERA_AIF3_FRAME_CTRL_6 0x58C +#define MADERA_AIF3_FRAME_CTRL_7 0x58D +#define MADERA_AIF3_FRAME_CTRL_8 0x58E +#define MADERA_AIF3_FRAME_CTRL_9 0x58F +#define MADERA_AIF3_FRAME_CTRL_10 0x590 #define MADERA_AIF3_FRAME_CTRL_11 0x591 #define MADERA_AIF3_FRAME_CTRL_12 0x592 +#define MADERA_AIF3_FRAME_CTRL_13 0x593 +#define MADERA_AIF3_FRAME_CTRL_14 0x594 +#define MADERA_AIF3_FRAME_CTRL_15 0x595 +#define MADERA_AIF3_FRAME_CTRL_16 0x596 +#define MADERA_AIF3_FRAME_CTRL_17 0x597 +#define MADERA_AIF3_FRAME_CTRL_18 0x598 #define MADERA_AIF3_TX_ENABLES 0x599 #define MADERA_AIF3_RX_ENABLES 0x59A #define MADERA_AIF3_FORCE_WRITE 0x59B @@ -662,6 +689,54 @@ #define MADERA_AIF3TX2MIX_INPUT_3_VOLUME 0x78D #define MADERA_AIF3TX2MIX_INPUT_4_SOURCE 0x78E #define MADERA_AIF3TX2MIX_INPUT_4_VOLUME 0x78F +#define MADERA_AIF3TX3MIX_INPUT_1_SOURCE 0x790 +#define MADERA_AIF3TX3MIX_INPUT_1_VOLUME 0x791 +#define MADERA_AIF3TX3MIX_INPUT_2_SOURCE 0x792 +#define MADERA_AIF3TX3MIX_INPUT_2_VOLUME 0x793 +#define MADERA_AIF3TX3MIX_INPUT_3_SOURCE 0x794 +#define MADERA_AIF3TX3MIX_INPUT_3_VOLUME 0x795 +#define MADERA_AIF3TX3MIX_INPUT_4_SOURCE 0x796 +#define MADERA_AIF3TX3MIX_INPUT_4_VOLUME 0x797 +#define MADERA_AIF3TX4MIX_INPUT_1_SOURCE 0x798 +#define MADERA_AIF3TX4MIX_INPUT_1_VOLUME 0x799 +#define MADERA_AIF3TX4MIX_INPUT_2_SOURCE 0x79A +#define MADERA_AIF3TX4MIX_INPUT_2_VOLUME 0x79B +#define MADERA_AIF3TX4MIX_INPUT_3_SOURCE 0x79C +#define MADERA_AIF3TX4MIX_INPUT_3_VOLUME 0x79D +#define MADERA_AIF3TX4MIX_INPUT_4_SOURCE 0x79E +#define MADERA_AIF3TX4MIX_INPUT_4_VOLUME 0x79F +#define CS47L92_AIF3TX5MIX_INPUT_1_SOURCE 0x7A0 +#define CS47L92_AIF3TX5MIX_INPUT_1_VOLUME 0x7A1 +#define CS47L92_AIF3TX5MIX_INPUT_2_SOURCE 0x7A2 +#define CS47L92_AIF3TX5MIX_INPUT_2_VOLUME 0x7A3 +#define CS47L92_AIF3TX5MIX_INPUT_3_SOURCE 0x7A4 +#define CS47L92_AIF3TX5MIX_INPUT_3_VOLUME 0x7A5 +#define CS47L92_AIF3TX5MIX_INPUT_4_SOURCE 0x7A6 +#define CS47L92_AIF3TX5MIX_INPUT_4_VOLUME 0x7A7 +#define CS47L92_AIF3TX6MIX_INPUT_1_SOURCE 0x7A8 +#define CS47L92_AIF3TX6MIX_INPUT_1_VOLUME 0x7A9 +#define CS47L92_AIF3TX6MIX_INPUT_2_SOURCE 0x7AA +#define CS47L92_AIF3TX6MIX_INPUT_2_VOLUME 0x7AB +#define CS47L92_AIF3TX6MIX_INPUT_3_SOURCE 0x7AC +#define CS47L92_AIF3TX6MIX_INPUT_3_VOLUME 0x7AD +#define CS47L92_AIF3TX6MIX_INPUT_4_SOURCE 0x7AE +#define CS47L92_AIF3TX6MIX_INPUT_4_VOLUME 0x7AF +#define CS47L92_AIF3TX7MIX_INPUT_1_SOURCE 0x7B0 +#define CS47L92_AIF3TX7MIX_INPUT_1_VOLUME 0x7B1 +#define CS47L92_AIF3TX7MIX_INPUT_2_SOURCE 0x7B2 +#define CS47L92_AIF3TX7MIX_INPUT_2_VOLUME 0x7B3 +#define CS47L92_AIF3TX7MIX_INPUT_3_SOURCE 0x7B4 +#define CS47L92_AIF3TX7MIX_INPUT_3_VOLUME 0x7B5 +#define CS47L92_AIF3TX7MIX_INPUT_4_SOURCE 0x7B6 +#define CS47L92_AIF3TX7MIX_INPUT_4_VOLUME 0x7B7 +#define CS47L92_AIF3TX8MIX_INPUT_1_SOURCE 0x7B8 +#define CS47L92_AIF3TX8MIX_INPUT_1_VOLUME 0x7B9 +#define CS47L92_AIF3TX8MIX_INPUT_2_SOURCE 0x7BA +#define CS47L92_AIF3TX8MIX_INPUT_2_VOLUME 0x7BB +#define CS47L92_AIF3TX8MIX_INPUT_3_SOURCE 0x7BC +#define CS47L92_AIF3TX8MIX_INPUT_3_VOLUME 0x7BD +#define CS47L92_AIF3TX8MIX_INPUT_4_SOURCE 0x7BE +#define CS47L92_AIF3TX8MIX_INPUT_4_VOLUME 0x7BF #define MADERA_AIF4TX1MIX_INPUT_1_SOURCE 0x7A0 #define MADERA_AIF4TX1MIX_INPUT_1_VOLUME 0x7A1 #define MADERA_AIF4TX1MIX_INPUT_2_SOURCE 0x7A2 @@ -1105,6 +1180,8 @@ #define MADERA_FCR_ADC_REFORMATTER_CONTROL 0xF73 #define MADERA_FCR_COEFF_START 0xF74 #define MADERA_FCR_COEFF_END 0xFC5 +#define MADERA_AUXPDM1_CTRL_0 0x10C0 +#define MADERA_AUXPDM1_CTRL_1 0x10C1 #define MADERA_DAC_COMP_1 0x1300 #define MADERA_DAC_COMP_2 0x1302 #define MADERA_FRF_COEFFICIENT_1L_1 0x1380 @@ -1446,6 +1523,12 @@ #define MADERA_OPCLK_ASYNC_SEL_WIDTH 3 /* (0x0171) FLL1_Control_1 */ +#define CS47L92_FLL1_REFCLK_SRC_MASK 0xF000 +#define CS47L92_FLL1_REFCLK_SRC_SHIFT 12 +#define CS47L92_FLL1_REFCLK_SRC_WIDTH 4 +#define MADERA_FLL1_HOLD_MASK 0x0004 +#define MADERA_FLL1_HOLD_SHIFT 2 +#define MADERA_FLL1_HOLD_WIDTH 1 #define MADERA_FLL1_FREERUN 0x0002 #define MADERA_FLL1_FREERUN_MASK 0x0002 #define MADERA_FLL1_FREERUN_SHIFT 1 @@ -1478,6 +1561,9 @@ #define MADERA_FLL1_FRATIO_MASK 0x0F00 #define MADERA_FLL1_FRATIO_SHIFT 8 #define MADERA_FLL1_FRATIO_WIDTH 4 +#define MADERA_FLL1_FB_DIV_MASK 0x03FF +#define MADERA_FLL1_FB_DIV_SHIFT 0 +#define MADERA_FLL1_FB_DIV_WIDTH 10 /* (0x0176) FLL1_Control_6 */ #define MADERA_FLL1_REFCLK_DIV_MASK 0x00C0 @@ -1509,6 +1595,30 @@ #define MADERA_FLL1_PHASE_ENA_SHIFT 11 #define MADERA_FLL1_PHASE_ENA_WIDTH 1 +/* (0x017A) FLL1_Control_10 */ +#define MADERA_FLL1_HP_MASK 0xC000 +#define MADERA_FLL1_HP_SHIFT 14 +#define MADERA_FLL1_HP_WIDTH 2 +#define MADERA_FLL1_PHASEDET_ENA_MASK 0x1000 +#define MADERA_FLL1_PHASEDET_ENA_SHIFT 12 +#define MADERA_FLL1_PHASEDET_ENA_WIDTH 1 + +/* (0x017B) FLL1_Control_11 */ +#define MADERA_FLL1_LOCKDET_THR_MASK 0x001E +#define MADERA_FLL1_LOCKDET_THR_SHIFT 1 +#define MADERA_FLL1_LOCKDET_THR_WIDTH 4 +#define MADERA_FLL1_LOCKDET_MASK 0x0001 +#define MADERA_FLL1_LOCKDET_SHIFT 0 +#define MADERA_FLL1_LOCKDET_WIDTH 1 + +/* (0x017D) FLL1_Digital_Test_1 */ +#define MADERA_FLL1_SYNC_EFS_ENA_MASK 0x0100 +#define MADERA_FLL1_SYNC_EFS_ENA_SHIFT 8 +#define MADERA_FLL1_SYNC_EFS_ENA_WIDTH 1 +#define MADERA_FLL1_CLK_VCO_FAST_SRC_MASK 0x0003 +#define MADERA_FLL1_CLK_VCO_FAST_SRC_SHIFT 0 +#define MADERA_FLL1_CLK_VCO_FAST_SRC_WIDTH 2 + /* (0x0181) FLL1_Synchroniser_1 */ #define MADERA_FLL1_SYNC_ENA 0x0001 #define MADERA_FLL1_SYNC_ENA_MASK 0x0001 @@ -1630,6 +1740,13 @@ #define MADERA_LDO2_ENA_WIDTH 1 /* (0x0218) Mic_Bias_Ctrl_1 */ +#define MADERA_MICB1_EXT_CAP 0x8000 +#define MADERA_MICB1_EXT_CAP_MASK 0x8000 +#define MADERA_MICB1_EXT_CAP_SHIFT 15 +#define MADERA_MICB1_EXT_CAP_WIDTH 1 +#define MADERA_MICB1_LVL_MASK 0x01E0 +#define MADERA_MICB1_LVL_SHIFT 5 +#define MADERA_MICB1_LVL_WIDTH 4 #define MADERA_MICB1_ENA 0x0001 #define MADERA_MICB1_ENA_MASK 0x0001 #define MADERA_MICB1_ENA_SHIFT 0 @@ -2313,6 +2430,17 @@ #define MADERA_OUT1R_ENA_SHIFT 0 #define MADERA_OUT1R_ENA_WIDTH 1 +/* (0x0408) Output_Rate_1 */ +#define MADERA_CP_DAC_MODE_MASK 0x0040 +#define MADERA_CP_DAC_MODE_SHIFT 6 +#define MADERA_CP_DAC_MODE_WIDTH 1 +#define MADERA_OUT_EXT_CLK_DIV_MASK 0x0030 +#define MADERA_OUT_EXT_CLK_DIV_SHIFT 4 +#define MADERA_OUT_EXT_CLK_DIV_WIDTH 2 +#define MADERA_OUT_CLK_SRC_MASK 0x0007 +#define MADERA_OUT_CLK_SRC_SHIFT 0 +#define MADERA_OUT_CLK_SRC_WIDTH 3 + /* (0x0409) Output_Volume_Ramp */ #define MADERA_OUT_VD_RAMP_MASK 0x0070 #define MADERA_OUT_VD_RAMP_SHIFT 4 @@ -2834,6 +2962,30 @@ #define MADERA_AIF2RX1_ENA_WIDTH 1 /* (0x0599) AIF3_Tx_Enables */ +#define MADERA_AIF3TX8_ENA 0x0080 +#define MADERA_AIF3TX8_ENA_MASK 0x0080 +#define MADERA_AIF3TX8_ENA_SHIFT 7 +#define MADERA_AIF3TX8_ENA_WIDTH 1 +#define MADERA_AIF3TX7_ENA 0x0040 +#define MADERA_AIF3TX7_ENA_MASK 0x0040 +#define MADERA_AIF3TX7_ENA_SHIFT 6 +#define MADERA_AIF3TX7_ENA_WIDTH 1 +#define MADERA_AIF3TX6_ENA 0x0020 +#define MADERA_AIF3TX6_ENA_MASK 0x0020 +#define MADERA_AIF3TX6_ENA_SHIFT 5 +#define MADERA_AIF3TX6_ENA_WIDTH 1 +#define MADERA_AIF3TX5_ENA 0x0010 +#define MADERA_AIF3TX5_ENA_MASK 0x0010 +#define MADERA_AIF3TX5_ENA_SHIFT 4 +#define MADERA_AIF3TX5_ENA_WIDTH 1 +#define MADERA_AIF3TX4_ENA 0x0008 +#define MADERA_AIF3TX4_ENA_MASK 0x0008 +#define MADERA_AIF3TX4_ENA_SHIFT 3 +#define MADERA_AIF3TX4_ENA_WIDTH 1 +#define MADERA_AIF3TX3_ENA 0x0004 +#define MADERA_AIF3TX3_ENA_MASK 0x0004 +#define MADERA_AIF3TX3_ENA_SHIFT 2 +#define MADERA_AIF3TX3_ENA_WIDTH 1 #define MADERA_AIF3TX2_ENA 0x0002 #define MADERA_AIF3TX2_ENA_MASK 0x0002 #define MADERA_AIF3TX2_ENA_SHIFT 1 @@ -2844,6 +2996,30 @@ #define MADERA_AIF3TX1_ENA_WIDTH 1 /* (0x059A) AIF3_Rx_Enables */ +#define MADERA_AIF3RX8_ENA 0x0080 +#define MADERA_AIF3RX8_ENA_MASK 0x0080 +#define MADERA_AIF3RX8_ENA_SHIFT 7 +#define MADERA_AIF3RX8_ENA_WIDTH 1 +#define MADERA_AIF3RX7_ENA 0x0040 +#define MADERA_AIF3RX7_ENA_MASK 0x0040 +#define MADERA_AIF3RX7_ENA_SHIFT 6 +#define MADERA_AIF3RX7_ENA_WIDTH 1 +#define MADERA_AIF3RX6_ENA 0x0020 +#define MADERA_AIF3RX6_ENA_MASK 0x0020 +#define MADERA_AIF3RX6_ENA_SHIFT 5 +#define MADERA_AIF3RX6_ENA_WIDTH 1 +#define MADERA_AIF3RX5_ENA 0x0010 +#define MADERA_AIF3RX5_ENA_MASK 0x0010 +#define MADERA_AIF3RX5_ENA_SHIFT 4 +#define MADERA_AIF3RX5_ENA_WIDTH 1 +#define MADERA_AIF3RX4_ENA 0x0008 +#define MADERA_AIF3RX4_ENA_MASK 0x0008 +#define MADERA_AIF3RX4_ENA_SHIFT 3 +#define MADERA_AIF3RX4_ENA_WIDTH 1 +#define MADERA_AIF3RX3_ENA 0x0004 +#define MADERA_AIF3RX3_ENA_MASK 0x0004 +#define MADERA_AIF3RX3_ENA_SHIFT 2 +#define MADERA_AIF3RX3_ENA_WIDTH 1 #define MADERA_AIF3RX2_ENA 0x0002 #define MADERA_AIF3RX2_ENA_MASK 0x0002 #define MADERA_AIF3RX2_ENA_SHIFT 1 @@ -3458,6 +3634,25 @@ #define MADERA_FCR_MIC_MODE_SEL_SHIFT 2 #define MADERA_FCR_MIC_MODE_SEL_WIDTH 2 +/* (0x10C0) AUXPDM1_CTRL_0 */ +#define MADERA_AUXPDM1_SRC_MASK 0x0F00 +#define MADERA_AUXPDM1_SRC_SHIFT 8 +#define MADERA_AUXPDM1_SRC_WIDTH 4 +#define MADERA_AUXPDM1_TXEDGE_MASK 0x0010 +#define MADERA_AUXPDM1_TXEDGE_SHIFT 4 +#define MADERA_AUXPDM1_TXEDGE_WIDTH 1 +#define MADERA_AUXPDM1_MSTR_MASK 0x0008 +#define MADERA_AUXPDM1_MSTR_SHIFT 3 +#define MADERA_AUXPDM1_MSTR_WIDTH 1 +#define MADERA_AUXPDM1_ENABLE_MASK 0x0001 +#define MADERA_AUXPDM1_ENABLE_SHIFT 0 +#define MADERA_AUXPDM1_ENABLE_WIDTH 1 + +/* (0x10C1) AUXPDM1_CTRL_1 */ +#define MADERA_AUXPDM1_CLK_FREQ_MASK 0xC000 +#define MADERA_AUXPDM1_CLK_FREQ_SHIFT 14 +#define MADERA_AUXPDM1_CLK_FREQ_WIDTH 2 + /* (0x1480) DFC1_CTRL_W0 */ #define MADERA_DFC1_RATE_MASK 0x007C #define MADERA_DFC1_RATE_SHIFT 2 -- cgit v1.2.3 From 554e937ec8d75930bc711612208af27961e3dc61 Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Mon, 3 Jun 2019 11:45:11 +0800 Subject: mfd: cros_ec: differentiate SCP from EC by feature bit System Companion Processor (SCP) is Cortex M4 co-processor on some MediaTek platform that can run EC-style firmware. Since a SCP and EC would both exist on a system, and use the cros_ec_dev driver, we need to differentiate between them for the userspace, or they would both be registered at /dev/cros_ec, causing a conflict. Signed-off-by: Pi-Hsun Shih Acked-by: Enric Balletbo i Serra Signed-off-by: Lee Jones --- include/linux/mfd/cros_ec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index cfa78bb4990f..751cb3756d49 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -27,6 +27,7 @@ #define CROS_EC_DEV_PD_NAME "cros_pd" #define CROS_EC_DEV_TP_NAME "cros_tp" #define CROS_EC_DEV_ISH_NAME "cros_ish" +#define CROS_EC_DEV_SCP_NAME "cros_scp" /* * The EC is unresponsive for a time after a reboot command. Add a -- cgit v1.2.3 From 76304994645028accc0cfe287652344b696f4470 Mon Sep 17 00:00:00 2001 From: Stefan Mavrodiev Date: Fri, 7 Jun 2019 15:42:25 +0300 Subject: mfd: rk808: Check pm_power_off pointer The function pointer pm_power_off may point to function from other module (PSCI for example). If rk808 is removed, pm_power_off is overwritten to NULL and the system cannot be powered off. This patch checks if pm_power_off points to a module function. Signed-off-by: Stefan Mavrodiev Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 2a9cd01691b2..286316375636 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -628,5 +628,6 @@ struct rk808 { long variant; const struct regmap_config *regmap_cfg; const struct regmap_irq_chip *regmap_irq_chip; + void (*pm_pwroff_fn)(void); }; #endif /* __LINUX_REGULATOR_RK808_H */ -- cgit v1.2.3 From ac195d94280a783f030a01ee84998a198b779d99 Mon Sep 17 00:00:00 2001 From: Stefan Mavrodiev Date: Fri, 7 Jun 2019 15:42:26 +0300 Subject: mfd: rk808: Prepare rk805 for poweroff RK805 has SLEEP signal, which can put the device into SLEEP or OFF mode. The default is SLEEP mode. However, when the kernel performs power-off (actually the ATF) the device will not go fully off and this will result in higher power consumption and inability to wake the device with RTC alarm. The solution is to enable pm_power_off_prepare function, which will configure SLEEP pin for OFF function. Signed-off-by: Stefan Mavrodiev Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 286316375636..b264ac794c74 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -629,5 +629,6 @@ struct rk808 { const struct regmap_config *regmap_cfg; const struct regmap_irq_chip *regmap_irq_chip; void (*pm_pwroff_fn)(void); + void (*pm_pwroff_prep_fn)(void); }; #endif /* __LINUX_REGULATOR_RK808_H */ -- cgit v1.2.3 From b1c83bd84618e5a3ec6395845d11803047a3ef9a Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 10 May 2019 18:23:01 -0700 Subject: mfd: stmfx: Fix macro definition spelling Clang warns: In file included from drivers/mfd/stmfx.c:13: include/linux/mfd/stmfx.h:7:9: warning: 'MFD_STMFX_H' is used as a header guard here, followed by #define of a different macro [-Wheader-guard] Fixes: 06252ade9156 ("mfd: Add ST Multi-Function eXpander (STMFX) core driver") Link: https://github.com/ClangBuiltLinux/linux/issues/475 Signed-off-by: Nathan Chancellor Signed-off-by: Lee Jones --- include/linux/mfd/stmfx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/stmfx.h b/include/linux/mfd/stmfx.h index d890595b89b6..3c67983678ec 100644 --- a/include/linux/mfd/stmfx.h +++ b/include/linux/mfd/stmfx.h @@ -5,7 +5,7 @@ */ #ifndef MFD_STMFX_H -#define MFX_STMFX_H +#define MFD_STMFX_H #include -- cgit v1.2.3 From 0772a34bb8a12fcc245074e0f76e96cba2c9a434 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 26 Jun 2019 14:33:35 +0100 Subject: mfd: madera: Remove some unused registers and fix some defaults Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/madera/registers.h | 80 ------------------------------------ 1 file changed, 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h index 6439c0282ac6..53c2377b54b2 100644 --- a/include/linux/mfd/madera/registers.h +++ b/include/linux/mfd/madera/registers.h @@ -76,9 +76,7 @@ #define MADERA_FLL1_CONTROL_4 0x174 #define MADERA_FLL1_CONTROL_5 0x175 #define MADERA_FLL1_CONTROL_6 0x176 -#define MADERA_FLL1_LOOP_FILTER_TEST_1 0x177 #define CS47L92_FLL1_CONTROL_7 0x177 -#define MADERA_FLL1_NCO_TEST_0 0x178 #define CS47L92_FLL1_CONTROL_8 0x178 #define MADERA_FLL1_CONTROL_7 0x179 #define CS47L92_FLL1_CONTROL_9 0x179 @@ -111,9 +109,7 @@ #define MADERA_FLL2_CONTROL_4 0x194 #define MADERA_FLL2_CONTROL_5 0x195 #define MADERA_FLL2_CONTROL_6 0x196 -#define MADERA_FLL2_LOOP_FILTER_TEST_1 0x197 #define CS47L92_FLL2_CONTROL_7 0x197 -#define MADERA_FLL2_NCO_TEST_0 0x198 #define CS47L92_FLL2_CONTROL_8 0x198 #define MADERA_FLL2_CONTROL_7 0x199 #define CS47L92_FLL2_CONTROL_9 0x199 @@ -137,8 +133,6 @@ #define MADERA_FLL3_CONTROL_4 0x1B4 #define MADERA_FLL3_CONTROL_5 0x1B5 #define MADERA_FLL3_CONTROL_6 0x1B6 -#define MADERA_FLL3_LOOP_FILTER_TEST_1 0x1B7 -#define MADERA_FLL3_NCO_TEST_0 0x1B8 #define MADERA_FLL3_CONTROL_7 0x1B9 #define MADERA_FLL3_SYNCHRONISER_1 0x1C1 #define MADERA_FLL3_SYNCHRONISER_2 0x1C2 @@ -304,9 +298,6 @@ #define MADERA_OUTPUT_PATH_CONFIG_6R 0x43C #define MADERA_DAC_DIGITAL_VOLUME_6R 0x43D #define MADERA_NOISE_GATE_SELECT_6R 0x43F -#define MADERA_DRE_ENABLE 0x440 -#define MADERA_EDRE_ENABLE 0x448 -#define MADERA_EDRE_MANUAL 0x44A #define MADERA_DAC_AEC_CONTROL_1 0x450 #define MADERA_DAC_AEC_CONTROL_2 0x451 #define MADERA_NOISE_GATE_CONTROL 0x458 @@ -1182,68 +1173,6 @@ #define MADERA_FCR_COEFF_END 0xFC5 #define MADERA_AUXPDM1_CTRL_0 0x10C0 #define MADERA_AUXPDM1_CTRL_1 0x10C1 -#define MADERA_DAC_COMP_1 0x1300 -#define MADERA_DAC_COMP_2 0x1302 -#define MADERA_FRF_COEFFICIENT_1L_1 0x1380 -#define MADERA_FRF_COEFFICIENT_1L_2 0x1381 -#define MADERA_FRF_COEFFICIENT_1L_3 0x1382 -#define MADERA_FRF_COEFFICIENT_1L_4 0x1383 -#define MADERA_FRF_COEFFICIENT_1R_1 0x1390 -#define MADERA_FRF_COEFFICIENT_1R_2 0x1391 -#define MADERA_FRF_COEFFICIENT_1R_3 0x1392 -#define MADERA_FRF_COEFFICIENT_1R_4 0x1393 -#define MADERA_FRF_COEFFICIENT_2L_1 0x13A0 -#define MADERA_FRF_COEFFICIENT_2L_2 0x13A1 -#define MADERA_FRF_COEFFICIENT_2L_3 0x13A2 -#define MADERA_FRF_COEFFICIENT_2L_4 0x13A3 -#define MADERA_FRF_COEFFICIENT_2R_1 0x13B0 -#define MADERA_FRF_COEFFICIENT_2R_2 0x13B1 -#define MADERA_FRF_COEFFICIENT_2R_3 0x13B2 -#define MADERA_FRF_COEFFICIENT_2R_4 0x13B3 -#define MADERA_FRF_COEFFICIENT_3L_1 0x13C0 -#define MADERA_FRF_COEFFICIENT_3L_2 0x13C1 -#define MADERA_FRF_COEFFICIENT_3L_3 0x13C2 -#define MADERA_FRF_COEFFICIENT_3L_4 0x13C3 -#define MADERA_FRF_COEFFICIENT_3R_1 0x13D0 -#define MADERA_FRF_COEFFICIENT_3R_2 0x13D1 -#define MADERA_FRF_COEFFICIENT_3R_3 0x13D2 -#define MADERA_FRF_COEFFICIENT_3R_4 0x13D3 -#define MADERA_FRF_COEFFICIENT_4L_1 0x13E0 -#define MADERA_FRF_COEFFICIENT_4L_2 0x13E1 -#define MADERA_FRF_COEFFICIENT_4L_3 0x13E2 -#define MADERA_FRF_COEFFICIENT_4L_4 0x13E3 -#define MADERA_FRF_COEFFICIENT_4R_1 0x13F0 -#define MADERA_FRF_COEFFICIENT_4R_2 0x13F1 -#define MADERA_FRF_COEFFICIENT_4R_3 0x13F2 -#define MADERA_FRF_COEFFICIENT_4R_4 0x13F3 -#define CS47L35_FRF_COEFFICIENT_4L_1 0x13A0 -#define CS47L35_FRF_COEFFICIENT_4L_2 0x13A1 -#define CS47L35_FRF_COEFFICIENT_4L_3 0x13A2 -#define CS47L35_FRF_COEFFICIENT_4L_4 0x13A3 -#define CS47L35_FRF_COEFFICIENT_5L_1 0x13B0 -#define CS47L35_FRF_COEFFICIENT_5L_2 0x13B1 -#define CS47L35_FRF_COEFFICIENT_5L_3 0x13B2 -#define CS47L35_FRF_COEFFICIENT_5L_4 0x13B3 -#define CS47L35_FRF_COEFFICIENT_5R_1 0x13C0 -#define CS47L35_FRF_COEFFICIENT_5R_2 0x13C1 -#define CS47L35_FRF_COEFFICIENT_5R_3 0x13C2 -#define CS47L35_FRF_COEFFICIENT_5R_4 0x13C3 -#define MADERA_FRF_COEFFICIENT_5L_1 0x1400 -#define MADERA_FRF_COEFFICIENT_5L_2 0x1401 -#define MADERA_FRF_COEFFICIENT_5L_3 0x1402 -#define MADERA_FRF_COEFFICIENT_5L_4 0x1403 -#define MADERA_FRF_COEFFICIENT_5R_1 0x1410 -#define MADERA_FRF_COEFFICIENT_5R_2 0x1411 -#define MADERA_FRF_COEFFICIENT_5R_3 0x1412 -#define MADERA_FRF_COEFFICIENT_5R_4 0x1413 -#define MADERA_FRF_COEFFICIENT_6L_1 0x1420 -#define MADERA_FRF_COEFFICIENT_6L_2 0x1421 -#define MADERA_FRF_COEFFICIENT_6L_3 0x1422 -#define MADERA_FRF_COEFFICIENT_6L_4 0x1423 -#define MADERA_FRF_COEFFICIENT_6R_1 0x1430 -#define MADERA_FRF_COEFFICIENT_6R_2 0x1431 -#define MADERA_FRF_COEFFICIENT_6R_3 0x1432 -#define MADERA_FRF_COEFFICIENT_6R_4 0x1433 #define MADERA_DFC1_CTRL 0x1480 #define MADERA_DFC1_RX 0x1482 #define MADERA_DFC1_TX 0x1484 @@ -1573,15 +1502,6 @@ #define MADERA_FLL1_REFCLK_SRC_SHIFT 0 #define MADERA_FLL1_REFCLK_SRC_WIDTH 4 -/* (0x0177) FLL1_Loop_Filter_Test_1 */ -#define MADERA_FLL1_FRC_INTEG_UPD 0x8000 -#define MADERA_FLL1_FRC_INTEG_UPD_MASK 0x8000 -#define MADERA_FLL1_FRC_INTEG_UPD_SHIFT 15 -#define MADERA_FLL1_FRC_INTEG_UPD_WIDTH 1 -#define MADERA_FLL1_FRC_INTEG_VAL_MASK 0x0FFF -#define MADERA_FLL1_FRC_INTEG_VAL_SHIFT 0 -#define MADERA_FLL1_FRC_INTEG_VAL_WIDTH 12 - /* (0x0179) FLL1_Control_7 */ #define MADERA_FLL1_GAIN_MASK 0x003c #define MADERA_FLL1_GAIN_SHIFT 2 -- cgit v1.2.3 From d6871a73387d51dfdde6ad1479aea54d3eafcc89 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 26 Jun 2019 14:33:36 +0100 Subject: mfd: madera: Fixup SPDX headers GPL-2.0-only is the preferred way of expressing v2 of the GPL, so switch to that. Remove some redundant copyright notices and correct some instances where the wrong comment type has been used in header files. Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 6 +----- include/linux/mfd/madera/pdata.h | 6 +----- include/linux/mfd/madera/registers.h | 6 +----- 3 files changed, 3 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index 7b87f9a02ecc..7ffa696cce7c 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -1,12 +1,8 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0-only */ /* * MFD internals for Cirrus Logic Madera codecs * * Copyright (C) 2015-2018 Cirrus Logic - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by the - * Free Software Foundation; version 2. */ #ifndef MADERA_CORE_H diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h index dd00ab824e5b..ec0711bcad50 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -1,12 +1,8 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Platform data for Cirrus Logic Madera codecs * * Copyright (C) 2015-2018 Cirrus Logic - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by the - * Free Software Foundation; version 2. */ #ifndef MADERA_PDATA_H diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h index 53c2377b54b2..fe909d177762 100644 --- a/include/linux/mfd/madera/registers.h +++ b/include/linux/mfd/madera/registers.h @@ -1,12 +1,8 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Madera register definitions * * Copyright (C) 2015-2018 Cirrus Logic - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by the - * Free Software Foundation; version 2. */ #ifndef MADERA_REGISTERS_H -- cgit v1.2.3 From 07ec38917e68f0114b9c8aeeb1c584b5e73e4dd6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:01 +0200 Subject: mm: remove the struct hmm_device infrastructure This code is a trivial wrapper around device model helpers, which should have been integrated into the driver device model usage from the start. Assuming it actually had users, which it never had since the code was added more than 1 1/2 years ago. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 044a36d7c3f8..99765be3284d 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -751,26 +751,6 @@ static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) { return page->hmm_data; } - - -/* - * struct hmm_device - fake device to hang device memory onto - * - * @device: device struct - * @minor: device minor number - */ -struct hmm_device { - struct device device; - unsigned int minor; -}; - -/* - * A device driver that wants to handle multiple devices memory through a - * single fake device can use hmm_device to do so. This is purely a helper and - * it is not strictly needed, in order to make use of any HMM functionality. - */ -struct hmm_device *hmm_device_new(void *drvdata); -void hmm_device_put(struct hmm_device *hmm_device); #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} -- cgit v1.2.3 From 25b2995a35b609119cf96f6b62eccd56c0234c7d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Jun 2019 22:50:49 +0200 Subject: mm: remove MEMORY_DEVICE_PUBLIC support The code hasn't been used since it was added to the tree, and doesn't appear to actually be usable. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Acked-by: Michal Hocko Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 7 ++----- include/linux/ioport.h | 1 - include/linux/memremap.h | 8 -------- include/linux/mm.h | 18 ++---------------- 4 files changed, 4 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 99765be3284d..44a5ac738bb5 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -584,7 +584,7 @@ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) struct hmm_devmem; struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, @@ -722,9 +722,6 @@ struct hmm_devmem { struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, struct device *device, unsigned long size); -struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, - struct device *device, - struct resource *res); /* * hmm_devmem_page_set_drvdata - set per-page driver data field @@ -751,7 +748,7 @@ static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) { return page->hmm_data; } -#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +#endif /* CONFIG_DEVICE_PRIVATE */ #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} diff --git a/include/linux/ioport.h b/include/linux/ioport.h index da0ebaec25f0..dd961882bc74 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -132,7 +132,6 @@ enum { IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, - IORES_DESC_DEVICE_PUBLIC_MEMORY = 7, }; /* helpers to define resources */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1732dea030b2..995c62c5a48b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -37,13 +37,6 @@ struct vmem_altmap { * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/vm/hmm.rst. * - * MEMORY_DEVICE_PUBLIC: - * Device memory that is cache coherent from device and CPU point of view. This - * is use on platform that have an advance system bus (like CAPI or CCIX). A - * driver can hotplug the device memory using ZONE_DEVICE and with that memory - * type. Any page of a process can be migrated to such memory. However no one - * should be allow to pin such memory so that it can always be evicted. - * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page @@ -58,7 +51,6 @@ struct vmem_altmap { */ enum memory_type { MEMORY_DEVICE_PRIVATE = 1, - MEMORY_DEVICE_PUBLIC, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_PCI_P2PDMA, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index dd0b5f4e1e45..7399f9f08de6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -944,7 +944,6 @@ static inline bool put_devmap_managed_page(struct page *page) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_PUBLIC: case MEMORY_DEVICE_FS_DAX: __put_devmap_managed_page(page); return true; @@ -960,12 +959,6 @@ static inline bool is_device_private_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PRIVATE; } -static inline bool is_device_public_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PUBLIC; -} - #ifdef CONFIG_PCI_P2PDMA static inline bool is_pci_p2pdma_page(const struct page *page) { @@ -998,11 +991,6 @@ static inline bool is_device_private_page(const struct page *page) return false; } -static inline bool is_device_public_page(const struct page *page) -{ - return false; -} - static inline bool is_pci_p2pdma_page(const struct page *page) { return false; @@ -1431,10 +1419,8 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ }; -struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte, bool with_public_device); -#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false) - +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); -- cgit v1.2.3 From 0092908d16c604b8207c2141ec64b0fa4473bb03 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:06 +0200 Subject: mm: factor out a devm_request_free_mem_region helper Keep the physical address allocation that hmm_add_device does with the rest of the resource code, and allow future reuse of it without the hmm wrapper. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: John Hubbard Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/ioport.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index dd961882bc74..a02b290ca08a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -285,6 +285,8 @@ static inline bool resource_overlaps(struct resource *r1, struct resource *r2) return (r1->start <= r2->end && r1->end >= r2->start); } +struct resource *devm_request_free_mem_region(struct device *dev, + struct resource *base, unsigned long size); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ -- cgit v1.2.3 From 3ed2dcdf54d5bf1f9823b5faf1a702e7cee53982 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:07 +0200 Subject: memremap: validate the pagemap type passed to devm_memremap_pages Most pgmap types are only supported when certain config options are enabled. Check for a type that is valid for the current configuration before setting up the pagemap. For this the usage of the 0 type for device dax gets replaced with an explicit MEMORY_DEVICE_DEVDAX type. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 995c62c5a48b..0c86f2c5ac9c 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -45,13 +45,21 @@ struct vmem_altmap { * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * + * MEMORY_DEVICE_DEVDAX: + * Host memory that has similar access semantics as System RAM i.e. DMA + * coherent and supports page pinning. In contrast to + * MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax + * character device. + * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { + /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_DEVDAX, MEMORY_DEVICE_PCI_P2PDMA, }; -- cgit v1.2.3 From 1e240e8d4a7d92232b6214e02a0a4197a53afd6c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:08 +0200 Subject: memremap: move dev_pagemap callbacks into a separate structure The dev_pagemap is a growing too many callbacks. Move them into a separate ops structure so that they are not duplicated for multiple instances, and an attacker can't easily overwrite them. Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 0c86f2c5ac9c..919755f48c7e 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -63,41 +63,45 @@ enum memory_type { MEMORY_DEVICE_PCI_P2PDMA, }; -/* - * Additional notes about MEMORY_DEVICE_PRIVATE may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. There is also a brief - * explanation in include/linux/memory_hotplug.h. - * - * The page_free() callback is called once the page refcount reaches 1 - * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. - * This allows the device driver to implement its own memory management.) - */ -typedef void (*dev_page_free_t)(struct page *page, void *data); +struct dev_pagemap_ops { + /* + * Called once the page refcount reaches 1. (ZONE_DEVICE pages never + * reach 0 refcount unless there is a refcount bug. This allows the + * device driver to implement its own memory management.) + */ + void (*page_free)(struct page *page, void *data); + + /* + * Transition the refcount in struct dev_pagemap to the dead state. + */ + void (*kill)(struct percpu_ref *ref); + + /* + * Wait for refcount in struct dev_pagemap to be idle and reap it. + */ + void (*cleanup)(struct percpu_ref *ref); +}; /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings - * @page_free: free page callback when page refcount reaches 1 * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping - * @kill: callback to transition @ref to the dead state - * @cleanup: callback to wait for @ref to be idle and reap it * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h + * @ops: method table */ struct dev_pagemap { - dev_page_free_t page_free; struct vmem_altmap altmap; bool altmap_valid; struct resource res; struct percpu_ref *ref; - void (*kill)(struct percpu_ref *ref); - void (*cleanup)(struct percpu_ref *ref); struct device *dev; void *data; enum memory_type type; u64 pci_p2pdma_bus_offset; + const struct dev_pagemap_ops *ops; }; #ifdef CONFIG_ZONE_DEVICE -- cgit v1.2.3 From d8668bb0451c3c45b59dbcde2654e0539aad1d2a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:09 +0200 Subject: memremap: pass a struct dev_pagemap to ->kill and ->cleanup Passing the actual typed structure leads to more understandable code vs just passing the ref member. Reported-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 919755f48c7e..b8666a0d8665 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -74,12 +74,12 @@ struct dev_pagemap_ops { /* * Transition the refcount in struct dev_pagemap to the dead state. */ - void (*kill)(struct percpu_ref *ref); + void (*kill)(struct dev_pagemap *pgmap); /* * Wait for refcount in struct dev_pagemap to be idle and reap it. */ - void (*cleanup)(struct percpu_ref *ref); + void (*cleanup)(struct dev_pagemap *pgmap); }; /** -- cgit v1.2.3 From f6a55e1a3fe6b3bb294a80a05437fcf86488d819 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:10 +0200 Subject: memremap: lift the devmap_enable manipulation into devm_memremap_pages Just check if there is a ->page_free operation set and take care of the static key enable, as well as the put using device managed resources. Also check that a ->page_free is provided for the pgmaps types that require it, and check for a valid type as well while we are at it. Note that this also fixes the fact that hmm never called dev_pagemap_put_ops and thus would leave the slow path enabled forever, even after a device driver unload or disable. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/mm.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7399f9f08de6..2425f4167ec2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -932,8 +932,6 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void dev_pagemap_get_ops(void); -void dev_pagemap_put_ops(void); void __put_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool put_devmap_managed_page(struct page *page) @@ -973,14 +971,6 @@ static inline bool is_pci_p2pdma_page(const struct page *page) #endif /* CONFIG_PCI_P2PDMA */ #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline void dev_pagemap_get_ops(void) -{ -} - -static inline void dev_pagemap_put_ops(void) -{ -} - static inline bool put_devmap_managed_page(struct page *page) { return false; -- cgit v1.2.3 From 897e6365cda6ba6356e83a3aaa68dec82ef4c548 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:11 +0200 Subject: memremap: add a migrate_to_ram method to struct dev_pagemap_ops This replaces the hacky ->fault callback, which is currently directly called from common code through a hmm specific data structure as an exercise in layering violations. Signed-off-by: Christoph Hellwig Reviewed-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 6 ------ include/linux/memremap.h | 6 ++++++ include/linux/swapops.h | 15 --------------- 3 files changed, 6 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 44a5ac738bb5..ba19c19e24ed 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -692,11 +692,6 @@ struct hmm_devmem_ops { * chunk, as an optimization. It must, however, prioritize the faulting address * over all the others. */ -typedef vm_fault_t (*dev_page_fault_t)(struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); struct hmm_devmem { struct completion completion; @@ -707,7 +702,6 @@ struct hmm_devmem { struct dev_pagemap pagemap; const struct hmm_devmem_ops *ops; struct percpu_ref ref; - dev_page_fault_t page_fault; }; /* diff --git a/include/linux/memremap.h b/include/linux/memremap.h index b8666a0d8665..ac985bd03a7f 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -80,6 +80,12 @@ struct dev_pagemap_ops { * Wait for refcount in struct dev_pagemap to be idle and reap it. */ void (*cleanup)(struct dev_pagemap *pgmap); + + /* + * Used for private (un-addressable) device memory only. Must migrate + * the page back to a CPU accessible page. + */ + vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); }; /** diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 4d961668e5fc..15bdb6fe71e5 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -129,12 +129,6 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return pfn_to_page(swp_offset(entry)); } - -vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp); #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { @@ -164,15 +158,6 @@ static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return NULL; } - -static inline vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp) -{ - return VM_FAULT_SIGBUS; -} #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION -- cgit v1.2.3 From 80a72d0af05ae97a8b106c172e431072ba587492 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:12 +0200 Subject: memremap: remove the data field in struct dev_pagemap struct dev_pagemap is always embedded into a containing structure, so there is no need to an additional private data field. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index ac985bd03a7f..336eca601dad 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -69,7 +69,7 @@ struct dev_pagemap_ops { * reach 0 refcount unless there is a refcount bug. This allows the * device driver to implement its own memory management.) */ - void (*page_free)(struct page *page, void *data); + void (*page_free)(struct page *page); /* * Transition the refcount in struct dev_pagemap to the dead state. @@ -104,7 +104,6 @@ struct dev_pagemap { struct resource res; struct percpu_ref *ref; struct device *dev; - void *data; enum memory_type type; u64 pci_p2pdma_bus_offset; const struct dev_pagemap_ops *ops; -- cgit v1.2.3 From 514caf23a70fd697fa2ece238b2cd8dcc73fb16f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:13 +0200 Subject: memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag Add a flags field to struct dev_pagemap to replace the altmap_valid boolean to be a little more extensible. Also add a pgmap_altmap() helper to find the optional altmap and clean up the code using the altmap using it. