diff options
Diffstat (limited to 'include/uapi/drm')
| -rw-r--r-- | include/uapi/drm/amdgpu_drm.h | 31 | ||||
| -rw-r--r-- | include/uapi/drm/drm_fourcc.h | 73 | ||||
| -rw-r--r-- | include/uapi/drm/drm_mode.h | 88 | ||||
| -rw-r--r-- | include/uapi/drm/i915_drm.h | 398 | ||||
| -rw-r--r-- | include/uapi/drm/msm_drm.h | 39 | ||||
| -rw-r--r-- | include/uapi/drm/panfrost_drm.h | 4 | ||||
| -rw-r--r-- | include/uapi/drm/vmwgfx_drm.h | 9 |
7 files changed, 509 insertions, 133 deletions
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 0b94ec7b73e7..18d3246d636e 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -140,6 +140,10 @@ extern "C" { * not require GTT memory accounting */ #define AMDGPU_GEM_CREATE_PREEMPTIBLE (1 << 11) +/* Flag that BO can be discarded under memory pressure without keeping the + * content. + */ +#define AMDGPU_GEM_CREATE_DISCARDABLE (1 << 12) struct drm_amdgpu_gem_create_in { /** the requested memory size */ @@ -206,6 +210,8 @@ union drm_amdgpu_bo_list { #define AMDGPU_CTX_OP_FREE_CTX 2 #define AMDGPU_CTX_OP_QUERY_STATE 3 #define AMDGPU_CTX_OP_QUERY_STATE2 4 +#define AMDGPU_CTX_OP_GET_STABLE_PSTATE 5 +#define AMDGPU_CTX_OP_SET_STABLE_PSTATE 6 /* GPU reset status */ #define AMDGPU_CTX_NO_RESET 0 @@ -238,10 +244,18 @@ union drm_amdgpu_bo_list { #define AMDGPU_CTX_PRIORITY_HIGH 512 #define AMDGPU_CTX_PRIORITY_VERY_HIGH 1023 +/* select a stable profiling pstate for perfmon tools */ +#define AMDGPU_CTX_STABLE_PSTATE_FLAGS_MASK 0xf +#define AMDGPU_CTX_STABLE_PSTATE_NONE 0 +#define AMDGPU_CTX_STABLE_PSTATE_STANDARD 1 +#define AMDGPU_CTX_STABLE_PSTATE_MIN_SCLK 2 +#define AMDGPU_CTX_STABLE_PSTATE_MIN_MCLK 3 +#define AMDGPU_CTX_STABLE_PSTATE_PEAK 4 + struct drm_amdgpu_ctx_in { /** AMDGPU_CTX_OP_* */ __u32 op; - /** For future use, no flags defined so far */ + /** Flags */ __u32 flags; __u32 ctx_id; /** AMDGPU_CTX_PRIORITY_* */ @@ -262,6 +276,11 @@ union drm_amdgpu_ctx_out { /** Reset status since the last call of the ioctl. */ __u32 reset_status; } state; + + struct { + __u32 flags; + __u32 _pad; + } pstate; }; union drm_amdgpu_ctx { @@ -514,6 +533,8 @@ struct drm_amdgpu_gem_op { #define AMDGPU_VM_MTYPE_UC (4 << 5) /* Use Read Write MTYPE instead of default MTYPE */ #define AMDGPU_VM_MTYPE_RW (5 << 5) +/* don't allocate MALL */ +#define AMDGPU_VM_PAGE_NOALLOC (1 << 9) struct drm_amdgpu_gem_va { /** GEM object handle */ @@ -728,6 +749,8 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_FW_DMCUB 0x14 /* Subquery id: Query TOC firmware version */ #define AMDGPU_INFO_FW_TOC 0x15 + /* Subquery id: Query CAP firmware version */ + #define AMDGPU_INFO_FW_CAP 0x16 /* number of bytes moved for TTM migration */ #define AMDGPU_INFO_NUM_BYTES_MOVED 0x0f @@ -971,6 +994,8 @@ struct drm_amdgpu_info_vbios { #define AMDGPU_VRAM_TYPE_DDR4 8 #define AMDGPU_VRAM_TYPE_GDDR6 9 #define AMDGPU_VRAM_TYPE_DDR5 10 +#define AMDGPU_VRAM_TYPE_LPDDR4 11 +#define AMDGPU_VRAM_TYPE_LPDDR5 12 struct drm_amdgpu_info_device { /** PCI Device ID */ @@ -1133,7 +1158,11 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_RV 142 /* Raven */ #define AMDGPU_FAMILY_NV 143 /* Navi10 */ #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ +#define AMDGPU_FAMILY_GC_11_0_0 145 /* GC 11.0.0 */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ +#define AMDGPU_FAMILY_GC_11_0_1 148 /* GC 11.0.1 */ +#define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ +#define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ #if defined(__cplusplus) } diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index fc0c1454d275..0980678d502d 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -573,6 +573,53 @@ extern "C" { #define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8) /* + * Intel Tile 4 layout + * + * This is a tiled layout using 4KB tiles in a row-major layout. It has the same + * shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It + * only differs from Tile Y at the 256B granularity in between. At this + * granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape + * of 64B x 8 rows. + */ +#define I915_FORMAT_MOD_4_TILED fourcc_mod_code(INTEL, 9) + +/* + * Intel color control surfaces (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * 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. