From 158350aae16a4e666e261da0bb4d91c0601a3edd Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Thu, 16 Feb 2023 13:09:45 +0000 Subject: drm: document DRM_IOCTL_GEM_CLOSE This is a bit tricky, because of the ref'counting considerations. See also [1] for more discussion about this topic. Since this is kernel docs, I've decided to elaborate a bit less on the user-space details. [1]: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/110 Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Pekka Paalanen Cc: Daniel Stone Reviewed-by: Daniel Vetter Acked-by: Pekka Paalanen Link: https://patchwork.freedesktop.org/patch/msgid/20230216130934.156541-2-contact@emersion.fr --- include/uapi/drm/drm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 642808520d92..c39fefb54613 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) -- cgit v1.2.3 From 61a55f8b1ebcde68bc7bfd57435b1b3bb1121b8f Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 17 Feb 2023 16:22:01 +0000 Subject: drm: document expectations for GETFB2 handles There are two important details missing from the docs: - If the memory object backing the FB already has a GEM handle, it's not re-used, a new one is generated. - Aliased planes will return the same GEM handle. v2: document how user-space can obtain DMA-BUF FDs without leaking handles (Pekka) Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Pekka Paalanen Cc: Daniel Stone Acked-by: Pekka Paalanen Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20230217162151.59996-1-contact@emersion.fr --- include/uapi/drm/drm.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index c39fefb54613..292e4778a2f4 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -1117,8 +1117,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1126,6 +1131,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) -- cgit v1.2.3 From 6068771673a38efc31ed5b99645176b4d3a33129 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 17 Feb 2023 16:22:04 +0000 Subject: drm: document DRM_IOCTL_PRIME_HANDLE_TO_FD and PRIME_FD_TO_HANDLE v2: mention caps, note that the IOCTLs might fail, document that user-space needs a data structure to keep track of the handles (Daniel V.) Signed-off-by: Simon Ser Cc: Daniel Vetter Cc: Pekka Paalanen Cc: Daniel Stone Reviewed-by: Daniel Vetter Acked-by: Pekka Paalanen Link: https://patchwork.freedesktop.org/patch/msgid/20230217162151.59996-2-contact@emersion.fr --- include/uapi/drm/drm.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 292e4778a2f4..a87bbbbca2d4 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -1025,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) -- cgit v1.2.3 From fd234e7581162573742dfb8cc4dc0af3d3148138 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Tue, 16 Nov 2021 23:15:55 -0500 Subject: drm/amdkfd: Implement DMA buf fd export from KFD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Exports a DMA buf fd of a given KFD buffer handle. This is intended for being able to import KFD BOs into GEM contexts to leverage the amdgpu_bo_va API for more flexible virtual address mappings. It will also be used for the new upstreamable RDMA solution coming to UCX and RCCL. The corresponding user mode change (Thunk API and kfdtest) is here: https://github.com/fxkamd/ROCT-Thunk-Interface/commits/fxkamd/dmabuf Signed-off-by: Felix Kuehling Acked-by: Christian König Reviewed-by: Xiaogang Chen Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 42b60198b6c5..2da5c3ad71bd 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -37,9 +37,10 @@ * - 1.9 - Add available memory ioctl * - 1.10 - Add SMI profiler event log * - 1.11 - Add unified memory for ctx save/restore area + * - 1.12 - Add DMA buf export ioctl */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 11 +#define KFD_IOCTL_MINOR_VERSION 12 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -463,6 +464,12 @@ struct kfd_ioctl_import_dmabuf_args { __u32 dmabuf_fd; /* to KFD */ }; +struct kfd_ioctl_export_dmabuf_args { + __u64 handle; /* to KFD */ + __u32 flags; /* to KFD */ + __u32 dmabuf_fd; /* from KFD */ +}; + /* * KFD SMI(System Management Interface) events */ @@ -877,7 +884,10 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_AVAILABLE_MEMORY \ AMDKFD_IOWR(0x23, struct kfd_ioctl_get_available_memory_args) +#define AMDKFD_IOC_EXPORT_DMABUF \ + AMDKFD_IOWR(0x24, struct kfd_ioctl_export_dmabuf_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x24 +#define AMDKFD_COMMAND_END 0x25 #endif -- cgit v1.2.3 From 313e9f63b74419ca14c2c09f581a79c7037ee0e2 Mon Sep 17 00:00:00 2001 From: Moti Haimovski Date: Tue, 10 Jan 2023 17:35:31 +0200 Subject: accel/habanalabs: add critical-event bit in notifier Enhance the existing user notifications by adding a HW and FW critical event bits to be used when a HW or FW event occur that requires both SW abort and hard-resetting the chip. Signed-off-by: Moti Haimovski Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Reviewed-by: Stanislaw Gruszka --- include/uapi/drm/habanalabs_accel.h | 43 +++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 331567ec9e79..3a62652a6452 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -723,6 +723,10 @@ enum hl_server_type { * HL_NOTIFIER_EVENT_GENERAL_HW_ERR - Indicates device HW error * HL_NOTIFIER_EVENT_RAZWI - Indicates razwi happened * HL_NOTIFIER_EVENT_PAGE_FAULT - Indicates page fault happened + * HL_NOTIFIER_EVENT_CRITICAL_HW_ERR - Indicates a HW error that requires SW abort and + * HW reset + * HL_NOTIFIER_EVENT_CRITICAL_FW_ERR - Indicates a FW error that requires SW abort and + * HW reset */ #define HL_NOTIFIER_EVENT_TPC_ASSERT (1ULL << 0) #define HL_NOTIFIER_EVENT_UNDEFINED_OPCODE (1ULL << 1) @@ -733,6 +737,8 @@ enum hl_server_type { #define HL_NOTIFIER_EVENT_GENERAL_HW_ERR (1ULL << 6) #define HL_NOTIFIER_EVENT_RAZWI (1ULL << 7) #define HL_NOTIFIER_EVENT_PAGE_FAULT (1ULL << 8) +#define HL_NOTIFIER_EVENT_CRITICL_HW_ERR (1ULL << 9) +#define HL_NOTIFIER_EVENT_CRITICL_FW_ERR (1ULL << 10) /* Opcode for management ioctl * @@ -790,6 +796,8 @@ enum hl_server_type { * HL_INFO_PAGE_FAULT_EVENT - Retrieve parameters of captured page fault. * HL_INFO_USER_MAPPINGS - Retrieve user mappings, captured after page fault event. * HL_INFO_FW_GENERIC_REQ - Send generic request to FW. + * HL_INFO_HW_ERR_EVENT - Retrieve information on the reported HW error. + * HL_INFO_FW_ERR_EVENT - Retrieve information on the reported FW error. */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -824,6 +832,8 @@ enum hl_server_type { #define HL_INFO_PAGE_FAULT_EVENT 33 #define HL_INFO_USER_MAPPINGS 34 #define HL_INFO_FW_GENERIC_REQ 35 +#define HL_INFO_HW_ERR_EVENT 36 +#define HL_INFO_FW_ERR_EVENT 37 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -1161,6 +1171,39 @@ struct hl_info_undefined_opcode_event { __u32 stream_id; }; +/** + * struct hl_info_hw_err_event - info about HW error + * @timestamp: timestamp of error occurrence + * @event_id: The async event ID (specific to each device type). + * @pad: size padding for u64 granularity. + */ +struct hl_info_hw_err_event { + __s64 timestamp; + __u16 event_id; + __u16 pad[3]; +}; + +/* FW error definition for event_type in struct hl_info_fw_err_event */ +enum hl_info_fw_err_type { + HL_INFO_FW_HEARTBEAT_ERR, + HL_INFO_FW_REPORTED_ERR, +}; + +/** + * struct hl_info_fw_err_event - info about FW error + * @timestamp: time-stamp of error occurrence + * @err_type: The type of event as defined in hl_info_fw_err_type. + * @event_id: The async event ID (specific to each device type, applicable only when event type is + * HL_INFO_FW_REPORTED_ERR). + * @pad: size padding for u64 granularity. + */ +struct hl_info_fw_err_event { + __s64 timestamp; + __u16 err_type; + __u16 event_id; + __u32 pad; +}; + /** * struct hl_info_dev_memalloc_page_sizes - valid page sizes in device mem alloc information. * @page_order_bitmask: bitmap in which a set bit represents the order of the supported page size -- cgit v1.2.3 From 7fc0d011c378c6b2abc65cb536e0df0ee055ed39 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Sun, 22 Jan 2023 14:06:15 +0200 Subject: accel/habanalabs: expose engine core int reg address In order for engine cores to raise interrupts towards FW, They need to know which register the event data should be written to. Hence, we forward the relevant scratchpad register received during dynamic regs handshake with FW. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Reviewed-by: Stanislaw Gruszka --- include/uapi/drm/habanalabs_accel.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 3a62652a6452..c1fdbb85d1d5 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -885,6 +885,8 @@ enum hl_server_type { * application to use. Relevant for Gaudi2 and later. * @device_mem_alloc_default_page_size: default page size used in device memory allocation. * @revision_id: PCI revision ID of the ASIC. + * @engine_core_interrupt_reg_addr: interrupt register address for engine core to use + * in order to raise events toward FW. */ struct hl_info_hw_ip_info { __u64 sram_base_address; @@ -921,6 +923,9 @@ struct hl_info_hw_ip_info { __u8 reserved8; __u8 revision_id; __u8 pad[2]; + __u32 reserved9; + __u8 pad3[4]; + __u64 engine_core_interrupt_reg_addr; }; struct hl_info_dram_usage { -- cgit v1.2.3 From 4713ace3246644519bf93cc8ea6e44efe57fc3ec Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Mon, 16 Jan 2023 19:56:23 +0200 Subject: accel/habanalabs: add support for TPC assert In order to allow TPC engines to raise an assert, we must expose the relevant MSIX interrupt to the user so he will configure the engine correctly. In addition, we implement the corresponding interrupt handler that will notify the user upon such an event. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Reviewed-by: Stanislaw Gruszka --- include/uapi/drm/habanalabs_accel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index c1fdbb85d1d5..359b19ef3c3f 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -885,6 +885,7 @@ enum hl_server_type { * application to use. Relevant for Gaudi2 and later. * @device_mem_alloc_default_page_size: default page size used in device memory allocation. * @revision_id: PCI revision ID of the ASIC. + * @tpc_interrupt_id: interrupt id for TPC to use in order to raise events towards the host. * @engine_core_interrupt_reg_addr: interrupt register address for engine core to use * in order to raise events toward FW. */ @@ -922,7 +923,7 @@ struct hl_info_hw_ip_info { __u32 reserved7; __u8 reserved8; __u8 revision_id; - __u8 pad[2]; + __u16 