From 125d10373ad991888c9e94d2da49bcc5ccba2127 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 20 Jul 2021 13:42:15 -0700 Subject: dmanegine: idxd: add software command status Enabling device and wq returns standard errno and that does not provide enough details to indicate what exactly failed. The hardware command status is only 8bits. Expand the command status to 32bits and use the upper 16 bits to define software errors to provide more details on the exact failure. Bit 31 will be used to indicate the error is software set as the driver is using some of the spec defined hardware error as well. Cc: Ramesh Thomas Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/162681373579.1968485.5891788397526827892.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index e33997b4d750..1c0175aa0e42 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -9,6 +9,29 @@ #include #endif +/* Driver command error status */ +enum idxd_scmd_stat { + IDXD_SCMD_DEV_ENABLED = 0x80000010, + IDXD_SCMD_DEV_NOT_ENABLED = 0x80000020, + IDXD_SCMD_WQ_ENABLED = 0x80000021, + IDXD_SCMD_DEV_DMA_ERR = 0x80020000, + IDXD_SCMD_WQ_NO_GRP = 0x80030000, + IDXD_SCMD_WQ_NO_NAME = 0x80040000, + IDXD_SCMD_WQ_NO_SVM = 0x80050000, + IDXD_SCMD_WQ_NO_THRESH = 0x80060000, + IDXD_SCMD_WQ_PORTAL_ERR = 0x80070000, + IDXD_SCMD_WQ_RES_ALLOC_ERR = 0x80080000, + IDXD_SCMD_PERCPU_ERR = 0x80090000, + IDXD_SCMD_DMA_CHAN_ERR = 0x800a0000, + IDXD_SCMD_CDEV_ERR = 0x800b0000, + IDXD_SCMD_WQ_NO_SWQ_SUPPORT = 0x800c0000, + IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000, + IDXD_SCMD_WQ_NO_SIZE = 0x800e0000, +}; + +#define IDXD_SCMD_SOFTERR_MASK 0x80000000 +#define IDXD_SCMD_SOFTERR_SHIFT 16 + /* Descriptor flags */ #define IDXD_OP_FLAG_FENCE 0x0001 #define IDXD_OP_FLAG_BOF 0x0002 -- cgit v1.2.3 From 6a241d2923c2c0f6893c78c79421ceb3935691fd Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 17 Aug 2021 17:53:29 +0200 Subject: um: virt-pci: fix uapi documentation The identifier names in the documentation here didn't match the real ones, and the reserved was missing. Fix that. Reported-by: Bjorn Helgaas Fixes: 68f5d3f3b654 ("um: add PCI over virtio emulation driver") Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- include/uapi/linux/virtio_pcidev.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_pcidev.h b/include/uapi/linux/virtio_pcidev.h index 89daa88bcfef..668b07ce515b 100644 --- a/include/uapi/linux/virtio_pcidev.h +++ b/include/uapi/linux/virtio_pcidev.h @@ -9,13 +9,14 @@ /** * enum virtio_pcidev_ops - virtual PCI device operations + * @VIRTIO_PCIDEV_OP_RESERVED: reserved to catch errors * @VIRTIO_PCIDEV_OP_CFG_READ: read config space, size is 1, 2, 4 or 8; * the @data field should be filled in by the device (in little endian). * @VIRTIO_PCIDEV_OP_CFG_WRITE: write config space, size is 1, 2, 4 or 8; * the @data field contains the data to write (in little endian). - * @VIRTIO_PCIDEV_OP_BAR_READ: read BAR mem/pio, size can be variable; + * @VIRTIO_PCIDEV_OP_MMIO_READ: read BAR mem/pio, size can be variable; * the @data field should be filled in by the device (in little endian). - * @VIRTIO_PCIDEV_OP_BAR_WRITE: write BAR mem/pio, size can be variable; + * @VIRTIO_PCIDEV_OP_MMIO_WRITE: write BAR mem/pio, size can be variable; * the @data field contains the data to write (in little endian). * @VIRTIO_PCIDEV_OP_MMIO_MEMSET: memset MMIO, size is variable but * the @data field only has one byte (unlike @VIRTIO_PCIDEV_OP_MMIO_WRITE) -- cgit v1.2.3 From 486e19795f2ee11f0334e2e3fcf8951d4981ff88 Mon Sep 17 00:00:00 2001 From: Yuri Nudelman Date: Thu, 3 Jun 2021 17:51:58 +0300 Subject: habanalabs: allow fail on inability to respect hint A new user flag is required to make memory map hint mandatory, in contrast to the current situation where it is best effort. This is due to the requirement to map certain data to specific pre-determined device virtual address ranges. Signed-off-by: Yuri Nudelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index a47a731e4527..18765eb75b65 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -813,6 +813,7 @@ union hl_wait_cs_args { #define HL_MEM_CONTIGUOUS 0x1 #define HL_MEM_SHARED 0x2 #define HL_MEM_USERPTR 0x4 +#define HL_MEM_FORCE_HINT 0x8 struct hl_mem_in { union { -- cgit v1.2.3 From 215f0c1775d5506c8a833b5c85a77b5fb65bf26b Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Mon, 