From: Jordan Justen Date: Wed, 28 Sep 2022 23:46:20 +0000 (-0700) Subject: include/drm/i915_drm.h: Update from Linux v6.0-rc7 X-Git-Tag: libdrm-2.4.114~15 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=e0df5fce890c8f70ccd72a3e7260aa8f5dd842d8;p=platform%2Fupstream%2Flibdrm.git include/drm/i915_drm.h: Update from Linux v6.0-rc7 Generated from the Linux v6.0-rc7 tag with a sha1 of f76349cf41451c5c42a99f18a9163377e4b364ff. Signed-off-by: Jordan Justen --- diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 72afd94..1de0433 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -55,15 +55,15 @@ extern "C" { * cause the related events to not be seen. * * I915_RESET_UEVENT - Event is generated just before an attempt to reset the - * the GPU. The value supplied with the event is always 1. NOTE: Disable + * GPU. The value supplied with the event is always 1. NOTE: Disable * reset via module parameter will cause this event to not be seen. */ #define I915_L3_PARITY_UEVENT "L3_PARITY_ERROR" #define I915_ERROR_UEVENT "ERROR" #define I915_RESET_UEVENT "RESET" -/* - * i915_user_extension: Base class for defining a chain of extensions +/** + * struct i915_user_extension - Base class for defining a chain of extensions * * Many interfaces need to grow over time. In most cases we can simply * extend the struct and have userspace pass in more data. Another option, @@ -76,12 +76,58 @@ extern "C" { * increasing complexity, and for large parts of that interface to be * entirely optional. The downside is more pointer chasing; chasing across * the boundary with pointers encapsulated inside u64. + * + * Example chaining: + * + * .. code-block:: C + * + * struct i915_user_extension ext3 { + * .next_extension = 0, // end + * .name = ..., + * }; + * struct i915_user_extension ext2 { + * .next_extension = (uintptr_t)&ext3, + * .name = ..., + * }; + * struct i915_user_extension ext1 { + * .next_extension = (uintptr_t)&ext2, + * .name = ..., + * }; + * + * Typically the struct i915_user_extension would be embedded in some uAPI + * struct, and in this case we would feed it the head of the chain(i.e ext1), + * which would then apply all of the above extensions. + * */ struct i915_user_extension { + /** + * @next_extension: + * + * Pointer to the next struct i915_user_extension, or zero if the end. + */ __u64 next_extension; + /** + * @name: Name of the extension. + * + * Note that the name here is just some integer. + * + * Also note that the name space for this is not global for the whole + * driver, but rather its scope/meaning is limited to the specific piece + * of uAPI which has embedded the struct i915_user_extension. + */ __u32 name; - __u32 flags; /* All undefined bits must be zero. */ - __u32 rsvd[4]; /* Reserved for future use; must be zero. */ + /** + * @flags: MBZ + * + * All undefined bits must be zero. + */ + __u32 flags; + /** + * @rsvd: MBZ + * + * Reserved for future use; must be zero. + */ + __u32 rsvd[4]; }; /* @@ -108,25 +154,102 @@ 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 + * access to any engine in the system will use struct i915_engine_class_instance + * for this identification. + */ +struct i915_engine_class_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; +}; + +/** * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 * */ @@ -163,8 +286,9 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) #define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2) #define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3) +#define I915_PMU_SOFTWARE_GT_AWAKE_TIME __I915_PMU_OTHER(4) -#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY +#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY /* Each region is a minimum of 16k, and there are at most 255 of them. */ @@ -343,6 +467,9 @@ typedef struct _drm_i915_sarea { #define DRM_I915_PERF_ADD_CONFIG 0x37 #define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_I915_QUERY 0x39 +#define DRM_I915_GEM_VM_CREATE 0x3a +#define DRM_I915_GEM_VM_DESTROY 0x3b +#define DRM_I915_GEM_CREATE_EXT 0x3c /* Must be kept compact -- no holes */ #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) @@ -375,10 +502,12 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_ENTERVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT) #define DRM_IOCTL_I915_GEM_LEAVEVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT) #define DRM_IOCTL_I915_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create) +#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext) #define DRM_IOCTL_I915_GEM_PREAD DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread) #define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite) #define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap) #define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt) +#define DRM_IOCTL_I915_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset) #define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain) #define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish) #define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling) @@ -403,6 +532,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) #define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query) +#define