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS fourcc_mod_code(INTEL, 10) + +/* + * Intel color control surfaces (CCS) for DG2 media compression. + * + * The main surface is Tile 4 and at plane index 0. For semi-planar formats + * like NV12, the Y and UV planes are Tile 4 and are located at plane indices + * 0 and 1, respectively. The CCS for all planes are stored 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. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_MC_CCS fourcc_mod_code(INTEL, 11) + +/* + * Intel Color Control Surface with Clear Color (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * 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 + * for details. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12) + +/* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * * Macroblocks are laid in a Z-shape, and each pixel data is following the @@ -609,6 +656,28 @@ extern "C" { */ #define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) +/* + * Qualcomm Tiled Format + * + * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_TILED3 fourcc_mod_code(QCOM, 3) + +/* + * Qualcomm Alternate Tiled Format + * + * Alternate tiled format typically only used within GMEM. + * Implementation may be platform and base-format specific. + */ +#define DRM_FORMAT_MOD_QCOM_TILED2 fourcc_mod_code(QCOM, 2) + + /* Vivante framebuffer modifiers */ /* @@ -1375,11 +1444,11 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) #define AMD_FMT_MOD_PIPE_MASK 0x7 #define AMD_FMT_MOD_SET(field, value) \ - ((uint64_t)(value) << AMD_FMT_MOD_##field##_SHIFT) + ((__u64)(value) << AMD_FMT_MOD_##field##_SHIFT) #define AMD_FMT_MOD_GET(field, value) \ (((value) >> AMD_FMT_MOD_##field##_SHIFT) & AMD_FMT_MOD_##field##_MASK) #define AMD_FMT_MOD_CLEAR(field) \ - (~((uint64_t)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT)) + (~((__u64)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT)) #if defined(__cplusplus) } diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index e1e351682872..0a0d56a6158e 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -663,41 +663,73 @@ struct drm_mode_fb_cmd { #define DRM_MODE_FB_INTERLACED (1<<0) /* for interlaced framebuffers */ #define DRM_MODE_FB_MODIFIERS (1<<1) /* enables ->modifer[] */ +/** + * struct drm_mode_fb_cmd2 - Frame-buffer metadata. + * + * This struct holds frame-buffer metadata. There are two ways to use it: + * + * - User-space can fill this struct and perform a &DRM_IOCTL_MODE_ADDFB2 + * ioctl to register a new frame-buffer. The new frame-buffer object ID will + * be set by the kernel in @fb_id. + * - User-space can set @fb_id and perform a &DRM_IOCTL_MODE_GETFB2 ioctl to + * fetch metadata about an existing frame-buffer. + * + * In case of planar formats, this struct allows up to 4 buffer objects with + * offsets and pitches per plane. The pitch and offset order is dictated by the + * format FourCC as defined by ``drm_fourcc.h``, e.g. NV12 is described as: + * + * YUV 4:2:0 image with a plane of 8 bit Y samples followed by an + * interleaved U/V plane containing 8 bit 2x2 subsampled colour difference + * samples. + * + * So it would consist of a Y plane at ``offsets[0]`` and a UV plane at + * ``offsets[1]``. + * + * To accommodate tiled, compressed, etc formats, a modifier can be specified. + * For more information see the "Format Modifiers" section. Note that even + * though it looks like we have a modifier per-plane, we in fact do not. The + * modifier for each plane must be identical. Thus all combinations of + * different data layouts for multi-plane formats must be enumerated as + * separate