14 Jun 2021 22:18:41 +0300 Subject: habanalabs: add wait-for-multi-CS uAPI When user sends multiple CSs, waiting for each CS is not efficient as it involves many user-kernel context switches. In order to address this issue we add support to "wait on multiple CSs" using a new uAPI which can wait on maximum of 32 CSs. The new uAPI is defined using a new flag - WAIT_FOR_MULTI_CS - in the wait_for_cs IOCTL. The input parameters for this uAPI will be: @seq: user pointer to an array of up to 32 CS's sequence numbers. @seq_array_len: length of sequence array. @timeout_us: timeout for waiting for any CS. The output paramateres for this API will be: @status: multi CS ioctl completion status (dedicated status was added as well). @flags: bitmap of output flags of the CS. @cs_completion_map: bitmap for multi CS, if CS sequence that was placed in index N in input seq array has completed- the N-th bit in cs_completion_map will be 1, otherwise it will be 0. @timestamp_nsec: timestamp of the first completed CS Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 18765eb75b65..49c737c4a2f6 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -735,11 +735,18 @@ union hl_cs_args { #define HL_WAIT_CS_FLAGS_INTERRUPT 0x2 #define HL_WAIT_CS_FLAGS_INTERRUPT_MASK 0xFFF00000 +#define HL_WAIT_CS_FLAGS_MULTI_CS 0x4 + +#define HL_WAIT_MULTI_CS_LIST_MAX_LEN 32 struct hl_wait_cs_in { union { struct { - /* Command submission sequence number */ + /* + * In case of wait_cs holds the CS sequence number. + * In case of wait for multi CS hold a user pointer to + * an array of CS sequence numbers + */ __u64 seq; /* Absolute timeout to wait for command submission * in microseconds @@ -767,12 +774,17 @@ struct hl_wait_cs_in { /* Context ID - Currently not in use */ __u32 ctx_id; + /* HL_WAIT_CS_FLAGS_* * If HL_WAIT_CS_FLAGS_INTERRUPT is set, this field should include * interrupt id according to HL_WAIT_CS_FLAGS_INTERRUPT_MASK, in order * not to specify an interrupt id ,set mask to all 1s. */ __u32 flags; + + /* Multi CS API info- valid entries in multi-CS array */ + __u8 seq_arr_len; + __u8 pad[7]; }; #define HL_WAIT_CS_STATUS_COMPLETED 0 @@ -789,8 +801,15 @@ struct hl_wait_cs_out { __u32 status; /* HL_WAIT_CS_STATUS_FLAG* */ __u32 flags; - /* valid only if HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD is set */ + /* + * valid only if HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD is set + * for wait_cs: timestamp of CS completion + * for wait_multi_cs: timestamp of FIRST CS completion + */ __s64 timestamp_nsec; + /* multi CS completion bitmap */ + __u32 cs_completion_map; + __u32 pad; }; union hl_wait_cs_args { -- cgit v1.2.3 From dadf17abb7245d9556591d8cc78bf57462e3b20a Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Mon, 24 May 2021 18:09:22 +0300 Subject: habanalabs: add support for encapsulated signals reservation The signaling from within encapsulated OP capability is merged into the existing stream architecture, such that one can trigger multiple signaling from an encapsulated op, according to the time the event was done in the graph execution and avoid the need to wait for the whole encapsulated OP execution to be complete before the stream can signal. This commit implements only the reserve/unreserve part. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 110 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 97 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 49c737c4a2f6..eca86c545916 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -628,12 +628,21 @@ struct hl_cs_chunk { __u64 cb_handle; /* Relevant only when HL_CS_FLAGS_WAIT or - * HL_CS_FLAGS_COLLECTIVE_WAIT is set. + * HL_CS_FLAGS_COLLECTIVE_WAIT is set * This holds address of array of u64 values that contain - * signal CS sequence numbers. The wait described by this job - * will listen on all those signals (wait event per signal) + * signal CS sequence numbers. The wait described by + * this job will listen on all those signals + * (wait event per signal) */ __u64 signal_seq_arr; + + /* + * Relevant only when HL_CS_FLAGS_WAIT or + * HL_CS_FLAGS_COLLECTIVE_WAIT is set + * along with HL_CS_FLAGS_ENCAP_SIGNALS. + * This is the CS sequence which has the encapsulated signals. + */ + __u64 encaps_signal_seq; }; /* Index of