DRM_IOCTL_I915_GEM_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control) +#define DRM_IOCTL_I915_GEM_VM_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -503,6 +634,16 @@ typedef struct drm_i915_irq_wait { #define I915_SCHEDULER_CAP_PRIORITY (1ul << 1) #define I915_SCHEDULER_CAP_PREEMPTION (1ul << 2) #define I915_SCHEDULER_CAP_SEMAPHORES (1ul << 3) +#define I915_SCHEDULER_CAP_ENGINE_BUSY_STATS (1ul << 4) +/* + * Indicates the 2k user priority levels are statically mapped into 3 buckets as + * follows: + * + * -1k to -1 Low priority + * 0 Normal priority + * 1 to 1k Highest priority + */ +#define I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP (1ul << 5) #define I915_PARAM_HUC_STATUS 42 @@ -520,7 +661,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_EXEC_FENCE 44 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture - * user specified buffers for post-mortem debugging of GPU hangs. See + * user specified bufffers for post-mortem debugging of GPU hangs. See * EXEC_OBJECT_CAPTURE. */ #define I915_PARAM_HAS_EXEC_CAPTURE 45 @@ -586,16 +727,51 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_MMAP_GTT_COHERENT 52 +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel + * execution through use of explicit fence support. + * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT. + */ +#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53 + +/* + * Revision of the i915-perf uAPI. The value returned helps determine what + * i915-perf features are available. See drm_i915_perf_property_id. + */ +#define I915_PARAM_PERF_REVISION 54 + +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See + * I915_EXEC_USE_EXTENSIONS. + */ +#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55 + +/* Query if the kernel supports the I915_USERPTR_PROBE flag. */ +#define I915_PARAM_HAS_USERPTR_PROBE 56 + /* 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 *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: */ @@ -761,14 +937,113 @@ struct drm_i915_gem_mmap_gtt { __u64 offset; }; +/** + * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object. + * + * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl, + * and is used to retrieve the fake offset to mmap an object specified by &handle. + * + * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+. + * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave + * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`. + */ +struct drm_i915_gem_mmap_offset { + /** @handle: Handle for the object being mapped. */ + __u32 handle; + /** @pad: Must be zero */ + __u32 pad; + /** + * @offset: The fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; + + /** + * @flags: Flags for extended behaviour. + * + * It is mandatory that one of the `MMAP_OFFSET` types + * should be included: + * + * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined) + * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching. + * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching. + * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching. + * + * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid + * type. On devices without local memory, this caching mode is invalid. + * + * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will + * be used, depending on the object placement on creation. WB will be used + * when the object can only exist in system memory, WC otherwise. + */ + __u64 flags; + +#define I915_MMAP_OFFSET_GTT 0 +#define I915_MMAP_OFFSET_WC 1 +#define I915_MMAP_OFFSET_WB 2 +#define I915_MMAP_OFFSET_UC 3 +#define I915_MMAP_OFFSET_FIXED 4 + + /** + * @extensions: Zero-terminated chain of extensions. + * + * No current extensions defined; mbz. + */ + __u64 extensions; +}; + +/** + * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in + * preparation for accessing the pages via some CPU domain. + * + * Specifying a new write or read domain will flush the object out of the + * previous domain(if required), before then updating the objects domain + * tracking with the new domain. + * + * Note this might involve waiting for the object first if it is still active on + * the GPU. + * + * Supported values for @read_domains and @write_domain: + * + * - I915_GEM_DOMAIN_WC: Uncached write-combined domain + * - I915_GEM_DOMAIN_CPU: CPU cache domain + * - I915_GEM_DOMAIN_GTT: Mappable aperture domain + * + * All other domains are rejected. + * + * Note that for discrete, starting from DG1, this is no longer supported, and + * is instead rejected. On such platforms the CPU domain is effectively static, + * where we also only support a single &drm_i915_gem_mmap_offset cache mode, + * which can't be set explicitly and instead depends on the object placements, + * as per the below. + * + * Implicit caching rules, starting from DG1: + * + * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions) + * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and + * mapped as write-combined only. + * + * - Everything else is always allocated and mapped as write-back, with the + * guarantee that everything is also coherent with the GPU. + * + * Note that this is likely to change in the future again, where we might need + * more flexibility on future devices, so making