tpc_interrupt_id; __u32 reserved9; __u8 pad3[4]; __u64 engine_core_interrupt_reg_addr; -- cgit v1.2.3 From f7f0085eec8d3c0c353d2e7bfa7fb54b3b925d7a Mon Sep 17 00:00:00 2001 From: Koby Elbaz Date: Wed, 15 Feb 2023 17:51:14 +0200 Subject: accel/habanalabs: add uapi to stall/resume engine The user might want to stall/resume engines to perform power testing for various scenarios. Because our current HL_CS_FLAGS_ENGINE_CORE_COMMAND command only handles the engines' cores, we need to add another opcode for handling entire engine and not just its core. The user supplies an array, where each entry holds the engine's ID and the command to send to the engine. The size of the array is limited by the number of engines in the ASIC (only Gaudi2 is currently supported). Signed-off-by: Koby Elbaz Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/drm/habanalabs_accel.h | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 359b19ef3c3f..7ca0ef802fd1 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -1535,17 +1535,31 @@ struct hl_cs_chunk { */ #define HL_CS_FLAGS_FLUSH_PCI_HBW_WRITES 0x8000 +/* + * The engines CS is merged into the existing CS ioctls. + * Use it to control engines modes. + */ +#define HL_CS_FLAGS_ENGINES_COMMAND 0x10000 + #define HL_CS_STATUS_SUCCESS 0 #define HL_MAX_JOBS_PER_CS 512 -/* HL_ENGINE_CORE_ values +/* + * enum hl_engine_command - engine command * - * HL_ENGINE_CORE_HALT: engine core halt - * HL_ENGINE_CORE_RUN: engine core run + * @HL_ENGINE_CORE_HALT: engine core halt + * @HL_ENGINE_CORE_RUN: engine core run + * @HL_ENGINE_STALL: user engine/s stall + * @HL_ENGINE_RESUME: user engine/s resume */ -#define HL_ENGINE_CORE_HALT (1 << 0) -#define HL_ENGINE_CORE_RUN (1 << 1) +enum hl_engine_command { + HL_ENGINE_CORE_HALT = 1, + HL_ENGINE_CORE_RUN = 2, + HL_ENGINE_STALL = 3, + HL_ENGINE_RESUME = 4, + HL_ENGINE_COMMAND_MAX +}; struct hl_cs_in { @@ -1569,6 +1583,18 @@ struct hl_cs_in { /* the core command to be sent towards engine cores */ __u32 core_command; }; + + /* Valid only when HL_CS_FLAGS_ENGINES_COMMAND is set */ + struct { + /* this holds address of array of uint32 for engines */ + __u64 engines; + + /* number of engines in engines array */ + __u32 num_engines; + + /* the engine command to be sent towards engines */ + __u32 engine_command; + }; }; union { -- cgit v1.2.3 From 60d7bbb5b4b875d613a43e3be797ddd4ff92cb7b Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 16 Mar 2023 12:13:34 +0200 Subject: accel/habanalabs: fix field names in hl_info_hw_ip_info Don't use padX for actual reservedX fields. Signed-off-by: Oded Gabbay Reviewed-by: Ofir Bitton --- include/uapi/drm/habanalabs_accel.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 7ca0ef802fd1..7d457eb4da74 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -915,17 +915,18 @@ struct hl_info_hw_ip_info { __u64 dram_page_size; __u32 edma_enabled_mask; __u16 number_of_user_interrupts; - __u16 pad2; - __u64 reserved4; + __u8 reserved1; + __u8 reserved2; + __u64 reserved3; __u64 device_mem_alloc_default_page_size; + __u64 reserved4; __u64 reserved5; - __u64 reserved6; - __u32 reserved7; - __u8 reserved8; + __u32 reserved6; + __u8 reserved7; __u8 revision_id; __u16 tpc_interrupt_id; + __u32 reserved8; __u32 reserved9; - __u8 pad3[4]; __u64 engine_core_interrupt_reg_addr; }; -- cgit v1.2.3 From 76e1ff37b6872c9f2d11660258fc8c88b2f97b06 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Mon, 13 Mar 2023 17:10:28 +0200 Subject: accel/habanalabs: expose dram reserved size by kmd We expose this in order for user applications to know how much dram is reserved for internal use. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/drm/habanalabs_accel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index 7d457eb4da74..e43688d30e96 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -888,6 +888,7 @@ enum hl_server_type { * @tpc_interrupt_id: interrupt id for TPC to use in order to raise events towards the host. * @engine_core_interrupt_reg_addr: interrupt register address for engine core to use * in order to raise events toward FW. + * @reserved_dram_size: DRAM size reserved for driver and firmware. */ struct hl_info_hw_ip_info { __u64 sram_base_address; @@ -928,6 +929,7 @@ struct hl_info_hw_ip_info { __u32 reserved8; __u32 reserved9; __u64 engine_core_interrupt_reg_addr; + __u64 reserved_dram_size; }; struct hl_info_dram_usage { -- cgit v1.2.3 From 958e47977bd12e06752a559541867028b120de76 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Mon, 13 Mar 2023 22:30:23 +0200 Subject: accel/habanalabs: expose rotator mask to userspace All engine masks are exposed to user, make sure user gets the correct rotator enabled mask in gaudi2. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/drm/habanalabs_accel.