diff options
Diffstat (limited to 'include/uapi')
| -rw-r--r-- | include/uapi/drm/amdgpu_drm.h | 7 | ||||
| -rw-r--r-- | include/uapi/drm/drm_fourcc.h | 10 | ||||
| -rw-r--r-- | include/uapi/drm/i915_drm.h | 387 | ||||
| -rw-r--r-- | include/uapi/linux/dma-buf.h | 84 | ||||
| -rw-r--r-- | include/uapi/linux/kfd_ioctl.h | 55 | ||||
| -rw-r--r-- | include/uapi/linux/media-bus-format.h | 6 |
6 files changed, 454 insertions, 95 deletions
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 18d3246d636e..c2c9c674a223 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -559,6 +559,10 @@ struct drm_amdgpu_gem_va { #define AMDGPU_HW_IP_VCE 4 #define AMDGPU_HW_IP_UVD_ENC 5 #define AMDGPU_HW_IP_VCN_DEC 6 +/* + * From VCN4, AMDGPU_HW_IP_VCN_ENC is re-used to support + * both encoding and decoding jobs. + */ #define AMDGPU_HW_IP_VCN_ENC 7 #define AMDGPU_HW_IP_VCN_JPEG 8 #define AMDGPU_HW_IP_NUM 9 @@ -1093,7 +1097,8 @@ struct drm_amdgpu_info_hw_ip { __u32 ib_size_alignment; /** Bitmask of available rings. Bit 0 means ring 0, etc. */ __u32 available_rings; - __u32 _pad; + /** version info: bits 23:16 major, 15:8 minor, 7:0 revision */ + __u32 ip_discovery_version; }; struct drm_amdgpu_info_num_handles { diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 0980678d502d..0206f812c569 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -559,7 +559,7 @@ extern "C" { * * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear * and at index 1. The clear color is stored at index 2, and the pitch should - * be ignored. The clear color structure is 256 bits. The first 128 bits + * be 64 bytes aligned. The clear color structure is 256 bits. The first 128 bits * represents Raw Clear Color Red, Green, Blue and Alpha color each represented * by 32 bits. The raw clear color is consumed by the 3d engine and generates * the converted clear color of size 64 bits. The first 32 bits store the Lower @@ -612,9 +612,9 @@ extern "C" { * outside of the GEM object in a reserved memory area dedicated for the * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The * main surface pitch is required to be a multiple of four Tile 4 widths. The - * clear color is stored at plane index 1 and the pitch should be ignored. The - * format of the 256 bits of clear color data matches the one used for the - * I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description + * clear color is stored at plane index 1 and the pitch should be 64 bytes + * aligned. The format of the 256 bits of clear color data matches the one used + * for the I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description * for details. */ #define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12) @@ -1363,6 +1363,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) #define AMD_FMT_MOD_TILE_VER_GFX9 1 #define AMD_FMT_MOD_TILE_VER_GFX10 2 #define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3 +#define AMD_FMT_MOD_TILE_VER_GFX11 4 /* * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical @@ -1378,6 +1379,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) #define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25 #define AMD_FMT_MOD_TILE_GFX9_64K_D_X 26 #define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27 +#define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31 #define AMD_FMT_MOD_DCC_BLOCK_64B 0 #define AMD_FMT_MOD_DCC_BLOCK_128B 1 diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index b28ff5d88145..520ad2691a99 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -751,14 +751,27 @@ typedef struct drm_i915_irq_wait { /* Must be kept compact -- no holes and well documented */ -typedef struct drm_i915_getparam { +/** + * struct drm_i915_getparam - Driver parameter query structure. + */ +struct drm_i915_getparam { + /** @param: Driver parameter to query. */ __s32 param; - /* + + /** + * @value: Address of memory where queried value should be put. + * * WARNING: Using pointers instead of fixed-size u64 means we need to write * compat32 code. Don't repeat this mistake. */ int __user *value; -} drm_i915_getparam_t; +}; + +/** + * typedef drm_i915_getparam_t - Driver parameter query structure. + * See struct drm_i915_getparam. + */ +typedef struct drm_i915_getparam drm_i915_getparam_t; /* Ioctl to set kernel params: */ @@ -1239,76 +1252,119 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +/** + * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf + * ioctl. + * + * The request will wait for input fence to signal before submission. + * + * The returned output fence will be signaled after the completion of the + * request. + */ struct drm_i915_gem_exec_fence { - /** - * User's handle for a drm_syncobj to wait on or signal. - */ + /** @handle: User's handle for a drm_syncobj to wait on or signal. */ __u32 handle; + /** + * @flags: Supported flags are: + * + * I915_EXEC_FENCE_WAIT: + * Wait for the input fence before request submission. + * + * I915_EXEC_FENCE_SIGNAL: + * Return request completion fence as output + */ + __u32 flags; #define I915_EXEC_FENCE_WAIT (1<<0) #define I915_EXEC_FENCE_SIGNAL (1<<1) #define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1)) - __u32 flags; }; -/* - * See drm_i915_gem_execbuffer_ext_timeline_fences. - */ -#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 - -/* +/** + * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences + * for execbuf ioctl. + * * This structure describes an array of drm_syncobj and associated points for * timeline variants of drm_syncobj. It is invalid to append this structure to * the execbuf if I915_EXEC_FENCE_ARRAY is set. */ struct drm_i915_gem_execbuffer_ext_timeline_fences { +#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 + /** @base: Extension link. See struct i915_user_extension. */ struct i915_user_extension base; /** - * Number of element in the handles_ptr & value_ptr arrays. + * @fence_count: Number of elements in the @handles_ptr & @value_ptr + * arrays. */ __u64 fence_count; /** - * Pointer to an array of struct drm_i915_gem_exec_fence of length - * fence_count. + * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence + * of length @fence_count. */ __u64 handles_ptr; /** - * Pointer to an array of u64 values of length fence_count. Values - * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline - * drm_syncobj is invalid as it turns a drm_syncobj into a binary one. + * @values_ptr: Pointer to an array of u64 values of length + * @fence_count. + * Values must be 0 for a binary drm_syncobj. A Value of 0 for a + * timeline drm_syncobj is invalid as it turns a drm_syncobj into a + * binary one. */ __u64 values_ptr; }; +/** + * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2 + * ioctl. + */ struct drm_i915_gem_execbuffer2 { - /** - * List of gem_exec_object2 structs - */ + /** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */ __u64 buffers_ptr; + + /** @buffer_count: Number of elements in @buffers_ptr array */ __u32 buffer_count; - /** Offset in the batchbuffer to start execution from. */ + /** + * @batch_start_offset: Offset in the batchbuffer to start execution + * from. + */ __u32 batch_start_offset; - /** Bytes used in batchbuffer from batch_start_offset */ + + /** + * @batch_len: Length in bytes of the batch buffer, starting from the + * @batch_start_offset. If 0, length is assumed to be the batch buffer + * object size. + */ __u32 batch_len; + + /** @DR1: deprecated */ __u32 DR1; + + /** @DR4: deprecated */ __u32 DR4; + + /** @num_cliprects: See @cliprects_ptr */ __u32 num_cliprects; + /** - * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY - * & I915_EXEC_USE_EXTENSIONS are not set. + * @cliprects_ptr: Kernel clipping was a DRI1 misfeature. + * + * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or + * I915_EXEC_USE_EXTENSIONS flags are not set. * * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array - * of struct drm_i915_gem_exec_fence and num_cliprects is the length - * of the array. + * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the + * array. * * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a - * single struct i915_user_extension and num_cliprects is 0. + * single &i915_user_extension and num_cliprects is 0. */ __u64 cliprects_ptr; + + /** @flags: Execbuf flags */ + __u64 flags; #define I915_EXEC_RING_MASK (0x3f) #define I915_EXEC_DEFAULT (0<<0) #define I915_EXEC_RENDER (1<<0) @@ -1326,10 +1382,6 @@ struct drm_i915_gem_execbuffer2 { #define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */ #define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6) #define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */ - __u64 flags; - __u64 rsvd1; /* now used for context info */ - __u64 rsvd2; -}; /** Resets the SO write offset registers for