this all explicit as part of a + * new &drm_i915_gem_create_ext extension is probable. + */ struct drm_i915_gem_set_domain { - /** Handle for the object */ + /** @handle: Handle for the object. */ __u32 handle; - /** New read domains */ + /** @read_domains: New read domains. */ __u32 read_domains; - /** New write domain */ + /** + * @write_domain: New write domain. + * + * Note that having something in the write domain implies it's in the + * read domain, and only that read domain. + */ __u32 write_domain; }; @@ -872,6 +1147,7 @@ struct drm_i915_gem_exec_object { __u64 offset; }; +/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */ struct drm_i915_gem_execbuffer { /** * List of buffers to be validated with their relocations to be @@ -918,10 +1194,16 @@ 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; @@ -970,38 +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; }; -struct drm_i915_gem_execbuffer2 { +/** + * 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; + + /** + * @fence_count: Number of elements in the @handles_ptr & @value_ptr + * arrays. + */ + __u64 fence_count; + + /** + * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence + * of length @fence_count. + */ + __u64 handles_ptr; + /** - * List of gem_exec_object2 structs + * @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 { + /** @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 - * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a - * struct drm_i915_gem_exec_fence *fences. + * @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 &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 &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) @@ -1019,10 +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) @@ -1108,7 +1467,39 @@ struct drm_i915_gem_execbuffer2 { */ #define I915_EXEC_FENCE_ARRAY (1<<19) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) +/* + * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent + * a sync_file fd to wait upon (in a nonblocking manner) prior to executing + * the batch. + * + * Returns -EINVAL if the sync_file fd cannot be found. + */ +#define I915_EXEC_FENCE_SUBMIT (1 << 20) + +/* + * Setting I915_EXEC_USE_EXTENSIONS implies that + * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked + * list of i915_user_extension. Each i915_user_extension node is the base of a + * larger structure. The list of supported structures are listed in the + * 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) \ @@ -1172,12 +1563,11 @@ struct drm_i915_gem_busy { * reading from the object simultaneously. * * The value of each engine class is the same as specified in the - * I915_CONTEXT_SET_ENGINES parameter and via perf, i.e. + * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e. * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc. - * reported as active itself. Some hardware may have parallel - * execution engines, e.g. multiple media engines, which are - * mapped to the same class identifier and so are not separately - * reported for busyness. + * Some hardware may have parallel execution engines, e.g. multiple + * media engines, which are mapped to the same class identifier and so + * are not separately reported for busyness. * * Caveat emptor: * Only the boolean result of this query is reliable; that is whether @@ -1188,49 +1578,91 @@ struct drm_i915_gem_busy { }; /** - * I915_CACHING_NONE + * struct drm_i915_gem_caching - Set or get the caching for given object + * handle. * - * GPU access is not coherent with cpu caches. Default for machines without an - * LLC. - */ -#define I915_CACHING_NONE 0 -/** - * I915_CACHING_CACHED + * Allow userspace to control the GTT caching bits for a given object when the + * object is later mapped through the ppGTT(or GGTT on older platforms lacking + * ppGTT support, or if the object is used for scanout). Note that this might + * require unbinding the object from the GTT first, if its current caching value + * doesn't match. * - * GPU access is coherent with cpu caches and furthermore the data is cached in - * last-level caches shared between cpu cores and the gpu GT. Default on - * machines with HAS_LLC. - */ -#define I915_CACHING_CACHED 1 -/** - * I915_CACHING_DISPLAY + * Note that this all changes on discrete platforms, starting from DG1, the + * set/get caching is no longer supported, and is now rejected. Instead the CPU + * caching attributes(WB vs WC) will become an immutable creation time property + * for the object, along with the GTT caching level. For now we don't expose any + * new uAPI for this, instead on DG1 this is all implicit, although this largely + * shouldn't matter since DG1 is coherent by default(without any way of + * controlling it). + * + * Implicit caching rules, starting from DG1: + * + * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions) + * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and + * mapped as write-combined only. + * + * - Everything else is always allocated and mapped as write-back, with the + * guarantee that everything is also coherent with the GPU. * - * Special GPU caching mode which is coherent with the scanout engines. - * Transparently falls back to I915_CACHING_NONE on platforms