modifiers. + * + * All of the entries in @handles, @pitches, @offsets and @modifier must be + * zero when unused. Warning, for @offsets and @modifier zero can't be used to + * figure out whether the entry is used or not since it's a valid value (a zero + * offset is common, and a zero modifier is &DRM_FORMAT_MOD_LINEAR). + */ struct drm_mode_fb_cmd2 { + /** @fb_id: Object ID of the frame-buffer. */ __u32 fb_id; + /** @width: Width of the frame-buffer. */ __u32 width; + /** @height: Height of the frame-buffer. */ __u32 height; - __u32 pixel_format; /* fourcc code from drm_fourcc.h */ - __u32 flags; /* see above flags */ + /** + * @pixel_format: FourCC format code, see ``DRM_FORMAT_*`` constants in + * ``drm_fourcc.h``. + */ + __u32 pixel_format; + /** + * @flags: Frame-buffer flags (see &DRM_MODE_FB_INTERLACED and + * &DRM_MODE_FB_MODIFIERS). + */ + __u32 flags; - /* - * In case of planar formats, this ioctl allows up to 4 - * buffer objects with offsets and pitches per plane. - * The pitch and offset order is dictated by the fourcc, - * e.g. NV12 (https://fourcc.org/yuv.php#NV12) is described as: - * - * YUV 4:2:0 image with a plane of 8 bit Y samples - * followed by an interleaved U/V plane containing - * 8 bit 2x2 subsampled colour difference samples. - * - * So it would consist of Y as offsets[0] and UV as - * offsets[1]. Note that offsets[0] will generally - * be 0 (but this is not required). - * - * To accommodate tiled, compressed, etc formats, a - * modifier can be specified. The default value of zero - * indicates "native" format as specified by the fourcc. - * Vendor specific modifier token. Note that even though - * it looks like we have a modifier per-plane, we in fact - * do not. The modifier for each plane must be identical. - * Thus all combinations of different data layouts for - * multi plane formats must be enumerated as separate - * modifiers. + /** + * @handles: GEM buffer handle, one per plane. Set to 0 if the plane is + * unused. The same handle can be used for multiple planes. */ __u32 handles[4]; - __u32 pitches[4]; /* pitch for each plane */ - __u32 offsets[4]; /* offset of each plane */ - __u64 modifier[4]; /* ie, tiling, compress */ + /** @pitches: Pitch (aka. stride) in bytes, one per plane. */ + __u32 pitches[4]; + /** @offsets: Offset into the buffer in bytes, one per plane. */ + __u32 offsets[4]; + /** + * @modifier: Format modifier, one per plane. See ``DRM_FORMAT_MOD_*`` + * constants in ``drm_fourcc.h``. All planes must use the same + * modifier. Ignored unless &DRM_MODE_FB_MODIFIERS is set in @flags. + */ + __u64 modifier[4]; }; #define DRM_MODE_FB_DIRTY_ANNOTATE_COPY 0x01 diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 914ebd9290e5..a2def7b27009 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -154,25 +154,77 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; -/* +/** + * enum drm_i915_gem_engine_class - uapi engine type enumeration + * * Different engines serve different roles, and there may be more than one - * engine serving each role. enum drm_i915_gem_engine_class provides a - * classification of the role of the engine, which may be used when requesting - * operations to be performed on a certain subset of engines, or for providing - * information about that group. + * engine serving each role. This enum provides a classification of the role + * of the engine, which may be used when requesting operations to be performed + * on a certain subset of engines, or for providing information about that + * group. */ enum drm_i915_gem_engine_class { + /** + * @I915_ENGINE_CLASS_RENDER: + * + * Render engines support instructions used for 3D, Compute (GPGPU), + * and programmable media workloads. These instructions fetch data and + * dispatch individual work items to threads that operate in parallel. + * The threads run small programs (called "kernels" or "shaders") on + * the GPU's execution units (EUs). + */ I915_ENGINE_CLASS_RENDER = 