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 336eca601dad..e25685b878e9 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -88,6 +88,8 @@ struct dev_pagemap_ops { vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); }; +#define PGMAP_ALTMAP_VALID (1 << 0) + /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations @@ -96,19 +98,27 @@ struct dev_pagemap_ops { * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h + * @flags: PGMAP_* flags to specify defailed behavior * @ops: method table */ struct dev_pagemap { struct vmem_altmap altmap; - bool altmap_valid; struct resource res; struct percpu_ref *ref; struct device *dev; enum memory_type type; + unsigned int flags; u64 pci_p2pdma_bus_offset; const struct dev_pagemap_ops *ops; }; +static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) +{ + if (pgmap->flags & PGMAP_ALTMAP_VALID) + return &pgmap->altmap; + return NULL; +} + #ifdef CONFIG_ZONE_DEVICE void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); -- cgit v1.2.3 From 24917f6b1041a73993178920656e13364f847995 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:14 +0200 Subject: memremap: provide an optional internal refcount in struct dev_pagemap Provide an internal refcounting logic if no ->ref field is provided in the pagemap passed into devm_memremap_pages so that callers don't have to reinvent it poorly. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/memremap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index e25685b878e9..f8a5b2a19945 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -95,6 +95,8 @@ struct dev_pagemap_ops { * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping + * @internal_ref: internal reference if @ref is not provided by the caller + * @done: completion for @internal_ref * @dev: host device of the mapping for debug * @data: private data pointer for page_free() * @type: memory type: see MEMORY_* in memory_hotplug.h @@ -105,6 +107,8 @@ struct dev_pagemap { struct vmem_altmap altmap; struct resource res; struct percpu_ref *ref; + struct percpu_ref internal_ref; + struct completion done; struct device *dev; enum memory_type type; unsigned int flags; -- cgit v1.2.3 From 47e9d836a5e827acdaa5cb6175648fbef15b4e84 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:19 +0200 Subject: mm: remove hmm_vma_alloc_locked_page The only user of it has just been removed, and there wasn't really any need to wrap a basic memory allocator to start with. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index ba19c19e24ed..1d55b7ea2da6 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -587,9 +587,6 @@ static inline void hmm_mm_init(struct mm_struct *mm) {} #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) struct hmm_devmem; -struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, - unsigned long addr); - /* * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events * -- cgit v1.2.3 From eee3ae41b153e55e25d6cf7bd5b5098ba0afe705 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:20 +0200 Subject: mm: remove hmm_devmem_add There isn't really much value add in the hmm_devmem_add wrapper and more, as using devm_memremap_pages directly now is just as simple. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 129 ---------------------------------------------------- 1 file changed, 129 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 1d55b7ea2da6..86aa4ec3404c 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -585,135 +585,6 @@ static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -struct hmm_devmem; - -/* - * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events - * - * @free: call when refcount on page reach 1 and thus is no longer use - * @fault: call when there is a page fault to unaddressable memory - * - * Both callback happens from page_free() and page_fault() callback of struct - * dev_pagemap respectively. See include/linux/memremap.h for more details on - * those. - * - * The hmm_devmem_ops callback are just here to provide a coherent and - * uniq API to device driver and device driver should not register their - * own page_free() or page_fault() but rely on the hmm_devmem_ops call- - * back. - */ -struct hmm_devmem_ops { - /* - * free() - free a device page - * @devmem: device memory structure (see struct hmm_devmem) - * @page: pointer to struct page being freed - * - * Call back occurs whenever a device page refcount reach 1 which - * means that no one is holding any reference on the page anymore - * (ZONE_DEVICE page have an elevated refcount of 1 as default so - * that they are not release to the general page allocator). - * - * Note that callback has exclusive ownership of the page (as no - * one is holding any reference). - */ - void (*free)(struct hmm_devmem *devmem, struct page *page); - /* - * fault() - CPU page fault or get user page (GUP) - * @devmem: device memory structure (see struct hmm_devmem) - * @vma: virtual memory area containing the virtual address - * @addr: virtual address that faulted or for which there is a GUP - * @page: pointer to struct page backing virtual address (unreliable) - * @flags: FAULT_FLAG_* (see include/linux/mm.h) - * @pmdp: page middle directory - * Returns: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR - * on error - * - * The callback occurs whenever there is a CPU page fault or GUP on a - * virtual address. This means that the device driver must migrate the - * page back to regular memory (CPU accessible). - * - * The device driver is free to migrate more than one page from the - * fault() callback as an optimization. However if device decide to - * migrate more than one page it must always priotirize the faulting - * address over the others. - * - * The struct page pointer is only given as an hint to allow quick - * lookup of internal device driver data. A concurrent migration - * might have already free that page and the virtual address might - * not longer be back by it. So it should not be modified by the - * callback. - * - * Note that mmap semaphore is held in read mode at least when this - * callback occurs, hence the vma is valid upon callback entry. - */ - vm_fault_t (*fault)(struct hmm_devmem *devmem, - struct vm_area_struct *vma, - unsigned long addr, - const struct page *page, - unsigned int flags, - pmd_t *pmdp); -}; - -/* - * struct hmm_devmem - track device memory - * - * @completion: completion object for device memory - * @pfn_first: first pfn for this resource (set by hmm_devmem_add()) - * @pfn_last: last pfn for this resource (set by hmm_devmem_add()) - * @resource: IO resource reserved for this chunk of memory - * @pagemap: device page map for that chunk - * @device: device to bind resource to - * @ops: memory operations callback - * @ref: per CPU refcount - * @page_fault: callback when CPU fault on an unaddressable device page - * - * This an helper structure for device drivers that do not wish to implement - * the gory details related to hotplugging new memoy and allocating struct - * pages. - * - * Device drivers can directly use ZONE_DEVICE memory on their own if they - * wish to do so. - * - * The page_fault() callback must migrate page back, from device memory to - * system memory, so that the CPU can access it. This might fail for various - * reasons (device issues, device have been unplugged, ...). When such error - * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and - * set the CPU page table entry to "poisoned". - * - * Note that because memory cgroup charges are transferred to the device memory, - * this should never fail due to memory restrictions. However, allocation - * of a regular system page might still fail because we are out of memory. If - * that happens, the page_fault() callback must return VM_FAULT_OOM. - * - * The page_fault() callback can also try to migrate back multiple pages in one - * chunk, as an optimization. It must, however, prioritize the faulting address - * over all the others. - */ - -struct hmm_devmem { - struct completion completion; - unsigned long pfn_first; - unsigned long pfn_last; - struct resource *resource; - struct device *device; - struct dev_pagemap pagemap; - const struct hmm_devmem_ops *ops; - struct percpu_ref ref; -}; - -/* - * To add (hotplug) device memory, HMM assumes that there is no real resource - * that reserves a range in the physical address space (this is intended to be - * use by unaddressable device memory). It will reserve a physical range big - * enough and allocate struct page for it. - * - * The device driver can wrap the hmm_devmem struct inside a private device - * driver struct. - */ -struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, - struct device *device, - unsigned long size); - /* * hmm_devmem_page_set_drvdata - set per-page driver data field * -- cgit v1.2.3 From 8a164fef9c4ccf6ff7757170397222860e40d192 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:21 +0200 Subject: mm: simplify ZONE_DEVICE page private data Remove the clumsy hmm_devmem_page_{get,set}_drvdata helpers, and instead just access the page directly. Also make the page data a void pointer, and thus much easier to use. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 32 -------------------------------- include/linux/mm_types.h | 2 +- 2 files changed, 1 insertion(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 86aa4ec3404c..3d00e9550e77 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -584,36 +584,4 @@ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -/* - * hmm_devmem_page_set_drvdata - set per-page driver data field - * - * @page: pointer to struct page - * @data: driver data value to set - * - * Because page can not be on lru we have an unsigned long that driver can use - * to store a per page field. This just a simple helper to do that. - */ -static inline void hmm_devmem_page_set_drvdata(struct page *page, - unsigned long data) -{ - page->hmm_data = data; -} - -/* - * hmm_devmem_page_get_drvdata - get per page driver data field - * - * @page: pointer to struct page - * Return: driver data value - */ -static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page) -{ - return page->hmm_data; -} -#endif /* CONFIG_DEVICE_PRIVATE */ -#else /* IS_ENABLED(CONFIG_HMM) */ -static inline void hmm_mm_destroy(struct mm_struct *mm) {} -static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM) */ - #endif /* LINUX_HMM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8ec38b11b361..f33a1289c101 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -158,7 +158,7 @@ struct page { struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; - unsigned long hmm_data; + void *zone_device_data; unsigned long _zd_pad_1; /* uses mapping */ }; -- cgit v1.2.3 From 43535b0aefab29ea6564e608de4c783ed2ab6c49 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 Jun 2019 14:27:23 +0200 Subject: mm: remove the HMM config option All the mm/hmm.c code is better keyed off HMM_MIRROR. Also let nouveau depend on it instead of the mix of a dummy dependency symbol plus the actually selected one. Drop various odd dependencies, as the code is pretty portable. Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 5 +---- include/linux/mm_types.h | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 3d00e9550e77..b697496e85ba 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -62,7 +62,7 @@ #include #include -#if IS_ENABLED(CONFIG_HMM) +#ifdef CONFIG_HMM_MIRROR #include #include @@ -332,9 +332,6 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, return hmm_device_entry_from_pfn(range, pfn); } - - -#if IS_ENABLED(CONFIG_HMM_MIRROR) /* * Mirroring: how to synchronize device page table with CPU page table. * diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f33a1289c101..8d37182f8dbe 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -501,7 +501,7 @@ struct mm_struct { #endif struct work_struct async_put_work; -#if IS_ENABLED(CONFIG_HMM) +#ifdef CONFIG_HMM_MIRROR /* HMM needs to track a few things per mm */ struct hmm *hmm; #endif -- cgit v1.2.3 From 0b07ee944701dabcddc294d903b5e8e21c2c5d95 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 4 Jul 2019 13:06:17 +0530 Subject: PM / QOS: Pass request type to dev_pm_qos_{add|remove}_notifier() In order to use the same set of routines to register notifiers for different request types, update the existing dev_pm_qos_{add|remove}_notifier() routines with an additional parameter: request-type. For now, it only supports resume-latency request type but will be extended to frequency limit (min/max) constraints later on. Reviewed-by: Matthias Kaehlcke Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 6ea1ae373d77..58e8749ceac5 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -146,9 +146,11 @@ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value); int dev_pm_qos_remove_request(struct dev_pm_qos_request *req); int dev_pm_qos_add_notifier(struct device *dev, - struct notifier_block *notifier); + struct notifier_block *notifier, + enum dev_pm_qos_req_type type); int dev_pm_qos_remove_notifier(struct device *dev, - struct notifier_block *notifier); + struct notifier_block *notifier, + enum dev_pm_qos_req_type type); void dev_pm_qos_constraints_init(struct device *dev); void dev_pm_qos_constraints_destroy(struct device *dev); int dev_pm_qos_add_ancestor_request(struct device *dev, @@ -202,10 +204,12 @@ static inline int dev_pm_qos_update_request(struct dev_pm_qos_request *req, static inline int dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { return 0; } static inline int dev_pm_qos_add_notifier(struct device *dev, - struct notifier_block *notifier) + struct notifier_block *notifier, + enum dev_pm_qos_req_type type) { return 0; } static inline int dev_pm_qos_remove_notifier(struct device *dev, - struct notifier_block *notifier) + struct notifier_block *notifier, + enum dev_pm_qos_req_type type) { return 0; } static inline void dev_pm_qos_constraints_init(struct device *dev) { -- cgit v1.2.3 From 8262331eaaf751076fb2c781f492bafd8344591d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 4 Jul 2019 13:06:18 +0530 Subject: PM / QOS: Rename __dev_pm_qos_read_value() and dev_pm_qos_raw_read_value() dev_pm_qos_read_value() will soon need to support more constraint types (min/max frequency) and will have another argument to it, i.e. type of the constraint. While that is fine for the existing users of dev_pm_qos_read_value(), but not that optimal for the callers of __dev_pm_qos_read_value() and dev_pm_qos_raw_read_value() as all the callers of these two routines are only looking for resume latency constraint. Lets make these two routines care only about the resume latency constraint and rename them to __dev_pm_qos_resume_latency() and dev_pm_qos_raw_resume_latency(). Suggested-by: Rafael J. Wysocki Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 58e8749ceac5..5e09d4980786 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -139,7 +139,7 @@ s32 pm_qos_read_value(struct pm_qos_constraints *c); #ifdef CONFIG_PM enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask); enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask); -s32 __dev_pm_qos_read_value(struct device *dev); +s32 __dev_pm_qos_resume_latency(struct device *dev); s32 dev_pm_qos_read_value(struct device *dev); int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value); @@ -176,7 +176,7 @@ static inline s32 dev_pm_qos_requested_flags(struct device *dev) return dev->power.qos->flags_req->data.flr.flags; } -static inline s32 dev_pm_qos_raw_read_value(struct device *dev) +static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) { return IS_ERR_OR_NULL(dev->power.qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : @@ -189,7 +189,7 @@ static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, static inline enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) { return PM_QOS_FLAGS_UNDEFINED; } -static inline s32 __dev_pm_qos_read_value(struct device *dev) +static inline s32 __dev_pm_qos_resume_latency(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } static inline s32 dev_pm_qos_read_value(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } @@ -245,7 +245,7 @@ static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; } -static inline s32 dev_pm_qos_raw_read_value(struct device *dev) +static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } -- cgit v1.2.3 From 2a79ea5ec53973c8711b54d33ace5c77659dc8f8 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 4 Jul 2019 13:06:19 +0530 Subject: PM / QOS: Pass request type to dev_pm_qos_read_value() In order to allow dev_pm_qos_read_value() to read values for different QoS requests, pass request type as a parameter to these routines. For now, it only supports resume-latency request type but will be extended to frequency limit (min/max) constraints later on. Reviewed-by: Matthias Kaehlcke Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 5e09d4980786..9a21b7ba72ae 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -140,7 +140,7 @@ s32 pm_qos_read_value(struct pm_qos_constraints *c); enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask); enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask); s32 __dev_pm_qos_resume_latency(struct device *dev); -s32 dev_pm_qos_read_value(struct device *dev); +s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type); int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value); int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value); @@ -191,8 +191,18 @@ static inline enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, { return PM_QOS_FLAGS_UNDEFINED; } static inline s32 __dev_pm_qos_resume_latency(struct device *dev) { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } -static inline s32 dev_pm_qos_read_value(struct device *dev) - { return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } +static inline s32 dev_pm_qos_read_value(struct device *dev, + enum dev_pm_qos_req_type type) +{ + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: + return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; + default: + WARN_ON(1); + return 0; + } +} + static inline int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, -- cgit v1.2.3 From 208637b37824c8956fe28d277835a403ee35fa84 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 4 Jul 2019 13:06:20 +0530 Subject: PM / QoS: Add support for MIN/MAX frequency constraints This patch introduces the min-frequency and max-frequency device constraints, which will be used by the cpufreq core to begin with. Reviewed-by: Matthias Kaehlcke Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 9a21b7ba72ae..2aebbc5b9950 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -40,6 +40,8 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 +#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 +#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE (-1) #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -58,6 +60,8 @@ struct pm_qos_flags_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_MIN_FREQUENCY, + DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -99,10 +103,14 @@ struct pm_qos_flags { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; + struct pm_qos_constraints min_frequency; + struct pm_qos_constraints max_frequency; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; struct dev_pm_qos_request *flags_req; + struct dev_pm_qos_request *min_frequency_req; + struct dev_pm_qos_request *max_frequency_req; }; /* Action requested to pm_qos_update_target */ @@ -197,6 +205,10 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; + case DEV_PM_QOS_MIN_FREQUENCY: + return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; + case DEV_PM_QOS_MAX_FREQUENCY: + return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; -- cgit v1.2.3 From 2ac295d4f0c095310addbcb03d91d2a4c9f7d435 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 1 Jun 2019 20:48:55 -0400 Subject: convenience helper get_tree_nodev() counterpart of mount_nodev(). Switch hugetlb and pseudo to it. Signed-off-by: Al Viro --- include/linux/fs_context.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c995b852ba40..38b1ec918a4e 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -151,6 +151,9 @@ extern int vfs_get_super(struct fs_context *fc, enum vfs_get_super_keying keying, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); +extern int get_tree_nodev(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc)); extern const struct file_operations fscontext_fops; -- cgit v1.2.3 From c23a0bbab30cc1714b6b1d6a1c153a5ccab3f0d8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 22 May 2019 21:23:39 -0400 Subject: convenience helper: get_tree_single() counterpart of mount_single(); switch fusectl to it Signed-off-by: Al Viro --- include/linux/fs_context.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 38b1ec918a4e..1775969e000d 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -154,6 +154,9 @@ extern int vfs_get_super(struct fs_context *fc, extern int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); +extern int get_tree_single(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc)); extern const struct file_operations fscontext_fops; -- cgit v1.2.3 From 14a253ce4210cd2ef133b392062477e9d656db4a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 30 May 2019 15:59:57 -0400 Subject: init_rootfs(): don't bother with init_ramfs_fs() the only thing done by the latter is making ramfs visible to mount(2); we don't need it there - rootfs is separate and, in fact, made visible to mount(2) in the same init_rootfs(). Signed-off-by: Al Viro --- include/linux/ramfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 5ef7d54caac2..ee582bdb7fda 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -19,7 +19,6 @@ extern int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize); extern const struct file_operations ramfs_file_operations; extern const struct vm_operations_struct generic_file_vm_ops; -extern int __init init_ramfs_fs(void); int ramfs_fill_super(struct super_block *sb, void *data, int silent); -- cgit v1.2.3 From fd3e007f6c6a0f677e4ee8aca4b9bab8ad6cab9a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 30 May 2019 17:48:35 -0400 Subject: don't bother with registering rootfs init_mount_tree() can get to rootfs_fs_type directly and that simplifies a lot of things. We don't need to register it, we don't need to look it up *and* we don't need to bother with preventing subsequent userland mounts. That's the way we should've done that from the very beginning. There is a user-visible change, namely the disappearance of "rootfs" from /proc/filesystems. Note that it's been unmountable all along and it didn't show up in /proc/mounts; however, it *is* a user-visible change and theoretically some script might've been using its presence in /proc/filesystems to tell 2.4.11+ from earlier kernels. *IF* any complaints about behaviour change do show up, we could fake it in /proc/filesystems. I very much doubt we'll have to, though. Signed-off-by: Al Viro --- include/linux/init.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 5255069f5a9f..cbe93521397e 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -137,6 +137,8 @@ extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; /* Used for contructor calls. */ typedef void (*ctor_fn_t)(void); +struct file_system_type; + /* Defined in init/main.c */ extern int do_one_initcall(initcall_t fn); extern char __initdata boot_command_line[]; @@ -147,6 +149,7 @@ extern unsigned int reset_devices; void setup_arch(char **); void prepare_namespace(void); int __init init_rootfs(void); +extern struct file_system_type rootfs_fs_type; #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) extern bool rodata_enabled; -- cgit v1.2.3 From 33488845f211afcdb7e5c00a3152890e06cdc78e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2019 20:09:15 -0400 Subject: constify ksys_mount() string arguments Signed-off-by: Al Viro --- include/linux/syscalls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e2870fe1be5b..2a0ac10a6f95 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1228,8 +1228,8 @@ asmlinkage long sys_ni_syscall(void); * the ksys_xyzyyz() functions prototyped below. */ -int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, - unsigned long flags, void __user *data); +int ksys_mount(const char __user *dev_name, const char __user *dir_name, + const char __user *type, unsigned long flags, void __user *data); int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); -- cgit v1.2.3 From 037f11b4752f717201143a1dc5d6acf3cb71ddfa Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 1 Jun 2019 18:09:44 -0400 Subject: mnt_init(): call shmem_init() unconditionally No point having two call sites (earlier in init_rootfs() from mnt_init() in case we are going to use shmem-style rootfs, later from do_basic_setup() unconditionally), along with the logics in shmem_init() itself to make the second call a no-op... Signed-off-by: Al Viro --- include/linux/init.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index cbe93521397e..212fc9e2f691 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -148,7 +148,7 @@ extern unsigned int reset_devices; /* used by init/main.c */ void setup_arch(char **); void prepare_namespace(void); -int __init init_rootfs(void); +void __init init_rootfs(void); extern struct file_system_type rootfs_fs_type; #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) -- cgit v1.2.3 From d14133dd41614aaaac1fa0505c7dab01f4211d2c Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Tue, 2 Jul 2019 13:02:36 +0300 Subject: IB/mlx5: Support set qp counter Support bind a qp with counter. If counter is null then bind the qp to the default counter. Different QP state has different operation: - RESET: Set the counter field so that it will take effective during RST2INIT change; - RTS: Issue an RTS2RTS change to update the QP counter; - Other: Set the counter field and mark the counter_pending flag, when QP is moved to RTS state and this flag is set, then issue an RTS2RTS modification to update the counter. Signed-off-by: Mark Zhang Reviewed-by: Majd Dibbiny Acked-by: Saeed Mahameed Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/qp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 937041101504..ae63b1ae9004 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -71,6 +71,7 @@ enum mlx5_qp_optpar { MLX5_QP_OPTPAR_CQN_RCV = 1 << 19, MLX5_QP_OPTPAR_DC_HS = 1 << 20, MLX5_QP_OPTPAR_DC_KEY = 1 << 21, + MLX5_QP_OPTPAR_COUNTER_SET_ID = 1 << 25, }; enum mlx5_qp_state { -- cgit v1.2.3 From c5d4355d10d414a96ca870b731756b89d068d57a Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Fri, 5 Jul 2019 19:33:22 +0530 Subject: libnvdimm: nd_region flush callback support This patch adds functionality to perform flush from guest to host over VIRTIO. We are registering a callback based on 'nd_region' type. virtio_pmem driver requires this special flush function. For rest of the region types we are registering existing flush function. Report error returned by host fsync failure to userspace. Signed-off-by: Pankaj Gupta Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 03d5c3aece9d..e13100f424c8 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -11,6 +11,7 @@ #include #include #include +#include struct badrange_entry { u64 start; @@ -57,6 +58,9 @@ enum { */ ND_REGION_PERSIST_MEMCTRL = 2, + /* Platform provides asynchronous flush mechanism */ + ND_REGION_ASYNC = 3, + /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, }; @@ -113,6 +117,7 @@ struct nd_mapping_desc { int position; }; +struct nd_region; struct nd_region_desc { struct resource *res; struct nd_mapping_desc *mapping; @@ -125,6 +130,7 @@ struct nd_region_desc { int target_node; unsigned long flags; struct device_node *of_node; + int (*flush)(struct nd_region *nd_region, struct bio *bio); }; struct device; @@ -252,7 +258,8 @@ unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); -void nvdimm_flush(struct nd_region *nd_region); +int nvdimm_flush(struct nd_region *nd_region, struct bio *bio); +int generic_nvdimm_flush(struct nd_region *nd_region); int nvdimm_has_flush(struct nd_region *nd_region); int nvdimm_has_cache(struct nd_region *nd_region); int nvdimm_in_overwrite(struct nvdimm *nvdimm); -- cgit v1.2.3 From fefc1d97fa4b5e016bbe15447dc3edcd9e1bcb9f Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Fri, 5 Jul 2019 19:33:24 +0530 Subject: libnvdimm: add dax_dev sync flag This patch adds 'DAXDEV_SYNC' flag which is set for nd_region doing synchronous flush. This later is used to disable MAP_SYNC functionality for ext4 & xfs filesystem for devices don't support synchronous flush. Signed-off-by: Pankaj Gupta Signed-off-by: Dan Williams --- include/linux/dax.h | 24 ++++++++++++++++++++++-- include/linux/libnvdimm.h | 1 + 2 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index becaea5f4488..8b535bc4526f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,6 +7,9 @@ #include #include +/* Flag for synchronous flush */ +#define DAXDEV_F_SYNC (1UL << 0) + typedef unsigned long dax_entry_t; struct iomap_ops; @@ -38,18 +41,28 @@ extern struct attribute_group dax_attribute_group; #if IS_ENABLED(CONFIG_DAX) struct dax_device *dax_get_by_host(const char *host); struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops); + const struct dax_operations *ops, unsigned long flags); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); +bool __dax_synchronous(struct dax_device *dax_dev); +static inline bool dax_synchronous(struct dax_device *dax_dev) +{ + return __dax_synchronous(dax_dev); +} +void __set_dax_synchronous(struct dax_device *dax_dev); +static inline void set_dax_synchronous(struct dax_device *dax_dev) +{ + __set_dax_synchronous(dax_dev); +} #else static inline struct dax_device *dax_get_by_host(const char *host) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops) + const struct dax_operations *ops, unsigned long flags) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this @@ -70,6 +83,13 @@ static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } +static inline bool dax_synchronous(struct dax_device *dax_dev) +{ + return true; +} +static inline void set_dax_synchronous(struct dax_device *dax_dev) +{ +} #endif struct writeback_control; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index e13100f424c8..7a64b3ddb408 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -263,6 +263,7 @@ int generic_nvdimm_flush(struct nd_region *nd_region); int nvdimm_has_flush(struct nd_region *nd_region); int nvdimm_has_cache(struct nd_region *nd_region); int nvdimm_in_overwrite(struct nvdimm *nvdimm); +bool is_nvdimm_sync(struct nd_region *nd_region); static inline int nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) -- cgit v1.2.3 From 32de1484648a837db5dea0a7007fe7136804e392 Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Fri, 5 Jul 2019 19:33:26 +0530 Subject: dax: check synchronous mapping is supported This patch introduces 'daxdev_mapping_supported' helper which checks if 'MAP_SYNC' is supported with filesystem mapping. It also checks if corresponding dax_device is synchronous. Virtio pmem device is asynchronous and does not not support VM_SYNC. Suggested-by: Jan Kara Signed-off-by: Pankaj Gupta Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 8b535bc4526f..9bd8528bd305 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -56,6 +56,18 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } +/* + * Check if given mapping is supported by the file / underlying device. + */ +static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, + struct dax_device *dax_dev) +{ + if (!(vma->vm_flags & VM_SYNC)) + return true; + if (!IS_DAX(file_inode(vma->vm_file))) + return false; + return dax_synchronous(dax_dev); +} #else static inline struct dax_device *dax_get_by_host(const char *host) { @@ -90,6 +102,11 @@ static inline bool dax_synchronous(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } +static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, + struct dax_device *dax_dev) +{ + return !(vma->vm_flags & VM_SYNC); +} #endif struct writeback_control; -- cgit v1.2.3 From 7e0a0e38fcfea47e74b0ff6da6266f00bcd2af43 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 1 May 2019 10:49:27 -0400 Subject: SUNRPC: Replace the queue timer with a delayed work function The queue timer function, which walks the RPC queue in order to locate candidates for waking up is one of the current constraints against removing the bh-safe queue spin locks. Replace it with a delayed work queue, so that we can do the actual rpc task wake ups from an ordinary process context. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index d0e451868f02..7d8db5dcac04 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -183,8 +183,9 @@ struct rpc_task_setup { #define RPC_NR_PRIORITY (1 + RPC_PRIORITY_PRIVILEGED - RPC_PRIORITY_LOW) struct rpc_timer { - struct timer_list timer; struct list_head list; + unsigned long expires; + struct delayed_work dwork; }; /* -- cgit v1.2.3 From 4f8943f8088348ec01456b075d44ad19dce3d698 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 1 May 2019 16:28:29 -0400 Subject: SUNRPC: Replace direct task wakeups from softirq context Replace the direct task wakeups from inside a softirq context with wakeups from a process context. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index b81d0b3e0799..7638dbe7bc50 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -56,6 +56,7 @@ struct sock_xprt { */ unsigned long sock_state; struct delayed_work connect_worker; + struct work_struct error_worker; struct work_struct recv_worker; struct mutex recv_mutex; struct sockaddr_storage srcaddr; @@ -84,6 +85,10 @@ struct sock_xprt { #define XPRT_SOCK_CONNECTING 1U #define XPRT_SOCK_DATA_READY (2) #define XPRT_SOCK_UPD_TIMEOUT (3) +#define XPRT_SOCK_WAKE_ERROR (4) +#define XPRT_SOCK_WAKE_WRITE (5) +#define XPRT_SOCK_WAKE_PENDING (6) +#define XPRT_SOCK_WAKE_DISCONNECT (7) #endif /* __KERNEL__ */ -- cgit v1.2.3 From 21f0ffaff510b0530bfdf77da7133c0b99dee2fe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 28 Apr 2017 10:52:42 -0400 Subject: SUNRPC: Add basic load balancing to the transport switch For now, just count the queue length. It is less accurate than counting number of bytes queued, but easier to implement. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + include/linux/sunrpc/xprtmultipath.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a6d9fce7f20e..15322c1d9c8c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -238,6 +238,7 @@ struct rpc_xprt { /* * Send stuff */ + atomic_long_t queuelen; spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ spinlock_t queue_lock; /* send/receive queue lock */ diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index af1257c030d2..c6cce3fbf29d 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -15,6 +15,8 @@ struct rpc_xprt_switch { struct kref xps_kref; unsigned int xps_nxprts; + unsigned int xps_nactive; + atomic_long_t xps_queuelen; struct list_head xps_xprt_list; struct net * xps_net; -- cgit v1.2.3 From 1c341b777501613aad83f9c233a3fe5701cff083 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 May 2019 08:38:57 -0400 Subject: NFS: Add deferred cache invalidation for close-to-open consistency violations If the client detects that close-to-open cache consistency has been violated, and that the file or directory has been changed on the server, then do a cache invalidation when we're done working with the file. The reason we don't do an immediate cache invalidation is that we want to avoid performance problems due to false positives. Also, note that we cannot guarantee cache consistency in this situation even if we do invalidate the cache. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d363d5765cdf..0a11712a80e3 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -223,6 +223,8 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_MTIME BIT(10) /* cached mtime is invalid */ #define NFS_INO_INVALID_SIZE BIT(11) /* cached size is invalid */ #define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ +#define NFS_INO_DATA_INVAL_DEFER \ + BIT(13) /* Deferred cache invalidation */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ -- cgit v1.2.3 From 612b41f808a98a124b23d72229693c3181733291 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Apr 2017 08:50:51 -0400 Subject: SUNRPC: Allow creation of RPC clients with multiple connections Add an argument to struct rpc_create_args that allows the specification of how many transport connections you want to set up to the server. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6e8073140a5d..4619098affa3 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -124,6 +124,7 @@ struct rpc_create_args { u32 prognumber; /* overrides program->number */ u32 version; rpc_authflavor_t authflavor; + u32 nconnect; unsigned long flags; char *client_name; struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ -- cgit v1.2.3 From 6619079d05404cb32be29af329b87ac3b0ad4f96 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 27 Apr 2017 11:13:40 -0400 Subject: NFSv4: Allow multiple connections to NFSv4.x (x>0) servers If the user specifies the -onconn= mount option, and the transport protocol is TCP, then set up connections to the server. The connections will all go to the same IP address. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1e78032a174b..a87fe854f008 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -58,6 +58,7 @@ struct nfs_client { struct nfs_subversion * cl_nfs_mod; /* pointer to nfs version module */ u32 cl_minorversion;/* NFSv4 minorversion */ + unsigned int cl_nconnect; /* Number of connections */ const char * cl_principal; /* used for machine cred */ #if IS_ENABLED(CONFIG_NFS_V4) -- cgit v1.2.3 From 5a0c257f8e0f4c4b3c33dff545317c21a921303e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 30 May 2019 10:41:28 +1000 Subject: NFS: send state management on a single connection. With NFSv4.1, different network connections need to be explicitly bound to a session. During session startup, this is not possible so only a single connection must be used for session startup. So add a task flag to disable the default round-robin choice of connections (when nconnect > 1) and force the use of a single connection. Then use that flag on all requests for session management - for consistence, include NFSv4.0 management (SETCLIENTID) and session destruction Reported-by: Chuck Lever Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index d0e451868f02..11424bdf09e6 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -126,6 +126,7 @@ struct rpc_task_setup { #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ +#define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ #define RPC_TASK_SOFTCONN 0x0400 /* Fail if can't connect */ #define RPC_TASK_SENT 0x0800 /* message was sent */ -- cgit v1.2.3 From a332518fda4731c07394164b3edcbb6efaf4c4d7 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 23 May 2019 16:13:50 -0400 Subject: SUNRPC: Count ops completing with tk_status < 0 We often see various error conditions with NFS4.x that show up with a very high operation count all completing with tk_status < 0 in a short period of time. Add a count to rpc_iostats to record on a per-op basis the ops that complete in this manner, which will enable lower overhead diagnostics. Signed-off-by: Dave Wysochanski Signed-off-by: Trond Myklebust --- include/linux/sunrpc/metrics.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 1b3751327575..0ee3f7052846 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -30,7 +30,7 @@ #include #include -#define RPC_IOSTATS_VERS "1.0" +#define RPC_IOSTATS_VERS "1.1" struct rpc_iostats { spinlock_t om_lock; @@ -66,6 +66,11 @@ struct rpc_iostats { ktime_t om_queue, /* queued for xmit */ om_rtt, /* RPC RTT */ om_execute; /* RPC execution */ + /* + * The count of operations that complete with tk_status < 0. + * These statuses usually indicate error conditions. + */ + unsigned long om_error_status; } ____cacheline_aligned; struct rpc_task; -- cgit v1.2.3 From 1dd7382b1bb608e7ccae3672621eaceca355ae8b Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Mon, 1 Jul 2019 21:14:01 +0300 Subject: net/mlx5: Introduce VHCA tunnel device capability When using the device emulation feature (introduced in Bluefield-1 SOC), a privileged function (the device emulation manager) will be able to create a channel to execute commands on behalf of the emulated function. This channel will be a general object of type VHCA_TUNNEL that will have a unique ID for each emulated function. This ID will be passed in each cmd that will be issued by the emulation SW in a well known offset in the command header. This channel is needed since the emulated function doesn't have a normal command interface to the HCA HW, but some basic configuration for that function is needed (e.g. initialize and enable the HCA). For that matter, a specific command-set was defined and only those commands will be issued by the HCA. Signed-off-by: Max Gurtovoy Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 06881b79167e..ba60bd17a92a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1390,7 +1390,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_6c8[0x28]; u8 sf_base_id[0x10]; - u8 reserved_at_700[0x100]; + u8 reserved_at_700[0x80]; + u8 vhca_tunnel_commands[0x40]; + u8 reserved_at_7c0[0x40]; }; enum mlx5_flow_destination_type { @@ -9694,7 +9696,7 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 opcode[0x10]; u8 uid[0x10]; - u8 reserved_at_20[0x10]; + u8 vhca_tunnel_id[0x10]; u8 obj_type[0x10]; u8 obj_id[0x20]; -- cgit v1.2.3 From 97a385e558292ba0851906783642239865670a5f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 May 2019 16:40:32 -0400 Subject: libceph: remove ceph_get_direct_page_vector() This function is entirely unused. Signed-off-by: Christoph Hellwig Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 337d5049ff93..a3cddf5f0e60 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -299,10 +299,6 @@ int ceph_wait_for_latest_osdmap(struct ceph_client *client, /* pagevec.c */ extern void ceph_release_page_vector(struct page **pages, int num_pages); - -extern struct page **ceph_get_direct_page_vector(const void __user *data, - int num_pages, - bool write_page); extern void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); -- cgit v1.2.3 From 6c37f0e64173571914a443f74d36e5a22dabfc05 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 3 Jun 2019 14:45:16 -0400 Subject: libceph: add ceph_decode_entity_addr Add a function for decoding an entity_addr_t. Once CEPH_FEATURE_MSG_ADDR2 is enabled, the server daemons will start encoding entity_addr_t differently. Add a new helper function that can handle either format. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index a6c2a48d42e0..1c0a665bfc03 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -230,6 +230,8 @@ static inline void ceph_decode_addr(struct ceph_entity_addr *a) WARN_ON(a->in_addr.ss_family == 512); } +extern int ceph_decode_entity_addr(void **p, void *end, + struct ceph_entity_addr *addr); /* * encoders */ -- cgit v1.2.3 From 0bfb0f288992adbf8d1f0d5f22f0fd398b146316 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 31 May 2019 15:32:28 -0400 Subject: libceph: ADDR2 support for monmap Switch the MonMap decoder to use the new decoding routine for entity_addr_t's. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/mon_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index 3a4688af7455..b4d134d3312a 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -104,7 +104,6 @@ struct ceph_mon_client { #endif }; -extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end); extern int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr); -- cgit v1.2.3 From d3c3c0a841d5dafc5395be363996d619255a732f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 17 Jun 2019 06:57:25 -0400 Subject: libceph: use TYPE_LEGACY for entity addrs instead of TYPE_NONE Going forward, we'll have different address types so let's use the addr2 TYPE_LEGACY for internal tracking rather than TYPE_NONE. Also, make ceph_pr_addr print the address type value as well. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 1c0a665bfc03..ce488d95be89 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -218,16 +218,23 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv, /* * sockaddr_storage <-> ceph_sockaddr */ +#define CEPH_ENTITY_ADDR_TYPE_NONE 0 +#define CEPH_ENTITY_ADDR_TYPE_LEGACY __cpu_to_le32(1) + static inline void ceph_encode_addr(struct ceph_entity_addr *a) { __be16 ss_family = htons(a->in_addr.ss_family); a->in_addr.ss_family = *(__u16 *)&ss_family; + + /* Banner addresses require TYPE_NONE */ + a->type = CEPH_ENTITY_ADDR_TYPE_NONE; } static inline void ceph_decode_addr(struct ceph_entity_addr *a) { __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; a->in_addr.ss_family = ntohs(ss_family); WARN_ON(a->in_addr.ss_family == 512); + a->type = CEPH_ENTITY_ADDR_TYPE_LEGACY; } extern int ceph_decode_entity_addr(void **p, void *end, -- cgit v1.2.3 From 2c66de560fa2dda0a600e908897116914db8f500 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 17 Jun 2019 09:24:31 -0400 Subject: libceph: rename ceph_encode_addr to ceph_encode_banner_addr ...ditto for the decode function. We only use these functions to fix up banner addresses now, so let's name them more appropriately. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index ce488d95be89..450384fe487c 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -221,7 +221,7 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv, #define CEPH_ENTITY_ADDR_TYPE_NONE 0 #define CEPH_ENTITY_ADDR_TYPE_LEGACY __cpu_to_le32(1) -static inline void ceph_encode_addr(struct ceph_entity_addr *a) +static inline void ceph_encode_banner_addr(struct ceph_entity_addr *a) { __be16 ss_family = htons(a->in_addr.ss_family); a->in_addr.ss_family = *(__u16 *)&ss_family; @@ -229,7 +229,7 @@ static inline void ceph_encode_addr(struct ceph_entity_addr *a) /* Banner addresses require TYPE_NONE */ a->type = CEPH_ENTITY_ADDR_TYPE_NONE; } -static inline void ceph_decode_addr(struct ceph_entity_addr *a) +static inline void ceph_decode_banner_addr(struct ceph_entity_addr *a) { __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; a->in_addr.ss_family = ntohs(ss_family); -- cgit v1.2.3 From 6adaaafdd81d5c01875fe233ab73deb81b34caa1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 31 May 2019 12:24:22 -0400 Subject: libceph: turn on CEPH_FEATURE_MSG_ADDR2 Now that the client can handle either address formatting, advertise to the peer that we can support it. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_features.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 65a38c4a02a1..39e6f4c57580 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -211,6 +211,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ + CEPH_FEATURE_MSG_ADDR2 | \ CEPH_FEATURE_CEPHX_V2) #define CEPH_FEATURES_REQUIRED_DEFAULT 0 -- cgit v1.2.3 From 441d367644e2f60b37f36bfc656deee551acba5b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 5 Jun 2019 17:24:22 -0400 Subject: iversion: add a routine to update a raw value with a larger one Under ceph, clients can be independently updating iversion themselves, while working under comprehensive sets of caps on an inode. In that situation we always want to prefer the largest value of a change attribute. Add a new function that will update a raw value with a larger one, but otherwise leave it alone. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/iversion.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iversion.h b/include/linux/iversion.h index be50ef7cedab..2917ef990d43 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -112,6 +112,30 @@ inode_peek_iversion_raw(const struct inode *inode) return atomic64_read(&inode->i_version); } +/** + * inode_set_max_iversion_raw - update i_version new value is larger + * @inode: inode to set + * @val: new i_version to set + * + * Some self-managed filesystems (e.g Ceph) will only update the i_version + * value if the new value is larger than the one we already have. + */ +static inline void +inode_set_max_iversion_raw(struct inode *inode, u64 val) +{ + u64 cur, old; + + cur = inode_peek_iversion_raw(inode); + for (;;) { + if (cur > val) + break; + old = atomic64_cmpxchg(&inode->i_version, cur, val); + if (likely(old == cur)) + break; + cur = old; + } +} + /** * inode_set_iversion - set i_version to a particular value * @inode: inode to set -- cgit v1.2.3 From 49ada6e8dc9f64ad1e8dd6f7b453c9e584e9f897 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 20 Jun 2019 12:09:08 +0800 Subject: ceph: more precise CEPH_CLIENT_CAPS_PENDING_CAPSNAP Client uses this flag to tell mds if there is more cap snap need to flush. It's mainly for the case that client needs to re-send cap/snap flushes after mds failover, but CEPH_CAP_ANY_FILE_WR on corresponding inodes are all released before mds failover. Signed-off-by: "Yan, Zheng" Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 3ac0feaf2b5e..cb21c5cf12c3 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -682,7 +682,7 @@ extern const char *ceph_cap_op_name(int op); /* flags field in client cap messages (version >= 10) */ #define CEPH_CLIENT_CAPS_SYNC (1<<0) #define CEPH_CLIENT_CAPS_NO_CAPSNAP (1<<1) -#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2); +#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2) /* * caps message, used for capability callbacks, acks, requests, etc. -- cgit v1.2.3 From 94e85771881027e62afdddadd31e3eec73025990 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 8 Jul 2019 12:50:09 +0200 Subject: libceph: rename r_unsafe_item to r_private_item This list item remained from when we had safe and unsafe replies (commit vs ack). It has since become a private list item for use by clients. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2294f963dab7..024f6fed0ac5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -198,9 +198,9 @@ struct ceph_osd_request { bool r_mempool; struct completion r_completion; /* private to osd_client.c */ ceph_osdc_callback_t r_callback; - struct list_head r_unsafe_item; struct inode *r_inode; /* for use by callbacks */ + struct list_head r_private_item; /* ditto */ void *r_priv; /* ditto */ /* set by submitter */ -- cgit v1.2.3 From ef83171b49c66d851a1a0dc6da5b4a4d8ee6ce9a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 8 Apr 2019 14:16:05 +0200 Subject: libceph: bump CEPH_MSG_MAX_DATA_LEN (again) This time for rbd object map. Object maps are limited in size to 256000000 objects, two bits per object. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang --- include/linux/ceph/libceph.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index a3cddf5f0e60..82156da3c650 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -84,11 +84,13 @@ struct ceph_options { #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) /* - * Handle the largest possible rbd object in one message. + * The largest possible rbd data object is 32M. + * The largest possible rbd object map object is 64M. + * * There is no limit on the size of cephfs objects, but it has to obey * rsize and wsize mount options anyway. */ -#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) +#define CEPH_MSG_MAX_DATA_LEN (64*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit v1.2.3 From 68ada915eea10f36760ffe414810390a104df093 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 14 Jun 2019 18:16:51 +0200 Subject: libceph: change ceph_osdc_call() to take page vector for response This will be used for loading object map. rbd_obj_read_sync() isn't suitable because object map must be accessed through class methods. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 024f6fed0ac5..c567cfa4f107 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -497,7 +497,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc, const char *class, const char *method, unsigned int flags, struct page *req_page, size_t req_len, - struct page *resp_page, size_t *resp_len); + struct page **resp_pages, size_t *resp_len); extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, struct ceph_vino vino, -- cgit v1.2.3 From 4cf3e6dff7ea517544e1da7810a0b3ebba380d2c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 14 Jun 2019 18:00:19 +0200 Subject: libceph: export osd_req_op_data() macro We already have one exported wrapper around it for extent.osd_data and rbd_object_map_update_finish() needs another one for cls.request_data. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index c567cfa4f107..ad7fe5d10dcd 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -389,6 +389,14 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err); +#define osd_req_op_data(oreq, whch, typ, fld) \ +({ \ + struct ceph_osd_request *__oreq = (oreq); \ + unsigned int __whch = (whch); \ + BUG_ON(__whch >= __oreq->r_num_ops); \ + &__oreq->r_ops[__whch].typ.fld; \ +}) + extern void osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); -- cgit v1.2.3 From 22e8bd51bb0469d1a524130a057f894ff632376a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 5 Jun 2019 19:25:11 +0200 Subject: rbd: support for object-map and fast-diff Speed up reads, discards and zeroouts through RBD_OBJ_FLAG_MAY_EXIST and RBD_OBJ_FLAG_NOOP_FOR_NONEXISTENT based on object map. Invalid object maps are not trusted, but still updated. Note that we never iterate, resize or invalidate object maps. If object-map feature is enabled but object map fails to load, we just fail the requester (either "rbd map" or I/O, by way of post-acquire action). Signed-off-by: Ilya Dryomov --- include/linux/ceph/cls_lock_client.h | 3 +++ include/linux/ceph/striper.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/cls_lock_client.h b/include/linux/ceph/cls_lock_client.h index bea6c77d2093..17bc7584d1fe 100644 --- a/include/linux/ceph/cls_lock_client.h +++ b/include/linux/ceph/cls_lock_client.h @@ -52,4 +52,7 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc, char *lock_name, u8 *type, char **tag, struct ceph_locker **lockers, u32 *num_lockers); +int ceph_cls_assert_locked(struct ceph_osd_request *req, int which, + char *lock_name, u8 type, char *cookie, char *tag); + #endif diff --git a/include/linux/ceph/striper.h b/include/linux/ceph/striper.h index cbd0d24b7148..3486636c0e6e 100644 --- a/include/linux/ceph/striper.h +++ b/include/linux/ceph/striper.h @@ -66,4 +66,6 @@ int ceph_extent_to_file(struct ceph_file_layout *l, struct ceph_file_extent **file_extents, u32 *num_file_extents); +u64 ceph_get_num_objects(struct ceph_file_layout *l, u64 size); + #endif -- cgit v1.2.3 From f4915455dcf07c4f237d6160a4b6adb0575d2909 Mon Sep 17 00:00:00 2001 From: Yamin Friedman Date: Mon, 8 Jul 2019 13:59:02 +0300 Subject: linux/dim: Implement RDMA adaptive moderation (DIM) RDMA DIM implements a different algorithm from net DIM and is based on completions which is how we can implement interrupt moderation in RDMA. The algorithm optimizes for number of completions and ratio between completions and events. In order to avoid long latencies, the implementation performs fast reduction of moderation level when the traffic changes. Signed-off-by: Yamin Friedman Reviewed-by: Max Gurtovoy Reviewed-by: Sagi Grimberg Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/dim.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dim.h b/include/linux/dim.h index aa9bdd47a648..aa69730c3b8d 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -82,6 +82,7 @@ struct dim_stats { * @prev_stats: Measured rates from previous iteration (for comparison) * @start_sample: Sampled data at start of current iteration * @work: Work to perform on action required + * @priv: A pointer to the struct that points to dim * @profile_ix: Current moderation profile * @mode: CQ period count mode * @tune_state: Algorithm tuning state (see below) @@ -95,6 +96,7 @@ struct dim { struct dim_sample start_sample; struct dim_sample measuring_sample; struct work_struct work; + void *priv; u8 profile_ix; u8 mode; u8 tune_state; @@ -363,4 +365,38 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); */ void net_dim(struct dim *dim, struct dim_sample end_sample); +/* RDMA DIM */ + +/* + * RDMA DIM profile: + * profile size must be of RDMA_DIM_PARAMS_NUM_PROFILES. + */ +#define RDMA_DIM_PARAMS_NUM_PROFILES 9 +#define RDMA_DIM_START_PROFILE 0 + +static const struct dim_cq_moder +rdma_dim_prof[RDMA_DIM_PARAMS_NUM_PROFILES] = { + {1, 0, 1, 0}, + {1, 0, 4, 0}, + {2, 0, 4, 0}, + {2, 0, 8, 0}, + {4, 0, 8, 0}, + {16, 0, 8, 0}, + {16, 0, 16, 0}, + {32, 0, 16, 0}, + {32, 0, 32, 0}, +}; + +/** + * rdma_dim - Runs the adaptive moderation. + * @dim: The moderation struct. + * @completions: The number of completions collected in this round. + * + * Each call to rdma_dim takes the latest amount of completions that + * have been collected and counts them as a new event. + * Once enough events have been collected the algorithm decides a new + * moderation level. + */ +void rdma_dim(struct dim *dim, u64 completions); + #endif /* DIM_H */ -- cgit v1.2.3 From 67d874c3b2c69d65274fa5ce44ba939788d5729d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 8 Jul 2019 16:27:52 +0530 Subject: cpufreq: Register notifiers with the PM QoS framework Register notifiers for min/max frequency constraints with the PM QoS framework. The constraints are also taken into consideration in cpufreq_set_policy(). This also relocates cpufreq_policy_put_kobj() as it is required to be called from cpufreq_policy_alloc() now. refresh_frequency_limits() is updated to avoid calling cpufreq_set_policy() for inactive policies and handle_update() is updated to have proper locking in place. No constraints are added until now though. Reviewed-by: Matthias Kaehlcke Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar Tested-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a1467aa7f58b..95425941f46d 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -147,6 +147,9 @@ struct cpufreq_policy { /* Pointer to the cooling device if used for thermal mitigation */ struct thermal_cooling_device *cdev; + + struct notifier_block nb_min; + struct notifier_block nb_max; }; struct cpufreq_freqs { -- cgit v1.2.3 From c57b25bdf7cd374af106992356536bf5df7c255b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 4 Jul 2019 13:06:22 +0530 Subject: cpufreq: intel_pstate: Reuse refresh_frequency_limits() The implementation of intel_pstate_update_max_freq() is quite similar to refresh_frequency_limits(), lets reuse it. Finding minimum of policy->user_policy.max and policy->cpuinfo.max_freq in intel_pstate_update_max_freq() is redundant as cpufreq_set_policy() will call the ->verify() callback of intel-pstate driver, which will do this comparison anyway and so dropping it from intel_pstate_update_max_freq() doesn't harm. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 95425941f46d..1fa37b675a80 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -207,6 +207,7 @@ void cpufreq_cpu_release(struct cpufreq_policy *policy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); int cpufreq_set_policy(struct cpufreq_policy *policy, struct cpufreq_policy *new_policy); +void refresh_frequency_limits(struct cpufreq_policy *policy); void cpufreq_update_policy(unsigned int cpu); void cpufreq_update_limits(unsigned int cpu); bool have_governor_per_policy(void); -- cgit v1.2.3 From 18c49926c4bf4915e5194d1de3299c0537229f9f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 5 Jul 2019 16:21:24 +0530 Subject: cpufreq: Add QoS requests for userspace constraints This implements QoS requests to manage userspace configuration of min and max frequency. Reviewed-by: Matthias Kaehlcke Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar Tested-by: syzbot Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1fa37b675a80..afc683021ac5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -50,11 +50,6 @@ struct cpufreq_cpuinfo { unsigned int transition_latency; }; -struct cpufreq_user_policy { - unsigned int min; /* in kHz */ - unsigned int max; /* in kHz */ -}; - struct cpufreq_policy { /* CPUs sharing clock, require sw coordination */ cpumask_var_t cpus; /* Online CPUs only */ @@ -84,7 +79,8 @@ struct cpufreq_policy { struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ - struct cpufreq_user_policy user_policy; + struct dev_pm_qos_request *min_freq_req; + struct dev_pm_qos_request *max_freq_req; struct cpufreq_frequency_table *freq_table; enum cpufreq_table_sorting freq_table_sorted; -- cgit v1.2.3 From 87b512def792579641499d9bef1d640994ea9c18 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 27 Jun 2019 20:50:46 -0500 Subject: objtool: Add support for C jump tables Objtool doesn't know how to read C jump tables, so it has to whitelist functions which use them, causing missing ORC unwinder data for such functions, e.g. ___bpf_prog_run(). C jump tables are very similar to GCC switch jump tables, which objtool already knows how to read. So adding support for C jump tables is easy. It just needs to be able to find the tables and distinguish them from other data. To allow the jump tables to be found, create an __annotate_jump_table macro which can be used to annotate them. The annotation is done by placing the jump table in an .rodata..c_jump_table section. The '.rodata' prefix ensures that the data will be placed in the rodata section by the vmlinux linker script. The double periods are part of an existing convention which distinguishes kernel sections from GCC sections. Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Song Liu Cc: Kairui Song Cc: Steven Rostedt Cc: Borislav Petkov Cc: Alexei Starovoitov Cc: Daniel Borkmann Link: https://lkml.kernel.org/r/0ba2ca30442b16b97165992381ce643dc27b3d1a.1561685471.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 8aaf7cd026b0..f0fd5636fddb 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -116,9 +116,14 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ".pushsection .discard.unreachable\n\t" \ ".long 999b - .\n\t" \ ".popsection\n\t" + +/* Annotate a C jump table to allow objtool to follow the code flow */ +#define __annotate_jump_table __section(".rodata..c_jump_table") + #else #define annotate_reachable() #define annotate_unreachable() +#define __annotate_jump_table #endif #ifndef ASM_UNREACHABLE -- cgit v1.2.3 From f6b6aefee70aa5261deec7feab80c249bf58397f Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 30 May 2019 08:05:58 -0500 Subject: PCI: Fix typos and whitespace errors Fix typos in drivers/pci. Comment and whitespace changes only. Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Reviewed-by: Randy Dunlap --- include/linux/pci.h | 2 +- include/linux/pci_ids.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4a5a84d7bdd4..fb207a22d686 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -382,7 +382,7 @@ struct pci_dev { unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ - unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ + unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ unsigned int block_cfg_access:1; /* Config space access blocked */ unsigned int broken_parity_status:1; /* Generates false positive parity */ unsigned int irq_reroute_variant:2; /* Needs IRQ rerouting variant */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 70e86148cb1e..0dd239f11e91 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1112,7 +1112,7 @@ #define PCI_VENDOR_ID_AL 0x10b9 #define PCI_DEVICE_ID_AL_M1533 0x1533 -#define PCI_DEVICE_ID_AL_M1535 0x1535 +#define PCI_DEVICE_ID_AL_M1535 0x1535 #define PCI_DEVICE_ID_AL_M1541 0x1541 #define PCI_DEVICE_ID_AL_M1563 0x1563 #define PCI_DEVICE_ID_AL_M1621 0x1621 @@ -1752,7 +1752,7 @@ #define PCI_VENDOR_ID_STALLION 0x124d /* Allied Telesyn */ -#define PCI_VENDOR_ID_AT 0x1259 +#define PCI_VENDOR_ID_AT 0x1259 #define PCI_SUBDEVICE_ID_AT_2700FX 0x2701 #define PCI_SUBDEVICE_ID_AT_2701FX 0x2703 @@ -2550,7 +2550,7 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF2 0x1700 #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff -#define PCI_VENDOR_ID_HUAWEI 0x19e5 +#define PCI_VENDOR_ID_HUAWEI 0x19e5 #define PCI_VENDOR_ID_NETRONOME 0x19ee #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 -- cgit v1.2.3 From 675dd90ad0932f2c03912a5252458d792bd7033a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 19 Jun 2019 10:33:42 -0400 Subject: xprtrdma: Modernize ops->connect Adapt and apply changes that were made to the TCP socket connect code. See the following commits for details on the purpose of these changes: Commit 7196dbb02ea0 ("SUNRPC: Allow changing of the TCP timeout parameters on the fly") Commit 3851f1cdb2b8 ("SUNRPC: Limit the reconnect backoff timer to the max RPC message timeout") Commit 02910177aede ("SUNRPC: Fix reconnection timeouts") Some common transport code is moved to xprt.c to satisfy the code duplication police. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a6d9fce7f20e..cc78fd38ea7d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -334,6 +334,9 @@ struct xprt_class { */ struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); +unsigned long xprt_reconnect_delay(const struct rpc_xprt *xprt); +void xprt_reconnect_backoff(struct rpc_xprt *xprt, + unsigned long init_to); void xprt_reserve(struct rpc_task *task); void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); -- cgit v1.2.3 From 0fa03c624d8fc9932d0f27c39a9deca6a37e0e17 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 19 Apr 2019 13:34:07 -0600 Subject: io_uring: add support for sendmsg() This is done through IORING_OP_SENDMSG. There's a new sqe->msg_flags for the flags argument, and the msghdr struct is passed in the sqe->addr field. We use MSG_DONTWAIT to force an inline fast path if sendmsg() doesn't block, and punt to async execution if it would have. Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/socket.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index b57cd8bf96e2..9d770ef3ced5 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -12,6 +12,7 @@ struct pid; struct cred; +struct socket; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -374,6 +375,9 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); +extern long __sys_sendmsg_sock(struct socket *sock, + struct user_msghdr __user *msg, + unsigned int flags); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, -- cgit v1.2.3 From aa1fa28fc73ea6b740ee7b62bf3b07141883dbb8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 19 Apr 2019 13:38:09 -0600 Subject: io_uring: add support for recvmsg() This is done through IORING_OP_RECVMSG. This opcode uses the same sqe->msg_flags that IORING_OP_SENDMSG added, and we pass in the msghdr struct in the sqe->addr field as well. We use MSG_DONTWAIT to force an inline fast path if recvmsg() doesn't block, and punt to async execution if it would have. Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/socket.