where no special - * cache mode (like write-through or gfdt flushing) is available. The kernel - * automatically sets this mode when using a buffer as a scanout target. - * Userspace can manually set this mode to avoid a costly stall and clflush in - * the hotpath of drawing the first frame. + * Note that this is likely to change in the future again, where we might need + * more flexibility on future devices, so making this all explicit as part of a + * new &drm_i915_gem_create_ext extension is probable. + * + * Side note: Part of the reason for this is that changing the at-allocation-time CPU + * caching attributes for the pages might be required(and is expensive) if we + * need to then CPU map the pages later with different caching attributes. This + * inconsistent caching behaviour, while supported on x86, is not universally + * supported on other architectures. So for simplicity we opt for setting + * everything at creation time, whilst also making it immutable, on discrete + * platforms. */ -#define I915_CACHING_DISPLAY 2 - struct drm_i915_gem_caching { /** - * Handle of the buffer to set/get the caching level of. */ + * @handle: Handle of the buffer to set/get the caching level. + */ __u32 handle; /** - * Caching level to apply or return value + * @caching: The GTT caching level to apply or possible return value. * - * bits0-15 are for generic caching control (i.e. the above defined - * values). bits16-31 are reserved for platform-specific variations - * (e.g. l3$ caching on gen7). */ + * The supported @caching values: + * + * I915_CACHING_NONE: + * + * GPU access is not coherent with CPU caches. Default for machines + * without an LLC. This means manual flushing might be needed, if we + * want GPU access to be coherent. + * + * I915_CACHING_CACHED: + * + * GPU access is coherent with CPU caches and furthermore the data is + * cached in last-level caches shared between CPU cores and the GPU GT. + * + * I915_CACHING_DISPLAY: + * + * Special GPU caching mode which is coherent with the scanout engines. + * Transparently falls back to I915_CACHING_NONE on platforms where no + * special cache mode (like write-through or gfdt flushing) is + * available. The kernel automatically sets this mode when using a + * buffer as a scanout target. Userspace can manually set this mode to + * avoid a costly stall and clflush in the hotpath of drawing the first + * frame. + */ +#define I915_CACHING_NONE 0 +#define I915_CACHING_CACHED 1 +#define I915_CACHING_DISPLAY 2 __u32 caching; }; #define I915_TILING_NONE 0 #define I915_TILING_X 1 #define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ #define I915_TILING_LAST I915_TILING_Y #define I915_BIT_6_SWIZZLE_NONE 0 @@ -1448,20 +1880,64 @@ 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_USE_EXTENSIONS << 1)) + (-(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 + * someone somewhere has attempted to use it, never re-use this context + * param number. + */ #define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2 #define I915_CONTEXT_PARAM_GTT_SIZE 0x3 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 @@ -1495,20 +1971,126 @@ struct drm_i915_gem_context_param { * On creation, all new contexts are marked as recoverable. */ #define I915_CONTEXT_PARAM_RECOVERABLE 0x8 -/* Must be kept compact -- no holes and well documented */ - __u64 value; -}; + /* + * The id of the associated virtual memory address space (ppGTT) of + * this context. Can be retrieved and passed to another context + * (on the same fd) for both to use the same ppGTT and so share + * address layouts, and avoid reloading the page tables on context + * switches between themselves. + * + * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY. + */ +#define I915_CONTEXT_PARAM_VM 0x9 -/** - * Context SSEU programming +/* + * I915_CONTEXT_PARAM_ENGINES: * - * It may be necessary for either functional or performance reason to configure - * a context to run with a reduced number of SSEU (where SSEU stands for Slice/ - * Sub-slice/EU). + * Bind this context to operate on this subset of available engines. Henceforth, + * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as + * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0] + * and upwards. Slots 0...N are filled in using the specified (class, instance). + * Use + * engine_class: I915_ENGINE_CLASS_INVALID, + * engine_instance: I915_ENGINE_CLASS_INVALID_NONE + * to specify a gap in the array that can be filled in later, e.g. by a + * virtual engine used for load balancing. * - * This is done by configuring SSEU configuration using the below - * @struct drm_i915_gem_context_param_sseu for every supported engine which + * Setting the number of engines bound to the context to 0, by passing a zero + * sized argument, will revert back to default settings. + * + * See struct i915_context_param_engines. + * + * Extensions: + * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) + * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT) + */ +#define I915_CONTEXT_PARAM_ENGINES 0xa + +/* + * I915_CONTEXT_PARAM_PERSISTENCE: + * + * Allow the context and active rendering to survive the process until + * completion. Persistence allows fire-and-forget clients