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index e43688d30e96..c139aab17c8a 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -886,6 +886,8 @@ enum hl_server_type { * @device_mem_alloc_default_page_size: default page size used in device memory allocation. * @revision_id: PCI revision ID of the ASIC. * @tpc_interrupt_id: interrupt id for TPC to use in order to raise events towards the host. + * @rotator_enabled_mask: Bit-mask that represents which rotators are enabled. + * Relevant for Gaudi3 and later. * @engine_core_interrupt_reg_addr: interrupt register address for engine core to use * in order to raise events toward FW. * @reserved_dram_size: DRAM size reserved for driver and firmware. @@ -926,7 +928,7 @@ struct hl_info_hw_ip_info { __u8 reserved7; __u8 revision_id; __u16 tpc_interrupt_id; - __u32 reserved8; + __u32 rotator_enabled_mask; __u32 reserved9; __u64 engine_core_interrupt_reg_addr; __u64 reserved_dram_size; -- cgit v1.2.3 From 02abecdeebfcd3848b26b70778dd7f6eb0db65e1 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 17 Mar 2023 12:18:01 -0600 Subject: drm/i915/uapi: Replace fake flex-array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Zero-length arrays as fake flexible arrays are deprecated and we are moving towards adopting C99 flexible-array members instead. Address the following warning found with GCC-13 and -fstrict-flex-arrays=3 enabled: drivers/gpu/drm/i915/gem/i915_gem_context.c: In function ‘set_proto_ctx_engines.isra’: drivers/gpu/drm/i915/gem/i915_gem_context.c:769:41: warning: array subscript n is outside array bounds of ‘struct i915_engine_class_instance[0]’ [-Warray-bounds=] 769 | if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) { | ^~~~~~~~~~~~~~~~~ ./include/uapi/drm/i915_drm.h:2494:43: note: while referencing ‘engines’ 2494 | struct i915_engine_class_instance engines[0]; This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help us make progress towards globally enabling -fstrict-flex-arrays=3 [1]. Link: https://github.com/KSPP/linux/issues/21 Link: https://github.com/KSPP/linux/issues/271 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [1] Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/ZBSu2QsUJy31kjSE@work --- include/uapi/drm/i915_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 8df261c5ab9b..5e458d6f2895 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ -- cgit v1.2.3 From c61d04c9eb4354980839cf938488ca703eba0f83 Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Thu, 23 Mar 2023 15:58:58 -0700 Subject: drm/i915/perf: Add engine class instance parameters to perf One or more engines map to a specific OA unit. All reports from these engines are captured in the OA buffer managed by this OA unit. Current i915 OA implementation supports only the OAG unit. OAG primarily caters to render engine, so i915 OA uses render as the default engine in the OA implementation. Since there are more OA units on newer hardware that map to other engines, allow user to pass engine class and instance to select and program specific OA units. UMD specific changes for GPUvis support: https://patchwork.freedesktop.org/patch/522827/?series=114023 https://patchwork.freedesktop.org/patch/522822/?series=114023 https://patchwork.freedesktop.org/patch/522826/?series=114023 https://patchwork.freedesktop.org/patch/522828/?series=114023 https://patchwork.freedesktop.org/patch/522816/?series=114023 https://patchwork.freedesktop.org/patch/522825/?series=114023 v2: (Ashutosh) - Clarify commit message - Add drm_dbg - Clarify uapi description v3: (Ashutosh) - Remove irrelevant info from the uapi comment v4: Ensure engine class:instance is passed together (Ashutosh) v5: Remove unnecessary quote (Ashutosh) Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Ashutosh Dixit Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-9-umesh.nerlige.ramappa@intel.com --- include/uapi/drm/i915_drm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 5e458d6f2895..384e74cac539 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2758,6 +2758,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; -- cgit v1.2.3 From 1cc064dce4ed0ff111b6d6cb06b3cccf1cba29f5 Mon Sep 17 00:00:00 2001 From: Umesh Nerlige Ramappa Date: Thu, 23 Mar 2023 15:58:59 -0700 Subject: drm/i915/perf: Add support for OA media units MTL introduces additional OA units dedicated to media use cases. Add support for programming these OA units by passing the media engine class and instance parameters. UMD specific changes for GPUvis support: https://patchwork.freedesktop.org/patch/522827/?series=114023 https://patchwork.freedesktop.org/patch/522822/?series=114023 https://patchwork.freedesktop.org/patch/522826/?series=114023 https://patchwork.freedesktop.org/patch/522828/?series=114023 https://patchwork.freedesktop.org/patch/522816/?series=114023 https://patchwork.freedesktop.org/patch/522825/?series=114023 v2: (Ashutosh) - check for IP_VER(12, 70) instead of MTL - remove PERF_GROUP_OAG comment in mtl_oa_base - remove oa_buffer.group - use engine->oa_group->type in engine_supports_oa_format - remove fw_domains and use FORCEWAKE_ALL - remove MPES/MPEC comment - s/xehp/mtl/ in b counter validation function name - remove engine_supports_oa in __oa_engine_group - remove warn_ON from __oam_engine_group - refactor oa_init_groups and oa_init_regs - assign g->type correctly - use enum oa_type definition v3: (Ashutosh) - Drop oa_unit_functional as engine_supports_oa is enough v4: - s/DRM_DEBUG/drm_dbg/ Signed-off-by: Umesh Nerlige Ramappa Reviewed-by: Ashutosh Dixit Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-10-umesh.nerlige.ramappa@intel.com --- include/uapi/drm/i915_drm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 384e74cac539..dba7c5a5b25e 