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 9d770ef3ced5..97523818cb14 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -378,6 +378,9 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, extern long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *msg, unsigned int flags); +extern long __sys_recvmsg_sock(struct socket *sock, + struct user_msghdr __user *msg, + unsigned int flags); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, -- cgit v1.2.3 From 6605bdd59c21bb34c8f14ac4d6f2d419185f3528 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 28 Jun 2019 09:53:29 -0700 Subject: nvme: add I/O characteristics fields Several new fields have been introduced in version 1.4 of the NVMe spec at offsets that were defined as reserved in version 1.3d of the NVMe spec. Update the definition of the nvme_id_ns data structure such that it is in sync with version 1.4 of the NVMe spec. This change preserves backwards compatibility. Signed-off-by: Bart Van Assche Reviewed-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d98b2d8baf4e..01aa6a6c241d 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -315,7 +315,7 @@ struct nvme_id_ns { __u8 nmic; __u8 rescap; __u8 fpi; - __u8 rsvd33; + __u8 dlfeat; __le16 nawun; __le16 nawupf; __le16 nacwu; @@ -324,11 +324,17 @@ struct nvme_id_ns { __le16 nabspf; __le16 noiob; __u8 nvmcap[16]; - __u8 rsvd64[28]; + __le16 npwg; + __le16 npwa; + __le16 npdg; + __le16 npda; + __le16 nows; + __u8 rsvd74[18]; __le32 anagrpid; __u8 rsvd96[3]; __u8 nsattr; - __u8 rsvd100[4]; + __le16 nvmsetid; + __le16 endgid; __u8 nguid[16]; __u8 eui64[8]; struct nvme_lbaf lbaf[16]; -- cgit v1.2.3 From 13990cf8a180cc070f0b1266140e799db8754289 Mon Sep 17 00:00:00 2001 From: Amol Surati Date: Sun, 7 Jul 2019 14:27:29 +0530 Subject: ide: use BIT() macro for defining bit-flags The BIT() macro is available for defining the required bit-flags. Since it operates on an unsigned value and expands to an unsigned result, using it, instead of an expression like (1 << x), also fixes the problem of shifting a signed 32-bit value by 31 bits (e.g. 1 << 31). Signed-off-by: Amol Surati Signed-off-by: David S. Miller --- include/linux/ide.h | 272 ++++++++++++++++++++++++++-------------------------- 1 file changed, 136 insertions(+), 136 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 971cf76a78a0..46b771d6999e 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -253,9 +253,9 @@ static inline void ide_std_init_ports(struct ide_hw *hw, * Special Driver Flags */ enum { - IDE_SFLAG_SET_GEOMETRY = (1 << 0), - IDE_SFLAG_RECALIBRATE = (1 << 1), - IDE_SFLAG_SET_MULTMODE = (1 << 2), + IDE_SFLAG_SET_GEOMETRY = BIT(0), + IDE_SFLAG_RECALIBRATE = BIT(1), + IDE_SFLAG_SET_MULTMODE = BIT(2), }; /* @@ -267,13 +267,13 @@ typedef enum { } ide_startstop_t; enum { - IDE_VALID_ERROR = (1 << 1), + IDE_VALID_ERROR = BIT(1), IDE_VALID_FEATURE = IDE_VALID_ERROR, - IDE_VALID_NSECT = (1 << 2), - IDE_VALID_LBAL = (1 << 3), - IDE_VALID_LBAM = (1 << 4), - IDE_VALID_LBAH = (1 << 5), - IDE_VALID_DEVICE = (1 << 6), + IDE_VALID_NSECT = BIT(2), + IDE_VALID_LBAL = BIT(3), + IDE_VALID_LBAM = BIT(4), + IDE_VALID_LBAH = BIT(5), + IDE_VALID_DEVICE = BIT(6), IDE_VALID_LBA = IDE_VALID_LBAL | IDE_VALID_LBAM | IDE_VALID_LBAH, @@ -289,24 +289,24 @@ enum { }; enum { - IDE_TFLAG_LBA48 = (1 << 0), - IDE_TFLAG_WRITE = (1 << 1), - IDE_TFLAG_CUSTOM_HANDLER = (1 << 2), - IDE_TFLAG_DMA_PIO_FALLBACK = (1 << 3), + IDE_TFLAG_LBA48 = BIT(0), + IDE_TFLAG_WRITE = BIT(1), + IDE_TFLAG_CUSTOM_HANDLER = BIT(2), + IDE_TFLAG_DMA_PIO_FALLBACK = BIT(3), /* force 16-bit I/O operations */ - IDE_TFLAG_IO_16BIT = (1 << 4), + IDE_TFLAG_IO_16BIT = BIT(4), /* struct ide_cmd was allocated using kmalloc() */ - IDE_TFLAG_DYN = (1 << 5), - IDE_TFLAG_FS = (1 << 6), - IDE_TFLAG_MULTI_PIO = (1 << 7), - IDE_TFLAG_SET_XFER = (1 << 8), + IDE_TFLAG_DYN = BIT(5), + IDE_TFLAG_FS = BIT(6), + IDE_TFLAG_MULTI_PIO = BIT(7), + IDE_TFLAG_SET_XFER = BIT(8), }; enum { - IDE_FTFLAG_FLAGGED = (1 << 0), - IDE_FTFLAG_SET_IN_FLAGS = (1 << 1), - IDE_FTFLAG_OUT_DATA = (1 << 2), - IDE_FTFLAG_IN_DATA = (1 << 3), + IDE_FTFLAG_FLAGGED = BIT(0), + IDE_FTFLAG_SET_IN_FLAGS = BIT(1), + IDE_FTFLAG_OUT_DATA = BIT(2), + IDE_FTFLAG_IN_DATA = BIT(3), }; struct ide_taskfile { @@ -357,13 +357,13 @@ struct ide_cmd { /* ATAPI packet command flags */ enum { /* set when an error is considered normal - no retry (ide-tape) */ - PC_FLAG_ABORT = (1 << 0), - PC_FLAG_SUPPRESS_ERROR = (1 << 1), - PC_FLAG_WAIT_FOR_DSC = (1 << 2), - PC_FLAG_DMA_OK = (1 << 3), - PC_FLAG_DMA_IN_PROGRESS = (1 << 4), - PC_FLAG_DMA_ERROR = (1 << 5), - PC_FLAG_WRITING = (1 << 6), + PC_FLAG_ABORT = BIT(0), + PC_FLAG_SUPPRESS_ERROR = BIT(1), + PC_FLAG_WAIT_FOR_DSC = BIT(2), + PC_FLAG_DMA_OK = BIT(3), + PC_FLAG_DMA_IN_PROGRESS = BIT(4), + PC_FLAG_DMA_ERROR = BIT(5), + PC_FLAG_WRITING = BIT(6), }; #define ATAPI_WAIT_PC (60 * HZ) @@ -417,111 +417,111 @@ struct ide_disk_ops { /* ATAPI device flags */ enum { - IDE_AFLAG_DRQ_INTERRUPT = (1 << 0), + IDE_AFLAG_DRQ_INTERRUPT = BIT(0), /* ide-cd */ /* Drive cannot eject the disc. */ - IDE_AFLAG_NO_EJECT = (1 << 1), + IDE_AFLAG_NO_EJECT = BIT(1), /* Drive is a pre ATAPI 1.2 drive. */ - IDE_AFLAG_PRE_ATAPI12 = (1 << 2), + IDE_AFLAG_PRE_ATAPI12 = BIT(2), /* TOC addresses are in BCD. */ - IDE_AFLAG_TOCADDR_AS_BCD = (1 << 3), + IDE_AFLAG_TOCADDR_AS_BCD = BIT(3), /* TOC track numbers are in BCD. */ - IDE_AFLAG_TOCTRACKS_AS_BCD = (1 << 4), + IDE_AFLAG_TOCTRACKS_AS_BCD = BIT(4), /* Saved TOC information is current. */ - IDE_AFLAG_TOC_VALID = (1 << 6), + IDE_AFLAG_TOC_VALID = BIT(6), /* We think that the drive door is locked. */ - IDE_AFLAG_DOOR_LOCKED = (1 << 7), + IDE_AFLAG_DOOR_LOCKED = BIT(7), /* SET_CD_SPEED command is unsupported. */ - IDE_AFLAG_NO_SPEED_SELECT = (1 << 8), - IDE_AFLAG_VERTOS_300_SSD = (1 << 9), - IDE_AFLAG_VERTOS_600_ESD = (1 << 10), - IDE_AFLAG_SANYO_3CD = (1 << 11), - IDE_AFLAG_FULL_CAPS_PAGE = (1 << 12), - IDE_AFLAG_PLAY_AUDIO_OK = (1 << 13), - IDE_AFLAG_LE_SPEED_FIELDS = (1 << 14), + IDE_AFLAG_NO_SPEED_SELECT = BIT(8), + IDE_AFLAG_VERTOS_300_SSD = BIT(9), + IDE_AFLAG_VERTOS_600_ESD = BIT(10), + IDE_AFLAG_SANYO_3CD = BIT(11), + IDE_AFLAG_FULL_CAPS_PAGE = BIT(12), + IDE_AFLAG_PLAY_AUDIO_OK = BIT(13), + IDE_AFLAG_LE_SPEED_FIELDS = BIT(14), /* ide-floppy */ /* Avoid commands not supported in Clik drive */ - IDE_AFLAG_CLIK_DRIVE = (1 << 15), + IDE_AFLAG_CLIK_DRIVE = BIT(15), /* Requires BH algorithm for packets */ - IDE_AFLAG_ZIP_DRIVE = (1 << 16), + IDE_AFLAG_ZIP_DRIVE = BIT(16), /* Supports format progress report */ - IDE_AFLAG_SRFP = (1 << 17), + IDE_AFLAG_SRFP = BIT(17), /* ide-tape */ - IDE_AFLAG_IGNORE_DSC = (1 << 18), + IDE_AFLAG_IGNORE_DSC = BIT(18), /* 0 When the tape position is unknown */ - IDE_AFLAG_ADDRESS_VALID = (1 << 19), + IDE_AFLAG_ADDRESS_VALID = BIT(19), /* Device already opened */ - IDE_AFLAG_BUSY = (1 << 20), + IDE_AFLAG_BUSY = BIT(20), /* Attempt to auto-detect the current user block size */ - IDE_AFLAG_DETECT_BS = (1 << 21), + IDE_AFLAG_DETECT_BS = BIT(21), /* Currently on a filemark */ - IDE_AFLAG_FILEMARK = (1 << 22), + IDE_AFLAG_FILEMARK = BIT(22), /* 0 = no tape is loaded, so we don't rewind after ejecting */ - IDE_AFLAG_MEDIUM_PRESENT = (1 << 23), + IDE_AFLAG_MEDIUM_PRESENT = BIT(23), - IDE_AFLAG_NO_AUTOCLOSE = (1 << 24), + IDE_AFLAG_NO_AUTOCLOSE = BIT(24), }; /* device flags */ enum { /* restore settings after device reset */ - IDE_DFLAG_KEEP_SETTINGS = (1 << 0), + IDE_DFLAG_KEEP_SETTINGS = BIT(0), /* device is using DMA for read/write */ - IDE_DFLAG_USING_DMA = (1 << 1), + IDE_DFLAG_USING_DMA = BIT(1), /* okay to unmask other IRQs */ - IDE_DFLAG_UNMASK = (1 << 2), + IDE_DFLAG_UNMASK = BIT(2), /* don't attempt flushes */ - IDE_DFLAG_NOFLUSH = (1 << 3), + IDE_DFLAG_NOFLUSH = BIT(3), /* DSC overlap */ - IDE_DFLAG_DSC_OVERLAP = (1 << 4), + IDE_DFLAG_DSC_OVERLAP = BIT(4), /* give potential excess bandwidth */ - IDE_DFLAG_NICE1 = (1 << 5), + IDE_DFLAG_NICE1 = BIT(5), /* device is physically present */ - IDE_DFLAG_PRESENT = (1 << 6), + IDE_DFLAG_PRESENT = BIT(6), /* disable Host Protected Area */ - IDE_DFLAG_NOHPA = (1 << 7), + IDE_DFLAG_NOHPA = BIT(7), /* id read from device (synthetic if not set) */ - IDE_DFLAG_ID_READ = (1 << 8), - IDE_DFLAG_NOPROBE = (1 << 9), + IDE_DFLAG_ID_READ = BIT(8), + IDE_DFLAG_NOPROBE = BIT(9), /* need to do check_media_change() */ - IDE_DFLAG_REMOVABLE = (1 << 10), + IDE_DFLAG_REMOVABLE = BIT(10), /* needed for removable devices */ - IDE_DFLAG_ATTACH = (1 << 11), - IDE_DFLAG_FORCED_GEOM = (1 << 12), + IDE_DFLAG_ATTACH = BIT(11), + IDE_DFLAG_FORCED_GEOM = BIT(12), /* disallow setting unmask bit */ - IDE_DFLAG_NO_UNMASK = (1 << 13), + IDE_DFLAG_NO_UNMASK = BIT(13), /* disallow enabling 32-bit I/O */ - IDE_DFLAG_NO_IO_32BIT = (1 << 14), + IDE_DFLAG_NO_IO_32BIT = BIT(14), /* for removable only: door lock/unlock works */ - IDE_DFLAG_DOORLOCKING = (1 << 15), + IDE_DFLAG_DOORLOCKING = BIT(15), /* disallow DMA */ - IDE_DFLAG_NODMA = (1 << 16), + IDE_DFLAG_NODMA = BIT(16), /* powermanagement told us not to do anything, so sleep nicely */ - IDE_DFLAG_BLOCKED = (1 << 17), + IDE_DFLAG_BLOCKED = BIT(17), /* sleeping & sleep field valid */ - IDE_DFLAG_SLEEPING = (1 << 18), - IDE_DFLAG_POST_RESET = (1 << 19), - IDE_DFLAG_UDMA33_WARNED = (1 << 20), - IDE_DFLAG_LBA48 = (1 << 21), + IDE_DFLAG_SLEEPING = BIT(18), + IDE_DFLAG_POST_RESET = BIT(19), + IDE_DFLAG_UDMA33_WARNED = BIT(20), + IDE_DFLAG_LBA48 = BIT(21), /* status of write cache */ - IDE_DFLAG_WCACHE = (1 << 22), + IDE_DFLAG_WCACHE = BIT(22), /* used for ignoring ATA_DF */ - IDE_DFLAG_NOWERR = (1 << 23), + IDE_DFLAG_NOWERR = BIT(23), /* retrying in PIO */ - IDE_DFLAG_DMA_PIO_RETRY = (1 << 24), - IDE_DFLAG_LBA = (1 << 25), + IDE_DFLAG_DMA_PIO_RETRY = BIT(24), + IDE_DFLAG_LBA = BIT(25), /* don't unload heads */ - IDE_DFLAG_NO_UNLOAD = (1 << 26), + IDE_DFLAG_NO_UNLOAD = BIT(26), /* heads unloaded, please don't reset port */ - IDE_DFLAG_PARKED = (1 << 27), - IDE_DFLAG_MEDIA_CHANGED = (1 << 28), + IDE_DFLAG_PARKED = BIT(27), + IDE_DFLAG_MEDIA_CHANGED = BIT(28), /* write protect */ - IDE_DFLAG_WP = (1 << 29), - IDE_DFLAG_FORMAT_IN_PROGRESS = (1 << 30), - IDE_DFLAG_NIEN_QUIRK = (1 << 31), + IDE_DFLAG_WP = BIT(29), + IDE_DFLAG_FORMAT_IN_PROGRESS = BIT(30), + IDE_DFLAG_NIEN_QUIRK = BIT(31), }; struct ide_drive_s { @@ -709,7 +709,7 @@ struct ide_dma_ops { }; enum { - IDE_PFLAG_PROBING = (1 << 0), + IDE_PFLAG_PROBING = BIT(0), }; struct ide_host; @@ -862,7 +862,7 @@ extern struct mutex ide_setting_mtx; * configurable drive settings */ -#define DS_SYNC (1 << 0) +#define DS_SYNC BIT(0) struct ide_devset { int (*get)(ide_drive_t *); @@ -1000,15 +1000,15 @@ static inline void ide_proc_unregister_driver(ide_drive_t *drive, enum { /* enter/exit functions */ - IDE_DBG_FUNC = (1 << 0), + IDE_DBG_FUNC = BIT(0), /* sense key/asc handling */ - IDE_DBG_SENSE = (1 << 1), + IDE_DBG_SENSE = BIT(1), /* packet commands handling */ - IDE_DBG_PC = (1 << 2), + IDE_DBG_PC = BIT(2), /* request handling */ - IDE_DBG_RQ = (1 << 3), + IDE_DBG_RQ = BIT(3), /* driver probing/setup */ - IDE_DBG_PROBE = (1 << 4), + IDE_DBG_PROBE = BIT(4), }; /* DRV_NAME has to be defined in the driver before using the macro below */ @@ -1171,10 +1171,10 @@ ssize_t ide_park_store(struct device *dev, struct device_attribute *attr, * the tail of our block device request queue and wait for their completion. */ enum { - REQ_IDETAPE_PC1 = (1 << 0), /* packet command (first stage) */ - REQ_IDETAPE_PC2 = (1 << 1), /* packet command (second stage) */ - REQ_IDETAPE_READ = (1 << 2), - REQ_IDETAPE_WRITE = (1 << 3), + REQ_IDETAPE_PC1 = BIT(0), /* packet command (first stage) */ + REQ_IDETAPE_PC2 = BIT(1), /* packet command (second stage) */ + REQ_IDETAPE_READ = BIT(2), + REQ_IDETAPE_WRITE = BIT(3), }; int ide_queue_pc_tail(ide_drive_t *, struct gendisk *, struct ide_atapi_pc *, @@ -1264,71 +1264,71 @@ struct ide_pci_enablebit { enum { /* Uses ISA control ports not PCI ones. */ - IDE_HFLAG_ISA_PORTS = (1 << 0), + IDE_HFLAG_ISA_PORTS = BIT(0), /* single port device */ - IDE_HFLAG_SINGLE = (1 << 1), + IDE_HFLAG_SINGLE = BIT(1), /* don't use legacy PIO blacklist */ - IDE_HFLAG_PIO_NO_BLACKLIST = (1 << 2), + IDE_HFLAG_PIO_NO_BLACKLIST = BIT(2), /* set for the second port of QD65xx */ - IDE_HFLAG_QD_2ND_PORT = (1 << 3), + IDE_HFLAG_QD_2ND_PORT = BIT(3), /* use PIO8/9 for prefetch off/on */ - IDE_HFLAG_ABUSE_PREFETCH = (1 << 4), + IDE_HFLAG_ABUSE_PREFETCH = BIT(4), /* use PIO6/7 for fast-devsel off/on */ - IDE_HFLAG_ABUSE_FAST_DEVSEL = (1 << 5), + IDE_HFLAG_ABUSE_FAST_DEVSEL = BIT(5), /* use 100-102 and 200-202 PIO values to set DMA modes */ - IDE_HFLAG_ABUSE_DMA_MODES = (1 << 6), + IDE_HFLAG_ABUSE_DMA_MODES = BIT(6), /* * keep DMA setting when programming PIO mode, may be used only * for hosts which have separate PIO and DMA timings (ie. PMAC) */ - IDE_HFLAG_SET_PIO_MODE_KEEP_DMA = (1 << 7), + IDE_HFLAG_SET_PIO_MODE_KEEP_DMA = BIT(7), /* program host for the transfer mode after programming device */ - IDE_HFLAG_POST_SET_MODE = (1 << 8), + IDE_HFLAG_POST_SET_MODE = BIT(8), /* don't program host/device for the transfer mode ("smart" hosts) */ - IDE_HFLAG_NO_SET_MODE = (1 << 9), + IDE_HFLAG_NO_SET_MODE = BIT(9), /* trust BIOS for programming chipset/device for DMA */ - IDE_HFLAG_TRUST_BIOS_FOR_DMA = (1 << 10), + IDE_HFLAG_TRUST_BIOS_FOR_DMA = BIT(10), /* host is CS5510/CS5520 */ - IDE_HFLAG_CS5520 = (1 << 11), + IDE_HFLAG_CS5520 = BIT(11), /* ATAPI DMA is unsupported */ - IDE_HFLAG_NO_ATAPI_DMA = (1 << 12), + IDE_HFLAG_NO_ATAPI_DMA = BIT(12), /* set if host is a "non-bootable" controller */ - IDE_HFLAG_NON_BOOTABLE = (1 << 13), + IDE_HFLAG_NON_BOOTABLE = BIT(13), /* host doesn't support DMA */ - IDE_HFLAG_NO_DMA = (1 << 14), + IDE_HFLAG_NO_DMA = BIT(14), /* check if host is PCI IDE device before allowing DMA */ - IDE_HFLAG_NO_AUTODMA = (1 << 15), + IDE_HFLAG_NO_AUTODMA = BIT(15), /* host uses MMIO */ - IDE_HFLAG_MMIO = (1 << 16), + IDE_HFLAG_MMIO = BIT(16), /* no LBA48 */ - IDE_HFLAG_NO_LBA48 = (1 << 17), + IDE_HFLAG_NO_LBA48 = BIT(17), /* no LBA48 DMA */ - IDE_HFLAG_NO_LBA48_DMA = (1 << 18), + IDE_HFLAG_NO_LBA48_DMA = BIT(18), /* data FIFO is cleared by an error */ - IDE_HFLAG_ERROR_STOPS_FIFO = (1 << 19), + IDE_HFLAG_ERROR_STOPS_FIFO = BIT(19), /* serialize ports */ - IDE_HFLAG_SERIALIZE = (1 << 20), + IDE_HFLAG_SERIALIZE = BIT(20), /* host is DTC2278 */ - IDE_HFLAG_DTC2278 = (1 << 21), + IDE_HFLAG_DTC2278 = BIT(21), /* 4 devices on a single set of I/O ports */ - IDE_HFLAG_4DRIVES = (1 << 22), + IDE_HFLAG_4DRIVES = BIT(22), /* host is TRM290 */ - IDE_HFLAG_TRM290 = (1 << 23), + IDE_HFLAG_TRM290 = BIT(23), /* use 32-bit I/O ops */ - IDE_HFLAG_IO_32BIT = (1 << 24), + IDE_HFLAG_IO_32BIT = BIT(24), /* unmask IRQs */ - IDE_HFLAG_UNMASK_IRQS = (1 << 25), - IDE_HFLAG_BROKEN_ALTSTATUS = (1 << 26), + IDE_HFLAG_UNMASK_IRQS = BIT(25), + IDE_HFLAG_BROKEN_ALTSTATUS = BIT(26), /* serialize ports if DMA is possible (for sl82c105) */ - IDE_HFLAG_SERIALIZE_DMA = (1 << 27), + IDE_HFLAG_SERIALIZE_DMA = BIT(27), /* force host out of "simplex" mode */ - IDE_HFLAG_CLEAR_SIMPLEX = (1 << 28), + IDE_HFLAG_CLEAR_SIMPLEX = BIT(28), /* DSC overlap is unsupported */ - IDE_HFLAG_NO_DSC = (1 << 29), + IDE_HFLAG_NO_DSC = BIT(29), /* never use 32-bit I/O ops */ - IDE_HFLAG_NO_IO_32BIT = (1 << 30), + IDE_HFLAG_NO_IO_32BIT = BIT(30), /* never unmask IRQs */ - IDE_HFLAG_NO_UNMASK_IRQS = (1 << 31), + IDE_HFLAG_NO_UNMASK_IRQS = BIT(31), }; #ifdef CONFIG_BLK_DEV_OFFBOARD @@ -1536,16 +1536,16 @@ struct ide_timing { }; enum { - IDE_TIMING_SETUP = (1 << 0), - IDE_TIMING_ACT8B = (1 << 1), - IDE_TIMING_REC8B = (1 << 2), - IDE_TIMING_CYC8B = (1 << 3), + IDE_TIMING_SETUP = BIT(0), + IDE_TIMING_ACT8B = BIT(1), + IDE_TIMING_REC8B = BIT(2), + IDE_TIMING_CYC8B = BIT(3), IDE_TIMING_8BIT = IDE_TIMING_ACT8B | IDE_TIMING_REC8B | IDE_TIMING_CYC8B, - IDE_TIMING_ACTIVE = (1 << 4), - IDE_TIMING_RECOVER = (1 << 5), - IDE_TIMING_CYCLE = (1 << 6), - IDE_TIMING_UDMA = (1 << 7), + IDE_TIMING_ACTIVE = BIT(4), + IDE_TIMING_RECOVER = BIT(5), + IDE_TIMING_CYCLE = BIT(6), + IDE_TIMING_UDMA = BIT(7), IDE_TIMING_ALL = IDE_TIMING_SETUP | IDE_TIMING_8BIT | IDE_TIMING_ACTIVE | IDE_TIMING_RECOVER | IDE_TIMING_CYCLE | IDE_TIMING_UDMA, -- cgit v1.2.3 From 9b0eb69b75bccada2d341d7e7ca342f0cb1c9a6a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:48 -0700 Subject: cgroup, blkcg: Prepare some symbols for module and !CONFIG_CGROUP usages btrfs is going to use css_put() and wbc helpers to improve cgroup writeback support. Add dummy css_get() definition and export wbc helpers to prepare for module and !CONFIG_CGROUP builds. Reported-by: kbuild test robot Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3745ecdad925..852d885df10a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -699,6 +699,7 @@ void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, struct cgroup_subsys_state; struct cgroup; +static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } -- cgit v1.2.3 From 34e51a5e1a6e939ed7d99c38173821ab86d577f4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:49 -0700 Subject: blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner() wbc_account_io() does a very specific job - try to see which cgroup is actually dirtying an inode and transfer its ownership to the majority dirtier if needed. The name is too generic and confusing. Let's rename it to something more specific. Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/writeback.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f..dda5cf228172 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -188,8 +188,8 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock); void wbc_detach_inode(struct writeback_control *wbc); -void wbc_account_io(struct writeback_control *wbc, struct page *page, - size_t bytes); +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, + size_t bytes); void cgroup_writeback_umount(void); /** @@ -291,8 +291,8 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { } -static inline void wbc_account_io(struct writeback_control *wbc, - struct page *page, size_t bytes) +static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, + struct page *page, size_t bytes) { } -- cgit v1.2.3 From 27b36d8fa81fa8274fb72f4eb1484026f6b6daa8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:50 -0700 Subject: blkcg, writeback: Add wbc->no_cgroup_owner When writeback IOs are bounced through async layers, the IOs should only be accounted against the wbc from the original bdi writeback to avoid confusing cgroup inode ownership arbitration. Add wbc->no_cgroup_owner to allow disabling wbc cgroup owner accounting. This will be used make btrfs compression work well with cgroup IO control. v2: Renamed from no_wbc_acct to no_cgroup_owner and added comment as per Jan. Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/writeback.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index dda5cf228172..33a50fa09fac 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,6 +68,15 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + + /* + * When writeback IOs are bounced through async layers, only the + * initial synchronous phase should be accounted towards inode + * cgroup ownership arbitration to avoid confusion. Later stages + * can set the following flag to disable the accounting. + */ + unsigned no_cgroup_owner:1; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ -- cgit v1.2.3 From 653c45c6b90c9659facbef10546d1f3a8e37d0cf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:51 -0700 Subject: blkcg, writeback: Implement wbc_blkcg_css() Add a helper to determine the target blkcg from wbc. Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/writeback.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 33a50fa09fac..e056a22075cf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -11,6 +11,7 @@ #include #include #include +#include struct bio; @@ -101,6 +102,16 @@ static inline int wbc_to_write_flags(struct writeback_control *wbc) return 0; } +static inline struct cgroup_subsys_state * +wbc_blkcg_css(struct writeback_control *wbc) +{ +#ifdef CONFIG_CGROUP_WRITEBACK + if (wbc->wb) + return wbc->wb->blkcg_css; +#endif + return blkcg_root_css; +} + /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global -- cgit v1.2.3 From d3f77dfdc71835f8db71ca57d272b1fbec9dfc18 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:52 -0700 Subject: blkcg: implement REQ_CGROUP_PUNT When a shared kthread needs to issue a bio for a cgroup, doing so synchronously can lead to priority inversions as the kthread can be trapped waiting for that cgroup. This patch implements REQ_CGROUP_PUNT flag which makes submit_bio() punt the actual issuing to a dedicated per-blkcg work item to avoid such priority inversions. This will be used to fix priority inversions in btrfs compression and should be generally useful as we grow filesystem support for comprehensive IO control. Cc: Chris Mason Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 + include/linux/blk-cgroup.h | 16 +++++++++++++++- include/linux/blk_types.h | 10 ++++++++++ include/linux/writeback.h | 13 ++++++++++--- 4 files changed, 36 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f9b029180241..35b31d176f74 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -48,6 +48,7 @@ extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; +extern struct workqueue_struct *bdi_async_bio_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 33f23a858438..689a58231288 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -132,13 +132,17 @@ struct blkcg_gq { struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - struct rcu_head rcu_head; + spinlock_t async_bio_lock; + struct bio_list async_bios; + struct work_struct async_bio_work; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; + + struct rcu_head rcu_head; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); @@ -701,6 +705,15 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif +bool __blkcg_punt_bio_submit(struct bio *bio); + +static inline bool blkcg_punt_bio_submit(struct bio *bio) +{ + if (bio->bi_opf & REQ_CGROUP_PUNT) + return __blkcg_punt_bio_submit(bio); + else + return false; +} static inline void blkcg_bio_issue_init(struct bio *bio) { @@ -848,6 +861,7 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } +static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6a53799c3fe2..feff3fe4467e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -311,6 +311,14 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ + /* + * When a shared kthread needs to issue a bio for a cgroup, doing + * so synchronously can lead to priority inversions as the kthread + * can be trapped waiting for that cgroup. CGROUP_PUNT flag makes + * submit_bio() punt the actual issuing to a dedicated per-blkcg + * work item to avoid such priority inversions. + */ + __REQ_CGROUP_PUNT, /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ @@ -337,6 +345,8 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) +#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) + #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_HIPRI (1ULL << __REQ_HIPRI) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index e056a22075cf..8945aac31392 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -78,6 +78,8 @@ struct writeback_control { */ unsigned no_cgroup_owner:1; + unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ @@ -94,12 +96,17 @@ struct writeback_control { static inline int wbc_to_write_flags(struct writeback_control *wbc) { + int flags = 0; + + if (wbc->punt_to_cgroup) + flags = REQ_CGROUP_PUNT; + if (wbc->sync_mode == WB_SYNC_ALL) - return REQ_SYNC; + flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) - return REQ_BACKGROUND; + flags |= REQ_BACKGROUND; - return 0; + return flags; } static inline struct cgroup_subsys_state * -- cgit v1.2.3 From 113ab72ed4794c193509a97d7c6d32a6886e1682 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 10 Jul 2019 13:53:10 +0900 Subject: block: Fix potential overflow in blk_report_zones() For large values of the number of zones reported and/or large zone sizes, the sector increment calculated with blk_queue_zone_sectors(q) * n in blk_report_zones() loop can overflow the unsigned int type used for the calculation as both "n" and blk_queue_zone_sectors() value are unsigned int. E.g. for a device with 256 MB zones (524288 sectors), overflow happens with 8192 or more zones reported. Changing the return type of blk_queue_zone_sectors() to sector_t, fixes this problem and avoids overflow problem for all other callers of this helper too. The same change is also applied to the bdev_zone_sectors() helper. Fixes: e76239a3748c ("block: add a report_zones method") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0c482371c8b3..259bd7ad8312 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -681,7 +681,7 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } -static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) +static inline sector_t blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } @@ -1418,7 +1418,7 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } -static inline unsigned int bdev_zone_sectors(struct block_device *bdev) +static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 36847a005489cfb74dc6388952da73346f867dca Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 Jul 2019 00:56:08 +0900 Subject: block: Remove unused definitions The ELV_MQUEUE_XXX definitions in include/linux/elevator.h are unused since the removal of elevator_may_queue_fn in kernel 5.0. Remove these definitions and also remove the documentation of elevator_may_queue_fn in Documentiation/block/biodoc.txt. Acked-by: Marcos Paulo de Souza Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/elevator.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 169bb2e02516..38590c30a11d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -160,15 +160,6 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t); #define ELEVATOR_INSERT_FLUSH 5 #define ELEVATOR_INSERT_SORT_MERGE 6 -/* - * return values from elevator_may_queue_fn - */ -enum { - ELV_MQUEUE_MAY, - ELV_MQUEUE_NO, - ELV_MQUEUE_MUST, -}; - #define rq_end_sector(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq)) #define rb_entry_rq(node) rb_entry((node), struct request, rb_node) -- cgit v1.2.3 From 9305d5d721f2bd5e2eeb670035159b560ca211ca Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 Jul 2019 00:57:41 +0900 Subject: block: Fix elevator name declaration The elevator_name field in struct elevator_type is declared as an array of characters (ELV_NAME_MAX size) but in practice used as a string pointer with its initialization done statically within each elevator elevator_type structure declaration. Change the declaration of elevator_name to the more appropriate "const char *" type. Acked-by: Marcos Paulo de Souza Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 38590c30a11d..17cd0078377c 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -75,7 +75,7 @@ struct elevator_type size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; - char elevator_name[ELV_NAME_MAX]; + const char *elevator_name; const char *elevator_alias; struct module *elevator_owner; #ifdef CONFIG_BLK_DEBUG_FS -- cgit v1.2.3 From 9c1f2a5dc2948b9f1170d4202c84745f0b0ff0c9 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 4 Jun 2019 12:01:46 -0500 Subject: mailbox: omap: Add support for TI K3 SoCs The TI K3 AM65x and J721E family of SoCs have a new Mailbox IP that is based on the existing Mailbox IP present in OMAP architecture based SoCs. Each instance of the legacy OMAP Mailbox IP is now a single cluster within the newer Mailbox IP instance on K3 architecture based SoCs. A single K3 Mailbox IP instance has multiple clusters with each cluster providing the same functionality as the existing OMAP Mailbox IP. Reuse the existing OMAP Mailbox driver to extend the support for this newer IP present within the Main NavSS block on K3 SoCs. The K3 family of SoCs use 64-bit ARMv8 processors for running Linux, so the driver is also enhanced to deal with the differences between the 32-bit message payloads and the 64-bit pointers used by the client drivers. Signed-off-by: Suman Anna Signed-off-by: Jassi Brar --- include/linux/omap-mailbox.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h index 6dbcd2da0332..8aa984ec1f38 100644 --- a/include/linux/omap-mailbox.h +++ b/include/linux/omap-mailbox.h @@ -6,7 +6,9 @@ #ifndef OMAP_MAILBOX_H #define OMAP_MAILBOX_H -typedef u32 mbox_msg_t; +typedef uintptr_t mbox_msg_t; + +#define omap_mbox_message(data) (u32)(mbox_msg_t)(data) typedef int __bitwise omap_mbox_irq_t; #define IRQ_TX ((__force omap_mbox_irq_t) 1) -- cgit v1.2.3 From ff956826a403f5cf189978d5ff6b3eb53aa11610 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:24 +0800 Subject: intel_rapl: introduce intel_rapl.h Create a new header file for the common definitions that might be used by different RAPL Interface. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 113 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 113 insertions(+) create mode 100644 include/linux/intel_rapl.h (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h new file mode 100644 index 000000000000..94716036d829 --- /dev/null +++ b/include/linux/intel_rapl.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Data types and headers for RAPL support + * + * Copyright (C) 2019 Intel Corporation. + * + * Author: Zhang Rui + */ + +#ifndef __INTEL_RAPL_H__ +#define __INTEL_RAPL_H__ + +#include +#include + +enum rapl_domain_type { + RAPL_DOMAIN_PACKAGE, /* entire package/socket */ + RAPL_DOMAIN_PP0, /* core power plane */ + RAPL_DOMAIN_PP1, /* graphics uncore */ + RAPL_DOMAIN_DRAM, /* DRAM control_type */ + RAPL_DOMAIN_PLATFORM, /* PSys control_type */ + RAPL_DOMAIN_MAX, +}; + +enum rapl_domain_reg_id { + RAPL_DOMAIN_REG_LIMIT, + RAPL_DOMAIN_REG_STATUS, + RAPL_DOMAIN_REG_PERF, + RAPL_DOMAIN_REG_POLICY, + RAPL_DOMAIN_REG_INFO, + RAPL_DOMAIN_REG_MAX, +}; + +struct rapl_package; + +enum rapl_primitives { + ENERGY_COUNTER, + POWER_LIMIT1, + POWER_LIMIT2, + FW_LOCK, + + PL1_ENABLE, /* power limit 1, aka long term */ + PL1_CLAMP, /* allow frequency to go below OS request */ + PL2_ENABLE, /* power limit 2, aka short term, instantaneous */ + PL2_CLAMP, + + TIME_WINDOW1, /* long term */ + TIME_WINDOW2, /* short term */ + THERMAL_SPEC_POWER, + MAX_POWER, + + MIN_POWER, + MAX_TIME_WINDOW, + THROTTLED_TIME, + PRIORITY_LEVEL, + + /* below are not raw primitive data */ + AVERAGE_POWER, + NR_RAPL_PRIMITIVES, +}; + +struct rapl_domain_data { + u64 primitives[NR_RAPL_PRIMITIVES]; + unsigned long timestamp; +}; + +#define NR_POWER_LIMITS (2) +struct rapl_power_limit { + struct powercap_zone_constraint *constraint; + int prim_id; /* primitive ID used to enable */ + struct rapl_domain *domain; + const char *name; + u64 last_power_limit; +}; + +struct rapl_package; + +struct rapl_domain { + const char *name; + enum rapl_domain_type id; + int regs[RAPL_DOMAIN_REG_MAX]; + struct powercap_zone power_zone; + struct rapl_domain_data rdd; + struct rapl_power_limit rpl[NR_POWER_LIMITS]; + u64 attr_map; /* track capabilities */ + unsigned int state; + unsigned int domain_energy_unit; + struct rapl_package *rp; +}; + +/* maximum rapl package domain name: package-%d-die-%d */ +#define PACKAGE_DOMAIN_NAME_LENGTH 30 + +struct rapl_package { + unsigned int id; /* logical die id, equals physical 1-die systems */ + unsigned int nr_domains; + unsigned long domain_map; /* bit map of active domains */ + unsigned int power_unit; + unsigned int energy_unit; + unsigned int time_unit; + struct rapl_domain *domains; /* array of domains, sized at runtime */ + struct powercap_zone *power_zone; /* keep track of parent zone */ + unsigned long power_limit_irq; /* keep track of package power limit + * notify interrupt enable status. + */ + struct list_head plist; + int lead_cpu; /* one active cpu per package for access */ + /* Track active cpus */ + struct cpumask cpumask; + char name[PACKAGE_DOMAIN_NAME_LENGTH]; +}; + +#endif /* __INTEL_RAPL_H__ */ -- cgit v1.2.3 From 7ebf8eff63b4f349e7b2ded6aa5036d94bdf94b9 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:25 +0800 Subject: intel_rapl: introduce struct rapl_if_private Introduce a new structure, rapl_if_private, to save the private data for different RAPL Interface. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 94716036d829..7bf1683e4a63 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -88,6 +88,20 @@ struct rapl_domain { struct rapl_package *rp; }; +/** + * struct rapl_if_priv: private data for different RAPL interfaces + * @control_type: Each RAPL interface must have its own powercap + * control type. + * @platform_rapl_domain: Optional. Some RAPL interface may have platform + * level RAPL control. + * @pcap_rapl_online: CPU hotplug state for each RAPL interface. + */ +struct rapl_if_priv { + struct powercap_control_type *control_type; + struct rapl_domain *platform_rapl_domain; + enum cpuhp_state pcap_rapl_online; +}; + /* maximum rapl package domain name: package-%d-die-%d */ #define PACKAGE_DOMAIN_NAME_LENGTH 30 @@ -108,6 +122,7 @@ struct rapl_package { /* Track active cpus */ struct cpumask cpumask; char name[PACKAGE_DOMAIN_NAME_LENGTH]; + struct rapl_if_priv *priv; }; #endif /* __INTEL_RAPL_H__ */ -- cgit v1.2.3 From 7fde2712a7adab721eaabafbd8ff93dff3262d35 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:26 +0800 Subject: intel_rapl: abstract register address MSR and MMIO RAPL interface have different sets of registers, thus the RAPL register address should be obtained from interface specific structure, i.e. struct rapl_if_private, instead. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 7bf1683e4a63..ec2c9e83274f 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -95,11 +95,15 @@ struct rapl_domain { * @platform_rapl_domain: Optional. Some RAPL interface may have platform * level RAPL control. * @pcap_rapl_online: CPU hotplug state for each RAPL interface. + * @reg_unit: Register for getting energy/power/time unit. + * @regs: Register sets for different RAPL Domains. */ struct rapl_if_priv { struct powercap_control_type *control_type; struct rapl_domain *platform_rapl_domain; enum cpuhp_state pcap_rapl_online; + u32 reg_unit; + u32 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; }; /* maximum rapl package domain name: package-%d-die-%d */ -- cgit v1.2.3 From beea8df821d928e7755917da6c1e45d6afde5148 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:27 +0800 Subject: intel_rapl: abstract register access operations MSR and MMIO RAPL interfaces have different ways to access the registers, thus in order to abstract the register access operations, two callbacks, .read_raw()/.write_raw() are introduced, and they should be implemented by MSR RAPL and MMIO RAPL interface driver respectly. This patch implements them for the MSR I/F only. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index ec2c9e83274f..ff215d64d114 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -88,6 +88,13 @@ struct rapl_domain { struct rapl_package *rp; }; +struct reg_action { + u32 reg; + u64 mask; + u64 value; + int err; +}; + /** * struct rapl_if_priv: private data for different RAPL interfaces * @control_type: Each RAPL interface must have its own powercap @@ -97,6 +104,10 @@ struct rapl_domain { * @pcap_rapl_online: CPU hotplug state for each RAPL interface. * @reg_unit: Register for getting energy/power/time unit. * @regs: Register sets for different RAPL Domains. + * @read_raw: Callback for reading RAPL interface specific + * registers. + * @write_raw: Callback for writing RAPL interface specific + * registers. */ struct rapl_if_priv { struct powercap_control_type *control_type; @@ -104,6 +115,8 @@ struct rapl_if_priv { enum cpuhp_state pcap_rapl_online; u32 reg_unit; u32 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; + int (*read_raw)(int cpu, struct reg_action *ra); + int (*write_raw)(int cpu, struct reg_action *ra); }; /* maximum rapl package domain name: package-%d-die-%d */ -- cgit v1.2.3 From 3382388d714891fc0f575926189f33d22e7c960b Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:30 +0800 Subject: intel_rapl: abstract RAPL common code Split intel_rapl.c to intel_rapl_common.c and intel_rapl_msr.c, where intel_rapl_common.c contains the common code that can be used by both MSR and MMIO interface. intel_rapl_msr.c contains the implementation of RAPL MSR interface. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index ff215d64d114..9579f458fe4d 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -142,4 +142,11 @@ struct rapl_package { struct rapl_if_priv *priv; }; +struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv); +struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv); +void rapl_remove_package(struct rapl_package *rp); + +int rapl_add_platform_domain(struct rapl_if_priv *priv); +void rapl_remove_platform_domain(struct rapl_if_priv *priv); + #endif /* __INTEL_RAPL_H__ */ -- cgit v1.2.3 From d978e755aabe215cb67bf713e103ed3916ec306d Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:31 +0800 Subject: intel_rapl: support 64 bit register RAPL MMIO interface uses 64 bit registers, thus force use 64 bit register for all the RAPL code. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 9579f458fe4d..649e19981eb0 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -78,7 +78,7 @@ struct rapl_package; struct rapl_domain { const char *name; enum rapl_domain_type id; - int regs[RAPL_DOMAIN_REG_MAX]; + u64 regs[RAPL_DOMAIN_REG_MAX]; struct powercap_zone power_zone; struct rapl_domain_data rdd; struct rapl_power_limit rpl[NR_POWER_LIMITS]; @@ -89,7 +89,7 @@ struct rapl_domain { }; struct reg_action { - u32 reg; + u64 reg; u64 mask; u64 value; int err; @@ -113,8 +113,8 @@ struct rapl_if_priv { struct powercap_control_type *control_type; struct rapl_domain *platform_rapl_domain; enum cpuhp_state pcap_rapl_online; - u32 reg_unit; - u32 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; + u64 reg_unit; + u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; int (*read_raw)(int cpu, struct reg_action *ra); int (*write_raw)(int cpu, struct reg_action *ra); }; -- cgit v1.2.3 From 0c2ddedd8bcb88c4100acb9e0fc5ac8752d09501 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Wed, 10 Jul 2019 21:44:32 +0800 Subject: intel_rapl: support two power limits for every RAPL domain RAPL MSR interface supports 2 power limits for package domain, and 1 power limit for other domains, while RAPL MMIO interface supports 2 power limits for both package and dram domains. And when 2 power limits are supported, the FW_LOCK bit is in bit 63 of the register, instead of bit 31. Remove the assumption that only pakcage domain supports 2 power limits. And allow the RAPL interface driver to specify the number of power limits supported, for every single RAPL domain it owns.. Reviewed-by: Pandruvada, Srinivas Tested-by: Pandruvada, Srinivas Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 649e19981eb0..0c179d92d110 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -104,6 +104,7 @@ struct reg_action { * @pcap_rapl_online: CPU hotplug state for each RAPL interface. * @reg_unit: Register for getting energy/power/time unit. * @regs: Register sets for different RAPL Domains. + * @limits: Number of power limits supported by each domain. * @read_raw: Callback for reading RAPL interface specific * registers. * @write_raw: Callback for writing RAPL interface specific @@ -115,6 +116,7 @@ struct rapl_if_priv { enum cpuhp_state pcap_rapl_online; u64 reg_unit; u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; + int limits[RAPL_DOMAIN_MAX]; int (*read_raw)(int cpu, struct reg_action *ra); int (*write_raw)(int cpu, struct reg_action *ra); }; -- cgit v1.2.3 From bedc0fd0f9b517698193d644f914b33951856fd2 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 11 Jul 2019 09:55:56 -0400 Subject: RDMA/core: Fix -Wunused-const-variable warnings The commit below introduced a few compilation warnings. In file included from ./include/rdma/ib_verbs.h:64, from ./include/linux/mlx5/device.h:37, from ./include/linux/mlx5/driver.h:51, from drivers/net/ethernet/mellanox/mlx5/core/uar.c:36: ./include/linux/dim.h:378:1: warning: 'rdma_dim_prof' defined but not used [-Wunused-const-variable=] rdma_dim_prof[RDMA_DIM_PARAMS_NUM_PROFILES] = { ^~~~~~~~~~~~~ In file included from ./include/rdma/ib_verbs.h:64, from ./include/linux/mlx5/device.h:37, from ./include/linux/mlx5/driver.h:51, from drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:37: ./include/linux/dim.h:378:1: warning: 'rdma_dim_prof' defined but not used [-Wunused-const-variable=] rdma_dim_prof[RDMA_DIM_PARAMS_NUM_PROFILES] = { ^~~~~~~~~~~~~ Since only ib_cq_rdma_dim_work() in drivers/infiniband/core/cq.c uses it, just move the definition over there. Fixes: f4915455dcf0 ("linux/dim: Implement RDMA adaptive moderation (DIM)") Signed-off-by: Qian Cai Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- include/linux/dim.