to queue up a + * bunch of work, hand the output over to a display server and then quit. + * If the context is marked as not persistent, upon closing (either via + * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure + * or process termination), the context and any outstanding requests will be + * cancelled (and exported fences for cancelled requests marked as -EIO). + * + * By default, new contexts allow persistence. + */ +#define I915_CONTEXT_PARAM_PERSISTENCE 0xb + +/* This API has been removed. On the off chance someone somewhere has + * attempted to use it, never re-use this context param number. + */ +#define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + */ +#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; +}; + +/* + * Context SSEU programming + * + * It may be necessary for either functional or performance reason to configure + * a context to run with a reduced number of SSEU (where SSEU stands for Slice/ + * Sub-slice/EU). + * + * This is done by configuring SSEU configuration using the below + * @struct drm_i915_gem_context_param_sseu for every supported engine which * userspace intends to use. * * Not all GPUs or engines support this functionality in which case an error @@ -1525,13 +2107,13 @@ struct drm_i915_gem_context_param_sseu { /* * Engine class & instance to be configured or queried. */ - __u16 engine_class; - __u16 engine_instance; + struct i915_engine_class_instance engine; /* - * Unused for now. Must be cleared to zero. + * Unknown flags must be cleared to zero. */ __u32 flags; +#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0) /* * Mask of slices to enable for the context. Valid values are a subset @@ -1559,9 +2141,354 @@ struct drm_i915_gem_context_param_sseu { __u32 rsvd; }; +/** + * DOC: Virtual Engine uAPI + * + * Virtual engine is a concept where userspace is able to configure a set of + * physical engines, submit a batch buffer, and let the driver execute it on any + * engine from the set as it sees fit. + * + * This is primarily useful on parts which have multiple instances of a same + * class engine, like for example GT3+ Skylake parts with their two VCS engines. + * + * For instance userspace can enumerate all engines of a certain class using the + * previously described `Engine Discovery uAPI`_. After that userspace can + * create a GEM context with a placeholder slot for the virtual engine (using + * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class + * and instance respectively) and finally using the + * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in + * the same reserved slot. + * + * Example of creating a virtual engine and submitting a batch buffer to it: + * + * .. code-block:: C + * + * I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = { + * .base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE, + * .engine_index = 0, // Place this virtual engine into engine map slot 0 + * .num_siblings = 2, + * .engines = { { I915_ENGINE_CLASS_VIDEO, 0 }, + * { I915_ENGINE_CLASS_VIDEO, 1 }, }, + * }; + * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = { + * .engines = { { I915_ENGINE_CLASS_INVALID, + * I915_ENGINE_CLASS_INVALID_NONE } }, + * .extensions = to_user_pointer(&virtual), // Chains after load_balance extension + * }; + * struct drm_i915_gem_context_create_ext_setparam p_engines = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_ENGINES, + * .value = to_user_pointer(&engines), + * .size = sizeof(engines), + * }, + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_engines); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * // Now we have created a GEM context with its engine map containing a + * // single virtual engine. Submissions to this slot can go either to + * // vcs0 or vcs1, depending on the load balancing algorithm used inside + * // the driver. The load balancing is dynamic from one batch buffer to + * // another and transparent to userspace. + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 0; // Submits to index 0 which is the virtual engine + * gem_execbuf(drm_fd, &execbuf); + */ + +/* + * i915_context_engines_load_balance: + * + * Enable load balancing across this set of engines. + * + * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when + * used will proxy the execbuffer request onto one of the set of engines + * in such a way as to distribute the load evenly across the set. + * + * The set of engines must be compatible (e.g. the same HW class) as they + * will share the same logical GPU context and ring. + * + * To intermix rendering with the virtual engine and direct rendering onto + * the backing engines (bypassing the load balancing proxy), the context must + * be defined to use a single timeline for all engines. + */ +struct i915_context_engines_load_balance { + struct i915_user_extension base; + + __u16 engine_index; + __u16 num_siblings; + __u32 flags; /* all undefined flags must be zero */ + + __u64 mbz64; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 num_siblings; \ + __u32 flags; \ + __u64 mbz64; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/* + * i915_context_engines_bond: + * + * Constructed bonded pairs for execution within a virtual engine. + * + * All