0, + + /** + * @I915_ENGINE_CLASS_COPY: + * + * Copy engines (also referred to as "blitters") support instructions + * that move blocks of data from one location in memory to another, + * or that fill a specified location of memory with fixed data. + * Copy engines can perform pre-defined logical or bitwise operations + * on the source, destination, or pattern data. + */ I915_ENGINE_CLASS_COPY = 1, + + /** + * @I915_ENGINE_CLASS_VIDEO: + * + * Video engines (also referred to as "bit stream decode" (BSD) or + * "vdbox") support instructions that perform fixed-function media + * decode and encode. + */ I915_ENGINE_CLASS_VIDEO = 2, + + /** + * @I915_ENGINE_CLASS_VIDEO_ENHANCE: + * + * Video enhancement engines (also referred to as "vebox") support + * instructions related to image enhancement. + */ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, - /* should be kept compact */ + /** + * @I915_ENGINE_CLASS_COMPUTE: + * + * Compute engines support a subset of the instructions available + * on render engines: compute engines support Compute (GPGPU) and + * programmable media workloads, but do not support the 3D pipeline. + */ + I915_ENGINE_CLASS_COMPUTE = 4, + + /* Values in this enum should be kept compact. */ + /** + * @I915_ENGINE_CLASS_INVALID: + * + * Placeholder value to represent an invalid engine class assignment. + */ I915_ENGINE_CLASS_INVALID = -1 }; -/* +/** + * struct i915_engine_class_instance - Engine class/instance identifier + * * There may be more than one engine fulfilling any role within the system. * Each engine of a class is given a unique instance number and therefore * any engine can be specified by its class:instance tuplet. APIs that allow @@ -180,10 +232,21 @@ enum drm_i915_gem_engine_class { * for this identification. */ struct i915_engine_class_instance { - __u16 engine_class; /* see enum drm_i915_gem_engine_class */ - __u16 engine_instance; + /** + * @engine_class: + * + * Engine class from enum drm_i915_gem_engine_class + */ + __u16 engine_class; #define I915_ENGINE_CLASS_INVALID_NONE -1 #define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 + + /** + * @engine_instance: + * + * Engine instance. + */ + __u16 engine_instance; }; /** @@ -1118,10 +1181,16 @@ struct drm_i915_gem_exec_object2 { /** * When the EXEC_OBJECT_PINNED flag is specified this is populated by * the user with the GTT offset at which this object will be pinned. + * * When the I915_EXEC_NO_RELOC flag is specified this must contain the * presumed_offset of the object. + * * During execbuffer2 the kernel populates it with the value of the * current GTT offset of the object, for future presumed_offset writes. + * + * See struct drm_i915_gem_create_ext for the rules when dealing with + * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with + * minimum page sizes, like DG2. */ __u64 offset; @@ -2651,24 +2720,65 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; -/* +/** + * struct drm_i915_perf_oa_config + * * Structure to upload perf dynamic configuration into the kernel. */ struct drm_i915_perf_oa_config { - /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + /** + * @uuid: + * + * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x" + */ char uuid[36]; + /** + * @n_mux_regs: + * + * Number of mux regs in &mux_regs_ptr. + */ __u32 n_mux_regs; + + /** + * @n_boolean_regs: + * + * Number of boolean regs in &boolean_regs_ptr. + */ __u32 n_boolean_regs; + + /** + * @n_flex_regs: + * + * Number of flex regs in &flex_regs_ptr. + */ __u32 n_flex_regs; - /* - * These fields are pointers to tuples of u32 values (register address, - * value). For example the expected length of the buffer pointed by - * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs). + /** + * @mux_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_mux_regs). */ __u64 mux_regs_ptr; + + /** + * @boolean_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_boolean_regs). + */ __u64 