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dim.h b/include/linux/dim.h index aa69730c3b8d..d3a0fbfff2bb 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -374,19 +374,6 @@ void net_dim(struct dim *dim, struct dim_sample end_sample); #define RDMA_DIM_PARAMS_NUM_PROFILES 9 #define RDMA_DIM_START_PROFILE 0 -static const struct dim_cq_moder -rdma_dim_prof[RDMA_DIM_PARAMS_NUM_PROFILES] = { - {1, 0, 1, 0}, - {1, 0, 4, 0}, - {2, 0, 4, 0}, - {2, 0, 8, 0}, - {4, 0, 8, 0}, - {16, 0, 8, 0}, - {16, 0, 16, 0}, - {32, 0, 16, 0}, - {32, 0, 32, 0}, -}; - /** * rdma_dim - Runs the adaptive moderation. * @dim: The moderation struct. -- cgit v1.2.3 From b516ea586d717472178e6ef1c152e85608b0ce32 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Mon, 8 Jul 2019 13:17:44 +0800 Subject: PCI: Enable NVIDIA HDA controllers Many NVIDIA GPUs can be configured as either a single-function video device or a multi-function device with video at function 0 and an HDA audio controller at function 1. The HDA controller can be enabled or disabled by a bit in the function 0 config space. Some BIOSes leave the HDA disabled, which means the HDMI connector from the NVIDIA GPU may not work. Sometimes the BIOS enables the HDA if an HDMI cable is connected at boot time, but that doesn't handle hotplug cases. Enable the HDA controller on device enumeration and resume and re-read the header type, which tells us whether the GPU is a multi-function device. This quirk is limited to NVIDIA PCI devices with the VGA Controller device class. This is expected to correspond to product configurations where the NVIDIA GPU has connectors attached. Other products where the device class is 3D Controller are expected to correspond to configurations where the NVIDIA GPU is dedicated (dGPU) and has no connectors. See original post (URL below) for more details. This commit takes inspiration from an earlier patch by Daniel Drake. Link: https://lore.kernel.org/r/20190708051744.24039-1-drake@endlessm.com v2 Link: https://lore.kernel.org/r/20190613063514.15317-1-drake@endlessm.com v1 Link: https://devtalk.nvidia.com/default/topic/1024022 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=75985 Signed-off-by: Lukas Wunner Signed-off-by: Daniel Drake [bhelgaas: commit log, log message, return early if already enabled] Signed-off-by: Bjorn Helgaas Cc: Aaron Plattner Cc: Peter Wu Cc: Ilia Mirkin Cc: Karol Herbst Cc: Maik Freudenberg --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 70e86148cb1e..66898463b81f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1336,6 +1336,7 @@ #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP78S_SMBUS 0x0752 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP77_IDE 0x0759 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP73_SMBUS 0x07D8 +#define PCI_DEVICE_ID_NVIDIA_GEFORCE_320M 0x08A0 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP79_SMBUS 0x0AA2 #define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP89_SATA 0x0D85 -- cgit v1.2.3 From db849faa9bef993a1379dc510623f750a72fa7ce Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 3 May 2019 13:14:59 -0700 Subject: net/mlx5e: Rx, Fix checksum calculation for new hardware CQE checksum full mode in new HW, provides a full checksum of rx frame. Covering bytes starting from eth protocol up to last byte in the received frame (frame_size - ETH_HLEN), as expected by the stack. Fixing up skb->csum by the driver is not required in such case. This fix is to avoid wrong checksum calculation in drivers which already support the new hardware with the new checksum mode. Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices") Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5e74305e2e57..7e42efa143a0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -749,7 +749,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp[0x1]; u8 swp_csum[0x1]; u8 swp_lso[0x1]; - u8 reserved_at_23[0xd]; + u8 cqe_checksum_full[0x1]; + u8 reserved_at_24[0xc]; u8 max_vxlan_udp_ports[0x8]; u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; -- cgit v1.2.3 From bd976e52725965ddcceb9abecbcc7ca46863665c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 1 Jul 2019 14:09:16 +0900 Subject: block: Kill gfp_t argument of blkdev_report_zones() Only GFP_KERNEL and GFP_NOIO are used with blkdev_report_zones(). In preparation of using vmalloc() for large report buffer and zone array allocations used by this function, remove its "gfp_t gfp_mask" argument and rely on the caller context to use memalloc_noio_save/restore() where necessary (block layer zone revalidation and dm-zoned I/O error path). Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- include/linux/device-mapper.h | 3 +-- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 259bd7ad8312..05036e3e3458 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -347,7 +347,7 @@ struct queue_limits { extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones, gfp_t gfp_mask); + unsigned int *nr_zones); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); @@ -1673,8 +1673,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask); + struct blk_zone *zones, unsigned int *nr_zones); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e1f51d607cc5..3b470cb03b66 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -95,8 +95,7 @@ typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device ** typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones, - gfp_t gfp_mask); + unsigned int *nr_zones); /* * These iteration functions are typically used to check (and combine) -- cgit v1.2.3 From 26202928fafad8bda8b478edb7e62c885be623d7 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 1 Jul 2019 14:09:18 +0900 Subject: block: Limit zone array allocation size Limit the size of the struct blk_zone array used in blk_revalidate_disk_zones() to avoid memory allocation failures leading to disk revalidation failure. Also further reduce the likelyhood of such failures by using kvcalloc() (that is vmalloc()) instead of allocating contiguous pages with alloc_pages(). Fixes: 515ce6061312 ("scsi: sd_zbc: Fix sd_zbc_report_zones() buffer allocation") Fixes: e76239a3748c ("block: add a report_zones method") Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 05036e3e3458..1ef375dafb1c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -344,6 +344,11 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED +/* + * Maximum number of zones to report with a single report zones command. + */ +#define BLK_ZONED_REPORT_MAX_ZONES 8192U + extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, -- cgit v1.2.3 From a101b043c44dfcb63bed7f29a675e9fa0259005e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 11 Jul 2019 16:33:12 -0400 Subject: SUNRPC: Fix transport accounting when caller specifies an rpc_xprt Ensure that we do the required accounting for the round robin queue when the caller to rpc_init_task() has passed in a transport to be used. Reported-by: Olga Kornievskaia Reported-by: Neil Brown Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 4619098affa3..4e070e00c143 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -164,6 +164,8 @@ void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); void rpc_task_release_transport(struct rpc_task *); void rpc_task_release_client(struct rpc_task *); +struct rpc_xprt *rpc_task_get_xprt(struct rpc_clnt *clnt, + struct rpc_xprt *xprt); int rpcb_create_local(struct net *); void rpcb_put_local(struct net *); -- cgit v1.2.3 From 1df379924304b687263942452836db1d725155df Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 2 Jul 2019 12:03:50 +1000 Subject: clk: consoldiate the __clk_get_hw() declarations Without this we were getting errors like: In file included from drivers/clk/clkdev.c:22:0: drivers/clk/clk.h:36:23: error: static declaration of '__clk_get_hw' follows non-static declaration include/linux/clk-provider.h:808:16: note: previous declaration of '__clk_get_hw' was here Fixes: 59fcdce425b7 ("clk: Remove ifdef for COMMON_CLK in clk-provider.h") fixes: 73e0e496afda ("clkdev: Always allocate a struct clk and call __clk_get() w/ CCF") Signed-off-by: Stephen Rothwell Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9ba000e3a50d..55d48140b0d0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -805,7 +805,14 @@ void devm_clk_hw_unregister(struct device *dev, struct clk_hw *hw); /* helper functions */ const char *__clk_get_name(const struct clk *clk); const char *clk_hw_get_name(const struct clk_hw *hw); +#ifdef CONFIG_COMMON_CLK struct clk_hw *__clk_get_hw(struct clk *clk); +#else +static inline struct clk_hw *__clk_get_hw(struct clk *clk) +{ + return (struct clk_hw *)clk; +} +#endif unsigned int clk_hw_get_num_parents(const struct clk_hw *hw); struct clk_hw *clk_hw_get_parent(const struct clk_hw *hw); struct clk_hw *clk_hw_get_parent_by_index(const struct clk_hw *hw, -- cgit v1.2.3 From 54638c6eaf445ecf901128599cfeb4620be47d2f Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Wed, 10 Jul 2019 21:03:24 +0300 Subject: net: phy: make exported variables non-static The variables phy_basic_ports_array, phy_fibre_port_array and phy_all_ports_features_array are declared static and marked EXPORT_SYMBOL_GPL(), which is at best an odd combination. Because the variables were decided to be a part of API, this commit removes the static attributes and adds the declarations to the header. Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode") Signed-off-by: Denis Efremov Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1739c6dc470e..462b90b73f93 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -55,6 +55,9 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) +extern const int phy_basic_ports_array[3]; +extern const int phy_fibre_port_array[1]; +extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[2]; extern const int phy_gbit_features_array[2]; -- cgit v1.2.3 From 8a58ddae23796c733c5dfbd717538d89d036c5bd Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Mon, 1 Jul 2019 14:07:55 +0300 Subject: perf/core: Fix exclusive events' grouping So far, we tried to disallow grouping exclusive events for the fear of complications they would cause with moving between contexts. Specifically, moving a software group to a hardware context would violate the exclusivity rules if both groups contain matching exclusive events. This attempt was, however, unsuccessful: the check that we have in the perf_event_open() syscall is both wrong (looks at wrong PMU) and insufficient (group leader may still be exclusive), as can be illustrated by running: $ perf record -e '{intel_pt//,cycles}' uname $ perf record -e '{cycles,intel_pt//}' uname ultimately successfully. Furthermore, we are completely free to trigger the exclusivity violation by: perf -e '{cycles,intel_pt//}' -e '{intel_pt//,instructions}' even though the helpful perf record will not allow that, the ABI will. The warning later in the perf_event_open() path will also not trigger, because it's also wrong. Fix all this by validating the original group before moving, getting rid of broken safeguards and placing a useful one to perf_install_in_context(). Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: mathieu.poirier@linaro.org Cc: will.deacon@arm.com Fixes: bed5b25ad9c8a ("perf: Add a pmu capability for "exclusive" events") Link: https://lkml.kernel.org/r/20190701110755.24646-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 16e38c286d46..e8ad3c590a23 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1055,6 +1055,11 @@ static inline int in_software_context(struct perf_event *event) return event->ctx->pmu->task_ctx_nr == perf_sw_context; } +static inline int is_exclusive_pmu(struct pmu *pmu) +{ + return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; +} + extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); -- cgit v1.2.3 From 028b6e8a89de9133a869bb4cd1bc72445b1ec8ca Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Sun, 14 Jul 2019 19:20:47 +0300 Subject: clone: fix CLONE_PIDFD support The introduction of clone3 syscall accidentally broke CLONE_PIDFD support in traditional clone syscall on compat x86 and those architectures that use do_fork to implement clone syscall. This bug was found by strace test suite. Link: https://strace.io/logs/strace/2019-07-12 Fixes: 7f192e3cd316 ("fork: add clone3") Bisected-and-tested-by: Anatoly Pugachev Signed-off-by: Dmitry V. Levin Link: https://lore.kernel.org/r/20190714162047.GB10389@altlinux.org Signed-off-by: Christian Brauner --- include/linux/sched/task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 109a0df5af39..0497091e40c1 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -89,6 +89,7 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern long _do_fork(struct kernel_clone_args *kargs); +extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); -- cgit v1.2.3 From 6dfc43d3a19174faead54575c204aee106225f43 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 15 Jul 2019 15:16:20 +1000 Subject: mm: adjust apply_to_pfn_range interface for dropped token. mm/pgtable: drop pgtable_t variable from pte_fn_t functions drops the token came in via the hmm tree, this caused lots of conflicts, but applying this cleanup patch should reduce it to something easier to handle. Just accept the token is unused at this point. Signed-off-by: Dave Airlie --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 798cdda9560e..c45f936bd81c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2687,7 +2687,7 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); struct pfn_range_apply; -typedef int (*pter_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, +typedef int (*pter_fn_t)(pte_t *pte, unsigned long addr, struct pfn_range_apply *closure); struct pfn_range_apply { struct mm_struct *mm; -- cgit v1.2.3 From dfd6f9ad36368b8dbd5f5a2b2f0a4705ae69a323 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Jul 2019 11:01:21 +0200 Subject: ACPI: fix false-positive -Wuninitialized warning clang gets confused by an uninitialized variable in what looks to it like a never executed code path: arch/x86/kernel/acpi/boot.c:618:13: error: variable 'polarity' is uninitialized when used here [-Werror,-Wuninitialized] polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH; ^~~~~~~~ arch/x86/kernel/acpi/boot.c:606:32: note: initialize the variable 'polarity' to silence this warning int rc, irq, trigger, polarity; ^ = 0 arch/x86/kernel/acpi/boot.c:617:12: error: variable 'trigger' is uninitialized when used here [-Werror,-Wuninitialized] trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE; ^~~~~~~ arch/x86/kernel/acpi/boot.c:606:22: note: initialize the variable 'trigger' to silence this warning int rc, irq, trigger, polarity; ^ = 0 This is unfortunately a design decision in clang and won't be fixed. Changing the acpi_get_override_irq() macro to an inline function reliably avoids the issue. Signed-off-by: Arnd Bergmann Reviewed-by: Andy Shevchenko Reviewed-by: Nathan Chancellor Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 451e7b544342..8309923eafe1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -324,7 +324,10 @@ struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else -#define acpi_get_override_irq(gsi, trigger, polarity) (-1) +static inline int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) +{ + return -1; +} #endif /* * This function undoes the effect of one call to acpi_register_gsi(). -- cgit v1.2.3 From 8da04e05cdfc715d414a1c5f8318c03030eb68fb Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 15 Jul 2019 09:56:30 +1000 Subject: intel_rapl: need linux/cpuhotplug.h for enum cpuhp_state Fixes: 7ebf8eff63b4 ("intel_rapl: introduce struct rapl_if_private") Signed-off-by: Stephen Rothwell Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 0c179d92d110..efb3ce892c20 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -12,6 +12,7 @@ #include #include +#include enum rapl_domain_type { RAPL_DOMAIN_PACKAGE, /* entire package/socket */ -- cgit v1.2.3 From 387b14684f94483cbbb72843db406ec9a8d0d6d2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 10 Apr 2019 08:32:41 -0300 Subject: docs: locking: convert docs to ReST and rename to *.rst Convert the locking documents to ReST and add them to the kernel development book where it belongs. Most of the stuff here is just to make Sphinx to properly parse the text file, as they're already in good shape, not requiring massive changes in order to be parsed. The conversion is actually: - add blank lines and identation in order to identify paragraphs; - fix tables markups; - add some lists markups; - mark literal blocks; - adjust title markups. At its new index.rst, let's add a :orphan: while this is not linked to the main index.rst file, in order to avoid build warnings. Signed-off-by: Mauro Carvalho Chehab Acked-by: Federico Vaga --- include/linux/lockdep.h | 2 +- include/linux/mutex.h | 2 +- include/linux/rwsem.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 57baa27f238c..0b0d7259276d 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -5,7 +5,7 @@ * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * - * see Documentation/locking/lockdep-design.txt for more details. + * see Documentation/locking/lockdep-design.rst for more details. */ #ifndef __LINUX_LOCKDEP_H #define __LINUX_LOCKDEP_H diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 3093dd162424..dcd03fee6e01 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -151,7 +151,7 @@ static inline bool mutex_is_locked(struct mutex *lock) /* * See kernel/locking/mutex.c for detailed documentation of these APIs. - * Also see Documentation/locking/mutex-design.txt. + * Also see Documentation/locking/mutex-design.rst. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index e401358c4e7e..9d9c663987d8 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -160,7 +160,7 @@ extern void downgrade_write(struct rw_semaphore *sem); * static then another method for expressing nested locking is * the explicit definition of lock class keys and the use of * lockdep_set_class() at lock initialization time. - * See Documentation/locking/lockdep-design.txt for more details.) + * See Documentation/locking/lockdep-design.rst for more details.) */ extern void down_read_nested(struct rw_semaphore *sem, int subclass); extern void down_write_nested(struct rw_semaphore *sem, int subclass); -- cgit v1.2.3 From 720594f691e5c8fb0624f3653b20b24ba8e57742 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 13 Apr 2019 22:54:53 -0300 Subject: docs: connector: convert to ReST and rename to connector.rst As it has some function definitions, move them to connector.h. The remaining conversion is actually: - add blank lines and identation in order to identify paragraphs; - fix tables markups; - add some lists markups; - mark literal blocks; - adjust title markups. At its new index.rst, let's add a :orphan: while this is not linked to the main index.rst file, in order to avoid build warnings. Signed-off-by: Mauro Carvalho Chehab --- include/linux/connector.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 62 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 1d72ef76f24f..6b6c7396a584 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -55,10 +55,71 @@ struct cn_dev { struct cn_queue_dev *cbdev; }; +/** + * cn_add_callback() - Registers new callback with connector core. + * + * @id: unique connector's user identifier. + * It must be registered in connector.h for legal + * in-kernel users. + * @name: connector's callback symbolic name. + * @callback: connector's callback. + * parameters are %cn_msg and the sender's credentials + */ int cn_add_callback(struct cb_id *id, const char *name, void (*callback)(struct cn_msg *, struct netlink_skb_parms *)); -void cn_del_callback(struct cb_id *); +/** + * cn_del_callback() - Unregisters new callback with connector core. + * + * @id: unique connector's user identifier. + */ +void cn_del_callback(struct cb_id *id); + + +/** + * cn_netlink_send_mult - Sends message to the specified groups. + * + * @msg: message header(with attached data). + * @len: Number of @msg to be sent. + * @portid: destination port. + * If non-zero the message will be sent to the given port, + * which should be set to the original sender. + * @group: destination group. + * If @portid and @group is zero, then appropriate group will + * be searched through all registered connector users, and + * message will be delivered to the group which was created + * for user with the same ID as in @msg. + * If @group is not zero, then message will be delivered + * to the specified group. + * @gfp_mask: GFP mask. + * + * It can be safely called from softirq context, but may silently + * fail under strong memory pressure. + * + * If there are no listeners for given group %-ESRCH can be returned. + */ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask); + +/** + * cn_netlink_send_mult - Sends message to the specified groups. + * + * @msg: message header(with attached data). + * @portid: destination port. + * If non-zero the message will be sent to the given port, + * which should be set to the original sender. + * @group: destination group. + * If @portid and @group is zero, then appropriate group will + * be searched through all registered connector users, and + * message will be delivered to the group which was created + * for user with the same ID as in @msg. + * If @group is not zero, then message will be delivered + * to the specified group. + * @gfp_mask: GFP mask. + * + * It can be safely called from softirq context, but may silently + * fail under strong memory pressure. + * + * If there are no listeners for given group %-ESRCH can be returned. + */ int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 group, gfp_t gfp_mask); int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name, -- cgit v1.2.3 From fe34c89d25429e079ba67416529514120dd715f8 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 18 Jun 2019 12:34:59 -0300 Subject: docs: driver-model: move it to the driver-api book The audience for the Kernel driver-model is clearly Kernel hackers. Signed-off-by: Mauro Carvalho Chehab Acked-by: Jeff Kirsher # ice driver changes --- include/linux/device.h | 2 +- include/linux/platform_device.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 5eabfa0c4dee..c330b75c6c57 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -6,7 +6,7 @@ * Copyright (c) 2004-2009 Greg Kroah-Hartman * Copyright (c) 2008-2009 Novell Inc. * - * See Documentation/driver-model/ for more information. + * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index beb25f277889..9bc36b589827 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -4,7 +4,7 @@ * * Copyright (c) 2001-2003 Patrick Mochel * - * See Documentation/driver-model/ for more information. + * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _PLATFORM_DEVICE_H_ -- cgit v1.2.3 From da82c92f1150f66afabf78d2c85ef9ac18dc6d38 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Jun 2019 13:08:35 -0300 Subject: docs: cgroup-v1: add it to the admin-guide book Those files belong to the admin guide, so add them. Signed-off-by: Mauro Carvalho Chehab --- include/linux/cgroup-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index c5311935239d..430e219e3aba 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -624,7 +624,7 @@ struct cftype { /* * Control Group subsystem type. - * See Documentation/cgroup-v1/cgroups.rst for details + * See Documentation/admin-guide/cgroup-v1/cgroups.rst for details */ struct cgroup_subsys { struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); -- cgit v1.2.3 From 4f4cfa6c560c93ba180c30675cf845e1597de44c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Jun 2019 14:56:51 -0300 Subject: docs: admin-guide: add a series of orphaned documents There are lots of documents that belong to the admin-guide but are on random places (most under Documentation root dir). Move them to the admin guide. Signed-off-by: Mauro Carvalho Chehab Acked-by: Alexandre Belloni Acked-by: Bartlomiej Zolnierkiewicz --- include/linux/hw_random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index c0b93e0ff0c0..8e6dd908da21 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -1,7 +1,7 @@ /* Hardware Random Number Generator - Please read Documentation/hw_random.txt for details on use. + Please read Documentation/admin-guide/hw_random.rst for details on use. ---------------------------------------------------------- This software may be used and distributed according to the terms -- cgit v1.2.3 From 65388dad1bbb51a4eb6cc91b9fa865b57646fb67 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Jun 2019 16:31:35 -0300 Subject: docs: serial: move it to the driver-api The contents of this directory is mostly driver-api stuff. Signed-off-by: Mauro Carvalho Chehab --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 05b179015d6c..2b78cc734719 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -32,7 +32,7 @@ struct device; /* * This structure describes all the operations that can be done on the - * physical hardware. See Documentation/serial/driver.rst for details. + * physical hardware. See Documentation/driver-api/serial/driver.rst for details. */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); -- cgit v1.2.3 From 7e4b4dfc98d54bc79f7ca29c8bc6307ed2948014 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 16 Jul 2019 04:06:29 +1000 Subject: Revert "mm: adjust apply_to_pfn_range interface for dropped token." This reverts commit 6dfc43d3a19174faead54575c204aee106225f43. Going to revert the whole vmwwgfx pull. Signed-off-by: Dave Airlie --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c45f936bd81c..798cdda9560e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2687,7 +2687,7 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); struct pfn_range_apply; -typedef int (*pter_fn_t)(pte_t *pte, unsigned long addr, +typedef int (*pter_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, struct pfn_range_apply *closure); struct pfn_range_apply { struct mm_struct *mm; -- cgit v1.2.3 From 3729fe2bc2a01f4cc1aa88be8f64af06084c87d6 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 16 Jul 2019 04:07:13 +1000 Subject: Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next" This reverts commit 031e610a6a21448a63dff7a0416e5e206724caac, reversing changes made to 52d2d44eee8091e740d0d275df1311fb8373c9a9. The mm changes in there we premature and not fully ack or reviewed by core mm folks, I dropped the ball by merging them via this tree, so lets take em all back out. Signed-off-by: Dave Airlie --- include/linux/mm.h | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 798cdda9560e..dd0b5f4e1e45 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2686,24 +2686,7 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -struct pfn_range_apply; -typedef int (*pter_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, - struct pfn_range_apply *closure); -struct pfn_range_apply { - struct mm_struct *mm; - pter_fn_t ptefn; - unsigned int alloc; -}; -extern int apply_to_pfn_range(struct pfn_range_apply *closure, - unsigned long address, unsigned long size); -unsigned long apply_as_wrprotect(struct address_space *mapping, - pgoff_t first_index, pgoff_t nr); -unsigned long apply_as_clean(struct address_space *mapping, - pgoff_t first_index, pgoff_t nr, - pgoff_t bitmap_pgoff, - unsigned long *bitmap, - pgoff_t *start, - pgoff_t *end); + #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); -- cgit v1.2.3 From b43995469e5804636a55372e9bbb17ccb22441c5 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 15 Jul 2019 09:39:52 -0700 Subject: bpf: rename bpf_ctx_wide_store_ok to bpf_ctx_wide_access_ok Rename bpf_ctx_wide_store_ok to bpf_ctx_wide_access_ok to indicate that it can be used for both loads and stores. Cc: Yonghong Song Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6d944369ca87..ff65d22cf336 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -747,7 +747,7 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } -#define bpf_ctx_wide_store_ok(off, size, type, field) \ +#define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ -- cgit v1.2.3 From c4dcc8a162784c1f827c7f6d8409598f19708fe6 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 16 Jul 2019 09:36:08 +0530 Subject: cpufreq: Make cpufreq_generic_init() return void It always returns 0 (success) and its return type should really be void. Over that, many drivers have added error handling code based on its return value, which is not required at all. Change its return type to void and update all the callers. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index afc683021ac5..441ff15b7768 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -995,7 +995,7 @@ extern struct freq_attr *cpufreq_generic_attr[]; int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy); unsigned int cpufreq_generic_get(unsigned int cpu); -int cpufreq_generic_init(struct cpufreq_policy *policy, +void cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency); #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From 46710f3a34b592ac5c51a95f696b2d2a2a0d9419 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 25 May 2019 09:57:59 -0700 Subject: tracing: Pass type into tracing_generic_entry_update() All callers of tracing_generic_entry_update() have to initialize entry->type, so let's just simply move it inside. Link: http://lkml.kernel.org/r/20190525165802.25944-2-xiyou.wangcong@gmail.com Cc: Ingo Molnar Signed-off-by: Cong Wang Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8a62731673f7..5c6f2a6c8cd2 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -142,6 +142,7 @@ enum print_line_t { enum print_line_t trace_handle_return(struct trace_seq *s); void tracing_generic_entry_update(struct trace_entry *entry, + unsigned short type, unsigned long flags, int pc); struct trace_event_file; -- cgit v1.2.3 From 0aeb1def44169cbe7119f26cf10b974a2046142e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 25 May 2019 09:58:01 -0700 Subject: tracing: Make trace_get_fields() global trace_get_fields() is the only way to read tracepoint fields at run time, as their fields are defined at compile-time with macros. Make this function visible to all users and it will be used by trace event injection code to calculate the size of a tracepoint entry. Link: http://lkml.kernel.org/r/20190525165802.25944-4-xiyou.wangcong@gmail.com Cc: Ingo Molnar Signed-off-by: Cong Wang Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 5c6f2a6c8cd2..5150436783e8 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -318,6 +318,14 @@ trace_event_name(struct trace_event_call *call) return call->name; } +static inline struct list_head * +trace_get_fields(struct trace_event_call *event_call) +{ + if (!event_call->class->get_fields) + return &event_call->class->fields; + return event_call->class->get_fields(event_call); +} + struct trace_array; struct trace_subsystem_dir; -- cgit v1.2.3 From 9087c37584fb7d8315877bb55f85e4268cc0b4f4 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Wed, 10 Jul 2019 19:01:19 +0000 Subject: dma-direct: Force unencrypted DMA under SME for certain DMA masks If a device doesn't support DMA to a physical address that includes the encryption bit (currently bit 47, so 48-bit DMA), then the DMA must occur to unencrypted memory. SWIOTLB is used to satisfy that requirement if an IOMMU is not active (enabled or configured in passthrough mode). However, commit fafadcd16595 ("swiotlb: don't dip into swiotlb pool for coherent allocations") modified the coherent allocation support in SWIOTLB to use the DMA direct coherent allocation support. When an IOMMU is not active, this resulted in dma_alloc_coherent() failing for devices that didn't support DMA addresses that included the encryption bit. Addressing this requires changes to the force_dma_unencrypted() function in kernel/dma/direct.c. Since the function is now non-trivial and SME/SEV specific, update the DMA direct support to add an arch override for the force_dma_unencrypted() function. The arch override is selected when CONFIG_AMD_MEM_ENCRYPT is set. The arch override function resides in the arch/x86/mm/mem_encrypt.c file and forces unencrypted DMA when either SEV is active or SME is active and the device does not support DMA to physical addresses that include the encryption bit. Fixes: fafadcd16595 ("swiotlb: don't dip into swiotlb pool for coherent allocations") Suggested-by: Christoph Hellwig Signed-off-by: Tom Lendacky Acked-by: Thomas Gleixner [hch: moved the force_dma_unencrypted declaration to dma-mapping.h, fold the s390 fix from Halil Pasic] Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index b7338702592a..adf993a3bd58 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -32,6 +32,15 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ +#ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED +bool force_dma_unencrypted(struct device *dev); +#else +static inline bool force_dma_unencrypted(struct device *dev) +{ + return false; +} +#endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */ + /* * If memory encryption is supported, phys_to_dma will set the memory encryption * bit in the DMA address, and dma_to_phys will clear it. The raw __phys_to_dma -- cgit v1.2.3 From 89165b8b0ee97bd775ac4376b932fd030f7462bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 16 Jul 2019 16:26:30 -0700 Subject: mm: provide a print_vma_addr stub for !CONFIG_MMU Link: http://lkml.kernel.org/r/20190703122359.18200-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Vladimir Murzin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0389c34ac529..74797ed20c2c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2767,7 +2767,13 @@ extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); +#ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); +#else +static inline void print_vma_addr(char *prefix, unsigned long rip) +{ +} +#endif void *sparse_buffer_alloc(unsigned long size); struct page *sparse_mem_map_populate(unsigned long pnum, int nid, -- cgit v1.2.3 From 9b98fa22948551e20a15b0b9d22589e3724c361a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 16 Jul 2019 16:26:33 -0700 Subject: mm: stub out all of swapops.h for !CONFIG_MMU The whole header file deals with swap entries and PTEs, none of which can exist for nommu builds. The current nommu ports have lots of stubs to allow the inline functions in swapops.h to compile, but as none of this functionality is actually used there is no point in even providing it. This way we don't have to provide the stubs for the upcoming RISC-V nommu port, and can eventually remove it from the existing ports. Link: http://lkml.kernel.org/r/20190703122359.18200-4-hch@lst.de Signed-off-by: Christoph Hellwig Cc: Vladimir Murzin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 15bdb6fe71e5..877fd239b6ff 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -6,6 +6,8 @@ #include #include +#ifdef CONFIG_MMU + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in @@ -50,13 +52,11 @@ static inline pgoff_t swp_offset(swp_entry_t entry) return entry.val & SWP_OFFSET_MASK; } -#ifdef CONFIG_MMU /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } -#endif /* * Convert the arch-dependent pte representation of a swp_entry_t into an @@ -360,4 +360,5 @@ static inline int non_swap_entry(swp_entry_t entry) } #endif +#endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ -- cgit v1.2.3 From ce251e0e3c0597ea8cab5787df579bd1f9c1aca1 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 16 Jul 2019 16:26:42 -0700 Subject: include/linux/kernel.h: add typeof_member() macro Add typeof_member() macro so that types can be extracted without introducing dummy variables. Link: http://lkml.kernel.org/r/20190529190720.GA5703@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 0c9bc231107f..4fa360a13c1e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -88,6 +88,8 @@ */ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) +#define typeof_member(T, m) typeof(((T*)0)->m) + #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_DOWN_ULL(ll, d) \ -- cgit v1.2.3 From 95b980d62d52c4c1768ee719e8db3efe27ef52b2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 16 Jul 2019 16:26:57 -0700 Subject: linux/bits.h: make BIT(), GENMASK(), and friends available in assembly BIT(), GENMASK(), etc. are useful to define register bits of hardware. However, low-level code is often written in assembly, where they are not available due to the hard-coded 1UL, 0UL. In fact, in-kernel headers such as arch/arm64/include/asm/sysreg.h use _BITUL() instead of BIT() so that the register bit macros are available in assembly. Using macros in include/uapi/linux/const.h have two reasons: [1] For use in uapi headers We should use underscore-prefixed variants for user-space. [2] For use in assembly code Since _BITUL() uses UL(1) instead of 1UL, it can be used as an alternative of BIT(). For [2], it is pretty easy to change BIT() etc. for use in assembly. This allows to replace _BUTUL() in kernel-space headers with BIT(). Link: http://lkml.kernel.org/r/20190609153941.17249-1-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bits.