engines are equal, but some are more equal than others. Given + * the distribution of resources in the HW, it may be preferable to run + * a request on a given subset of engines in parallel to a request on a + * specific engine. We enable this selection of engines within a virtual + * engine by specifying bonding pairs, for any given master engine we will + * only execute on one of the corresponding siblings within the virtual engine. + * + * To execute a request in parallel on the master engine and a sibling requires + * coordination with a I915_EXEC_FENCE_SUBMIT. + */ +struct i915_context_engines_bond { + struct i915_user_extension base; + + struct i915_engine_class_instance master; + + __u16 virtual_index; /* index of virtual engine in ctx->engines[] */ + __u16 num_bonds; + + __u64 flags; /* all undefined flags must be zero */ + __u64 mbz64[4]; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ + struct i915_user_extension base; \ + struct i915_engine_class_instance master; \ + __u16 virtual_index; \ + __u16 num_bonds; \ + __u64 flags; \ + __u64 mbz64[4]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/** + * struct i915_context_engines_parallel_submit - Configure engine for + * parallel submission. + * + * Setup a slot in the context engine map to allow multiple BBs to be submitted + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU + * in parallel. Multiple hardware contexts are created internally in the i915 to + * run these BBs. Once a slot is configured for N BBs only N BBs can be + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how + * many BBs there are based on the slot's configuration. The N BBs are the last + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. + * + * The default placement behavior is to create implicit bonds between each + * context if each context maps to more than 1 physical engine (e.g. context is + * a virtual engine). Also we only allow contexts of same engine class and these + * contexts must be in logically contiguous order. Examples of the placement + * behavior are described below. Lastly, the default is to not allow BBs to be + * preempted mid-batch. Rather insert coordinated preemption points on all + * hardware contexts between each set of BBs. Flags could be added in the future + * to change both of these default behaviors. + * + * Returns -EINVAL if hardware context placement configuration is invalid or if + * the placement configuration isn't supported on the platform / submission + * interface. + * Returns -ENODEV if extension isn't supported on the platform / submission + * interface. + * + * .. code-block:: none + * + * Examples syntax: + * CS[X] = generic engine of same class, logical instance X + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE + * + * Example 1 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=1, + * engines=CS[0],CS[1]) + * + * Results in the following valid placement: + * CS[0], CS[1] + * + * Example 2 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[2],CS[1],CS[3]) + * + * Results in the following valid placements: + * CS[0], CS[1] + * CS[2], CS[3] + * + * This can be thought of as two virtual engines, each containing two + * engines thereby making a 2D array. However, there are bonds tying the + * entries together and placing restrictions on how they can be scheduled. + * Specifically, the scheduler can choose only vertical columns from the 2D + * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the + * scheduler wants to submit to CS[0], it must also choose CS[1] and vice + * versa. Same for CS[2] requires also using CS[3]. + * VE[0] = CS[0], CS[2] + * VE[1] = CS[1], CS[3] + * + * Example 3 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[1],CS[1],CS[3]) + * + * Results in the following valid and invalid placements: + * CS[0], CS[1] + * CS[1], CS[3] - Not logically contiguous, return -EINVAL + */ +struct i915_context_engines_parallel_submit { + /** + * @base: base user extension. + */ + struct i915_user_extension base; + + /** + * @engine_index: slot for parallel engine + */ + __u16 engine_index; + + /** + * @width: number of contexts per parallel engine or in other words the + * number of batches in each submission + */ + __u16 width; + + /** + * @num_siblings: number of siblings per context or in other words the + * number of possible placements for each submission + */ + __u16 num_siblings; + + /** + * @mbz16: reserved for future use; must be zero + */ + __u16 mbz16; + + /** + * @flags: all undefined flags must be zero, currently not defined flags + */ + __u64 flags; + + /** + * @mbz64: reserved for future use; must be zero + */ + __u64 mbz64[3]; + + /** + * @engines: 2-d array of engine instances to configure parallel engine + * + * length = width (i) * num_siblings (j) + * index = j + i * num_siblings + */ + struct i915_engine_class_instance engines[]; + +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 width; \ + __u16 num_siblings; \ + __u16 mbz16; \ + __u64 flags; \ + __u64 mbz64[3]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/** + * DOC: Context Engine Map uAPI + * + * Context engine map is a new way of addressing engines when submitting batch- + * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT` + * inside