transform feedback on gen7. */ #define I915_EXEC_GEN7_SOL_RESET (1<<8) @@ -1432,9 +1484,23 @@ struct drm_i915_gem_execbuffer2 { * drm_i915_gem_execbuffer_ext enum. */ #define I915_EXEC_USE_EXTENSIONS (1 << 21) - #define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1)) + /** @rsvd1: Context id */ + __u64 rsvd1; + + /** + * @rsvd2: in and out sync_file file descriptors. + * + * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the + * lower 32 bits of this field will have the in sync_file fd (input). + * + * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this + * field will have the out sync_file fd (output). + */ + __u64 rsvd2; +}; + #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ (eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK @@ -1814,19 +1880,58 @@ struct drm_i915_gem_context_create { __u32 pad; }; +/** + * struct drm_i915_gem_context_create_ext - Structure for creating contexts. + */ struct drm_i915_gem_context_create_ext { - __u32 ctx_id; /* output: id of new context*/ + /** @ctx_id: Id of the created context (output) */ + __u32 ctx_id; + + /** + * @flags: Supported flags are: + * + * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS: + * + * Extensions may be appended to this structure and driver must check + * for those. See @extensions. + * + * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE + * + * Created context will have single timeline. + */ __u32 flags; #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) #define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1) #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) + + /** + * @extensions: Zero-terminated chain of extensions. + * + * I915_CONTEXT_CREATE_EXT_SETPARAM: + * Context parameter to set or query during context creation. + * See struct drm_i915_gem_context_create_ext_setparam. + * + * I915_CONTEXT_CREATE_EXT_CLONE: + * This extension has been removed. On the off chance someone somewhere + * has attempted to use it, never re-use this extension number. + */ __u64 extensions; +#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 +#define I915_CONTEXT_CREATE_EXT_CLONE 1 }; +/** + * struct drm_i915_gem_context_param - Context parameter to set or query. + */ struct drm_i915_gem_context_param { + /** @ctx_id: Context id */ __u32 ctx_id; + + /** @size: Size of the parameter @value */ __u32 size; + + /** @param: Parameter to set or query */ __u64 param; #define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 /* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed. On the off chance @@ -1973,6 +2078,7 @@ struct drm_i915_gem_context_param { #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ + /** @value: Context parameter value to be set or queried */ __u64 value; }; @@ -2371,23 +2477,29 @@ struct i915_context_param_engines { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +/** + * struct drm_i915_gem_context_create_ext_setparam - Context parameter + * to set or query during context creation. + */ struct drm_i915_gem_context_create_ext_setparam { -#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 + /** @base: Extension link. See struct i915_user_extension. */ struct i915_user_extension base; + + /** + * @param: Context parameter to set or query. + * See struct drm_i915_gem_context_param. + */ struct drm_i915_gem_context_param param; }; -/* This API has been removed. On the off chance someone somewhere has - * attempted to use it, never re-use this extension number. - */ -#define I915_CONTEXT_CREATE_EXT_CLONE 1 - struct drm_i915_gem_context_destroy { __u32 ctx_id; __u32 pad; }; -/* +/** + * struct drm_i915_gem_vm_control - Structure to create or destroy VM. + * * DRM_I915_GEM_VM_CREATE - * * Create a new virtual memory address space (ppGTT) for use within a context @@ -2397,20 +2509,23 @@ struct drm_i915_gem_context_destroy { * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is * returned in the outparam @id. * - * No flags are defined, with all bits reserved and must be zero. - * * An extension chain maybe provided, starting with @extensions, and terminated * by the @next_extension being 0. Currently, no extensions are defined. * * DRM_I915_GEM_VM_DESTROY - * - * Destroys a previously created VM id, specified in @id. + * Destroys a previously created VM id, specified in @vm_id. * * No extensions or flags are allowed currently, and so must be zero. */ struct