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bits.h b/include/linux/bits.h index 2b7b532c1d51..669d69441a62 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -1,13 +1,15 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BITS_H #define __LINUX_BITS_H + +#include #include -#define BIT(nr) (1UL << (nr)) -#define BIT_ULL(nr) (1ULL << (nr)) -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT(nr) (UL(1) << (nr)) +#define BIT_ULL(nr) (ULL(1) << (nr)) +#define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG)) #define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) #define BITS_PER_BYTE 8 @@ -17,10 +19,11 @@ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ #define GENMASK(h, l) \ - (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + (((~UL(0)) - (UL(1) << (l)) + 1) & \ + (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ - (((~0ULL) - (1ULL << (l)) + 1) & \ - (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ + (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) #endif /* __LINUX_BITS_H */ -- cgit v1.2.3 From 4c6080cd6f8baad9f7faa3deac9a90e59726b119 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 16 Jul 2019 16:27:12 -0700 Subject: lib/list: tweak LIST_POISON2 for better code generation on x86_64 list_del() poisoning can generate 2 64-bit immediate loads but it also can generate one 64-bit immediate load and an addition: 48 b8 00 01 00 00 00 00 ad de movabs rax,0xdead000000000100 48 89 47 58 mov QWORD PTR [rdi+0x58],rax 48 05 00 01 00 00 <=====> add rax,0x100 48 89 47 60 mov QWORD PTR [rdi+0x60],rax However on x86_64 not all constants are equal: those within [-128, 127] range can be added with shorter "add r64, imm32" instruction: 48 b8 00 01 00 00 00 00 ad de movabs rax,0xdead000000000100 48 89 47 58 mov QWORD PTR [rdi+0x58],rax 48 83 c0 22 <======> add rax,0x22 48 89 47 60 mov QWORD PTR [rdi+0x60],rax Patch saves 2 bytes per some LIST_POISON2 usage. (Slightly disappointing) space savings on F29 x86_64 config: add/remove: 0/0 grow/shrink: 0/2164 up/down: 0/-5184 (-5184) Function old new delta zstd_get_workspace 548 546 -2 ... mlx4_delete_all_resources_for_slave 4826 4804 -22 Total: Before=83304131, After=83298947, chg -0.01% New constants are: 0xdead000000000100 0xdead000000000122 Note: LIST_POISON1 can't be changed to ...11 because something in page allocator requires low bit unset. Link: http://lkml.kernel.org/r/20190513191502.GA8492@avx2 Signed-off-by: Alexey Dobriyan Cc: Vasiliy Kulikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/poison.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/poison.h b/include/linux/poison.h index d6d980a681c7..df34330b4e34 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -21,7 +21,7 @@ * non-initialized list entries. */ #define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA) -#define LIST_POISON2 ((void *) 0x200 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x122 + POISON_POINTER_DELTA) /********** include/linux/timer.h **********/ /* -- cgit v1.2.3 From 0f472d04f59ff89d15b2a1c4eafde7317ddd67a2 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 16 Jul 2019 16:27:33 -0700 Subject: mm/ioremap: probe platform for p4d huge map support Finish up what commit c2febafc6773 ("mm: convert generic code to 5-level paging") started while levelling up P4D huge mapping support at par with PUD and PMD. A new arch call back arch_ioremap_p4d_supported() is added which just maintains status quo (P4D huge map not supported) on x86, arm64 and powerpc. When HAVE_ARCH_HUGE_VMAP is enabled its just a simple check from the arch about the support, hence runtime effects are minimal. Link: http://lkml.kernel.org/r/1561699231-20991-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: Thomas Gleixner Acked-by: Michael Ellerman (powerpc) Cc: Catalin Marinas Cc: Will Deacon Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 9876e5801a9d..accac822336a 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -33,6 +33,7 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end, #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP void __init ioremap_huge_init(void); +int arch_ioremap_p4d_supported(void); int arch_ioremap_pud_supported(void); int arch_ioremap_pmd_supported(void); #else -- cgit v1.2.3 From 9f973cb38088e0cf42e0bae97ff140813e623f13 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Tue, 16 Jul 2019 16:27:45 -0700 Subject: lib/rbtree: avoid generating code twice for the cached versions As was already noted in rbtree.h, the logic to cache rb_first (or rb_last) can easily be implemented externally to the core rbtree api. Change the implementation to do just that. Previously the update of rb_leftmost was wired deeper into the implmentation, but there were some disadvantages to that - mostly, lib/rbtree.c had separate instantiations for rb_insert_color() vs rb_insert_color_cached(), as well as rb_erase() vs rb_erase_cached(), which were doing exactly the same thing save for the rb_leftmost update at the start of either function. text data bss dec hex filename 5405 120 0 5525 1595 lib/rbtree.o-vanilla 3827 96 0 3923 f53 lib/rbtree.o-patch [dave@stgolabs.net: changelog addition] Link: http://lkml.kernel.org/r/20190628171416.by5gdizl3rcxk5h5@linux-r8p5 [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20190628045008.39926-1-walken@google.com Signed-off-by: Michel Lespinasse Acked-by: Davidlohr Bueso Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree.h | 70 ++++++++++++++++++++++++++-------------- include/linux/rbtree_augmented.h | 27 ++++++---------- 2 files changed, 56 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index e6337fce08f2..1fd61a9af45c 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -32,25 +32,9 @@ struct rb_root { struct rb_node *rb_node; }; -/* - * Leftmost-cached rbtrees. - * - * We do not cache the rightmost node based on footprint - * size vs number of potential users that could benefit - * from O(1) rb_last(). Just not worth it, users that want - * this feature can always implement the logic explicitly. - * Furthermore, users that want to cache both pointers may - * find it a bit asymmetric, but that's ok. - */ -struct rb_root_cached { - struct rb_root rb_root; - struct rb_node *rb_leftmost; -}; - #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } -#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) @@ -72,12 +56,6 @@ extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); -extern void rb_insert_color_cached(struct rb_node *, - struct rb_root_cached *, bool); -extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *); -/* Same as rb_first(), but O(1) */ -#define rb_first_cached(root) (root)->rb_leftmost - /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); @@ -87,8 +65,6 @@ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root); -extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, - struct rb_root_cached *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) @@ -136,4 +112,50 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent typeof(*pos), field); 1; }); \ pos = n) +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; + +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } + +/* Same as rb_first(), but O(1) */ +#define rb_first_cached(root) (root)->rb_leftmost + +static inline void rb_insert_color_cached(struct rb_node *node, + struct rb_root_cached *root, + bool leftmost) +{ + if (leftmost) + root->rb_leftmost = node; + rb_insert_color(node, &root->rb_root); +} + +static inline void rb_erase_cached(struct rb_node *node, + struct rb_root_cached *root) +{ + if (root->rb_leftmost == node) + root->rb_leftmost = rb_next(node); + rb_erase(node, &root->rb_root); +} + +static inline void rb_replace_node_cached(struct rb_node *victim, + struct rb_node *new, + struct rb_root_cached *root) +{ + if (root->rb_leftmost == victim) + root->rb_leftmost = new; + rb_replace_node(victim, new, &root->rb_root); +} + #endif /* _LINUX_RBTREE_H */ diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 0f902ccb48b0..179faab29f52 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -30,10 +30,9 @@ struct rb_augment_callbacks { void (*rotate)(struct rb_node *old, struct rb_node *new); }; -extern void __rb_insert_augmented(struct rb_node *node, - struct rb_root *root, - bool newleft, struct rb_node **leftmost, +extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); + /* * Fixup the rbtree and update the augmented information when rebalancing. * @@ -48,7 +47,7 @@ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, root, false, NULL, augment->rotate); + __rb_insert_augmented(node, root, augment->rotate); } static inline void @@ -56,8 +55,9 @@ rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, &root->rb_root, - newleft, &root->rb_leftmost, augment->rotate); + if (newleft) + root->rb_leftmost = node; + rb_insert_augmented(node, &root->rb_root, augment); } #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \ @@ -150,7 +150,6 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, - struct rb_node **leftmost, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; @@ -158,9 +157,6 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, struct rb_node *parent, *rebalance; unsigned long pc; - if (leftmost && node == *leftmost) - *leftmost = rb_next(node); - if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) @@ -260,8 +256,7 @@ static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, root, - NULL, augment); + struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } @@ -270,11 +265,9 @@ static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root, - &root->rb_leftmost, - augment); - if (rebalance) - __rb_erase_color(rebalance, &root->rb_root, augment->rotate); + if (root->rb_leftmost == node) + root->rb_leftmost = rb_next(node); + rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ -- cgit v1.2.3 From b98cca444d287a63dd96df04af7fb9793567599e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 16 Jul 2019 16:28:00 -0700 Subject: mm, kprobes: generalize and rename notify_page_fault() as kprobe_page_fault() Architectures which support kprobes have very similar boilerplate around calling kprobe_fault_handler(). Use a helper function in kprobes.h to unify them, based on the x86 code. This changes the behaviour for other architectures when preemption is enabled. Previously, they would have disabled preemption while calling the kprobe handler. However, preemption would be disabled if this fault was due to a kprobe, so we know the fault was not due to a kprobe handler and can simply return failure. This behaviour was introduced in commit a980c0ef9f6d ("x86/kprobes: Refactor kprobes_fault() like kprobe_exceptions_notify()") [anshuman.khandual@arm.com: export kprobe_fault_handler()] Link: http://lkml.kernel.org/r/1561133358-8876-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r/1560420444-25737-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Dave Hansen Cc: Michal Hocko Cc: Matthew Wilcox Cc: Mark Rutland Cc: Christophe Leroy Cc: Stephen Rothwell Cc: Andrey Konovalov Cc: Michael Ellerman Cc: Paul Mackerras Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Tony Luck Cc: Fenghua Yu Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Yoshinori Sato Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Andy Lutomirski Cc: Vineet Gupta Cc: James Hogan Cc: Paul Burton Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 443d9800ca3f..04bdaf01112c 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -458,4 +458,23 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) } #endif +/* Returns true if kprobes handled the fault */ +static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs, + unsigned int trap) +{ + if (!kprobes_built_in()) + return false; + if (user_mode(regs)) + return false; + /* + * To be potentially processing a kprobe fault and to be allowed + * to call kprobe_running(), we have to be non-preemptible. + */ + if (preemptible()) + return false; + if (!kprobe_running()) + return false; + return kprobe_fault_handler(regs, trap); +} + #endif /* _LINUX_KPROBES_H */ -- cgit v1.2.3 From f90fb3c7e2c13ae829db2274b88b845a75038b8a Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Tue, 16 Jul 2019 16:28:10 -0700 Subject: uapi linux/coda_psdev.h: move upc_req definition from uapi to kernel side headers Only users of upc_req in kernel side fs/coda/psdev.c and fs/coda/upcall.c already include linux/coda_psdev.h. Suggested by Jan Harkes in https://lore.kernel.org/lkml/20150531111913.GA23377@cs.cmu.edu/ Fixes these include/uapi/linux/coda_psdev.h compilation errors in userspace: linux/coda_psdev.h:12:19: error: field `uc_chain' has incomplete type struct list_head uc_chain; ^ linux/coda_psdev.h:13:2: error: unknown type name `caddr_t' caddr_t uc_data; ^ linux/coda_psdev.h:14:2: error: unknown type name `u_short' u_short uc_flags; ^ linux/coda_psdev.h:15:2: error: unknown type name `u_short' u_short uc_inSize; /* Size is at most 5000 bytes */ ^ linux/coda_psdev.h:16:2: error: unknown type name `u_short' u_short uc_outSize; ^ linux/coda_psdev.h:17:2: error: unknown type name `u_short' u_short uc_opcode; /* copied from data to save lookup */ ^ linux/coda_psdev.h:19:2: error: unknown type name `wait_queue_head_t' wait_queue_head_t uc_sleep; /* process' wait queue */ ^ Link: http://lkml.kernel.org/r/9f99f5ce6a0563d5266e6cf7aa9585aac2cae971.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Mikko Rapeli Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda_psdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index 15170954aa2b..57d2b2faf6a3 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -19,6 +19,17 @@ struct venus_comm { struct mutex vc_mutex; }; +/* messages between coda filesystem in kernel and Venus */ +struct upc_req { + struct list_head uc_chain; + caddr_t uc_data; + u_short uc_flags; + u_short uc_inSize; /* Size is at most 5000 bytes */ + u_short uc_outSize; + u_short uc_opcode; /* copied from data to save lookup */ + int uc_unique; + wait_queue_head_t uc_sleep; /* process' wait queue */ +}; static inline struct venus_comm *coda_vcp(struct super_block *sb) { -- cgit v1.2.3 From 6e51f8aa76b67d0a6eb168fd41a81e8478ae07a9 Mon Sep 17 00:00:00 2001 From: Jan Harkes Date: Tue, 16 Jul 2019 16:28:16 -0700 Subject: coda: potential buffer overflow in coda_psdev_write() Add checks to make sure the downcall message we got from the Coda cache manager is large enough to contain the data it is supposed to have. i.e. when we get a CODA_ZAPDIR we can access &out->coda_zapdir.CodaFid. Link: http://lkml.kernel.org/r/894fb6b250add09e4e3935f14649f21284a5cb18.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Jan Harkes Reported-by: Dan Carpenter Cc: Arnd Bergmann Cc: Colin Ian King Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda_psdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index 57d2b2faf6a3..d1672fd5e638 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -71,7 +71,8 @@ int venus_symlink(struct super_block *sb, struct CodaFid *fid, int venus_access(struct super_block *sb, struct CodaFid *fid, int mask); int venus_pioctl(struct super_block *sb, struct CodaFid *fid, unsigned int cmd, struct PioctlData *data); -int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out); +int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out, + size_t nbytes); int venus_fsync(struct super_block *sb, struct CodaFid *fid); int venus_statfs(struct dentry *dentry, struct kstatfs *sfs); -- cgit v1.2.3 From b2a57e334086602be56b74958d9f29b955cd157f Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Tue, 16 Jul 2019 16:28:20 -0700 Subject: coda: fix build using bare-metal toolchain The kernel is self-contained project and can be built with bare-metal toolchain. But bare-metal toolchain doesn't define __linux__. Because of this u_quad_t type is not defined when using bare-metal toolchain and codafs build fails. This patch fixes it by defining u_quad_t type unconditionally. Link: http://lkml.kernel.org/r/3cbb40b0a57b6f9923a9d67b53473c0b691a3eaa.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Sam Protsenko Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coda.h b/include/linux/coda.h index d30209b9cef8..0ca0c83fdb1c 100644 --- a/include/linux/coda.h +++ b/include/linux/coda.h @@ -58,8 +58,7 @@ Mellon the rights to redistribute these changes without encumbrance. #ifndef _CODA_HEADER_ #define _CODA_HEADER_ -#if defined(__linux__) typedef unsigned long long u_quad_t; -#endif + #include #endif -- cgit v1.2.3 From 2fe7491d219428a32f09948e88bfaf8e71b9a66b Mon Sep 17 00:00:00 2001 From: Jan Harkes Date: Tue, 16 Jul 2019 16:28:26 -0700 Subject: uapi linux/coda_psdev.h: move CODA_REQ_ from uapi to kernel side headers These constants only used internally and not exposed to userspace. Link: http://lkml.kernel.org/r/baeafc30dad70d8b422ee679420099c2d8aa7da0.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda_psdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h index d1672fd5e638..9487f792770c 100644 --- a/include/linux/coda_psdev.h +++ b/include/linux/coda_psdev.h @@ -31,6 +31,11 @@ struct upc_req { wait_queue_head_t uc_sleep; /* process' wait queue */ }; +#define CODA_REQ_ASYNC 0x1 +#define CODA_REQ_READ 0x2 +#define CODA_REQ_WRITE 0x4 +#define CODA_REQ_ABORT 0x8 + static inline struct venus_comm *coda_vcp(struct super_block *sb) { return (struct venus_comm *)((sb)->s_fs_info); -- cgit v1.2.3 From 8fc8b9df831387e0d02c1d0f5bb53d327e0d477a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 16 Jul 2019 16:28:47 -0700 Subject: coda: move internal defs out of include/linux/ [ver #2] Move include/linux/coda_psdev.h to fs/coda/ as there's nothing else that uses it. Link: http://lkml.kernel.org/r/3ceeee0415a929b89fb02700b6b4b3a07938acb8.1558117389.git.jaharkes@cs.cmu.edu Link: https://patchwork.kernel.org/patch/10590257/ Signed-off-by: David Howells Signed-off-by: Jan Harkes Cc: Yann Droneaud Cc: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/coda_psdev.h | 89 ---------------------------------------------- 1 file changed, 89 deletions(-) delete mode 100644 include/linux/coda_psdev.h (limited to 'include/linux') diff --git a/include/linux/coda_psdev.h b/include/linux/coda_psdev.h deleted file mode 100644 index 9487f792770c..000000000000 --- a/include/linux/coda_psdev.h +++ /dev/null @@ -1,89 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __CODA_PSDEV_H -#define __CODA_PSDEV_H - -#include -#include -#include - -struct kstatfs; - -/* communication pending/processing queues */ -struct venus_comm { - u_long vc_seq; - wait_queue_head_t vc_waitq; /* Venus wait queue */ - struct list_head vc_pending; - struct list_head vc_processing; - int vc_inuse; - struct super_block *vc_sb; - struct mutex vc_mutex; -}; - -/* messages between coda filesystem in kernel and Venus */ -struct upc_req { - struct list_head uc_chain; - caddr_t uc_data; - u_short uc_flags; - u_short uc_inSize; /* Size is at most 5000 bytes */ - u_short uc_outSize; - u_short uc_opcode; /* copied from data to save lookup */ - int uc_unique; - wait_queue_head_t uc_sleep; /* process' wait queue */ -}; - -#define CODA_REQ_ASYNC 0x1 -#define CODA_REQ_READ 0x2 -#define CODA_REQ_WRITE 0x4 -#define CODA_REQ_ABORT 0x8 - -static inline struct venus_comm *coda_vcp(struct super_block *sb) -{ - return (struct venus_comm *)((sb)->s_fs_info); -} - -/* upcalls */ -int venus_rootfid(struct super_block *sb, struct CodaFid *fidp); -int venus_getattr(struct super_block *sb, struct CodaFid *fid, - struct coda_vattr *attr); -int venus_setattr(struct super_block *, struct CodaFid *, struct coda_vattr *); -int venus_lookup(struct super_block *sb, struct CodaFid *fid, - const char *name, int length, int *type, - struct CodaFid *resfid); -int venus_close(struct super_block *sb, struct CodaFid *fid, int flags, - kuid_t uid); -int venus_open(struct super_block *sb, struct CodaFid *fid, int flags, - struct file **f); -int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid, - const char *name, int length, - struct CodaFid *newfid, struct coda_vattr *attrs); -int venus_create(struct super_block *sb, struct CodaFid *dirfid, - const char *name, int length, int excl, int mode, - struct CodaFid *newfid, struct coda_vattr *attrs) ; -int venus_rmdir(struct super_block *sb, struct CodaFid *dirfid, - const char *name, int length); -int venus_remove(struct super_block *sb, struct CodaFid *dirfid, - const char *name, int length); -int venus_readlink(struct super_block *sb, struct CodaFid *fid, - char *buffer, int *length); -int venus_rename(struct super_block *, struct CodaFid *new_fid, - struct CodaFid *old_fid, size_t old_length, - size_t new_length, const char *old_name, - const char *new_name); -int venus_link(struct super_block *sb, struct CodaFid *fid, - struct CodaFid *dirfid, const char *name, int len ); -int venus_symlink(struct super_block *sb, struct CodaFid *fid, - const char *name, int len, const char *symname, int symlen); -int venus_access(struct super_block *sb, struct CodaFid *fid, int mask); -int venus_pioctl(struct super_block *sb, struct CodaFid *fid, - unsigned int cmd, struct PioctlData *data); -int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out, - size_t nbytes); -int venus_fsync(struct super_block *sb, struct CodaFid *fid); -int venus_statfs(struct dentry *dentry, struct kstatfs *sfs); - -/* - * Statistics - */ - -extern struct venus_comm coda_comms[]; -#endif -- cgit v1.2.3 From 201766a20e30f982ccfe36bebfad9602c3ff574a Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Tue, 16 Jul 2019 16:29:42 -0700 Subject: ptrace: add PTRACE_GET_SYSCALL_INFO request PTRACE_GET_SYSCALL_INFO is a generic ptrace API that lets ptracer obtain details of the syscall the tracee is blocked in. There are two reasons for a special syscall-related ptrace request. Firstly, with the current ptrace API there are cases when ptracer cannot retrieve necessary information about syscalls. Some examples include: * The notorious int-0x80-from-64-bit-task issue. See [1] for details. In short, if a 64-bit task performs a syscall through int 0x80, its tracer has no reliable means to find out that the syscall was, in fact, a compat syscall, and misidentifies it. * Syscall-enter-stop and syscall-exit-stop look the same for the tracer. Common practice is to keep track of the sequence of ptrace-stops in order not to mix the two syscall-stops up. But it is not as simple as it looks; for example, strace had a (just recently fixed) long-standing bug where attaching strace to a tracee that is performing the execve system call led to the tracer identifying the following syscall-exit-stop as syscall-enter-stop, which messed up all the state tracking. * Since the introduction of commit 84d77d3f06e7 ("ptrace: Don't allow accessing an undumpable mm"), both PTRACE_PEEKDATA and process_vm_readv become unavailable when the process dumpable flag is cleared. On such architectures as ia64 this results in all syscall arguments being unavailable for the tracer. Secondly, ptracers also have to support a lot of arch-specific code for obtaining information about the tracee. For some architectures, this requires a ptrace(PTRACE_PEEKUSER, ...) invocation for every syscall argument and return value. ptrace(2) man page: long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data); ... PTRACE_GET_SYSCALL_INFO Retrieve information about the syscall that caused the stop. The information is placed into the buffer pointed by "data" argument, which should be a pointer to a buffer of type "struct ptrace_syscall_info". The "addr" argument contains the size of the buffer pointed to by "data" argument (i.e., sizeof(struct ptrace_syscall_info)). The return value contains the number of bytes available to be written by the kernel. If the size of data to be written by the kernel exceeds the size specified by "addr" argument, the output is truncated. [ldv@altlinux.org: selftests/seccomp/seccomp_bpf: update for PTRACE_GET_SYSCALL_INFO] Link: http://lkml.kernel.org/r/20190708182904.GA12332@altlinux.org Link: http://lkml.kernel.org/r/20190510152842.GF28558@altlinux.org Signed-off-by: Elvira Khabirova Co-developed-by: Dmitry V. Levin Signed-off-by: Dmitry V. Levin Reviewed-by: Oleg Nesterov Reviewed-by: Kees Cook Reviewed-by: Andy Lutomirski Cc: Eugene Syromyatnikov Cc: Benjamin Herrenschmidt Cc: Greentime Hu Cc: Helge Deller [parisc] Cc: James E.J. Bottomley Cc: James Hogan Cc: kbuild test robot Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Ralf Baechle Cc: Richard Kuo Cc: Shuah Khan Cc: Vincent Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8446573cc682..36fb3bbed6b2 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -54,13 +54,15 @@ struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ -static inline int ptrace_report_syscall(struct pt_regs *regs) +static inline int ptrace_report_syscall(struct pt_regs *regs, + unsigned long message) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; + current->ptrace_message = message; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* @@ -73,6 +75,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) current->exit_code = 0; } + current->ptrace_message = 0; return fatal_signal_pending(current); } @@ -98,7 +101,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { - return ptrace_report_syscall(regs); + return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** @@ -123,7 +126,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) if (step) user_single_step_report(regs); else - ptrace_report_syscall(regs); + ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); } /** -- cgit v1.2.3 From e2d9018e81ba9357d3bb8bddc0ee58d460d092fe Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 16 Jul 2019 16:29:50 -0700 Subject: signal: reorder struct sighand_struct struct sighand_struct::siglock field is the most used field by far, put it first so that is can be accessed without IMM8 or IMM32 encoding on x86_64. Space savings (on trimmed down VM test config): add/remove: 0/0 grow/shrink: 8/68 up/down: 49/-1147 (-1098) Function old new delta complete_signal 512 533 +21 do_signalfd4 335 346 +11 __cleanup_sighand 39 43 +4 unhandled_signal 49 52 +3 prepare_signal 692 695 +3 ignore_signals 37 40 +3 __tty_check_change.part 248 251 +3 ksys_unshare 780 781 +1 sighand_ctor 33 29 -4 ptrace_trap_notify 60 56 -4 sigqueue_free 98 91 -7 run_posix_cpu_timers 1389 1382 -7 proc_pid_status 2448 2441 -7 proc_pid_limits 344 337 -7 posix_cpu_timer_rearm 222 215 -7 posix_cpu_timer_get 249 242 -7 kill_pid_info_as_cred 243 236 -7 freeze_task 197 190 -7 flush_old_exec 1873 1866 -7 do_task_stat 3363 3356 -7 do_send_sig_info 98 91 -7 do_group_exit 147 140 -7 init_sighand 2088 2080 -8 do_notify_parent_cldstop 399 391 -8 signalfd_cleanup 50 41 -9 do_notify_parent 557 545 -12 __send_signal 1029 1017 -12 ptrace_stop 590 577 -13 get_signal 1576 1563 -13 __lock_task_sighand 112 99 -13 zap_pid_ns_processes 391 377 -14 update_rlimit_cpu 78 64 -14 tty_signal_session_leader 413 399 -14 tty_open_proc_set_tty 149 135 -14 tty_jobctrl_ioctl 936 922 -14 set_cpu_itimer 339 325 -14 ptrace_resume 226 212 -14 ptrace_notify 110 96 -14 proc_clear_tty 81 67 -14 posix_cpu_timer_del 229 215 -14 kernel_sigaction 156 142 -14 getrusage 977 963 -14 get_current_tty 98 84 -14 force_sigsegv 89 75 -14 force_sig_info 205 191 -14 flush_signals 83 69 -14 flush_itimer_signals 85 71 -14 do_timer_create 1120 1106 -14 do_sigpending 88 74 -14 do_signal_stop 537 523 -14 cgroup_init_fs_context 644 630 -14 call_usermodehelper_exec_async 402 388 -14 calculate_sigpending 58 44 -14 __x64_sys_timer_delete 248 234 -14 __set_current_blocked 80 66 -14 __ptrace_unlink 310 296 -14 __ptrace_detach.part 187 173 -14 send_sigqueue 362 347 -15 get_cpu_itimer 214 199 -15 signalfd_poll 175 159 -16 dequeue_signal 340 323 -17 do_getitimer 192 174 -18 release_task.part 1060 1040 -20 ptrace_peek_siginfo 408 387 -21 posix_cpu_timer_set 827 806 -21 exit_signals 437 416 -21 do_sigaction 541 520 -21 do_setitimer 485 464 -21 disassociate_ctty.part 545 517 -28 __x64_sys_rt_sigtimedwait 721 679 -42 __x64_sys_ptrace 1319 1277 -42 ptrace_request 1828 1782 -46 signalfd_read 507 459 -48 wait_consider_task 2027 1971 -56 do_coredump 3672 3616 -56 copy_process.part 6936 6871 -65 Link: http://lkml.kernel.org/r/20190503192800.GA18004@avx2 Signed-off-by: Alexey Dobriyan Cc: Michal Hocko Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/signal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 532458698bde..01add55a609b 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -15,10 +15,10 @@ */ struct sighand_struct { - refcount_t count; - struct k_sigaction action[_NSIG]; spinlock_t siglock; + refcount_t count; wait_queue_head_t signalfd_wqh; + struct k_sigaction action[_NSIG]; }; /* -- cgit v1.2.3 From b772434be0891ed1081a08ae7cfd4666728f8e82 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 16 Jul 2019 16:29:53 -0700 Subject: signal: simplify set_user_sigmask/restore_user_sigmask task->saved_sigmask and ->restore_sigmask are only used in the ret-from- syscall paths. This means that set_user_sigmask() can save ->blocked in ->saved_sigmask and do set_restore_sigmask() to indicate that ->blocked was modified. This way the callers do not need 2 sigset_t's passed to set/restore and restore_user_sigmask() renamed to restore_saved_sigmask_unless() turns into the trivial helper which just calls restore_saved_sigmask(). Link: http://lkml.kernel.org/r/20190606113206.GA9464@redhat.com Signed-off-by: Oleg Nesterov Cc: Deepa Dinamani Cc: Arnd Bergmann Cc: Jens Axboe Cc: Davidlohr Bueso Cc: Eric Wong Cc: Jason Baron Cc: Thomas Gleixner Cc: Al Viro Cc: Eric W. Biederman Cc: David Laight Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 3 +-- include/linux/sched/signal.h | 12 ++++++++++-- include/linux/signal.h | 4 ---- 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index ebddcb6cfcf8..16dafd9f4b86 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -138,8 +138,7 @@ typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; -int set_compat_user_sigmask(const compat_sigset_t __user *usigmask, - sigset_t *set, sigset_t *oldset, +int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); struct compat_sigaction { diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 01add55a609b..efd8ce7675ed 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -420,7 +420,6 @@ void task_join_group_stop(struct task_struct *task); static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) @@ -451,7 +450,6 @@ static inline bool test_and_clear_restore_sigmask(void) static inline void set_restore_sigmask(void) { current->restore_sigmask = true; - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { @@ -484,6 +482,16 @@ static inline void restore_saved_sigmask(void) __set_current_blocked(¤t->saved_sigmask); } +extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); + +static inline void restore_saved_sigmask_unless(bool interrupted) +{ + if (interrupted) + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); + else + restore_saved_sigmask(); +} + static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; diff --git a/include/linux/signal.h b/include/linux/signal.h index 78c2bb376954..b5d99482d3fe 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -273,10 +273,6 @@ extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); -extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set, - sigset_t *oldset, size_t sigsetsize); -extern void restore_user_sigmask(const void __user *usigmask, - sigset_t *sigsaved, bool interrupted); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -- cgit v1.2.3 From f57e515a1b56325a28a0972c632a623a9c84590c Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Tue, 16 Jul 2019 16:30:06 -0700 Subject: kernel/pid.c: convert struct pid count to refcount_t struct pid's count is an atomic_t field used as a refcount. Use refcount_t for it which is basically atomic_t but does additional checking to prevent use-after-free bugs. For memory ordering, the only change is with the following: - if ((atomic_read(&pid->count) == 1) || - atomic_dec_and_test(&pid->count)) { + if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); Here the change is from: Fully ordered --> RELEASE + ACQUIRE (as per refcount-vs-atomic.rst) This ACQUIRE should take care of making sure the free happens after the refcount_dec_and_test(). The above hunk also removes atomic_read() since it is not needed for the code to work and it is unclear how beneficial it is. The removal lets refcount_dec_and_test() check for cases where get_pid() happened before the object was freed. Link: http://lkml.kernel.org/r/20190701183826.191936-1-joel@joelfernandes.org Signed-off-by: Joel Fernandes (Google) Reviewed-by: Andrea Parri Reviewed-by: Kees Cook Cc: Mathieu Desnoyers Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Will Deacon Cc: Paul E. McKenney Cc: Elena Reshetova Cc: Jann Horn Cc: Eric W. Biederman Cc: KJ Tsanaktsidis Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 1484db6ca8d1..2a83e434db9d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -4,6 +4,7 @@ #include #include +#include enum pid_type { @@ -57,7 +58,7 @@ struct upid { struct pid { - atomic_t count; + refcount_t count; unsigned int level; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; @@ -74,7 +75,7 @@ extern const struct file_operations pidfd_fops; static inline struct pid *get_pid(struct pid *pid) { if (pid) - atomic_inc(&pid->count); + refcount_inc(&pid->count); return pid; } -- cgit v1.2.3 From 97a0efea657e986322b09b99016b3f7d2ce37021 Mon Sep 17 00:00:00 2001 From: Tom Levy Date: Tue, 16 Jul 2019 16:30:24 -0700 Subject: include/linux/lz4.h: fix spelling and copy-paste errors in documentation Fix a few spelling and grammar errors, and two places where fast/safe in the documentation did not match the function. Link: http://lkml.kernel.org/r/20190321014452.13297-1-tomlevy93@gmail.com Signed-off-by: Tom Levy Reviewed-by: Andrew Morton Cc: Jiri Kosina Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lz4.