boolean_regs_ptr; + + /** + * @flex_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_flex_regs). + */ __u64 flex_regs_ptr; }; @@ -2679,12 +2789,24 @@ struct drm_i915_perf_oa_config { * @data_ptr is also depends on the specific @query_id. */ struct drm_i915_query_item { - /** @query_id: The id for this query */ + /** + * @query_id: + * + * The id for this query. Currently accepted query IDs are: + * - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info) + * - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config) + * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) + * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) + * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) + */ __u64 query_id; -#define DRM_I915_QUERY_TOPOLOGY_INFO 1 -#define DRM_I915_QUERY_ENGINE_INFO 2 -#define DRM_I915_QUERY_PERF_CONFIG 3 -#define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_TOPOLOGY_INFO 1 +#define DRM_I915_QUERY_ENGINE_INFO 2 +#define DRM_I915_QUERY_PERF_CONFIG 3 +#define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_HWCONFIG_BLOB 5 +#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 /* Must be kept compact -- no holes and well documented */ /** @@ -2700,14 +2822,17 @@ struct drm_i915_query_item { /** * @flags: * - * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. * - * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the + * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the * following: * - * - DRM_I915_QUERY_PERF_CONFIG_LIST - * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID - * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_LIST + * - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * + * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain + * a struct i915_engine_class_instance that references a render engine. */ __u32 flags; #define DRM_I915_QUERY_PERF_CONFIG_LIST 1 @@ -2765,66 +2890,112 @@ struct drm_i915_query { __u64 items_ptr; }; -/* - * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO : - * - * data: contains the 3 pieces of information : - * - * - the slice mask with one bit per slice telling whether a slice is - * available. The availability of slice X can be queried with the following - * formula : - * - * (data[X / 8] >> (X % 8)) & 1 - * - * - the subslice mask for each slice with one bit per subslice telling - * whether a subslice is available. Gen12 has dual-subslices, which are - * similar to two gen11 subslices. For gen12, this array represents dual- - * subslices. The availability of subslice Y in slice X can be queried - * with the following formula : - * - * (data[subslice_offset + - * X * subslice_stride + - * Y / 8] >> (Y % 8)) & 1 - * - * - the EU mask for each subslice in each slice with one bit per EU telling - * whether an EU is available. The availability of EU Z in subslice Y in - * slice X can be queried with the following formula : +/** + * struct drm_i915_query_topology_info * - * (data[eu_offset + - * (X * max_subslices + Y) * eu_stride + - * Z / 8] >> (Z % 8)) & 1 + * Describes slice/subslice/EU information queried by + * %DRM_I915_QUERY_TOPOLOGY_INFO */ struct drm_i915_query_topology_info { - /* + /** + * @flags: + * * Unused for now. Must be cleared to zero. */ __u16 flags; + /** + * @max_slices: + * + * The number of bits used to express the slice mask. + */ __u16 max_slices; + + /** + * @max_subslices: + * + * The number of bits used to express the subslice mask. + */ __u16 max_subslices; + + /** + * @max_eus_per_subslice: + * + * The number of bits in the EU mask that correspond to a single + * subslice's EUs. + */ __u16 max_eus_per_subslice; - /* + /** + * @subslice_offset: + * * Offset in data[] at which the subslice masks are stored. */ __u16 subslice_offset; - /* + /** + * @subslice_stride: + * * Stride at which each of the subslice masks for each slice are * stored. */ __u16 subslice_stride; - /* + /** + * @eu_offset: + * * Offset in data[] at which the EU masks are stored. */ __u16 