drm_i915_gem_vm_control { + /** @extensions: Zero-terminated chain of extensions. */ __u64 extensions; + + /** @flags: reserved for future usage, currently MBZ */ __u32 flags; + + /** @vm_id: Id of the VM created or to be destroyed */ __u32 vm_id; }; @@ -3207,36 +3322,6 @@ struct drm_i915_gem_memory_class_instance { * struct drm_i915_memory_region_info - Describes one region as known to the * driver. * - * Note that we reserve some stuff here for potential future work. As an example - * we might want expose the capabilities for a given region, which could include - * things like if the region is CPU mappable/accessible, what are the supported - * mapping types etc. - * - * Note that to extend struct drm_i915_memory_region_info and struct - * drm_i915_query_memory_regions in the future the plan is to do the following: - * - * .. code-block:: C - * - * struct drm_i915_memory_region_info { - * struct drm_i915_gem_memory_class_instance region; - * union { - * __u32 rsvd0; - * __u32 new_thing1; - * }; - * ... - * union { - * __u64 rsvd1[8]; - * struct { - * __u64 new_thing2; - * __u64 new_thing3; - * ... - * }; - * }; - * }; - * - * With this things should remain source compatible between versions for - * userspace, even as we add new fields. - * * Note this is using both struct drm_i915_query_item and struct drm_i915_query. * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS * at &drm_i915_query_item.query_id. @@ -3248,14 +3333,81 @@ struct drm_i915_memory_region_info { /** @rsvd0: MBZ */ __u32 rsvd0; - /** @probed_size: Memory probed by the driver (-1 = unknown) */ + /** + * @probed_size: Memory probed by the driver + * + * Note that it should not be possible to ever encounter a zero value + * here, also note that no current region type will ever return -1 here. + * Although for future region types, this might be a possibility. The + * same applies to the other size fields. + */ __u64 probed_size; - /** @unallocated_size: Estimate of memory remaining (-1 = unknown) */ + /** + * @unallocated_size: Estimate of memory remaining + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting. + * Without this (or if this is an older kernel) the value here will + * always equal the @probed_size. Note this is only currently tracked + * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here + * will always equal the @probed_size). + */ __u64 unallocated_size; - /** @rsvd1: MBZ */ - __u64 rsvd1[8]; + union { + /** @rsvd1: MBZ */ + __u64 rsvd1[8]; + struct { + /** + * @probed_cpu_visible_size: Memory probed by the driver + * that is CPU accessible. + * + * This will be always be <= @probed_size, and the + * remainder (if there is any) will not be CPU + * accessible. + * + * On systems without small BAR, the @probed_size will + * always equal the @probed_cpu_visible_size, since all + * of it will be CPU accessible. + * + * Note this is only tracked for + * I915_MEMORY_CLASS_DEVICE regions (for other types the + * value here will always equal the @probed_size). + * + * Note that if the value returned here is zero, then + * this must be an old kernel which lacks the relevant + * small-bar uAPI support (including + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on + * such systems we should never actually end up with a + * small BAR configuration, assuming we are able to load + * the kernel module. Hence it should be safe to treat + * this the same as when @probed_cpu_visible_size == + * @probed_size. + */ + __u64 probed_cpu_visible_size; + + /** + * @unallocated_cpu_visible_size: Estimate of CPU + * visible memory remaining. + * + * Note this is only tracked for + * I915_MEMORY_CLASS_DEVICE regions (for other types the + * value here will always equal the + * @probed_cpu_visible_size). + * + * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable + * accounting. Without this the value here will always + * equal the @probed_cpu_visible_size. Note this is only + * currently tracked for I915_MEMORY_CLASS_DEVICE + * regions (for other types the value here will also + * always equal the @probed_cpu_visible_size). + * + * If this is an older kernel the value here will be + * zero, see also @probed_cpu_visible_size. + */ + __u64 unallocated_cpu_visible_size; + }; + }; }; /** @@ -3329,11 +3481,11 @@ struct drm_i915_query_memory_regions { * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added * extension