queue to put the CB on */ @@ -651,6 +660,17 @@ struct hl_cs_chunk { * Number of entries in signal_seq_arr */ __u32 num_signal_seq_arr; + + /* Relevant only when HL_CS_FLAGS_WAIT or + * HL_CS_FLAGS_COLLECTIVE_WAIT is set along + * with HL_CS_FLAGS_ENCAP_SIGNALS + * This set the signals range that the user want to wait for + * out of the whole reserved signals range. + * e.g if the signals range is 20, and user don't want + * to wait for signal 8, so he set this offset to 7, then + * he call the API again with 9 and so on till 20. + */ + __u32 encaps_signal_offset; }; /* HL_CS_CHUNK_FLAGS_* */ @@ -678,6 +698,28 @@ struct hl_cs_chunk { #define HL_CS_FLAGS_CUSTOM_TIMEOUT 0x200 #define HL_CS_FLAGS_SKIP_RESET_ON_TIMEOUT 0x400 +/* + * The encapsulated signals CS is merged into the existing CS ioctls. + * In order to use this feature need to follow the below procedure: + * 1. Reserve signals, set the CS type to HL_CS_FLAGS_RESERVE_SIGNALS_ONLY + * the output of this API will be the SOB offset from CFG_BASE. + * this address will be used to patch CB cmds to do the signaling for this + * SOB by incrementing it's value. + * for reverting the reservation use HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY + * CS type, note that this might fail if out-of-sync happened to the SOB + * value, in case other signaling request to the same SOB occurred between + * reserve-unreserve calls. + * 2. Use the staged CS to do the encapsulated signaling jobs. + * use HL_CS_FLAGS_STAGED_SUBMISSION and HL_CS_FLAGS_STAGED_SUBMISSION_FIRST + * along with HL_CS_FLAGS_ENCAP_SIGNALS flag, and set encaps_signal_offset + * field. This offset allows app to wait on part of the reserved signals. + * 3. Use WAIT/COLLECTIVE WAIT CS along with HL_CS_FLAGS_ENCAP_SIGNALS flag + * to wait for the encapsulated signals. + */ +#define HL_CS_FLAGS_ENCAP_SIGNALS 0x800 +#define HL_CS_FLAGS_RESERVE_SIGNALS_ONLY 0x1000 +#define HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY 0x2000 + #define HL_CS_STATUS_SUCCESS 0 #define HL_MAX_JOBS_PER_CS 512 @@ -690,10 +732,35 @@ struct hl_cs_in { /* holds address of array of hl_cs_chunk for execution phase */ __u64 chunks_execute; - /* Sequence number of a staged submission CS - * valid only if HL_CS_FLAGS_STAGED_SUBMISSION is set - */ - __u64 seq; + union { + /* + * Sequence number of a staged submission CS + * valid only if HL_CS_FLAGS_STAGED_SUBMISSION is set and + * HL_CS_FLAGS_STAGED_SUBMISSION_FIRST is unset. + */ + __u64 seq; + + /* + * Encapsulated signals handle id + * Valid for two flows: + * 1. CS with encapsulated signals: + * when HL_CS_FLAGS_STAGED_SUBMISSION and + * HL_CS_FLAGS_STAGED_SUBMISSION_FIRST + * and HL_CS_FLAGS_ENCAP_SIGNALS are set. + * 2. unreserve signals: + * valid when HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY is set. + */ + __u32 encaps_sig_handle_id; + + /* Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */ + struct { + /* Encapsulated signals number */ + __u32 encaps_signals_count; + + /* Encapsulated signals queue index (stream) */ + __u32 encaps_signals_q_idx; + }; + }; /* Number of chunks in restore phase array. Maximum number is * HL_MAX_JOBS_PER_CS @@ -718,14 +785,31 @@ struct hl_cs_in { }; struct hl_cs_out { + union { + /* + * seq holds the sequence number of the CS to pass to wait + * ioctl. All values are valid except for 0 and ULLONG_MAX + */ + __u64 seq; + + /* Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */ + struct { + /* This is the resereved signal handle id */ + __u32 handle_id; + + /* This is the signals count */ + __u32 count; + }; + }; + + /* HL_CS_STATUS */ + __u32 status; + /* - * seq holds the sequence number of the CS to pass to wait ioctl. All - * values are valid except for 0 and ULLONG_MAX + * SOB base address offset + * Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */ - __u64 seq; - /* HL_CS_STATUS_* */ - __u32 status; - __u32 pad; + __u32 sob_base_addr_offset; }; union hl_cs_args { -- cgit v1.2.3 From d8071323c5632bdf0a8ef9b9e5662fac43649f9d Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 19 Aug 2021 09:34:06 -0700 Subject: dmaengine: idxd: fix setting up priv mode for dwq DSA spec says WQ priv bit is 0 if the Privileged Mode Enable field of the PCI Express PASID capability is 0 and pasid is enabled. Make sure that the WQCFG priv field is set correctly according to usage type. Reject config if setting up kernel WQ type and no support. Also add the correct priv setup for a descriptor. Fixes: 484f910e93b4 ("dmaengine: idxd: fix wq config registers offset programming") Cc: Ramesh Thomas Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/162939084657.903168.14160019185148244596.