eu_offset; - /* + /** + * @eu_stride: + * * Stride at which each of the EU masks for each subslice are stored. */ __u16 eu_stride; + /** + * @data: + * + * Contains 3 pieces of information : + * + * - The slice mask with one bit per slice telling whether a slice is + * available. The availability of slice X can be queried with the + * following formula : + * + * .. code:: c + * + * (data[X / 8] >> (X % 8)) & 1 + * + * Starting with Xe_HP platforms, Intel hardware no longer has + * traditional slices so i915 will always report a single slice + * (hardcoded slicemask = 0x1) which contains all of the platform's + * subslices. I.e., the mask here does not reflect any of the newer + * hardware concepts such as "gslices" or "cslices" since userspace + * is capable of inferring those from the subslice mask. + * + * - The subslice mask for each slice with one bit per subslice telling + * whether a subslice is available. Starting with Gen12 we use the + * term "subslice" to refer to what the hardware documentation + * describes as a "dual-subslices." The availability of subslice Y + * in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1 + * + * - The EU mask for each subslice in each slice, with one bit per EU + * telling whether an EU is available. The availability of EU Z in + * subslice Y in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[eu_offset + + * (X * max_subslices + Y) * eu_stride + + * Z / 8 + * ] >> (Z % 8)) & 1 + */ __u8 data[]; }; @@ -2945,52 +3116,68 @@ struct drm_i915_query_engine_info { struct drm_i915_engine_info engines[]; }; -/* - * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG. +/** + * struct drm_i915_query_perf_config + * + * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and + * %DRM_I915_QUERY_GEOMETRY_SUBSLICES. */ struct drm_i915_query_perf_config { union { - /* - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets - * this fields to the number of configurations available. + /** + * @n_configs: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to + * the number of configurations available. */ __u64 n_configs; - /* - * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, - * i915 will use the value in this field as configuration - * identifier to decide what data to write into config_ptr. + /** + * @config: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. */ __u64 config; - /* - * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, - * i915 will use the value in this field as configuration - * identifier to decide what data to write into config_ptr. + /** + * @uuid: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. * * String formatted like "%08x-%04x-%04x-%04x-%012x" */ char uuid[36]; }; - /* + /** + * @flags: + * * Unused for now. Must be cleared to zero. */ __u32 flags; - /* - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will - * write an array of __u64 of configuration identifiers. + /** + * @data: * - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will - * write a struct drm_i915_perf_oa_config. If the following fields of - * drm_i915_perf_oa_config are set not set to 0, i915 will write into - * the associated pointers the values of submitted when the + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST, + * i915 will write an array of __u64 of configuration identifiers. + * + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA, + * i915 will write a struct drm_i915_perf_oa_config. If the following + * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will + * write into the associated pointers the values of submitted when the * configuration was created : * - * - n_mux_regs - * - n_boolean_regs - * - n_flex_regs + * - &drm_i915_perf_oa_config.n_mux_regs + * - &drm_i915_perf_oa_config.n_boolean_regs + * - &drm_i915_perf_oa_config.n_flex_regs */ __u8 data[]; }; @@ -3129,6 +3316,16 @@ struct drm_i915_query_memory_regions { }; /** + * DOC: GuC HWCONFIG blob uAPI + * + * The GuC produces a blob with information