the flags field of `struct drm_i915_gem_execbuffer2`. + * + * To use it created GEM contexts need to be configured with a list of engines + * the user is intending to submit to. This is accomplished using the + * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct + * i915_context_param_engines`. + * + * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the + * configured map. + * + * Example of creating such context and submitting against it: + * + * .. code-block:: C + * + * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = { + * .engines = { { I915_ENGINE_CLASS_RENDER, 0 }, + * { I915_ENGINE_CLASS_COPY, 0 } } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_engines = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_ENGINES, + * .value = to_user_pointer(&engines), + * .size = sizeof(engines), + * }, + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_engines); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * // We have now created a GEM context with two engines in the map: + * // Index 0 points to rcs0 while index 1 points to bcs0. Other engines + * // will not be accessible from this context. + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context + * gem_execbuf(drm_fd, &execbuf); + * + * ... + * execbuf.rsvd1 = ctx_id; + * execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context + * gem_execbuf(drm_fd, &execbuf); + */ + +struct i915_context_param_engines { + __u64 extensions; /* linked chain of extension blocks, 0 terminates */ +#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]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ + __u64 extensions; \ + 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; }; @@ -1570,7 +2497,9 @@ struct drm_i915_gem_context_destroy { __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 @@ -1580,20 +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; }; @@ -1635,14 +2567,69 @@ struct drm_i915_reset_stats { __u32 pad; }; +/** + * struct drm_i915_gem_userptr - Create GEM object from user allocated memory. + * + * Userptr objects have several restrictions on what ioctls can be used with the + * object handle. + */ struct drm_i915_gem_userptr { + /** + * @user_ptr: The pointer to the allocated memory. + * + * Needs to be aligned to PAGE_SIZE. + */ __u64 user_ptr; + + /** + * @user_size: + * + * The size in bytes for the allocated memory. This will also become the + * object size. + * + * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE, + * or larger. + */ __u64 user_size; + + /** + * @flags: + * + * Supported flags: + * + * I915_USERPTR_READ_ONLY: + * + * Mark the object as readonly, this also means GPU access can only be + * readonly. This is only supported on HW which supports readonly access + * through the GTT. If the HW can't support readonly access, an error is + * returned. + * + * I915_USERPTR_PROBE: + * + * Probe the provided @user_ptr range and validate that the @user_ptr is + * indeed pointing to normal memory and that the range is also valid. + * For example if some garbage address is given to the kernel, then this + * should complain. + * + * Returns -EFAULT if the probe failed. + * + * Note that this doesn't populate the backing pages, and also doesn't + * guarantee that the object will remain valid when the object is + * eventually used. + * + * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE + * returns a non-zero value. + * + * I915_USERPTR_UNSYNCHRONIZED: + * + * NOT USED. Setting this flag will result in an error. + */ __u32 flags; #define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_PROBE 0x2 #define I915_USERPTR_UNSYNCHRONIZED 0x80000000 /** - * Returned handle for the object. + * @handle: Returned handle for the object. * * Object handles are nonzero. */ @@ -1671,23 +2658,31 @@ enum drm_i915_perf_property_id { * Open the stream for a specific context handle (as used with * execbuffer2). A stream opened for a specific context this way * won't typically require root privileges. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_CTX_HANDLE = 1, /** * A value of 1 requests the inclusion of raw OA unit reports as * part of stream samples. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_SAMPLE_OA, /** * The value specifies which set of OA unit metrics should be - * be configured, defining the contents of any OA unit reports. + * configured, defining the contents of any OA unit reports. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_METRICS_SET, /** * The value specifies the size and layout of OA unit reports. + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_FORMAT, @@ -1697,9 +2692,46 @@ enum drm_i915_perf_property_id { * from this exponent as follows: * * 80ns * 2^(period_exponent + 1) + * + * This property is available in perf revision 1. */ DRM_I915_PERF_PROP_OA_EXPONENT, + /** + * Specifying this property is only valid when specify a context to + * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property + * will hold preemption of the particular context we want to gather + * performance data about. The execbuf2 submissions must include a + * drm_i915_gem_execbuffer_ext_perf parameter for this to apply. + * + * This property is available