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index ca24c25252fb..c750eac09fc9 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -27,6 +27,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_NO_SWQ_SUPPORT = 0x800c0000, IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000, IDXD_SCMD_WQ_NO_SIZE = 0x800e0000, + IDXD_SCMD_WQ_NO_PRIV = 0x800f0000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 -- cgit v1.2.3 From 5dc9ffaff1420676827c4054bc789a7710f2a272 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 15 Jul 2021 10:48:43 +0300 Subject: habanalabs: expose server type in INFO IOCTL Add the server type property to the hl_info_hw_ip_info structure that is exposed to the user via the INFO IOCTL. This is needed by the userspace s/w stack to know the connections map of the internal links that connect the ASIC among themselves inside the server. The F/W will tell us, as part of the NIC information, the server type that the GAUDI is located in. Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 48 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index eca86c545916..6686b73a0834 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -279,6 +279,14 @@ enum hl_device_status { HL_DEVICE_STATUS_NEEDS_RESET }; +enum hl_server_type { + HL_SERVER_TYPE_UNKNOWN = 0, + HL_SERVER_GAUDI_HLS1 = 1, + HL_SERVER_GAUDI_HLS1H = 2, + HL_SERVER_GAUDI_TYPE1 = 3, + HL_SERVER_GAUDI_TYPE2 = 4 +}; + /* Opcode for management ioctl * * HW_IP_INFO - Receive information about different IP blocks in the @@ -337,17 +345,49 @@ enum hl_device_status { #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 +/** + * struct hl_info_hw_ip_info - hardware information on various IPs in the ASIC + * @sram_base_address: The first SRAM physical base address that is free to be + * used by the user. + * @dram_base_address: The first DRAM virtual or physical base address that is + * free to be used by the user. + * @dram_size: The DRAM size that is available to the user. + * @sram_size: The SRAM size that is available to the user. + * @num_of_events: The number of events that can be received from the f/w. This + * is needed so the user can what is the size of the h/w events + * array he needs to pass to the kernel when he wants to fetch + * the event counters. + * @device_id: PCI device ID of the ASIC. + * @module_id: Module ID of the ASIC for mezzanine cards in servers + * (From OCP spec). + * @first_available_interrupt_id: The first available interrupt ID for the user + * to be used when it works with user interrupts. + * @server_type: Server type that the Gaudi ASIC is currently installed in. + * The value is according to enum hl_server_type + * @cpld_version: CPLD version on the board. + * @psoc_pci_pll_nr: PCI PLL NR value. Needed by the profiler in some ASICs. + * @psoc_pci_pll_nf: PCI PLL NF value. Needed by the profiler in some ASICs. + * @psoc_pci_pll_od: PCI PLL OD value. Needed by the profiler in some ASICs. + * @psoc_pci_pll_div_factor: PCI PLL DIV factor value. Needed by the profiler + * in some ASICs. + * @tpc_enabled_mask: Bit-mask that represents which TPCs are enabled. Relevant + * for Goya/Gaudi only. + * @dram_enabled: Whether the DRAM is enabled. + * @cpucp_version: The CPUCP f/w version. + * @card_name: The card name as passed by the f/w. + * @dram_page_size: The DRAM physical page size. + */ struct hl_info_hw_ip_info { __u64 sram_base_address; __u64 dram_base_address; __u64 dram_size; __u32 sram_size; __u32 num_of_events; - __u32 device_id; /* PCI Device ID */ - __u32 module_id; /* For mezzanine cards in servers (From OCP spec.) */ + __u32 device_id; + __u32 module_id; __u32 reserved; __u16 first_available_interrupt_id; - __u16 reserved2; + __u16 server_type; __u32 cpld_version; __u32 psoc_pci_pll_nr; __u32 psoc_pci_pll_nf; @@ -358,7 +398,7 @@ struct hl_info_hw_ip_info { __u8 pad[2]; __u8 cpucp_version[HL_INFO_VERSION_MAX_LEN]; __u8 card_name[HL_INFO_CARD_NAME_MAX_LEN]; - __u64 reserved3; + __u64 