about the current device. + * i915 reads this blob from GuC and makes it available via this uAPI. + * + * The format and meaning of the blob content are documented in the + * Programmer's Reference Manual. + */ + +/** * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added * extension support using struct i915_user_extension. * @@ -3144,11 +3341,40 @@ struct drm_i915_gem_create_ext { * * The (page-aligned) allocated size for the object will be returned. * - * Note that for some devices we have might have further minimum - * page-size restrictions(larger than 4K), like for device local-memory. - * However in general the final size here should always reflect any - * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS - * extension to place the object in device local-memory. + * + * DG2 64K min page size implications: + * + * On discrete platforms, starting from DG2, we have to contend with GTT + * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE + * objects. Specifically the hardware only supports 64K or larger GTT + * page sizes for such memory. The kernel will already ensure that all + * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page + * sizes underneath. + * + * 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. + * + * Special DG2 GTT address alignment requirement: + * + * The GTT alignment will also need to be at least 2M for such objects. + * + * Note that due to how the hardware implements 64K GTT page support, we + * have some further complications: + * + * 1) The entire PDE (which covers a 2MB virtual address range), must + * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same + * PDE is forbidden by the hardware. + * + * 2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM + * objects. + * + * To keep things simple for userland, we mandate that any GTT mappings + * must be aligned to and rounded up to 2MB. The kernel will internally + * pad them out to the next 2MB boundary. As this only wastes virtual + * address space and avoids userland having to copy any needlessly + * complicated PDE sharing scheme (coloring) and only affects DG2, this + * is deemed to be a good compromise. */ __u64 size; /** diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 6b8fffc28a50..3c7b097c4e3d 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -67,16 +67,25 @@ struct drm_msm_timespec { __s64 tv_nsec; /* nanoseconds */ }; -#define MSM_PARAM_GPU_ID 0x01 -#define MSM_PARAM_GMEM_SIZE 0x02 -#define MSM_PARAM_CHIP_ID 0x03 -#define MSM_PARAM_MAX_FREQ 0x04 -#define MSM_PARAM_TIMESTAMP 0x05 -#define MSM_PARAM_GMEM_BASE 0x06 -#define MSM_PARAM_PRIORITIES 0x07 /* The # of priority levels */ -#define MSM_PARAM_PP_PGTABLE 0x08 /* => 1 for per-process pagetables, else 0 */ -#define MSM_PARAM_FAULTS 0x09 -#define MSM_PARAM_SUSPENDS 0x0a +/* Below "RO" indicates a read-only param, "WO" indicates write-only, and + * "RW" indicates a param that can be both read (GET_PARAM) and written + * (SET_PARAM) + */ +#define MSM_PARAM_GPU_ID 0x01 /* RO */ +#define MSM_PARAM_GMEM_SIZE 0x02 /* RO */ +#define MSM_PARAM_CHIP_ID 0x03 /* RO */ +#define MSM_PARAM_MAX_FREQ 0x04 /* RO */ +#define MSM_PARAM_TIMESTAMP 0x05 /* RO */ +#define MSM_PARAM_GMEM_BASE 0x06 /* RO */ +#define MSM_PARAM_PRIORITIES 0x07 /* RO: The # of priority levels */ +#define MSM_PARAM_PP_PGTABLE 0x08 /* RO: Deprecated, always returns zero */ +#define MSM_PARAM_FAULTS 0x09 /* RO */ +#define MSM_PARAM_SUSPENDS 0x0a /* RO */ +#define MSM_PARAM_SYSPROF 0x0b /* WO: 1 preserves perfcntrs, 2 also disables suspend */ +#define MSM_PARAM_COMM 0x0c /* WO: override for task->comm */ +#define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ +#define MSM_PARAM_VA_START 0x0e /* RO: start of valid GPU iova range */ +#define MSM_PARAM_VA_SIZE 0x0f /* RO: size of valid GPU iova range (bytes) */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # @@ -90,6 +99,8 @@ struct drm_msm_param { __u32 pipe; /* in, MSM_PIPE_x */ __u32 