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; -- cgit v1.2.3 From d71c11cc79d259c059f4ad377c0f930263f77c53 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 28 Feb 2023 10:10:11 -0800 Subject: dma-buf/sync_file: Surface sync-file uABI We had all of the internal driver APIs, but not the all important userspace uABI, in the dma-buf doc. Fix that. And re-arrange the comments slightly as otherwise the comments for the ioctl nr defines would not show up. v2: Fix docs build warning coming from newly including the uabi header in the docs build Signed-off-by: Rob Clark Acked-by: Pekka Paalanen --- include/uapi/linux/sync_file.h | 37 +++++++++++++++---------------------- 1 file changed, 15 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index ee2dcfb3d660..7e42a5b7558b 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -16,12 +16,16 @@ #include /** - * struct sync_merge_data - data passed to merge ioctl + * struct sync_merge_data - SYNC_IOC_MERGE: merge two fences * @name: name of new fence * @fd2: file descriptor of second fence * @fence: returns the fd of the new fence to userspace * @flags: merge_data flags * @pad: padding for 64-bit alignment, should always be zero + * + * Creates a new fence containing copies of the sync_pts in both + * the calling fd and sync_merge_data.fd2. Returns the new fence's + * fd in sync_merge_data.fence */ struct sync_merge_data { char name[32]; @@ -34,8 +38,8 @@ struct sync_merge_data { /** * struct sync_fence_info - detailed fence information * @obj_name: name of parent sync_timeline -* @driver_name: name of driver implementing the parent -* @status: status of the fence 0:active 1:signaled <0:error + * @driver_name: name of driver implementing the parent + * @status: status of the fence 0:active 1:signaled <0:error * @flags: fence_info flags * @timestamp_ns: timestamp of status change in nanoseconds */ @@ -48,14 +52,19 @@ struct sync_fence_info { }; /** - * struct sync_file_info - data returned from fence info ioctl + * struct sync_file_info - SYNC_IOC_FILE_INFO: get detailed information on a sync_file * @name: name of fence * @status: status of fence. 1: signaled 0:active <0:error * @flags: sync_file_info flags * @num_fences number of fences in the sync_file * @pad: padding for 64-bit alignment, should always be zero - * @sync_fence_info: pointer to array of structs sync_fence_info with all + * @sync_fence_info: pointer to array of struct &sync_fence_info with all * fences in the sync_file + * + * Takes a struct sync_file_info. If num_fences is 0, the field is updated + * with the actual number of fences. If num_fences is > 0, the system will + * use the pointer provided on sync_fence_info to return up to num_fences of + * struct sync_fence_info, with detailed fence information. */ struct sync_file_info { char name[32]; @@ -69,30 +78,14 @@ struct sync_file_info { #define SYNC_IOC_MAGIC '>' -/** +/* * Opcodes 0, 1 and 2 were burned during a API change to avoid users of the * old API to get weird errors when trying to handling sync_files. The API * change happened during the de-stage of the Sync Framework when there was * no upstream users available. */ -/** - * DOC: SYNC_IOC_MERGE - merge two fences - * - * Takes a struct sync_merge_data. Creates a new fence containing copies of - * the sync_pts in both the calling fd and sync_merge_data.fd2. Returns the - * new fence's fd in sync_merge_data.fence - */ #define SYNC_IOC_MERGE _IOWR(SYNC_IOC_MAGIC, 3, struct sync_merge_data) - -/** - * DOC: SYNC_IOC_FILE_INFO - get detailed information on a sync_file - * - * Takes a struct sync_file_info. If num_fences is 0, the field is updated - * with the actual number of fences. If num_fences is > 0, the system will - * use the pointer provided on sync_fence_info to return up to num_fences of - * struct sync_fence_info, with detailed fence information. - */ #define SYNC_IOC_FILE_INFO _IOWR(SYNC_IOC_MAGIC, 4, struct sync_file_info) #endif /* _UAPI_LINUX_SYNC_H */ -- cgit v1.2.3 From b5a24e13c8c8b2c98d114b16da40712b80d5cfc1 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 8 Mar 2023 07:53:04 -0800 Subject: drm/msm: Add wait-boost support Add a way for various userspace waits to signal urgency. Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/525817/ Link: https://lore.kernel.org/r/20230308155322.344664-14-robdclark@gmail.com --- include/uapi/drm/msm_drm.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 329100016e7c..dbf0d6f43fa9 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -151,8 +151,13 @@ struct drm_msm_gem_info { #define MSM_PREP_READ 0x01 #define MSM_PREP_WRITE 0x02 #define MSM_PREP_NOSYNC 0x04 +#define MSM_PREP_BOOST 0x08 -#define MSM_PREP_FLAGS (MSM_PREP_READ | MSM_PREP_WRITE | MSM_PREP_NOSYNC) +#define MSM_PREP_FLAGS (MSM_PREP_READ | \ + MSM_PREP_WRITE | \ + MSM_PREP_NOSYNC | \ + MSM_PREP_BOOST | \ + 0) struct drm_msm_gem_cpu_prep { __u32 handle; /* in */ @@ -286,6 +291,11 @@ struct drm_msm_gem_submit { }; +#define MSM_WAIT_FENCE_BOOST 0x00000001 +#define MSM_WAIT_FENCE_FLAGS ( \ + MSM_WAIT_FENCE_BOOST | \ + 0) + /* The normal way to synchronize with the GPU is just to CPU_PREP on * a buffer if you need to access it from the CPU (other cmdstream * submission from same or other contexts, PAGE_FLIP ioctl, etc, all @@ -295,7 +305,7 @@ struct drm_msm_gem_submit { */ struct drm_msm_wait_fence { __u32 fence; /* in */ - __u32 pad; + __u32 flags; /* in, bitmask of MSM_WAIT_FENCE_x */ struct drm_msm_timespec timeout; /* in */ __u32 queueid; /* in, submitqueue id */ }; -- cgit v1.2.3 From c501ca23a6a306a7c11631e02a26c8e0a768d64b Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 27 Mar 2023 09:54:51 -0600 Subject: accel/qaic: Add uapi and core driver file Add the QAIC driver uapi file and core driver file that binds to the PCIe device. The core driver file also creates the accel device and manages all the interconnections between the different parts of the driver. The driver can be built as a module. If so, it will be called "qaic.ko". Signed-off-by: Jeffrey Hugo Reviewed-by: Carl Vanderlip Reviewed-by: Pranjal Ramajor Asha Kanojiya Reviewed-by: Stanislaw Gruszka Reviewed-by: Jacek Lawrynowicz Acked-by: Oded Gabbay Signed-off-by: Jacek Lawrynowicz Link: https://patchwork.freedesktop.org/patch/msgid/1679932497-30277-3-git-send-email-quic_jhugo@quicinc.com --- include/uapi/drm/qaic_accel.h | 397 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 397 insertions(+) create mode 100644 include/uapi/drm/qaic_accel.h (limited to 'include/uapi') diff --git a/include/uapi/drm/qaic_accel.h b/include/uapi/drm/qaic_accel.h new file mode 100644 index 000000000000..2d348744a853 --- /dev/null +++ b/include/uapi/drm/qaic_accel.h @@ -0,0 +1,397 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note + * + * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef QAIC_ACCEL_H_ +#define QAIC_ACCEL_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/* The length(4K) includes len and count fields of qaic_manage_msg */ +#define QAIC_MANAGE_MAX_MSG_LENGTH SZ_4K + +/* semaphore flags */ +#define QAIC_SEM_INSYNCFENCE 2 +#define QAIC_SEM_OUTSYNCFENCE 1 + +/* Semaphore commands */ +#define QAIC_SEM_NOP 0 +#define QAIC_SEM_INIT 1 +#define QAIC_SEM_INC 2 +#define QAIC_SEM_DEC 3 +#define QAIC_SEM_WAIT_EQUAL 4 +#define QAIC_SEM_WAIT_GT_EQ 5 /* Greater than or equal */ +#define QAIC_SEM_WAIT_GT_0 6 /* Greater than 0 */ + +#define QAIC_TRANS_UNDEFINED 0 +#define QAIC_TRANS_PASSTHROUGH_FROM_USR 1 +#define QAIC_TRANS_PASSTHROUGH_TO_USR 2 +#define QAIC_TRANS_PASSTHROUGH_FROM_DEV 3 +#define QAIC_TRANS_PASSTHROUGH_TO_DEV 4 +#define QAIC_TRANS_DMA_XFER_FROM_USR 5 +#define QAIC_TRANS_DMA_XFER_TO_DEV 6 +#define QAIC_TRANS_ACTIVATE_FROM_USR 7 +#define QAIC_TRANS_ACTIVATE_FROM_DEV 8 +#define QAIC_TRANS_ACTIVATE_TO_DEV 9 +#define QAIC_TRANS_DEACTIVATE_FROM_USR 10 +#define QAIC_TRANS_DEACTIVATE_FROM_DEV 11 +#define QAIC_TRANS_STATUS_FROM_USR 12 +#define QAIC_TRANS_STATUS_TO_USR 13 +#define QAIC_TRANS_STATUS_FROM_DEV 14 +#define QAIC_TRANS_STATUS_TO_DEV 15 +#define QAIC_TRANS_TERMINATE_FROM_DEV 16 +#define QAIC_TRANS_TERMINATE_TO_DEV 17 +#define QAIC_TRANS_DMA_XFER_CONT 18 +#define QAIC_TRANS_VALIDATE_PARTITION_FROM_DEV 19 +#define QAIC_TRANS_VALIDATE_PARTITION_TO_DEV 20 + +/** + * struct qaic_manage_trans_hdr - Header for a transaction in a manage message. + * @type: In. Identifies this transaction. See QAIC_TRANS_* defines. + * @len: In. Length of this transaction, including this header. + */ +struct qaic_manage_trans_hdr { + __u32 type; + __u32 len; +}; + +/** + * struct qaic_manage_trans_passthrough - Defines a passthrough transaction. + * @hdr: In. Header to identify this transaction. + * @data: In. Payload of this ransaction. Opaque to the driver. Userspace must + * encode in little endian and align/pad to 64-bit. + */ +struct qaic_manage_trans_passthrough { + struct qaic_manage_trans_hdr hdr; + __u8 data[]; +}; + +/** + * struct qaic_manage_trans_dma_xfer - Defines a DMA transfer transaction. + * @hdr: In. Header to identify this transaction. + * @tag: In. Identified this transfer in other transactions. Opaque to the + * driver. + * @pad: Structure padding. + * @addr: In. Address of the data to DMA to the device. + * @size: In. Length of the data to DMA to the device. + */ +struct qaic_manage_trans_dma_xfer { + struct qaic_manage_trans_hdr hdr; + __u32 tag; + __u32 pad; + __u64 addr; + __u64 size; +}; + +/** + * struct qaic_manage_trans_activate_to_dev - Defines an activate request. + * @hdr: In. Header to identify this transaction. + * @queue_size: In. Number of elements for DBC request and response queues. + * @eventfd: Unused. + * @options: In. Device specific options for this activate. + * @pad: Structure padding. Must be 0. + */ +struct qaic_manage_trans_activate_to_dev { + struct qaic_manage_trans_hdr hdr; + __u32 queue_size; + __u32 eventfd; + __u32 options; + __u32 pad; +}; + +/** + * struct qaic_manage_trans_activate_from_dev - Defines an activate response. + * @hdr: Out. Header to identify this transaction. + * @status: Out. Return code of the request from the device. + * @dbc_id: Out. Id of the assigned DBC for successful request. + * @options: Out. Device specific options for this activate. + */ +struct qaic_manage_trans_activate_from_dev { + struct qaic_manage_trans_hdr hdr; + __u32 status; + __u32 dbc_id; + __u64 options; +}; + +/** + * struct qaic_manage_trans_deactivate - Defines a deactivate request. + * @hdr: In. Header to identify this transaction. + * @dbc_id: In. Id of assigned DBC. + * @pad: Structure padding. Must be 0. + */ +struct qaic_manage_trans_deactivate { + struct qaic_manage_trans_hdr hdr; + __u32 dbc_id; + __u32 pad; +}; + +/** + * struct qaic_manage_trans_status_to_dev - Defines a status request. + * @hdr: In. Header to identify this transaction. + */ +struct qaic_manage_trans_status_to_dev { + struct qaic_manage_trans_hdr hdr; +}; + +/** + * struct qaic_manage_trans_status_from_dev - Defines a status response. + * @hdr: Out. Header to identify this transaction. + * @major: Out. NNC protocol version major number. + * @minor: Out. NNC protocol version minor number. + * @status: Out. Return code from device. + * @status_flags: Out. Flags from device. Bit 0 indicates if CRCs are required. + */ +struct qaic_manage_trans_status_from_dev { + struct qaic_manage_trans_hdr hdr; + __u16 major; + __u16 minor; + __u32 status; + __u64 status_flags; +}; + +/** + * struct qaic_manage_msg - Defines a message to the device. + * @len: In. Length of all the transactions contained within this message. + * @count: In. Number of transactions in this message. + * @data: In. Address to an array where the transactions can be found. + */ +struct qaic_manage_msg { + __u32 len; + __u32 count; + __u64 data; +}; + +/** + * struct qaic_create_bo - Defines a request to create a buffer object. + * @size: In. Size of the buffer in bytes. + * @handle: Out. GEM handle for the BO. + * @pad: Structure padding. Must be 0. + */ +struct qaic_create_bo { + __u64 size; + __u32 handle; + __u32 pad; +}; + +/** + * struct qaic_mmap_bo - Defines a request to prepare a BO for mmap(). + * @handle: In. Handle of the GEM BO to prepare for mmap(). + * @pad: Structure padding. Must be 0. + * @offset: Out. Offset value to provide to mmap(). + */ +struct qaic_mmap_bo { + __u32 handle; + __u32 pad; + __u64 offset; +}; + +/** + * struct qaic_sem - Defines a semaphore command for a BO slice. + * @val: In. Only lower 12 bits are valid. + * @index: In. Only lower 5 bits are valid. + * @presync: In. 1 if presync operation, 0 if postsync. + * @cmd: In. One of QAIC_SEM_*. + * @flags: In. Bitfield. See QAIC_SEM_INSYNCFENCE and QAIC_SEM_OUTSYNCFENCE + * @pad: Structure padding. Must be 0. + */ +struct qaic_sem { + __u16 val; + __u8 index; + __u8 presync; + __u8 cmd; + __u8 flags; + __u16 pad; +}; + +/** + * struct qaic_attach_slice_entry - Defines a single BO slice. + * @size: In. Size of this slice in bytes. + * @sem0: In. Semaphore command 0. Must be 0 is not valid. + * @sem1: In. Semaphore command 1. Must be 0 is not valid. + * @sem2: In. Semaphore command 2. Must be 0 is not valid. + * @sem3: In. Semaphore command 3. Must be 0 is not valid. + * @dev_addr: In. Device address this slice pushes to or pulls from. + * @db_addr: In. Address of the doorbell to ring. + * @db_data: In. Data to write to the doorbell. + * @db_len: In. Size of the doorbell data in bits - 32, 16, or 8. 0 is for + * inactive doorbells. + * @offset: In. Start of this slice as an offset from the start of the BO. + */ +struct qaic_attach_slice_entry { + __u64 size; + struct qaic_sem sem0; + struct qaic_sem sem1; + struct qaic_sem sem2; + struct qaic_sem sem3; + __u64 dev_addr; + __u64 db_addr; + __u32 db_data; + __u32 db_len; + __u64 offset; +}; + +/** + * struct qaic_attach_slice_hdr - Defines metadata for a set of BO slices. + * @count: In. Number of slices for this BO. + * @dbc_id: In. Associate the sliced BO with this DBC. + * @handle: In. GEM handle of the BO to slice. + * @dir: In. Direction of data flow. 1 = DMA_TO_DEVICE, 2 = DMA_FROM_DEVICE + * @size: In. Total length of the BO. + * If BO is imported (DMABUF/PRIME) then this size + * should not exceed the size of DMABUF provided. + * If BO is allocated using DRM_IOCTL_QAIC_CREATE_BO + * then this size should be exactly same as the size + * provided during DRM_IOCTL_QAIC_CREATE_BO. + * @dev_addr: In. Device address this slice pushes to or pulls from. + * @db_addr: In. Address of the doorbell to ring. + * @db_data: In. Data to write to the doorbell. + * @db_len: In. Size of the doorbell data in bits - 32, 16, or 8. 0 is for + * inactive doorbells. + * @offset: In. Start of this slice as an offset from the start of the BO. + */ +struct qaic_attach_slice_hdr { + __u32 count; + __u32 dbc_id; + __u32 handle; + __u32 dir; + __u64 size; +}; + +/** + * struct qaic_attach_slice - Defines a set of BO slices. + * @hdr: In. Metadata of the set of slices. + * @data: In. Pointer to an array containing the slice definitions. + */ +struct qaic_attach_slice { + struct qaic_attach_slice_hdr hdr; + __u64 data; +}; + +/** + * struct qaic_execute_entry - Defines a BO to submit to the device. + * @handle: In. GEM handle of the BO to commit to the device. + * @dir: In. Direction of data. 1 = to device, 2 = from device. + */ +struct qaic_execute_entry { + __u32 handle; + __u32 dir; +}; + +/** + * struct qaic_partial_execute_entry - Defines a BO to resize and submit. + * @handle: In. GEM handle of the BO to commit to the device. + * @dir: In. Direction of data. 1 = to device, 2 = from device. + * @resize: In. New size of the BO. Must be <= the original BO size. 0 is + * short for no resize. + */ +struct qaic_partial_execute_entry { + __u32 handle; + __u32 dir; + __u64 resize; +}; + +/** + * struct