support using struct i915_user_extension. * - * Note that in the future we want to have our buffer flags here, at least for - * the stuff that is immutable. Previously we would have two ioctls, one to - * create the object with gem_create, and another to apply various parameters, - * however this creates some ambiguity for the params which are considered - * immutable. Also in general we're phasing out the various SET/GET ioctls. + * Note that new buffer flags should be added here, at least for the stuff that + * is immutable. Previously we would have two ioctls, one to create the object + * with gem_create, and another to apply various parameters, however this + * creates some ambiguity for the params which are considered immutable. Also in + * general we're phasing out the various SET/GET ioctls. */ struct drm_i915_gem_create_ext { /** @@ -3341,7 +3493,6 @@ struct drm_i915_gem_create_ext { * * The (page-aligned) allocated size for the object will be returned. * - * * DG2 64K min page size implications: * * On discrete platforms, starting from DG2, we have to contend with GTT @@ -3353,7 +3504,9 @@ struct drm_i915_gem_create_ext { * * Note that the returned size here will always reflect any required * rounding up done by the kernel, i.e 4K will now become 64K on devices - * such as DG2. + * such as DG2. The kernel will always select the largest minimum + * page-size for the set of possible placements as the value to use when + * rounding up the @size. * * Special DG2 GTT address alignment requirement: * @@ -3377,14 +3530,58 @@ struct drm_i915_gem_create_ext { * is deemed to be a good compromise. */ __u64 size; + /** * @handle: Returned handle for the object. * * Object handles are nonzero. */ __u32 handle; - /** @flags: MBZ */ + + /** + * @flags: Optional flags. + * + * Supported values: + * + * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that + * the object will need to be accessed via the CPU. + * + * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only + * strictly required on configurations where some subset of the device + * memory is directly visible/mappable through the CPU (which we also + * call small BAR), like on some DG2+ systems. Note that this is quite + * undesirable, but due to various factors like the client CPU, BIOS etc + * it's something we can expect to see in the wild. See + * &drm_i915_memory_region_info.probed_cpu_visible_size for how to + * determine if this system applies. + * + * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to + * ensure the kernel can always spill the allocation to system memory, + * if the object can't be allocated in the mappable part of + * I915_MEMORY_CLASS_DEVICE. + * + * Also note that since the kernel only supports flat-CCS on objects + * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore + * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with + * flat-CCS. + * + * Without this hint, the kernel will assume that non-mappable + * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the + * kernel can still migrate the object to the mappable part, as a last + * resort, if userspace ever CPU faults this object, but this might be + * expensive, and so ideally should be avoided. + * + * On older kernels which lack the relevant small-bar uAPI support (see + * also &drm_i915_memory_region_info.probed_cpu_visible_size), + * usage of the flag will result in an error, but it should NEVER be + * possible to end up with a small BAR configuration, assuming we can + * also successfully load the i915 kernel module. In such cases the + * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as + * such there are zero restrictions on where the object can be placed. + */ +#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0) __u32 flags; + /** * @extensions: The chain of extensions to apply to this object. * @@ -3443,6 +3640,22 @@ struct drm_i915_gem_create_ext { * At which point we get the object handle in &drm_i915_gem_create_ext.handle, * along with the final object size in &drm_i915_gem_create_ext.size, which * should account for any rounding up, if required. + * + * Note that userspace has no means of knowing the current backing region + * for objects where @num_regions is larger than one. The kernel will only + * ensure that the priority order of the @regions array is honoured, either + * when initially placing the