param; /* in, MSM_PARAM_x */ __u64 value; /* out (get_param) or in (set_param) */ + __u32 len; /* zero for non-pointer params */ + __u32 pad; /* must be zero */ }; /* @@ -126,6 +137,7 @@ struct drm_msm_gem_new { #define MSM_INFO_GET_IOVA 0x01 /* get iova, returned by value */ #define MSM_INFO_SET_NAME 0x02 /* set the debug name (by pointer) */ #define MSM_INFO_GET_NAME 0x03 /* get debug name, returned by pointer */ +#define MSM_INFO_SET_IOVA 0x04 /* set the iova, passed by value */ struct drm_msm_gem_info { __u32 handle; /* in */ @@ -227,6 +239,7 @@ struct drm_msm_gem_submit_bo { #define MSM_SUBMIT_SUDO 0x10000000 /* run submitted cmds from RB */ #define MSM_SUBMIT_SYNCOBJ_IN 0x08000000 /* enable input syncobj */ #define MSM_SUBMIT_SYNCOBJ_OUT 0x04000000 /* enable output syncobj */ +#define MSM_SUBMIT_FENCE_SN_IN 0x02000000 /* userspace passes in seqno fence */ #define MSM_SUBMIT_FLAGS ( \ MSM_SUBMIT_NO_IMPLICIT | \ MSM_SUBMIT_FENCE_FD_IN | \ @@ -234,6 +247,7 @@ struct drm_msm_gem_submit_bo { MSM_SUBMIT_SUDO | \ MSM_SUBMIT_SYNCOBJ_IN | \ MSM_SUBMIT_SYNCOBJ_OUT | \ + MSM_SUBMIT_FENCE_SN_IN | \ 0) #define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */ @@ -253,7 +267,7 @@ struct drm_msm_gem_submit_syncobj { */ struct drm_msm_gem_submit { __u32 flags; /* MSM_PIPE_x | MSM_SUBMIT_x */ - __u32 fence; /* out */ + __u32 fence; /* out (or in with MSM_SUBMIT_FENCE_SN_IN flag) */ __u32 nr_bos; /* in, number of submit_bo's */ __u32 nr_cmds; /* in, number of submit_cmd's */ __u64 bos; /* in, ptr to array of submit_bo's */ @@ -333,9 +347,7 @@ struct drm_msm_submitqueue_query { }; #define DRM_MSM_GET_PARAM 0x00 -/* placeholder: #define DRM_MSM_SET_PARAM 0x01 - */ #define DRM_MSM_GEM_NEW 0x02 #define DRM_MSM_GEM_INFO 0x03 #define DRM_MSM_GEM_CPU_PREP 0x04 @@ -351,6 +363,7 @@ struct drm_msm_submitqueue_query { #define DRM_MSM_SUBMITQUEUE_QUERY 0x0C #define DRM_IOCTL_MSM_GET_PARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param) +#define DRM_IOCTL_MSM_SET_PARAM DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SET_PARAM, struct drm_msm_param) #define DRM_IOCTL_MSM_GEM_NEW DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new) #define DRM_IOCTL_MSM_GEM_INFO DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_INFO, struct drm_msm_gem_info) #define DRM_IOCTL_MSM_GEM_CPU_PREP DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_GEM_CPU_PREP, struct drm_msm_gem_cpu_prep) diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index 061e700dd06c..9e40277d8185 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -84,14 +84,14 @@ struct drm_panfrost_wait_bo { __s64 timeout_ns; /* absolute */ }; +/* Valid flags to pass to drm_panfrost_create_bo */ #define PANFROST_BO_NOEXEC 1 #define PANFROST_BO_HEAP 2 /** * struct drm_panfrost_create_bo - ioctl argument for creating Panfrost BOs. * - * There are currently no values for the flags argument, but it may be - * used in a future extension. + * The flags argument is a bit mask of PANFROST_BO_* flags. */ struct drm_panfrost_create_bo { __u32 size; diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 8277644c1144..26549c86a91f 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -1,6 +1,6 @@ /************************************************************************** * - * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright © 2009-2022 VMware, Inc., Palo Alto, CA., USA * All Rights Reserved. * * Permission is hereby granted, free of charge, to any person obtaining a @@ -92,6 +92,12 @@ extern "C" { * * DRM_VMW_PARAM_SM5 * SM5 support is enabled. + * + * DRM_VMW_PARAM_GL43 + * SM5.1+GL4.3 support is enabled. + * + * DRM_VMW_PARAM_DEVICE_ID + * PCI ID of the underlying SVGA device. */ #define DRM_VMW_PARAM_NUM_STREAMS 0 @@ -111,6 +117,7 @@ extern "C" { #define DRM_VMW_PARAM_SM4_1 14 #define DRM_VMW_PARAM_SM5 15 #define DRM_VMW_PARAM_GL43 16 +#define DRM_VMW_PARAM_DEVICE_ID 17 /** * enum drm_vmw_handle_type - handle type for ref ioctls |