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lz4.h b/include/linux/lz4.h index 394e3d9213b8..b16e15b9587a 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -278,7 +278,7 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize); * @compressedSize: is the precise full size of the compressed block * @maxDecompressedSize: is the size of 'dest' buffer * - * Decompresses data fom 'source' into 'dest'. + * Decompresses data from 'source' into 'dest'. * If the source stream is detected malformed, the function will * stop decoding and return a negative result. * This function is protected against buffer overflow exploits, @@ -522,7 +522,7 @@ int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode, const char *dictionary, int dictSize); /** - * LZ4_decompress_fast_continue() - Decompress blocks in streaming mode + * LZ4_decompress_safe_continue() - Decompress blocks in streaming mode * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure * @source: source address of the compressed data * @dest: output buffer address of the uncompressed data @@ -530,7 +530,7 @@ int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode, * @compressedSize: is the precise full size of the compressed block * @maxDecompressedSize: is the size of 'dest' buffer * - * These decoding function allows decompression of multiple blocks + * This decoding function allows decompression of multiple blocks * in "streaming" mode. * Previously decoded blocks *must* remain available at the memory position * where they were decoded (up to 64 KB) @@ -569,7 +569,7 @@ int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode, * which must be already allocated with 'originalSize' bytes * @originalSize: is the original and therefore uncompressed size * - * These decoding function allows decompression of multiple blocks + * This decoding function allows decompression of multiple blocks * in "streaming" mode. * Previously decoded blocks *must* remain available at the memory position * where they were decoded (up to 64 KB) @@ -610,10 +610,10 @@ int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode, * @dictStart: pointer to the start of the dictionary in memory * @dictSize: size of dictionary * - * These decoding function works the same as + * This decoding function works the same as * a combination of LZ4_setStreamDecode() followed by * LZ4_decompress_safe_continue() - * It is stand-alone, and don'tn eed a LZ4_streamDecode_t structure. + * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure. * * Return: number of bytes decompressed into destination buffer * (necessarily <= maxDecompressedSize) @@ -633,10 +633,10 @@ int LZ4_decompress_safe_usingDict(const char *source, char *dest, * @dictStart: pointer to the start of the dictionary in memory * @dictSize: size of dictionary * - * These decoding function works the same as + * This decoding function works the same as * a combination of LZ4_setStreamDecode() followed by - * LZ4_decompress_safe_continue() - * It is stand-alone, and don'tn eed a LZ4_streamDecode_t structure. + * LZ4_decompress_fast_continue() + * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure. * * Return: number of bytes decompressed into destination buffer * (necessarily <= maxDecompressedSize) -- cgit v1.2.3 From eca499ab3749a4537dee77ffead47a1a2c0dee19 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 16 Jul 2019 16:30:31 -0700 Subject: mm/hotplug: make remove_memory() interface usable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Presently the remove_memory() interface is inherently broken. It tries to remove memory but panics if some memory is not offline. The problem is that it is impossible to ensure that all memory blocks are offline as this function also takes lock_device_hotplug that is required to change memory state via sysfs. So, between calling this function and offlining all memory blocks there is always a window when lock_device_hotplug is released, and therefore, there is always a chance for a panic during this window. Make this interface to return an error if memory removal fails. This way it is safe to call this function without panicking machine, and also makes it symmetric to add_memory() which already returns an error. Link: http://lkml.kernel.org/r/20190517215438.6487-3-pasha.tatashin@soleen.com Signed-off-by: Pavel Tatashin Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Cc: Bjorn Helgaas Cc: Borislav Petkov Cc: Dan Williams Cc: Dave Hansen Cc: Dave Hansen Cc: Dave Jiang Cc: Fengguang Wu Cc: Huang Ying Cc: James Morris Cc: Jérôme Glisse Cc: Keith Busch Cc: Ross Zwisler Cc: Sasha Levin Cc: Takashi Iwai Cc: Tom Lendacky Cc: Vishal Verma Cc: Yaowei Bai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ae892eef8b82..988fde33cd7f 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -324,7 +324,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); -extern void remove_memory(int nid, u64 start, u64 size); +extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); #else @@ -341,7 +341,11 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) return -EINVAL; } -static inline void remove_memory(int nid, u64 start, u64 size) {} +static inline int remove_memory(int nid, u64 start, u64 size) +{ + return -EBUSY; +} + static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ -- cgit v1.2.3 From 7588adf8dff12c4b358557a13796a25fef796548 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 16 Jul 2019 16:30:44 -0700 Subject: mm: clean up is_device_*_page() definitions Refactor is_device_{public,private}_page() with is_pci_p2pdma_page() to make them all consistent in depending on their respective config options even when CONFIG_DEV_PAGEMAP_OPS is enabled for other reasons. This allows a little more compile-time optimisation as well as the conceptual and cosmetic cleanup. Link: http://lkml.kernel.org/r/187c2ab27dea70635d375a61b2f2076d26c032b0.1558547956.git.robin.murphy@arm.com Signed-off-by: Robin Murphy Suggested-by: Jerome Glisse Reviewed-by: Anshuman Khandual Cc: Catalin Marinas Cc: Dan Williams Cc: David Hildenbrand Cc: Ira Weiny Cc: Michael Ellerman Cc: Michal Hocko Cc: Oliver O'Halloran Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 31 +++++++++---------------------- 1 file changed, 9 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 74797ed20c2c..baa8b8761d8c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -956,41 +956,28 @@ static inline bool put_devmap_managed_page(struct page *page) return false; } -static inline bool is_device_private_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -#ifdef CONFIG_PCI_P2PDMA -static inline bool is_pci_p2pdma_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; -} -#else /* CONFIG_PCI_P2PDMA */ -static inline bool is_pci_p2pdma_page(const struct page *page) -{ - return false; -} -#endif /* CONFIG_PCI_P2PDMA */ - #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool put_devmap_managed_page(struct page *page) { return false; } +#endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) { - return false; + return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && + IS_ENABLED(CONFIG_DEVICE_PRIVATE) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_pci_p2pdma_page(const struct page *page) { - return false; + return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && + IS_ENABLED(CONFIG_PCI_P2PDMA) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } -#endif /* CONFIG_DEV_PAGEMAP_OPS */ /* 127: arbitrary random number, small enough to assemble well */ #define page_ref_zero_or_close_to_overflow(page) \ -- cgit v1.2.3 From 175967318c3018d01931ac950c82adab5deb47ca Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 16 Jul 2019 16:30:47 -0700 Subject: mm: introduce ARCH_HAS_PTE_DEVMAP ARCH_HAS_ZONE_DEVICE is somewhat meaningless in itself, and combined with the long-out-of-date comment can lead to the impression than an architecture may just enable it (since __add_pages() now "comprehends device memory" for itself) and expect things to work. In practice, however, ZONE_DEVICE users have little chance of functioning correctly without __HAVE_ARCH_PTE_DEVMAP, so let's clean that up the same way as ARCH_HAS_PTE_SPECIAL and make it the proper dependency so the real situation is clearer. Link: http://lkml.kernel.org/r/87554aa78478a02a63f2c4cf60a847279ae3eb3b.1558547956.git.robin.murphy@arm.com Signed-off-by: Robin Murphy Acked-by: Dan Williams Reviewed-by: Ira Weiny Acked-by: Oliver O'Halloran Reviewed-by: Anshuman Khandual Cc: Michael Ellerman Cc: Catalin Marinas Cc: David Hildenbrand Cc: Jerome Glisse Cc: Michal Hocko Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- include/linux/pfn_t.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index baa8b8761d8c..f43f4de4de68 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -547,7 +547,7 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma) struct mmu_gather; struct inode; -#if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { return 0; @@ -1750,7 +1750,7 @@ static inline void sync_mm_rss(struct mm_struct *mm) } #endif -#ifndef __HAVE_ARCH_PTE_DEVMAP +#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 01e8037023f7..2d9148221e9a 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -97,7 +97,7 @@ static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot) #endif #endif -#ifdef __HAVE_ARCH_PTE_DEVMAP +#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline bool pfn_t_devmap(pfn_t pfn) { const u64 flags = PFN_DEV|PFN_MAP; @@ -115,7 +115,7 @@ pmd_t pmd_mkdevmap(pmd_t pmd); defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pud_mkdevmap(pud_t pud); #endif -#endif /* __HAVE_ARCH_PTE_DEVMAP */ +#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL static inline bool pfn_t_special(pfn_t pfn) -- cgit v1.2.3 From 79eb597cba06c435b72f220e9d426ae413fc2579 Mon Sep 17 00:00:00 2001 From: Daniel Jordan Date: Tue, 16 Jul 2019 16:30:54 -0700 Subject: mm: add account_locked_vm utility function locked_vm accounting is done roughly the same way in five places, so unify them in a helper. Include the helper's caller in the debug print to distinguish between callsites. Error codes stay the same, so user-visible behavior does too. The one exception is that the -EPERM case in tce_account_locked_vm is removed because Alexey has never seen it triggered. [daniel.m.jordan@oracle.com: v3] Link: http://lkml.kernel.org/r/20190529205019.20927-1-daniel.m.jordan@oracle.com [sfr@canb.auug.org.au: fix mm/util.c] Link: http://lkml.kernel.org/r/20190524175045.26897-1-daniel.m.jordan@oracle.com Signed-off-by: Daniel Jordan Signed-off-by: Stephen Rothwell Tested-by: Alexey Kardashevskiy Acked-by: Alex Williamson Cc: Alan Tull Cc: Alex Williamson Cc: Benjamin Herrenschmidt Cc: Christoph Lameter Cc: Christophe Leroy Cc: Davidlohr Bueso Cc: Jason Gunthorpe Cc: Mark Rutland Cc: Michael Ellerman Cc: Moritz Fischer Cc: Paul Mackerras Cc: Steve Sistare Cc: Wu Hao Cc: Ira Weiny Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f43f4de4de68..bd6512559bed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1543,6 +1543,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); +int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, + struct task_struct *task, bool bypass_rlim); + /* Container for pinned pfns / pages */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ -- cgit v1.2.3 From 56cbb429d911991170fe867b4bba14f0efed5829 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 4 Jul 2019 16:57:51 -0400 Subject: switch the remnants of releasing the mountpoint away from fs_pin We used to need rather convoluted ordering trickery to guarantee that dput() of ex-mountpoints happens before the final mntput() of the same. Since we don't need that anymore, there's no point playing with fs_pin for that. Signed-off-by: Al Viro --- include/linux/fs_pin.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_pin.h b/include/linux/fs_pin.h index 7cab74d66f85..bdd09fd2520c 100644 --- a/include/linux/fs_pin.h +++ b/include/linux/fs_pin.h @@ -20,6 +20,5 @@ static inline void init_fs_pin(struct fs_pin *p, void (*kill)(struct fs_pin *)) } void pin_remove(struct fs_pin *); -void pin_insert_group(struct fs_pin *, struct vfsmount *, struct hlist_head *); void pin_insert(struct fs_pin *, struct vfsmount *); void pin_kill(struct fs_pin *); -- cgit v1.2.3 From b866455423e040813f113d8b87e8297778ee2014 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 16 Jul 2019 21:59:11 +0200 Subject: dma-mapping: add a dma_addressing_limited helper This helper returns if the device has issues addressing all present memory in the system. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 8d13e28a8e07..e11b115dd0e4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -679,6 +679,20 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) return dma_set_mask_and_coherent(dev, mask); } +/** + * dma_addressing_limited - return if the device is addressing limited + * @dev: device to check + * + * Return %true if the devices DMA mask is too small to address all memory in + * the system, else %false. Lack of addressing bits is the prime reason for + * bounce buffering, but might not be the only one. + */ +static inline bool dma_addressing_limited(struct device *dev) +{ + return min_not_zero(*dev->dma_mask, dev->bus_dma_mask) < + dma_get_required_mask(dev); +} + #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent); -- cgit v1.2.3 From db074436f421967f4f30cfbb6fbc2a728f3e62b3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 15 Jul 2019 08:50:59 -0700 Subject: iomap: move the direct IO code into a separate file Move the direct IO code into a separate file so that we can group related functions in a single file instead of having a single enormous source file. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- include/linux/iomap.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1df9ea187a9a..baa1e2d31f05 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -7,6 +7,7 @@ #include #include #include +#include struct address_space; struct fiemap_extent_info; @@ -69,6 +70,12 @@ struct iomap { const struct iomap_page_ops *page_ops; }; +static inline sector_t +iomap_sector(struct iomap *iomap, loff_t pos) +{ + return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; +} + /* * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare * and page_done will be called for each page written to. This only applies to -- cgit v1.2.3 From 5d907307adc14cd5148b07629c2b4535acd06062 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 15 Jul 2019 08:51:01 -0700 Subject: iomap: move internal declarations into fs/iomap/ Move internal function declarations out of fs/internal.h into include/linux/iomap.h so that our transition is complete. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- include/linux/iomap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index baa1e2d31f05..bc499ceae392 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -122,6 +122,16 @@ struct iomap_ops { ssize_t written, unsigned flags, struct iomap *iomap); }; +/* + * Main iomap iterator function. + */ +typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, + void *data, struct iomap *iomap); + +loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, + unsigned flags, const struct iomap_ops *ops, void *data, + iomap_actor_t actor); + /* * Structure allocate for each page when block size < PAGE_SIZE to track * sub-page uptodate status and I/O completions. -- cgit v1.2.3 From 9af93db9e140a4e6e79cdb098919bc928a72cd59 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Wed, 17 Jul 2019 13:10:58 +0800 Subject: platform/x86: asus: Rename "fan mode" to "fan boost mode" The Asus WMI spec indicates that the function being controlled here is called "Fan Boost Mode". The user-facing documentation also calls it this. The spec uses the term "fan mode" is used to refer to other things, including functionality expected to appear on future products. We missed this before as we are not dealing with the most readable of specs, and didn't forsee any confusion around shortening the name. Rename "fan mode" to "fan boost mode" to improve consistency with the spec and to avoid a future naming conflict. There is no interface breakage here since this has yet to be included in an official kernel release. I also updated the kernel version listed under ABI accordingly. Signed-off-by: Daniel Drake Acked-by: Yurii Pavlovskyi Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 8551156b8dca..4802cd2c7309 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -57,7 +57,7 @@ #define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 #define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ #define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 -#define ASUS_WMI_DEVID_FAN_MODE 0x00110018 +#define ASUS_WMI_DEVID_FAN_BOOST_MODE 0x00110018 /* Misc */ #define ASUS_WMI_DEVID_CAMERA 0x00060013 -- cgit v1.2.3 From 733232f8c852bcc2ad6fc1db7f4c43eb01c7c217 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 17 Jul 2019 12:57:06 -0400 Subject: dm: use printk ratelimiting functions DM provided its own ratelimiting printk wrapper but given printk advances this is no longer needed. Also, switching DMDEBUG_LIMIT to using pr_debug_ratelimited() fixes the reported issue where DMDEBUG_LIMIT() still caused a flood of "callbacks suppressed" messages. Reported-by: Milan Broz Depends-on: 29fc2bc7539386 ("printk: pr_debug_ratelimited: check state first to reduce "callbacks suppressed" messages") Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e1f51d607cc5..603ce5bb4fac 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -530,29 +530,20 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); *---------------------------------------------------------------*/ #define DM_NAME "device-mapper" -#define DM_RATELIMIT(pr_func, fmt, ...) \ -do { \ - static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, \ - DEFAULT_RATELIMIT_BURST); \ - \ - if (__ratelimit(&rs)) \ - pr_func(DM_FMT(fmt), ##__VA_ARGS__); \ -} while (0) - #define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n" #define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__) #define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__) -#define DMERR_LIMIT(fmt, ...) DM_RATELIMIT(pr_err, fmt, ##__VA_ARGS__) +#define DMERR_LIMIT(fmt, ...) pr_err_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) #define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__) -#define DMWARN_LIMIT(fmt, ...) DM_RATELIMIT(pr_warn, fmt, ##__VA_ARGS__) +#define DMWARN_LIMIT(fmt, ...) pr_warn_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) #define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) -#define DMINFO_LIMIT(fmt, ...) DM_RATELIMIT(pr_info, fmt, ##__VA_ARGS__) +#define DMINFO_LIMIT(fmt, ...) pr_info_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) #ifdef CONFIG_DM_DEBUG #define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) -#define DMDEBUG_LIMIT(fmt, ...) DM_RATELIMIT(pr_debug, fmt, ##__VA_ARGS__) +#define DMDEBUG_LIMIT(fmt, ...) pr_debug_ratelimited(DM_FMT(fmt), ##__VA_ARGS__) #else #define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -- cgit v1.2.3 From 7402a4fedc2bc448100c2d086406c708451b16dc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Jul 2019 13:51:29 -0400 Subject: SUNRPC: Fix up backchannel slot table accounting Add a per-transport maximum limit in the socket case, and add helpers to allow the NFSv4 code to discover that limit. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 1 + include/linux/sunrpc/clnt.h | 1 + include/linux/sunrpc/xprt.h | 6 ++++-- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index d4229a78524a..87d27e13d885 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -43,6 +43,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs); void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs); void xprt_free_bc_rqst(struct rpc_rqst *req); +unsigned int xprt_bc_max_slots(struct rpc_xprt *xprt); /* * Determine if a shared backchannel is in use diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 4e070e00c143..abc63bd1be2b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -194,6 +194,7 @@ void rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int); struct net * rpc_net_ns(struct rpc_clnt *); size_t rpc_max_payload(struct rpc_clnt *); size_t rpc_max_bc_payload(struct rpc_clnt *); +unsigned int rpc_num_bc_slots(struct rpc_clnt *); void rpc_force_rebind(struct rpc_clnt *); size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ed76e5fb36c1..13e108bcc9eb 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -158,6 +158,7 @@ struct rpc_xprt_ops { int (*bc_setup)(struct rpc_xprt *xprt, unsigned int min_reqs); size_t (*bc_maxpayload)(struct rpc_xprt *xprt); + unsigned int (*bc_num_slots)(struct rpc_xprt *xprt); void (*bc_free_rqst)(struct rpc_rqst *rqst); void (*bc_destroy)(struct rpc_xprt *xprt, unsigned int max_reqs); @@ -251,8 +252,9 @@ struct rpc_xprt { #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ /* process the callback */ - int bc_alloc_count; /* Total number of preallocs */ - atomic_t bc_free_slots; + unsigned int bc_alloc_max; + unsigned int bc_alloc_count; /* Total number of preallocs */ + atomic_t bc_slot_count; /* Number of allocated slots */ spinlock_t bc_pa_lock; /* Protects the preallocated * items */ struct list_head bc_pa_list; /* List of preallocated -- cgit v1.2.3 From 3193c0836f203a91bef96d88c64cccf0be090d9c Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 17 Jul 2019 20:36:45 -0500 Subject: bpf: Disable GCC -fgcse optimization for ___bpf_prog_run() On x86-64, with CONFIG_RETPOLINE=n, GCC's "global common subexpression elimination" optimization results in ___bpf_prog_run()'s jumptable code changing from this: select_insn: jmp *jumptable(, %rax, 8) ... ALU64_ADD_X: ... jmp *jumptable(, %rax, 8) ALU_ADD_X: ... jmp *jumptable(, %rax, 8) to this: select_insn: mov jumptable, %r12 jmp *(%r12, %rax, 8) ... ALU64_ADD_X: ... jmp *(%r12, %rax, 8) ALU_ADD_X: ... jmp *(%r12, %rax, 8) The jumptable address is placed in a register once, at the beginning of the function. The function execution can then go through multiple indirect jumps which rely on that same register value. This has a few issues: 1) Objtool isn't smart enough to be able to track such a register value across multiple recursive indirect jumps through the jump table. 2) With CONFIG_RETPOLINE enabled, this optimization actually results in a small slowdown. I measured a ~4.7% slowdown in the test_bpf "tcpdump port 22" selftest. This slowdown is actually predicted by the GCC manual: Note: When compiling a program using computed gotos, a GCC extension, you may get better run-time performance if you disable the global common subexpression elimination pass by adding -fno-gcse to the command line. So just disable the optimization for this function. Fixes: e55a73251da3 ("bpf: Fix ORC unwinding in non-JIT BPF code") Reported-by: Randy Dunlap Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Acked-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/30c3ca29ba037afcbd860a8672eef0021addf9fe.1563413318.git.jpoimboe@redhat.com --- include/linux/compiler-gcc.h | 2 ++ include/linux/compiler_types.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e8579412ad21..d7ee4c6bad48 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -170,3 +170,5 @@ #else #define __diag_GCC_8(s) #endif + +#define __no_fgcse __attribute__((optimize("-fno-gcse"))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 095d55c3834d..599c27b56c29 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -189,6 +189,10 @@ struct ftrace_likely_data { #define asm_volatile_goto(x...) asm goto(x) #endif +#ifndef __no_fgcse +# define __no_fgcse +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -- cgit v1.2.3 From d5b9216fd5114be4ed98ca9c1ecc5f164cd8cf5e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 18 Jul 2019 09:32:17 -0400 Subject: pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS Add tracepoints to allow debugging of the event chain leading to a pnfs fallback to doing I/O through the MDS. Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 22494d170619..fd59904a282c 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -660,6 +660,7 @@ enum pnfs_update_layout_reason { PNFS_UPDATE_LAYOUT_BLOCKED, PNFS_UPDATE_LAYOUT_INVALID_OPEN, PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, + PNFS_UPDATE_LAYOUT_EXIT, }; #define NFS4_OP_MAP_NUM_LONGS \ -- cgit v1.2.3 From 80ec922dbd87fd38d15719c86a94457204648aeb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:56:51 -0700 Subject: mm/memory_hotplug: allow arch_remove_memory() without CONFIG_MEMORY_HOTREMOVE We want to improve error handling while adding memory by allowing to use arch_remove_memory() and __remove_pages() even if CONFIG_MEMORY_HOTREMOVE is not set to e.g., implement something like: arch_add_memory() rc = do_something(); if (rc) { arch_remove_memory(); } We won't get rid of CONFIG_MEMORY_HOTREMOVE for now, as it will require quite some dependencies for memory offlining. Link: http://lkml.kernel.org/r/20190527111152.16324-7-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Cc: Tony Luck Cc: Fenghua Yu Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Heiko Carstens Cc: Yoshinori Sato Cc: Rich Felker Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Michal Hocko Cc: David Hildenbrand Cc: Oscar Salvador Cc: "Kirill A. Shutemov" Cc: Alex Deucher Cc: "David S. Miller" Cc: Mark Brown Cc: Chris Wilson Cc: Christophe Leroy Cc: Nicholas Piggin Cc: Vasily Gorbik Cc: Rob Herring Cc: Masahiro Yamada Cc: "mike.travis@hpe.com" Cc: Andrew Banman Cc: Arun KS Cc: Qian Cai Cc: Mathieu Malaterre Cc: Baoquan He Cc: Logan Gunthorpe Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: Chintan Pandya Cc: Dan Williams Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Joonsoo Kim Cc: Jun Yao Cc: Mark Rutland Cc: Mike Rapoport Cc: Oscar Salvador Cc: Robin Murphy Cc: Wei Yang Cc: Will Deacon Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 -- include/linux/memory_hotplug.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index e1dc1bb2b787..474c7c60c8f2 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -112,9 +112,7 @@ extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); int hotplug_memory_register(int nid, struct mem_section *section); -#ifdef CONFIG_MEMORY_HOTREMOVE extern void unregister_memory_section(struct mem_section *); -#endif extern int memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); extern int memory_isolate_notify(unsigned long val, void *v); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 988fde33cd7f..87bf9c4a889e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -123,12 +123,10 @@ static inline bool movable_node_is_enabled(void) return movable_node_enabled; } -#ifdef CONFIG_MEMORY_HOTREMOVE extern void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap); extern void __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); -#endif /* CONFIG_MEMORY_HOTREMOVE */ /* * Do we want sysfs memblock files created. This will allow userspace to online -- cgit v1.2.3 From db051a0dac13db24d58470d75cee0ce7c6b031a1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:56:56 -0700 Subject: mm/memory_hotplug: create memory block devices after arch_add_memory() Only memory to be added to the buddy and to be onlined/offlined by user space using /sys/devices/system/memory/... needs (and should have!) memory block devices. Factor out creation of memory block devices. Create all devices after arch_add_memory() succeeded. We can later drop the want_memblock parameter, because it is now effectively stale. Only after memory block devices have been added, memory can be onlined by user space. This implies, that memory is not visible to user space at all before arch_add_memory() succeeded. While at it - use WARN_ON_ONCE instead of BUG_ON in moved unregister_memory() - introduce find_memory_block_by_id() to search via block id - Use find_memory_block_by_id() in init_memory_block() to catch duplicates Link: http://lkml.kernel.org/r/20190527111152.16324-8-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: David Hildenbrand Cc: "mike.travis@hpe.com" Cc: Ingo Molnar Cc: Andrew Banman Cc: Oscar Salvador Cc: Qian Cai Cc: Wei Yang Cc: Arun KS Cc: Mathieu Malaterre Cc: Alex Deucher Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Chintan Pandya Cc: Christophe Leroy Cc: Chris Wilson Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Fenghua Yu Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Jonathan Cameron Cc: Joonsoo Kim Cc: Jun Yao Cc: "Kirill A. Shutemov" Cc: Logan Gunthorpe Cc: Mark Brown Cc: Mark Rutland Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Rich Felker Cc: Rob Herring Cc: Robin Murphy Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 474c7c60c8f2..db3e8567f900 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -111,7 +111,7 @@ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); -int hotplug_memory_register(int nid, struct mem_section *section); +int create_memory_block_devices(unsigned long start, unsigned long size); extern void unregister_memory_section(struct mem_section *); extern int memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); -- cgit v1.2.3 From 05f800a0bd08e14606ac63e0a5c63ed6880acaab Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:01 -0700 Subject: mm/memory_hotplug: drop MHP_MEMBLOCK_API No longer needed, the callers of arch_add_memory() can handle this manually. Link: http://lkml.kernel.org/r/20190527111152.16324-9-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Wei Yang Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Joonsoo Kim Cc: Qian Cai Cc: Arun KS Cc: Mathieu Malaterre Cc: Mike Rapoport Cc: Alex Deucher Cc: Andrew Banman Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Chintan Pandya Cc: Christophe Leroy Cc: Chris Wilson Cc: Dan Williams Cc: Dave Hansen Cc: "David S. Miller" Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Jun Yao Cc: "Kirill A. Shutemov" Cc: Logan Gunthorpe Cc: Mark Brown Cc: Mark Rutland Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Mike Rapoport Cc: "mike.travis@hpe.com" Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Rob Herring Cc: Robin Murphy Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 87bf9c4a889e..36c514b80cf1 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -128,14 +128,6 @@ extern void arch_remove_memory(int nid, u64 start, u64 size, extern void __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); -/* - * Do we want sysfs memblock files created. This will allow userspace to online - * and offline memory explicitly. Lack of this bit means that the caller has to - * call move_pfn_range_to_zone to finish the initialization. - */ - -#define MHP_MEMBLOCK_API (1<<0) - /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_restrictions *restrictions); -- cgit v1.2.3 From 4c4b7f9ba9486c565aead99a198ceeef73ae81f6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:06 -0700 Subject: mm/memory_hotplug: remove memory block devices before arch_remove_memory() Let's factor out removing of memory block devices, which is only necessary for memory added via add_memory() and friends that created memory block devices. Remove the devices before calling arch_remove_memory(). This finishes factoring out memory block device handling from arch_add_memory() and arch_remove_memory(). Link: http://lkml.kernel.org/r/20190527111152.16324-10-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Dan Williams Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: David Hildenbrand Cc: "mike.travis@hpe.com" Cc: Andrew Banman Cc: Ingo Molnar Cc: Alex Deucher Cc: "David S. Miller" Cc: Mark Brown Cc: Chris Wilson Cc: Oscar Salvador Cc: Jonathan Cameron Cc: Arun KS Cc: Mathieu Malaterre Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Chintan Pandya Cc: Christophe Leroy Cc: Dave Hansen Cc: Fenghua Yu Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Joonsoo Kim Cc: Jun Yao Cc: "Kirill A. Shutemov" Cc: Logan Gunthorpe Cc: Mark Rutland Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Qian Cai Cc: Rich Felker Cc: Rob Herring Cc: Robin Murphy Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Wei Yang Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 +- include/linux/node.h | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index db3e8567f900..f26a5417ec5d 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -112,7 +112,7 @@ extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size); -extern void unregister_memory_section(struct mem_section *); +void remove_memory_block_devices(unsigned long start, unsigned long size); extern int memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); extern int memory_isolate_notify(unsigned long val, void *v); diff --git a/include/linux/node.h b/include/linux/node.h index 1a557c589ecb..02a29e71b175 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -139,8 +139,7 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); extern int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg); -extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, - unsigned long phys_index); +extern int unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, @@ -176,8 +175,7 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk, { return 0; } -static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, - unsigned long phys_index) +static inline int unregister_memory_block_under_nodes(struct memory_block *mem_blk) { return 0; } -- cgit v1.2.3 From a31b264c2b415b29660da0bc2ba291a98629ce51 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:12 -0700 Subject: mm/memory_hotplug: make unregister_memory_block_under_nodes() never fail We really don't want anything during memory hotunplug to fail. We always pass a valid memory block device, that check can go. Avoid allocating memory and eventually failing. As we are always called under lock, we can use a static piece of memory. This avoids having to put the structure onto the stack, having to guess about the stack size of callers. Patch inspired by a patch from Oscar Salvador. In the future, there might be no need to iterate over nodes at all. mem->nid should tell us exactly what to remove. Memory block devices with mixed nodes (added during boot) should properly fenced off and never removed. Link: http://lkml.kernel.org/r/20190527111152.16324-11-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Wei Yang Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Alex Deucher Cc: "David S. Miller" Cc: Mark Brown Cc: Chris Wilson Cc: David Hildenbrand Cc: Jonathan Cameron Cc: Andrew Banman Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Arun KS Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Chintan Pandya Cc: Christophe Leroy Cc: Dan Williams Cc: Dave Hansen Cc: Fenghua Yu Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joonsoo Kim Cc: Jun Yao Cc: "Kirill A. Shutemov" Cc: Logan Gunthorpe Cc: Mark Rutland Cc: Masahiro Yamada Cc: Mathieu Malaterre Cc: Michael Ellerman Cc: Mike Rapoport Cc: "mike.travis@hpe.com" Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Qian Cai Cc: Rich Felker Cc: Rob Herring Cc: Robin Murphy Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/node.