reserved2; __u64 dram_page_size; }; -- cgit v1.2.3 From 71731090ab17a208a58020e4b342fdfee280458a Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Mon, 16 Aug 2021 13:27:12 +0300 Subject: habanalabs: add "in device creation" status On init, the disabled state is cleared right before hw_init and that causes the device to report on "Operational" state before the device initialization is finished. Although the char device is not yet exposed to the user at this stage, the sysfs entries are exposed. This can cause errors in monitoring applications that use the sysfs entries. In order to avoid this, a new state "in device creation" is introduced to ne reported when the device is not disabled but is still in init flow. Signed-off-by: Omer Shpigelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 6686b73a0834..7cc2a0f3f2f5 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -276,7 +276,9 @@ enum hl_device_status { HL_DEVICE_STATUS_OPERATIONAL, HL_DEVICE_STATUS_IN_RESET, HL_DEVICE_STATUS_MALFUNCTION, - HL_DEVICE_STATUS_NEEDS_RESET + HL_DEVICE_STATUS_NEEDS_RESET, + HL_DEVICE_STATUS_IN_DEVICE_CREATION, + HL_DEVICE_STATUS_LAST = HL_DEVICE_STATUS_IN_DEVICE_CREATION }; enum hl_server_type { -- cgit v1.2.3 From d5a8680dfab0547a4ecd708b1fe9de48598a6757 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 27 Jul 2021 10:53:51 +0530 Subject: uapi: virtio_ids: Sync ids with specification This synchronizes the virtio ids with the latest list from virtio specification. Signed-off-by: Viresh Kumar Link: https://lore.kernel.org/r/61b27e3bc61fb0c9f067001e95cfafc5d37d414a.1627362340.git.viresh.kumar@linaro.org Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 70a8057ad4bb..3c8e11820fdb 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -54,8 +54,20 @@ #define VIRTIO_ID_SOUND 25 /* virtio sound */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ +#define VIRTIO_ID_RPMB 28 /* virtio rpmb */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ +#define VIRTIO_ID_VIDEO_ENCODER 30 /* virtio video encoder */ +#define VIRTIO_ID_VIDEO_DECODER 31 /* virtio video decoder */ +#define VIRTIO_ID_SCMI 32 /* virtio scmi */ +#define VIRTIO_ID_NITRO_SEC_MOD 33 /* virtio nitro secure module*/ +#define VIRTIO_ID_I2C_ADAPTER 34 /* virtio i2c adapter */ +#define VIRTIO_ID_WATCHDOG 35 /* virtio watchdog */ +#define VIRTIO_ID_CAN 36 /* virtio can */ +#define VIRTIO_ID_DMABUF 37 /* virtio dmabuf */ +#define VIRTIO_ID_PARAM_SERV 38 /* virtio parameter server */ +#define VIRTIO_ID_AUDIO_POLICY 39 /* virtio audio policy */ #define VIRTIO_ID_BT 40 /* virtio bluetooth */ +#define VIRTIO_ID_GPIO 41 /* virtio gpio */ /* * Virtio Transitional IDs -- cgit v1.2.3 From 9af8f1061646e8e22b66413bedf7b3e2ab3d69e5 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 3 Sep 2021 15:31:06 +0300 Subject: virtio/vsock: rename 'EOR' to 'EOM' bit. This current implemented bit is used to mark end of messages ('EOM' - end of message), not records('EOR' - end of record). Also rename 'record' to 'message' in implementation as it is different things. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20210903123109.3273053-1-arseny.krasnov@kaspersky.com Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_vsock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 3dd3555b2740..8485b004a5f8 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -97,7 +97,7 @@ enum virtio_vsock_shutdown { /* VIRTIO_VSOCK_OP_RW flags values */ enum virtio_vsock_rw { - VIRTIO_VSOCK_SEQ_EOR = 1, + VIRTIO_VSOCK_SEQ_EOM = 1, }; #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From 41116599a0731f4cd451e9d191d879ab45e31945 Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 3 Sep 2021 15:32:23 +0300 Subject: virtio/vsock: add 'VIRTIO_VSOCK_SEQ_EOR' bit. This bit is used to handle POSIX MSG_EOR flag passed from userspace in 'send*()' system calls. It marks end of each record and is visible to receiver using 'recvmsg()' system call. Signed-off-by: Arseny Krasnov Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20210903123225.3273425-1-arseny.krasnov@kaspersky.com Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 8485b004a5f8..64738838bee5 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -98,6 +98,7 @@ enum virtio_vsock_shutdown { /* VIRTIO_VSOCK_OP_RW flags values */ enum virtio_vsock_rw { VIRTIO_VSOCK_SEQ_EOM = 1, + VIRTIO_VSOCK_SEQ_EOR = 2, }; #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From c8a6153b6c59d95c0e091f053f6f180952ade91e Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 31 Aug 2021 18:36:33 +0800 Subject: vduse: Introduce VDUSE - vDPA Device in Userspace This VDUSE driver enables implementing software-emulated vDPA devices in userspace. The vDPA device is created by ioctl(VDUSE_CREATE_DEV) on /dev/vduse/control. Then a char device interface (/dev/vduse/$NAME) is exported to userspace for device emulation. In order to make the device emulation more secure, the device's control path is handled in kernel. A message mechnism is introduced to forward some dataplane related control messages to userspace. And in the data path, the DMA buffer will be mapped into userspace address space through different ways depending on the vDPA bus to which the vDPA device is attached. In virtio-vdpa case, the MMU-based software IOTLB is used to achieve that. And in vhost-vdpa case, the DMA buffer is reside in a userspace memory region which can be shared to the VDUSE userspace processs via transferring the shmfd. For more details on VDUSE design and usage, please see the follow-on Documentation commit. NB(mst): when merging this with b542e383d8c0 ("eventfd: Make signal recursion protection a task bit") replace eventfd_signal_count with eventfd_signal_allowed, and drop the previous ("eventfd: Export eventfd_wake_count to modules"). Signed-off-by: Xie Yongji Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210831103634.33-13-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vduse.h | 306 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 306 insertions(+) create mode 100644 include/uapi/linux/vduse.h (limited to 'include/uapi') diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h new file mode 100644 index 000000000000..7cfe1c1280c0 --- /dev/null +++ b/include/uapi/linux/vduse.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_VDUSE_H_ +#define _UAPI_VDUSE_H_ + +#include + +#define VDUSE_BASE 0x81 + +/* The ioctls for control device (/dev/vduse/control) */ + +#define VDUSE_API_VERSION 0 + +/* + * Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION). + * This is used for future extension. + */ +#define VDUSE_GET_API_VERSION _IOR(VDUSE_BASE, 0x00, __u64) + +/* Set the version of VDUSE API that userspace supported. */ +#define VDUSE_SET_API_VERSION _IOW(VDUSE_BASE, 0x01, __u64) + +/** + * struct vduse_dev_config - basic configuration of a VDUSE device + * @name: VDUSE device name, needs to be NUL terminated + * @vendor_id: virtio vendor id + * @device_id: virtio device id + * @features: virtio features + * @vq_num: the number of virtqueues + * @vq_align: the allocation alignment of virtqueue's metadata + * @reserved: for future use, needs to be initialized to zero + * @config_size: the size of the configuration space + * @config: the buffer of the configuration space + * + * Structure used by VDUSE_CREATE_DEV ioctl to create VDUSE device. + */ +struct vduse_dev_config { +#define VDUSE_NAME_MAX 256 + char name[VDUSE_NAME_MAX]; + __u32 vendor_id; + __u32 device_id; + __u64 features; + __u32 vq_num; + __u32 vq_align; + __u32 reserved[13]; + __u32 config_size; + __u8 config[]; +}; + +/* Create a VDUSE device which is represented by a char device (/dev/vduse/$NAME) */ +#define VDUSE_CREATE_DEV _IOW(VDUSE_BASE, 0x02, struct vduse_dev_config) + +/* + * Destroy a VDUSE device. Make sure there are no more references + * to the char device (/dev/vduse/$NAME). + */ +#define VDUSE_DESTROY_DEV _IOW(VDUSE_BASE, 0x03, char[VDUSE_NAME_MAX]) + +/* The ioctls for VDUSE device (/dev/vduse/$NAME) */ + +/** + * struct vduse_iotlb_entry - entry of IOTLB to describe one IOVA region [start, last] + * @offset: the mmap offset on returned file descriptor + * @start: start of the IOVA region + * @last: last of the IOVA region + * @perm: access permission of the IOVA region + * + * Structure used by VDUSE_IOTLB_GET_FD ioctl to find an overlapped IOVA region. + */ +struct vduse_iotlb_entry { + __u64 offset; + __u64 start; + __u64 last; +#define VDUSE_ACCESS_RO 0x1 +#define VDUSE_ACCESS_WO 0x2 +#define VDUSE_ACCESS_RW 0x3 + __u8 perm; +}; + +/* + * Find the first IOVA region that overlaps with the range [start, last] + * and return the