qaic_execute_hdr - Defines metadata for BO submission. + * @count: In. Number of BOs to submit. + * @dbc_id: In. DBC to submit the BOs on. + */ +struct qaic_execute_hdr { + __u32 count; + __u32 dbc_id; +}; + +/** + * struct qaic_execute - Defines a list of BOs to submit to the device. + * @hdr: In. BO list metadata. + * @data: In. Pointer to an array of BOs to submit. + */ +struct qaic_execute { + struct qaic_execute_hdr hdr; + __u64 data; +}; + +/** + * struct qaic_wait - Defines a blocking wait for BO execution. + * @handle: In. GEM handle of the BO to wait on. + * @timeout: In. Maximum time in ms to wait for the BO. + * @dbc_id: In. DBC the BO is submitted to. + * @pad: Structure padding. Must be 0. + */ +struct qaic_wait { + __u32 handle; + __u32 timeout; + __u32 dbc_id; + __u32 pad; +}; + +/** + * struct qaic_perf_stats_hdr - Defines metadata for getting BO perf info. + * @count: In. Number of BOs requested. + * @pad: Structure padding. Must be 0. + * @dbc_id: In. DBC the BO are associated with. + */ +struct qaic_perf_stats_hdr { + __u16 count; + __u16 pad; + __u32 dbc_id; +}; + +/** + * struct qaic_perf_stats - Defines a request for getting BO perf info. + * @hdr: In. Request metadata + * @data: In. Pointer to array of stats structures that will receive the data. + */ +struct qaic_perf_stats { + struct qaic_perf_stats_hdr hdr; + __u64 data; +}; + +/** + * struct qaic_perf_stats_entry - Defines a BO perf info. + * @handle: In. GEM handle of the BO to get perf stats for. + * @queue_level_before: Out. Number of elements in the queue before this BO + * was submitted. + * @num_queue_element: Out. Number of elements added to the queue to submit + * this BO. + * @submit_latency_us: Out. Time taken by the driver to submit this BO. + * @device_latency_us: Out. Time taken by the device to execute this BO. + * @pad: Structure padding. Must be 0. + */ +struct qaic_perf_stats_entry { + __u32 handle; + __u32 queue_level_before; + __u32 num_queue_element; + __u32 submit_latency_us; + __u32 device_latency_us; + __u32 pad; +}; + +#define DRM_QAIC_MANAGE 0x00 +#define DRM_QAIC_CREATE_BO 0x01 +#define DRM_QAIC_MMAP_BO 0x02 +#define DRM_QAIC_ATTACH_SLICE_BO 0x03 +#define DRM_QAIC_EXECUTE_BO 0x04 +#define DRM_QAIC_PARTIAL_EXECUTE_BO 0x05 +#define DRM_QAIC_WAIT_BO 0x06 +#define DRM_QAIC_PERF_STATS_BO 0x07 + +#define DRM_IOCTL_QAIC_MANAGE DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_MANAGE, struct qaic_manage_msg) +#define DRM_IOCTL_QAIC_CREATE_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_CREATE_BO, struct qaic_create_bo) +#define DRM_IOCTL_QAIC_MMAP_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_MMAP_BO, struct qaic_mmap_bo) +#define DRM_IOCTL_QAIC_ATTACH_SLICE_BO DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_ATTACH_SLICE_BO, struct qaic_attach_slice) +#define DRM_IOCTL_QAIC_EXECUTE_BO DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_EXECUTE_BO, struct qaic_execute) +#define DRM_IOCTL_QAIC_PARTIAL_EXECUTE_BO DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_PARTIAL_EXECUTE_BO, struct qaic_execute) +#define DRM_IOCTL_QAIC_WAIT_BO DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_WAIT_BO, struct qaic_wait) +#define DRM_IOCTL_QAIC_PERF_STATS_BO DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_PERF_STATS_BO, struct qaic_perf_stats) + +#if defined(__cplusplus) +} +#endif + +#endif /* QAIC_ACCEL_H_ */ -- cgit v1.2.3 From f1af066bcfd38daa9eee7195ef772dadaaa18520 Mon Sep 17 00:00:00 2001 From: Danylo Piliaiev Date: Sun, 26 Mar 2023 09:38:13 -0700 Subject: drm/msm: Rename drm_msm_gem_submit_reloc::or in C++ code Clashes with C++ `or` keyword Signed-off-by: Danylo Piliaiev Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/528751/ Link: https://lore.kernel.org/r/20230326163813.535762-1-robdclark@gmail.com Signed-off-by: Dmitry Baryshkov --- include/uapi/drm/msm_drm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index dbf0d6f43fa9..6c34272a13fd 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -186,7 +186,11 @@ struct drm_msm_gem_cpu_fini { */ struct drm_msm_gem_submit_reloc { __u32 submit_offset; /* in, offset from submit_bo */ +#ifdef __cplusplus + __u32 _or; /* in, value OR'd with result */ +#else __u32 or; /* in, value OR'd with result */ +#endif __s32 shift; /* in, amount of left shift (can be negative) */ __u32 reloc_idx; /* in, index of reloc_bo buffer */ __u64 reloc_offset; /* in, offset from start of reloc_bo */ -- cgit v1.2.3 From a25c2f7a467265fa24d63fb6dd46fa7ba4e3b108 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 30 Mar 2023 12:30:56 +0300 Subject: accel/habanalabs/uapi: new Gaudi2 server type Add definition of a new Gaudi2 server type. This represents the connectivity between the cards in that server type. Signed-off-by: Oded Gabbay Reviewed-by: Stanislaw Gruszka --- include/uapi/drm/habanalabs_accel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h index c139aab17c8a..d9ef1b151d04 100644 --- a/include/uapi/drm/habanalabs_accel.h +++ b/include/uapi/drm/habanalabs_accel.h @@ -708,7 +708,8 @@ enum hl_server_type { HL_SERVER_GAUDI_HLS1H = 2, HL_SERVER_GAUDI_TYPE1 = 3, HL_SERVER_GAUDI_TYPE2 = 4, - HL_SERVER_GAUDI2_HLS2 = 5 + HL_SERVER_GAUDI2_HLS2 = 5, + HL_SERVER_GAUDI2_TYPE1 = 7 }; /* -- cgit v1.2.3