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/node.h b/include/linux/node.h index 02a29e71b175..548c226966a2 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -139,7 +139,7 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); extern int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg); -extern int unregister_memory_block_under_nodes(struct memory_block *mem_blk); +extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, @@ -175,9 +175,8 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk, { return 0; } -static inline int unregister_memory_block_under_nodes(struct memory_block *mem_blk) +static inline void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { - return 0; } static inline void register_hugetlbfs_with_node(node_registration_func_t reg, -- cgit v1.2.3 From b9bf8d342d9b443c0d19aa57883d8ddb38d965de Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:17 -0700 Subject: mm/memory_hotplug: remove "zone" parameter from sparse_remove_one_section The parameter is unused, so let's drop it. Memory removal paths should never care about zones. This is the job of memory offlining and will require more refactorings. Link: http://lkml.kernel.org/r/20190527111152.16324-12-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Dan Williams Reviewed-by: Wei Yang Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Alex Deucher Cc: Andrew Banman Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Arun KS Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Chintan Pandya Cc: Christophe Leroy Cc: Chris Wilson Cc: Dave Hansen Cc: "David S. Miller" Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Joonsoo Kim Cc: Jun Yao Cc: "Kirill A. Shutemov" Cc: Logan Gunthorpe Cc: Mark Brown Cc: Mark Rutland Cc: Masahiro Yamada Cc: Mathieu Malaterre Cc: Michael Ellerman Cc: Mike Rapoport Cc: "mike.travis@hpe.com" Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Qian Cai Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Rob Herring Cc: Robin Murphy Cc: Thomas Gleixner Cc: Tony Luck Cc: Vasily Gorbik Cc: Will Deacon Cc: Yoshinori Sato Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 36c514b80cf1..79e0add6a597 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -350,7 +350,7 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_one_section(int nid, unsigned long start_pfn, struct vmem_altmap *altmap); -extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, +extern void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -- cgit v1.2.3 From 43675e6fbbeadca90c6c5031557ff95e217e6d2f Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 18 Jul 2019 15:57:24 -0700 Subject: mm: thp: make transhuge_vma_suitable available for anonymous THP transhuge_vma_suitable() was only available for shmem THP, but anonymous THP has the same check except pgoff check. And, it will be used for THP eligible check in the later patch, so make it available for all kind of THPs. This also helps reduce code duplication slightly. Since anonymous THP doesn't have to check pgoff, so make pgoff check shmem vma only. And regroup some functions in include/linux/mm.h to solve compile issue since transhuge_vma_suitable() needs call vma_is_anonymous() which was defined after huge_mm.h is included. [akpm@linux-foundation.org: fix typo] [yang.shi@linux.alibaba.com: v4] Link: http://lkml.kernel.org/r/1563400758-124759-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1560401041-32207-2-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Hugh Dickins Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 23 +++++++++++++++++++++++ include/linux/mm.h | 34 +++++++++++++++++----------------- 2 files changed, 40 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 7cd5c150c21d..45ede62aa85b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -121,6 +121,23 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) bool transparent_hugepage_enabled(struct vm_area_struct *vma); +#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1) + +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + /* Don't have to check pgoff for anonymous vma */ + if (!vma_is_anonymous(vma)) { + if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) != + (vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK)) + return false; + } + + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<vm_ops = NULL; } +static inline bool vma_is_anonymous(struct vm_area_struct *vma) +{ + return !vma->vm_ops; +} + +#ifdef CONFIG_SHMEM +/* + * The vma_is_shmem is not inline because it is used only by slow + * paths in userfault. + */ +bool vma_is_shmem(struct vm_area_struct *vma); +#else +static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } +#endif + +int vma_is_stack_for_current(struct vm_area_struct *vma); + /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } @@ -1620,23 +1637,6 @@ int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -static inline bool vma_is_anonymous(struct vm_area_struct *vma) -{ - return !vma->vm_ops; -} - -#ifdef CONFIG_SHMEM -/* - * The vma_is_shmem is not inline because it is used only by slow - * paths in userfault. - */ -bool vma_is_shmem(struct vm_area_struct *vma); -#else -static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } -#endif - -int vma_is_stack_for_current(struct vm_area_struct *vma); - extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, -- cgit v1.2.3 From 2491f0a2c0b117b9097e9c9eee0c21f2e5f716d7 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:37 -0700 Subject: mm: section numbers use the type "unsigned long" Patch series "mm: Further memory block device cleanups", v1. Some further cleanups around memory block devices. Especially, clean up and simplify walk_memory_range(). Including some other minor cleanups. This patch (of 6): We are using a mixture of "int" and "unsigned long". Let's make this consistent by using "unsigned long" everywhere. We'll do the same with memory block ids next. While at it, turn the "unsigned long i" in removable_show() into an int - sections_per_block is an int. [akpm@linux-foundation.org: s/unsigned long i/unsigned long nr/] [david@redhat.com: v3] Link: http://lkml.kernel.org/r/20190620183139.4352-2-david@redhat.com Link: http://lkml.kernel.org/r/20190614100114.311-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Vlastimil Babka Cc: Michal Hocko Cc: Dan Williams Cc: Mel Gorman Cc: Wei Yang Cc: Johannes Weiner Cc: Arun KS Cc: Pavel Tatashin Cc: Oscar Salvador Cc: Stephen Rothwell Cc: Mike Rapoport Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 70394cabaf4e..298d1c3e4c2e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1219,7 +1219,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return NULL; return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } -extern int __section_nr(struct mem_section* ms); +extern unsigned long __section_nr(struct mem_section *ms); extern unsigned long usemap_size(void); /* @@ -1291,7 +1291,7 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn) return __nr_to_section(pfn_to_section_nr(pfn)); } -extern int __highest_present_section_nr; +extern unsigned long __highest_present_section_nr; #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) -- cgit v1.2.3 From 8d595c4c0f768f19db043d378b22e98405f9fd47 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:43 -0700 Subject: mm: make register_mem_sect_under_node() static It is only used internally. Link: http://lkml.kernel.org/r/20190614100114.311-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Keith Busch Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/node.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/node.h b/include/linux/node.h index 548c226966a2..4866f32a02d8 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -137,8 +137,6 @@ static inline int register_one_node(int nid) extern void unregister_one_node(int nid); extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); -extern int register_mem_sect_under_node(struct memory_block *mem_blk, - void *arg); extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, @@ -170,11 +168,6 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) { return 0; } -static inline int register_mem_sect_under_node(struct memory_block *mem_blk, - void *arg) -{ - return 0; -} static inline void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { } -- cgit v1.2.3 From fbcf73ce65827c3d8935f38b832a43153a0c78d1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:46 -0700 Subject: mm/memory_hotplug: rename walk_memory_range() and pass start+size instead of pfns walk_memory_range() was once used to iterate over sections. Now, it iterates over memory blocks. Rename the function, fixup the documentation. Also, pass start+size instead of PFNs, which is what most callers already have at hand. (we'll rework link_mem_sections() most probably soon) Follow-up patches will rework, simplify, and move walk_memory_blocks() to drivers/base/memory.c. Note: walk_memory_blocks() only works correctly right now if the start_pfn is aligned to a section start. This is the case right now, but we'll generalize the function in a follow up patch so the semantics match the documentation. [akpm@linux-foundation.org: remove unused variable] Link: http://lkml.kernel.org/r/20190614100114.311-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: David Hildenbrand Cc: Rashmica Gupta Cc: Pavel Tatashin Cc: Anshuman Khandual Cc: Michael Neuling Cc: Thomas Gleixner Cc: Oscar Salvador Cc: Michal Hocko Cc: Wei Yang Cc: Juergen Gross Cc: Qian Cai Cc: Arun KS Cc: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 79e0add6a597..d9fffc34949f 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -340,7 +340,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void __ref free_area_init_core_hotplug(int nid); -extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, +extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, int (*func)(struct memory_block *, void *)); extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); -- cgit v1.2.3 From ea8846411ad686ff626e00bb2c3821b3db2ab56a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 18 Jul 2019 15:57:50 -0700 Subject: mm/memory_hotplug: move and simplify walk_memory_blocks() Let's move walk_memory_blocks() to the place where memory block logic resides and simplify it. While at it, add a type for the callback function. Link: http://lkml.kernel.org/r/20190614100114.311-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: David Hildenbrand Cc: Stephen Rothwell Cc: Pavel Tatashin Cc: Andrew Banman Cc: Mike Travis Cc: Oscar Salvador Cc: Michal Hocko Cc: Wei Yang Cc: Arun KS Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 3 +++ include/linux/memory_hotplug.h | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index f26a5417ec5d..b3b388775a30 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -119,6 +119,9 @@ extern int memory_isolate_notify(unsigned long val, void *v); extern struct memory_block *find_memory_block_hinted(struct mem_section *, struct memory_block *); extern struct memory_block *find_memory_block(struct mem_section *); +typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); +extern int walk_memory_blocks(unsigned long start, unsigned long size, + void *arg, walk_memory_blocks_func_t func); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Thu, 18 Jul 2019 15:57:53 -0700 Subject: drivers/base/memory.c: get rid of find_memory_block_hinted() No longer needed, let's remove it. Also, drop the "hint" parameter completely from "find_memory_block_by_id", as nobody needs it anymore. [david@redhat.com: v3] Link: http://lkml.kernel.org/r/20190620183139.4352-7-david@redhat.com [david@redhat.com: handle zero-length walks] Link: http://lkml.kernel.org/r/1c2edc22-afd7-2211-c4c7-40e54e5007e8@redhat.com Link: http://lkml.kernel.org/r/20190614100114.311-7-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Tested-by: Qian Cai Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: David Hildenbrand Cc: Stephen Rothwell Cc: Pavel Tatashin Cc: Andrew Banman Cc: Mike Travis Cc: Oscar Salvador Cc: Michal Hocko Cc: Wei Yang Cc: Arun KS Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index b3b388775a30..02e633f3ede0 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -116,8 +116,6 @@ void remove_memory_block_devices(unsigned long start, unsigned long size); extern int memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); extern int memory_isolate_notify(unsigned long val, void *v); -extern struct memory_block *find_memory_block_hinted(struct mem_section *, - struct memory_block *); extern struct memory_block *find_memory_block(struct mem_section *); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, -- cgit v1.2.3 From f1eca35a0dc7cb3cdb00c88c8c5e5138a65face0 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:57:57 -0700 Subject: mm/sparsemem: introduce struct mem_section_usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm: Sub-section memory hotplug support", v10. The memory hotplug section is an arbitrary / convenient unit for memory hotplug. 'Section-size' units have bled into the user interface ('memblock' sysfs) and can not be changed without breaking existing userspace. The section-size constraint, while mostly benign for typical memory hotplug, has and continues to wreak havoc with 'device-memory' use cases, persistent memory (pmem) in particular. Recall that pmem uses devm_memremap_pages(), and subsequently arch_add_memory(), to allocate a 'struct page' memmap for pmem. However, it does not use the 'bottom half' of memory hotplug, i.e. never marks pmem pages online and never exposes the userspace memblock interface for pmem. This leaves an opening to redress the section-size constraint. To date, the libnvdimm subsystem has attempted to inject padding to satisfy the internal constraints of arch_add_memory(). Beyond complicating the code, leading to bugs [2], wasting memory, and limiting configuration flexibility, the padding hack is broken when the platform changes this physical memory alignment of pmem from one boot to the next. Device failure (intermittent or permanent) and physical reconfiguration are events that can cause the platform firmware to change the physical placement of pmem on a subsequent boot, and device failure is an everyday event in a data-center. It turns out that sections are only a hard requirement of the user-facing interface for memory hotplug and with a bit more infrastructure sub-section arch_add_memory() support can be added for kernel internal usages like devm_memremap_pages(). Here is an analysis of the current design assumptions in the current code and how they are addressed in the new implementation: Current design assumptions: - Sections that describe boot memory (early sections) are never unplugged / removed. - pfn_valid(), in the CONFIG_SPARSEMEM_VMEMMAP=y, case devolves to a valid_section() check - __add_pages() and helper routines assume all operations occur in PAGES_PER_SECTION units. - The memblock sysfs interface only comprehends full sections New design assumptions: - Sections are instrumented with a sub-section bitmask to track (on x86) individual 2MB sub-divisions of a 128MB section. - Partially populated early sections can be extended with additional sub-sections, and those sub-sections can be removed with arch_remove_memory(). With this in place we no longer lose usable memory capacity to padding. - pfn_valid() is updated to look deeper than valid_section() to also check the active-sub-section mask. This indication is in the same cacheline as the valid_section() so the performance impact is expected to be negligible. So far the lkp robot has not reported any regressions. - Outside of the core vmemmap population routines which are replaced, other helper routines like shrink_{zone,pgdat}_span() are updated to handle the smaller granularity. Core memory hotplug routines that deal with online memory are not touched. - The existing memblock sysfs user api guarantees / assumptions are not touched since this capability is limited to !online !memblock-sysfs-accessible sections. Meanwhile the issue reports continue to roll in from users that do not understand when and how the 128MB constraint will bite them. The current implementation relied on being able to support at least one misaligned namespace, but that immediately falls over on any moderately complex namespace creation attempt. Beyond the initial problem of 'System RAM' colliding with pmem, and the unsolvable problem of physical alignment changes, Linux is now being exposed to platforms that collide pmem ranges with other pmem ranges by default [3]. In short, devm_memremap_pages() has pushed the venerable section-size constraint past the breaking point, and the simplicity of section-aligned arch_add_memory() is no longer tenable. These patches are exposed to the kbuild robot on a subsection-v10 branch [4], and a preview of the unit test for this functionality is available on the 'subsection-pending' branch of ndctl [5]. [2]: https://lore.kernel.org/r/155000671719.348031.2347363160141119237.stgit@dwillia2-desk3.amr.corp.intel.com [3]: https://github.com/pmem/ndctl/issues/76 [4]: https://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm.git/log/?h=subsection-v10 [5]: https://github.com/pmem/ndctl/commit/7c59b4867e1c This patch (of 13): Towards enabling memory hotplug to track partial population of a section, introduce 'struct mem_section_usage'. A pointer to a 'struct mem_section_usage' instance replaces the existing pointer to a 'pageblock_flags' bitmap. Effectively it adds one more 'unsigned long' beyond the 'pageblock_flags' (usemap) allocation to house a new 'subsection_map' bitmap. The new bitmap enables the memory hot{plug,remove} implementation to act on incremental sub-divisions of a section. SUBSECTION_SHIFT is defined as global constant instead of per-architecture value like SECTION_SIZE_BITS in order to allow cross-arch compatibility of subsection users. Specifically a common subsection size allows for the possibility that persistent memory namespace configurations be made compatible across architectures. The primary motivation for this functionality is to support platforms that mix "System RAM" and "Persistent Memory" within a single section, or multiple PMEM ranges with different mapping lifetimes within a single section. The section restriction for hotplug has caused an ongoing saga of hacks and bugs for devm_memremap_pages() users. Beyond the fixups to teach existing paths how to retrieve the 'usemap' from a section, and updates to usemap allocation path, there are no expected behavior changes. Link: http://lkml.kernel.org/r/156092349845.979959.73333291612799019.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reviewed-by: Oscar Salvador Reviewed-by: Wei Yang Tested-by: Aneesh Kumar K.V [ppc64] Cc: Michal Hocko Cc: Vlastimil Babka Cc: Logan Gunthorpe Cc: Pavel Tatashin Cc: David Hildenbrand Cc: Jérôme Glisse Cc: Mike Rapoport Cc: Jane Chu Cc: Pavel Tatashin Cc: Jonathan Corbet Cc: Qian Cai Cc: Logan Gunthorpe Cc: Toshi Kani Cc: Jeff Moyer Cc: Michal Hocko Cc: Vlastimil Babka Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 298d1c3e4c2e..2520336bdfd1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1160,6 +1160,24 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) +#define SUBSECTION_SHIFT 21 + +#define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) +#define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) +#define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) + +#if SUBSECTION_SHIFT > SECTION_SIZE_BITS +#error Subsection size exceeds section size +#else +#define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) +#endif + +struct mem_section_usage { + DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); + /* See declaration of similar field in struct zone */ + unsigned long pageblock_flags[0]; +}; + struct page; struct page_ext; struct mem_section { @@ -1177,8 +1195,7 @@ struct mem_section { */ unsigned long section_mem_map; - /* See declaration of similar field in struct zone */ - unsigned long *pageblock_flags; + struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use @@ -1209,6 +1226,11 @@ extern struct mem_section **mem_section; extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif +static inline unsigned long *section_to_usemap(struct mem_section *ms) +{ + return ms->usage->pageblock_flags; +} + static inline struct mem_section *__nr_to_section(unsigned long nr) { #ifdef CONFIG_SPARSEMEM_EXTREME @@ -1220,7 +1242,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } extern unsigned long __section_nr(struct mem_section *ms); -extern unsigned long usemap_size(void); +extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store -- cgit v1.2.3 From 326e1b8f83a4318b09033ef754f40c785aed5e68 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:00 -0700 Subject: mm/sparsemem: introduce a SECTION_IS_EARLY flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation for sub-section hotplug, track whether a given section was created during early memory initialization, or later via memory hotplug. This distinction is needed to maintain the coarse expectation that pfn_valid() returns true for any pfn within a given section even if that section has pages that are reserved from the page allocator. For example one of the of goals of subsection hotplug is to support cases where the system physical memory layout collides System RAM and PMEM within a section. Several pfn_valid() users expect to just check if a section is valid, but they are not careful to check if the given pfn is within a "System RAM" boundary and instead expect pgdat information to further validate the pfn. Rather than unwind those paths to make their pfn_valid() queries more precise a follow on patch uses the SECTION_IS_EARLY flag to maintain the traditional expectation that pfn_valid() returns true for all early sections. Link: https://lore.kernel.org/lkml/1560366952-10660-1-git-send-email-cai@lca.pw/ Link: http://lkml.kernel.org/r/156092350358.979959.5817209875548072819.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Qian Cai Tested-by: Aneesh Kumar K.V [ppc64] Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Logan Gunthorpe Cc: David Hildenbrand Cc: Pavel Tatashin Cc: Jane Chu Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Vlastimil Babka Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2520336bdfd1..4be40634238b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1260,7 +1260,8 @@ extern size_t mem_section_usage_size(void); #define SECTION_MARKED_PRESENT (1UL<<0) #define SECTION_HAS_MEM_MAP (1UL<<1) #define SECTION_IS_ONLINE (1UL<<2) -#define SECTION_MAP_LAST_BIT (1UL<<3) +#define SECTION_IS_EARLY (1UL<<3) +#define SECTION_MAP_LAST_BIT (1UL<<4) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) #define SECTION_NID_SHIFT 3 @@ -1286,6 +1287,11 @@ static inline int valid_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } +static inline int early_section(struct mem_section *section) +{ + return (section && (section->section_mem_map & SECTION_IS_EARLY)); +} + static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); -- cgit v1.2.3 From f46edbd1b1516da1fb34c917775168d5df576f78 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:04 -0700 Subject: mm/sparsemem: add helpers track active portions of a section at boot MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prepare for hot{plug,remove} of sub-ranges of a section by tracking a sub-section active bitmask, each bit representing a PMD_SIZE span of the architecture's memory hotplug section size. The implications of a partially populated section is that pfn_valid() needs to go beyond a valid_section() check and either determine that the section is an "early section", or read the sub-section active ranges from the bitmask. The expectation is that the bitmask (subsection_map) fits in the same cacheline as the valid_section() / early_section() data, so the incremental performance overhead to pfn_valid() should be negligible. The rationale for using early_section() to short-ciruit the subsection_map check is that there are legacy code paths that use pfn_valid() at section granularity before validating the pfn against pgdat data. So, the early_section() check allows those traditional assumptions to persist while also permitting subsection_map to tell the truth for purposes of populating the unused portions of early sections with PMEM and other ZONE_DEVICE mappings. Link: http://lkml.kernel.org/r/156092350874.979959.18185938451405518285.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Qian Cai Tested-by: Jane Chu Tested-by: Aneesh Kumar K.V [ppc64] Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Vlastimil Babka Cc: Logan Gunthorpe Cc: Pavel Tatashin Cc: David Hildenbrand Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4be40634238b..7747ec9de588 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1178,6 +1178,8 @@ struct mem_section_usage { unsigned long pageblock_flags[0]; }; +void subsection_map_init(unsigned long pfn, unsigned long nr_pages); + struct page; struct page_ext; struct mem_section { @@ -1321,12 +1323,40 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn) extern unsigned long __highest_present_section_nr; +static inline int subsection_map_index(unsigned long pfn) +{ + return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +{ + int idx = subsection_map_index(pfn); + + return test_bit(idx, ms->usage->subsection_map); +} +#else +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +{ + return 1; +} +#endif + #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { + struct mem_section *ms; + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return valid_section(__nr_to_section(pfn_to_section_nr(pfn))); + ms = __nr_to_section(pfn_to_section_nr(pfn)); + if (!valid_section(ms)) + return 0; + /* + * Traditionally early sections always returned pfn_valid() for + * the entire section-sized span. + */ + return early_section(ms) || pfn_section_valid(ms, pfn); } #endif @@ -1358,6 +1388,7 @@ void sparse_init(void); #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_present pfn_valid +#define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ /* -- cgit v1.2.3 From e9c0a3f05477e18d2dae816cb61b62be1b7e90d3 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:11 -0700 Subject: mm/sparsemem: convert kmalloc_section_memmap() to populate_section_memmap() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow sub-section sized ranges to be added to the memmap. populate_section_memmap() takes an explict pfn range rather than assuming a full section, and those parameters are plumbed all the way through to vmmemap_populate(). There should be no sub-section usage in current deployments. New warnings are added to clarify which memmap allocation paths are sub-section capable. Link: http://lkml.kernel.org/r/156092352058.979959.6551283472062305149.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reviewed-by: Pavel Tatashin Tested-by: Aneesh Kumar K.V [ppc64] Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: David Hildenbrand Cc: Logan Gunthorpe Cc: Jane Chu Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Vlastimil Babka Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 48ab7b982d82..0334ca97c584 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2767,8 +2767,8 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) #endif void *sparse_buffer_alloc(unsigned long size); -struct page *sparse_mem_map_populate(unsigned long pnum, int nid, - struct vmem_altmap *altmap); +struct page * __populate_section_memmap(unsigned long pfn, + unsigned long nr_pages, int nid, struct vmem_altmap *altmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); -- cgit v1.2.3 From 46d945aeab4d7dd837bd0724662de2caf712f047 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:18 -0700 Subject: mm: kill is_dev_zone() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Given there are no more usages of is_dev_zone() outside of 'ifdef CONFIG_ZONE_DEVICE' protection, kill off the compilation helper. Link: http://lkml.kernel.org/r/156092353211.979959.1489004866360828964.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reviewed-by: Oscar Salvador Reviewed-by: Pavel Tatashin Reviewed-by: Wei Yang Acked-by: David Hildenbrand Tested-by: Aneesh Kumar K.V [ppc64] Cc: Michal Hocko Cc: Logan Gunthorpe Cc: Jane Chu Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Vlastimil Babka Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7747ec9de588..8331e76677c0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -855,18 +855,6 @@ static inline int local_memory_node(int node_id) { return node_id; }; */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) -#ifdef CONFIG_ZONE_DEVICE -static inline bool is_dev_zone(const struct zone *zone) -{ - return zone_idx(zone) == ZONE_DEVICE; -} -#else -static inline bool is_dev_zone(const struct zone *zone) -{ - return false; -} -#endif - /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than -- cgit v1.2.3 From 7ea6216049ff9cf250a6722cd766d99c8d1424e5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:22 -0700 Subject: mm/sparsemem: prepare for sub-section ranges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prepare the memory hot-{add,remove} paths for handling sub-section ranges by plumbing the starting page frame and number of pages being handled through arch_{add,remove}_memory() to sparse_{add,remove}_one_section(). This is simply plumbing, small cleanups, and some identifier renames. No intended functional changes. Link: http://lkml.kernel.org/r/156092353780.979959.9713046515562743194.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reviewed-by: Pavel Tatashin Tested-by: Aneesh Kumar K.V [ppc64] Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Vlastimil Babka Cc: Logan Gunthorpe Cc: David Hildenbrand Cc: Jane Chu Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 475aff8efbf8..2d636a7491a4 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -346,9 +346,10 @@ extern int add_memory_resource(int nid, struct resource *resource); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern bool is_memblock_offlined(struct memory_block *mem); -extern int sparse_add_one_section(int nid, unsigned long start_pfn, - struct vmem_altmap *altmap); +extern int sparse_add_section(int nid, unsigned long pfn, + unsigned long nr_pages, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct mem_section *ms, + unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -- cgit v1.2.3 From ba72b4c8cf60e452cf6f0258ed9ee697957b7dfd Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:26 -0700 Subject: mm/sparsemem: support sub-section hotplug MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The libnvdimm sub-system has suffered a series of hacks and broken workarounds for the memory-hotplug implementation's awkward section-aligned (128MB) granularity. For example the following backtrace is emitted when attempting arch_add_memory() with physical address ranges that intersect 'System RAM' (RAM) with 'Persistent Memory' (PMEM) within a given section: # cat /proc/iomem | grep -A1 -B1 Persistent\ Memory 100000000-1ffffffff : System RAM 200000000-303ffffff : Persistent Memory (legacy) 304000000-43fffffff : System RAM 440000000-23ffffffff : Persistent Memory 2400000000-43bfffffff : Persistent Memory 2400000000-43bfffffff : namespace2.0 WARNING: CPU: 38 PID: 928 at arch/x86/mm/init_64.c:850 add_pages+0x5c/0x60 [..] RIP: 0010:add_pages+0x5c/0x60 [..] Call Trace: devm_memremap_pages+0x460/0x6e0 pmem_attach_disk+0x29e/0x680 [nd_pmem] ? nd_dax_probe+0xfc/0x120 [libnvdimm] nvdimm_bus_probe+0x66/0x160 [libnvdimm] It was discovered that the problem goes beyond RAM vs PMEM collisions as some platform produce PMEM vs PMEM collisions within a given section. The libnvdimm workaround for that case revealed that the libnvdimm section-alignment-padding implementation has been broken for a long while. A fix for that long-standing breakage introduces as many problems as it solves as it would require a backward-incompatible change to the namespace metadata interpretation. Instead of that dubious route [1], address the root problem in the memory-hotplug implementation. Note that EEXIST is no longer treated as success as that is how sparse_add_section() reports subsection collisions, it was also obviated by recent changes to perform the request_region() for 'System RAM' before arch_add_memory() in the add_memory() sequence. [1] https://lore.kernel.org/r/155000671719.348031.2347363160141119237.stgit@dwillia2-desk3.amr.corp.intel.com [osalvador@suse.de: fix deactivate_section for early sections] Link: http://lkml.kernel.org/r/20190715081549.32577-2-osalvador@suse.de Link: http://lkml.kernel.org/r/156092354368.979959.6232443923440952359.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Signed-off-by: Oscar Salvador Tested-by: Aneesh Kumar K.V [ppc64] Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Vlastimil Babka Cc: Logan Gunthorpe Cc: Pavel Tatashin Cc: David Hildenbrand Cc: Jane Chu Cc: Jeff Moyer Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Toshi Kani Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2d636a7491a4..f46ea71b4ffd 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -348,7 +348,7 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap); -extern void sparse_remove_one_section(struct mem_section *ms, +extern void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, -- cgit v1.2.3 From a3619190d62ed9d66416891be2416f6bea2b3ca4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 18 Jul 2019 15:58:40 -0700 Subject: libnvdimm/pfn: stop padding pmem namespaces to section alignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the mm core supports section-unaligned hotplug of ZONE_DEVICE memory, we no longer need to add padding at pfn/dax device creation time. The kernel will still honor padding established by older kernels. Link: http://lkml.kernel.org/r/156092356588.979959.6793371748950931916.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Jeff Moyer Tested-by: Aneesh Kumar K.V [ppc64] Cc: David Hildenbrand Cc: Jane Chu Cc: Jérôme Glisse Cc: Jonathan Corbet Cc: Logan Gunthorpe Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Toshi Kani Cc: Vlastimil Babka Cc: Wei Yang Cc: Jason Gunthorpe Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8331e76677c0..d77d717c620c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1160,6 +1160,9 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif +#define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) +#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) + struct mem_section_usage { DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); /* See declaration of similar field in struct zone */ -- cgit v1.2.3 From 371096949f0ad3950b06729989bd27de51b8c5f5 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 18 Jul 2019 15:58:46 -0700 Subject: mm: migrate: remove unused mode argument migrate_page_move_mapping() doesn't use the mode argument. Remove it and update callers accordingly. Link: http://lkml.kernel.org/r/20190508210301.8472-1-keith.busch@intel.com Signed-off-by: Keith Busch Reviewed-by: Zi Yan Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index e13d9bf2f9a5..7f04754c7f2b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -77,8 +77,7 @@ extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page, enum migrate_mode mode, - int extra_count); + struct page *newpage, struct page *page, int extra_count); #else static inline void putback_movable_pages(struct list_head *l) {} -- cgit v1.2.3 From eec4844fae7c033a0c1fc1eb3b8517aeb8b6cc49 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 18 Jul 2019 15:58:50 -0700 Subject: proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce Signed-off-by: Arnd Bergmann Acked-by: Kees Cook Reviewed-by: Aaron Tomlin Cc: Matthew Wilcox Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index aadd310769d0..6df477329b76 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -37,6 +37,13 @@ struct ctl_table_root; struct ctl_table_header; struct ctl_dir; +/* Keep the same order as in fs/proc/proc_sysctl.c */ +#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) +#define SYSCTL_ONE ((void *)&sysctl_vals[1]) +#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2]) + +extern const int sysctl_vals[]; + typedef int proc_handler (struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3