corresponding file descriptor. Return -EINVAL means the + * IOVA region doesn't exist. Caller should set start and last fields. + */ +#define VDUSE_IOTLB_GET_FD _IOWR(VDUSE_BASE, 0x10, struct vduse_iotlb_entry) + +/* + * Get the negotiated virtio features. It's a subset of the features in + * struct vduse_dev_config which can be accepted by virtio driver. It's + * only valid after FEATURES_OK status bit is set. + */ +#define VDUSE_DEV_GET_FEATURES _IOR(VDUSE_BASE, 0x11, __u64) + +/** + * struct vduse_config_data - data used to update configuration space + * @offset: the offset from the beginning of configuration space + * @length: the length to write to configuration space + * @buffer: the buffer used to write from + * + * Structure used by VDUSE_DEV_SET_CONFIG ioctl to update device + * configuration space. + */ +struct vduse_config_data { + __u32 offset; + __u32 length; + __u8 buffer[]; +}; + +/* Set device configuration space */ +#define VDUSE_DEV_SET_CONFIG _IOW(VDUSE_BASE, 0x12, struct vduse_config_data) + +/* + * Inject a config interrupt. It's usually used to notify virtio driver + * that device configuration space has changed. + */ +#define VDUSE_DEV_INJECT_CONFIG_IRQ _IO(VDUSE_BASE, 0x13) + +/** + * struct vduse_vq_config - basic configuration of a virtqueue + * @index: virtqueue index + * @max_size: the max size of virtqueue + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_VQ_SETUP ioctl to setup a virtqueue. + */ +struct vduse_vq_config { + __u32 index; + __u16 max_size; + __u16 reserved[13]; +}; + +/* + * Setup the specified virtqueue. Make sure all virtqueues have been + * configured before the device is attached to vDPA bus. + */ +#define VDUSE_VQ_SETUP _IOW(VDUSE_BASE, 0x14, struct vduse_vq_config) + +/** + * struct vduse_vq_state_split - split virtqueue state + * @avail_index: available index + */ +struct vduse_vq_state_split { + __u16 avail_index; +}; + +/** + * struct vduse_vq_state_packed - packed virtqueue state + * @last_avail_counter: last driver ring wrap counter observed by device + * @last_avail_idx: device available index + * @last_used_counter: device ring wrap counter + * @last_used_idx: used index + */ +struct vduse_vq_state_packed { + __u16 last_avail_counter; + __u16 last_avail_idx; + __u16 last_used_counter; + __u16 last_used_idx; +}; + +/** + * struct vduse_vq_info - information of a virtqueue + * @index: virtqueue index + * @num: the size of virtqueue + * @desc_addr: address of desc area + * @driver_addr: address of driver area + * @device_addr: address of device area + * @split: split virtqueue state + * @packed: packed virtqueue state + * @ready: ready status of virtqueue + * + * Structure used by VDUSE_VQ_GET_INFO ioctl to get virtqueue's information. + */ +struct vduse_vq_info { + __u32 index; + __u32 num; + __u64 desc_addr; + __u64 driver_addr; + __u64 device_addr; + union { + struct vduse_vq_state_split split; + struct vduse_vq_state_packed packed; + }; + __u8 ready; +}; + +/* Get the specified virtqueue's information. Caller should set index field. */ +#define VDUSE_VQ_GET_INFO _IOWR(VDUSE_BASE, 0x15, struct vduse_vq_info) + +/** + * struct vduse_vq_eventfd - eventfd configuration for a virtqueue + * @index: virtqueue index + * @fd: eventfd, -1 means de-assigning the eventfd + * + * Structure used by VDUSE_VQ_SETUP_KICKFD ioctl to setup kick eventfd. + */ +struct vduse_vq_eventfd { + __u32 index; +#define VDUSE_EVENTFD_DEASSIGN -1 + int fd; +}; + +/* + * Setup kick eventfd for specified virtqueue. The kick eventfd is used + * by VDUSE kernel module to notify userspace to consume the avail vring. + */ +#define VDUSE_VQ_SETUP_KICKFD _IOW(VDUSE_BASE, 0x16, struct vduse_vq_eventfd) + +/* + * Inject an interrupt for specific virtqueue. It's used to notify virtio driver + * to consume the used vring. + */ +#define VDUSE_VQ_INJECT_IRQ _IOW(VDUSE_BASE, 0x17, __u32) + +/* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ + +/** + * enum vduse_req_type - request type + * @VDUSE_GET_VQ_STATE: get the state for specified virtqueue from userspace + * @VDUSE_SET_STATUS: set the device status + * @VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for + * specified IOVA range via VDUSE_IOTLB_GET_FD ioctl + */ +enum vduse_req_type { + VDUSE_GET_VQ_STATE, + VDUSE_SET_STATUS, + VDUSE_UPDATE_IOTLB, +}; + +/** + * struct