object, or when moving memory around due to + * memory pressure + * + * On Flat-CCS capable HW, compression is supported for the objects residing + * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other + * memory class in @regions and migrated (by i915, due to memory + * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to + * decompress the content. But i915 doesn't have the required information to + * decompress the userspace compressed objects. + * + * So i915 supports Flat-CCS, on the objects which can reside only on + * I915_MEMORY_CLASS_DEVICE regions. */ struct drm_i915_gem_create_ext_memory_regions { /** @base: Extension link. See struct i915_user_extension. */ diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index b1523cb8ab30..5a6fda66d9ad 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -85,6 +85,88 @@ struct dma_buf_sync { #define DMA_BUF_NAME_LEN 32 +/** + * struct dma_buf_export_sync_file - Get a sync_file from a dma-buf + * + * Userspace can perform a DMA_BUF_IOCTL_EXPORT_SYNC_FILE to retrieve the + * current set of fences on a dma-buf file descriptor as a sync_file. CPU + * waits via poll() or other driver-specific mechanisms typically wait on + * whatever fences are on the dma-buf at the time the wait begins. This + * is similar except that it takes a snapshot of the current fences on the + * dma-buf for waiting later instead of waiting immediately. This is + * useful for modern graphics APIs such as Vulkan which assume an explicit + * synchronization model but still need to inter-operate with dma-buf. + * + * The intended usage pattern is the following: + * + * 1. Export a sync_file with flags corresponding to the expected GPU usage + * via DMA_BUF_IOCTL_EXPORT_SYNC_FILE. + * + * 2. Submit rendering work which uses the dma-buf. The work should wait on + * the exported sync file before rendering and produce another sync_file + * when complete. + * + * 3. Import the rendering-complete sync_file into the dma-buf with flags + * corresponding to the GPU usage via DMA_BUF_IOCTL_IMPORT_SYNC_FILE. + * + * Unlike doing implicit synchronization via a GPU kernel driver's exec ioctl, + * the above is not a single atomic operation. If userspace wants to ensure + * ordering via these fences, it is the respnosibility of userspace to use + * locks or other mechanisms to ensure that no other context adds fences or + * submits work between steps 1 and 3 above. + */ +struct dma_buf_export_sync_file { + /** + * @flags: Read/write flags + * + * Must be DMA_BUF_SYNC_READ, DMA_BUF_SYNC_WRITE, or both. + * + * If DMA_BUF_SYNC_READ is set and DMA_BUF_SYNC_WRITE is not set, + * the returned sync file waits on any writers of the dma-buf to + * complete. Waiting on the returned sync file is equivalent to + * poll() with POLLIN. + * + * If DMA_BUF_SYNC_WRITE is set, the returned sync file waits on + * any users of the dma-buf (read or write) to complete. Waiting + * on the returned sync file is equivalent to poll() with POLLOUT. + * If both DMA_BUF_SYNC_WRITE and DMA_BUF_SYNC_READ are set, this + * is equivalent to just DMA_BUF_SYNC_WRITE. + */ + __u32 flags; + /** @fd: Returned sync file descriptor */ + __s32 fd; +}; + +/** + * struct dma_buf_import_sync_file - Insert a sync_file into a dma-buf + * + * Userspace can perform a DMA_BUF_IOCTL_IMPORT_SYNC_FILE to insert a + * sync_file into a dma-buf for the purposes of implicit synchronization + * with other dma-buf consumers. This allows clients using explicitly + * synchronized APIs such as Vulkan to inter-op with dma-buf consumers + * which expect implicit synchronization such as OpenGL or most media + * drivers/video. + */ +struct dma_buf_import_sync_file { + /** + * @flags: Read/write flags + * + * Must be DMA_BUF_SYNC_READ, DMA_BUF_SYNC_WRITE, or both. + * + * If DMA_BUF_SYNC_READ is set and DMA_BUF_SYNC_WRITE is not set, + * this inserts the sync_file as a read-only fence. Any subsequent + * implicitly synchronized writes to this dma-buf will wait on this + * fence but reads will not. + * + * If DMA_BUF_SYNC_WRITE is set, this inserts the sync_file as a + * write fence. All subsequent implicitly synchronized access to + * this dma-buf will wait on this fence. + */ + __u32 flags; + /** @fd: Sync file descriptor */ + __s32 fd; +}; + #define DMA_BUF_BASE 'b' #define DMA_BUF_IOCTL_SYNC _IOW(DMA_BUF_BASE, 0, struct dma_buf_sync) @@ -94,5 +176,7 @@ struct dma_buf_sync { #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) #define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) #define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64) +#define DMA_BUF_IOCTL_EXPORT_SYNC_FILE _IOWR(DMA_BUF_BASE, 2, struct dma_buf_export_sync_file) +#define DMA_BUF_IOCTL_IMPORT_SYNC_FILE _IOW(DMA_BUF_BASE, 3, struct dma_buf_import_sync_file) #endif diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 42975e940758..42b60198b6c5 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -34,9 +34,12 @@ * - 1.6 - Query clear flags in SVM get_attr API * - 1.7 - Checkpoint Restore (CRIU) API * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs + * - 1.9 - Add available memory ioctl + * - 1.10 - Add SMI profiler event log + * - 1.11 - Add unified memory for ctx save/restore area */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 8 +#define KFD_IOCTL_MINOR_VERSION 11 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -100,6 +103,12 @@ struct kfd_ioctl_get_queue_wave_state_args { __u32 pad; }; +struct kfd_ioctl_get_available_memory_args { + __u64 available; /* from KFD */ + __u32 gpu_id; /* to KFD */ + __u32 pad; +}; + /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 @@ -463,6 +472,43 @@ enum kfd_smi_event { KFD_SMI_EVENT_THERMAL_THROTTLE = 2, KFD_SMI_EVENT_GPU_PRE_RESET = 3, KFD_SMI_EVENT_GPU_POST_RESET = 4, + KFD_SMI_EVENT_MIGRATE_START = 5, + KFD_SMI_EVENT_MIGRATE_END = 6, + KFD_SMI_EVENT_PAGE_FAULT_START = 7, + KFD_SMI_EVENT_PAGE_FAULT_END = 8, + KFD_SMI_EVENT_QUEUE_EVICTION = 9, + KFD_SMI_EVENT_QUEUE_RESTORE = 10, + KFD_SMI_EVENT_UNMAP_FROM_GPU = 11, + + /* + * max event number, as a flag bit to get events from all processes, + * this requires super user permission, otherwise will not be able to + * receive event from any process. Without this flag to receive events + * from same process. + */ + KFD_SMI_EVENT_ALL_PROCESS = 64 +}; + +enum KFD_MIGRATE_TRIGGERS { + KFD_MIGRATE_TRIGGER_PREFETCH, + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU, + KFD_MIGRATE_TRIGGER_TTM_EVICTION +}; + +enum KFD_QUEUE_EVICTION_TRIGGERS { + KFD_QUEUE_EVICTION_TRIGGER_SVM, + KFD_QUEUE_EVICTION_TRIGGER_USERPTR, + KFD_QUEUE_EVICTION_TRIGGER_TTM, + KFD_QUEUE_EVICTION_TRIGGER_SUSPEND, + KFD_QUEUE_EVICTION_CRIU_CHECKPOINT, + KFD_QUEUE_EVICTION_CRIU_RESTORE +}; + +enum KFD_SVM_UNMAP_TRIGGERS { + KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY, + KFD_SVM_UNMAP_TRIGGER_MMU_NOTIFY_MIGRATE, + KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU }; #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) @@ -568,6 +614,8 @@ enum kfd_mmio_remap { #define KFD_IOCTL_SVM_FLAG_GPU_EXEC 0x00000010 /* GPUs mostly read, may allow similar optimizations as RO, but writes fault */ #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY 0x00000020 +/* Keep GPU memory mapping always valid as if XNACK is disable */ +#define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED 0x00000040 /** * kfd_ioctl_svm_op - SVM ioctl operations @@ -826,7 +874,10 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_CRIU_OP \ AMDKFD_IOWR(0x22, struct kfd_ioctl_criu_args) +#define AMDKFD_IOC_AVAILABLE_MEMORY \ + AMDKFD_IOWR(0x23, struct kfd_ioctl_get_available_memory_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x23 +#define AMDKFD_COMMAND_END 0x24 #endif diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index 0dfc11ee243a..ec3323dbb927 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -34,7 +34,7 @@ #define MEDIA_BUS_FMT_FIXED 0x0001 -/* RGB - next is 0x101e */ +/* RGB - next is 0x1022 */ #define MEDIA_BUS_FMT_RGB444_1X12 0x1016 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE 0x1001 #define MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE 0x1002 @@ -59,9 +59,13 @@ #define MEDIA_BUS_FMT_RGB888_3X8_DELTA 0x101d #define MEDIA_BUS_FMT_RGB888_1X7X4_SPWG 0x1011 #define MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA 0x1012 +#define MEDIA_BUS_FMT_RGB666_1X30_CPADLO 0x101e +#define MEDIA_BUS_FMT_RGB888_1X30_CPADLO 0x101f #define MEDIA_BUS_FMT_ARGB8888_1X32 0x100d #define MEDIA_BUS_FMT_RGB888_1X32_PADHI 0x100f #define MEDIA_BUS_FMT_RGB101010_1X30 0x1018 +#define MEDIA_BUS_FMT_RGB666_1X36_CPADLO 0x1020 +#define MEDIA_BUS_FMT_RGB888_1X36_CPADLO 0x1021 #define MEDIA_BUS_FMT_RGB121212_1X36 0x1019 #define MEDIA_BUS_FMT_RGB161616_1X48 0x101a |