vduse_vq_state - virtqueue state + * @index: virtqueue index + * @split: split virtqueue state + * @packed: packed virtqueue state + */ +struct vduse_vq_state { + __u32 index; + union { + struct vduse_vq_state_split split; + struct vduse_vq_state_packed packed; + }; +}; + +/** + * struct vduse_dev_status - device status + * @status: device status + */ +struct vduse_dev_status { + __u8 status; +}; + +/** + * struct vduse_iova_range - IOVA range [start, last] + * @start: start of the IOVA range + * @last: last of the IOVA range + */ +struct vduse_iova_range { + __u64 start; + __u64 last; +}; + +/** + * struct vduse_dev_request - control request + * @type: request type + * @request_id: request id + * @reserved: for future use + * @vq_state: virtqueue state, only index field is available + * @s: device status + * @iova: IOVA range for updating + * @padding: padding + * + * Structure used by read(2) on /dev/vduse/$NAME. + */ +struct vduse_dev_request { + __u32 type; + __u32 request_id; + __u32 reserved[4]; + union { + struct vduse_vq_state vq_state; + struct vduse_dev_status s; + struct vduse_iova_range iova; + __u32 padding[32]; + }; +}; + +/** + * struct vduse_dev_response - response to control request + * @request_id: corresponding request id + * @result: the result of request + * @reserved: for future use, needs to be initialized to zero + * @vq_state: virtqueue state + * @padding: padding + * + * Structure used by write(2) on /dev/vduse/$NAME. + */ +struct vduse_dev_response { + __u32 request_id; +#define VDUSE_REQ_RESULT_OK 0x00 +#define VDUSE_REQ_RESULT_FAILED 0x01 + __u32 result; + __u32 reserved[4]; + union { + struct vduse_vq_state vq_state; + __u32 padding[32]; + }; +}; + +#endif /* _UAPI_VDUSE_H_ */ -- cgit v1.2.3 From 9d1b3afd73047d4dd30e3636412c9f9b5def2b14 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Fri, 3 Sep 2021 19:20:56 -0700 Subject: cxl/uapi: Fix defined but not used warnings Fix unused-const-variable warnings emitted by gcc when cxlmem.h is used by pretty much all files except pci.c Signed-off-by: Ben Widawsky Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163072205652.2250120.16833548560832424468.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/uapi/linux/cxl_mem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index f6e8a005b113..8d206f27bb6d 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -50,7 +50,7 @@ enum { CXL_CMDS }; #define ___C(a, b) { b } static const struct { const char *name; -} cxl_command_names[] = { CXL_CMDS }; +} cxl_command_names[] __attribute__((__unused__)) = { CXL_CMDS }; /* * Here's how this actually breaks out: -- cgit v1.2.3 From 59ab844eed9c6b01d32dcb27b57accc23771b324 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 8 Sep 2021 15:18:25 -0700 Subject: compat: remove some compat entry points These are all handled correctly when calling the native system call entry point, so remove the special cases. Link: https://lkml.kernel.org/r/20210727144859.4150043-6-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Cc: Al Viro Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: "David S. Miller" Cc: Eric Biederman Cc: Feng Tang Cc: Heiko Carstens Cc: Helge Deller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/asm-generic/unistd.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 14c8fe863c6d..1c5fb86d455a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -673,15 +673,15 @@ __SYSCALL(__NR_madvise, sys_madvise) #define __NR_remap_file_pages 234 __SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) #define __NR_mbind 235 -__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind) +__SYSCALL(__NR_mbind, sys_mbind) #define __NR_get_mempolicy 236 -__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy) +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) #define __NR_set_mempolicy 237 -__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy) +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) #define __NR_migrate_pages 238 -__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages) +__SYSCALL(__NR_migrate_pages, sys_migrate_pages) #define __NR_move_pages 239 -__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages) +__SYSCALL(__NR_move_pages, sys_move_pages) #endif #define __NR_rt_tgsigqueueinfo 240 -- cgit v1.2.3