in perf revision 3. + */ + DRM_I915_PERF_PROP_HOLD_PREEMPTION, + + /** + * Specifying this pins all contexts to the specified SSEU power + * configuration for the duration of the recording. + * + * This parameter's value is a pointer to a struct + * drm_i915_gem_context_param_sseu. + * + * This property is available in perf revision 4. + */ + DRM_I915_PERF_PROP_GLOBAL_SSEU, + + /** + * This optional parameter specifies the timer interval in nanoseconds + * at which the i915 driver will check the OA buffer for available data. + * Minimum allowed value is 100 microseconds. A default value is used by + * the driver if this parameter is not specified. Note that larger timer + * values will reduce cpu consumption during OA perf captures. However, + * excessively large values would potentially result in OA buffer + * overwrites as captures reach end of the OA buffer. + * + * This property is available in perf revision 5. + */ + DRM_I915_PERF_PROP_POLL_OA_PERIOD, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; @@ -1719,7 +2751,7 @@ struct drm_i915_perf_open_param { __u64 properties_ptr; }; -/** +/* * Enable data capture for a stream that was either opened in a disabled state * via I915_PERF_FLAG_DISABLED or was later disabled via * I915_PERF_IOCTL_DISABLE. @@ -1728,17 +2760,34 @@ struct drm_i915_perf_open_param { * to close and re-open a stream with the same configuration. * * It's undefined whether any pending data for the stream will be lost. + * + * This ioctl is available in perf revision 1. */ #define I915_PERF_IOCTL_ENABLE _IO('i', 0x0) -/** +/* * Disable data capture for a stream. * * It is an error to try and read a stream that is disabled. + * + * This ioctl is available in perf revision 1. */ #define I915_PERF_IOCTL_DISABLE _IO('i', 0x1) -/** +/* + * Change metrics_set captured by a stream. + * + * If the stream is bound to a specific context, the configuration change + * will performed __inline__ with that context such that it takes effect before + * the next execbuf submission. + * + * Returns the previously bound metrics set id, or a negative error code. + * + * This ioctl is available in perf revision 2. + */ +#define I915_PERF_IOCTL_CONFIG _IO('i', 0x2) + +/* * Common to all i915 perf records */ struct drm_i915_perf_record_header { @@ -1787,127 +2836,887 @@ enum drm_i915_perf_record_type { }; /** + * 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; }; +/** + * struct drm_i915_query_item - An individual query for the kernel to process. + * + * The behaviour is determined by the @query_id. Note that exactly what + * @data_ptr is also depends on the specific @query_id. + */ struct drm_i915_query_item { + /** + * @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_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 */ - /* + /** + * @length: + * * When set to zero by userspace, this is filled with the size of the - * data to be written at the data_ptr pointer. The kernel sets this + * data to be written at the @data_ptr pointer. The kernel sets this * value to a negative value to signal an error on a particular query * item. */ __s32 length; - /* - * Unused for now. Must be cleared to zero. + /** + * @flags: + * + * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * + * 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 + * + * 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 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2 +#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID 3 - /* - * Data will be written at the location pointed by data_ptr when the - * value of length matches the length of the data to be written by the + /** + * @data_ptr: + * + * Data will be written at the location pointed by @data_ptr when the + * value of @length matches the length of the data to be written by the * kernel. */ __u64 data_ptr; }; +/** + * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the + * kernel to fill out. + * + * Note that this is generally a two step process for each struct + * drm_i915_query_item in the array: + * + * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct + * drm_i915_query_item, with &drm_i915_query_item.length set to zero. The + * kernel will then fill in the size, in bytes, which tells userspace how + * memory it needs to allocate for the blob(say for an array of properties). + * + * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the + * &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that + * the &drm_i915_query_item.length should still be the same as what the + * kernel previously set. At this point the kernel can fill in the blob. + * + * Note that for some query items it can make sense for userspace to just pass + * in a buffer/blob equal to or larger than the required size. In this case only + * a single ioctl call is needed. For some smaller query items this can work + * quite well. + * + */ struct drm_i915_query { + /** @num_items: The number of elements in the @items_ptr array */ __u32 num_items; - /* - * Unused for now. Must be cleared to zero. + /** + * @flags: Unused for now. Must be cleared to zero. */ __u32 flags; - /* - * This points to an array of num_items drm_i915_query_item structures. + /** + * @items_ptr: + * + * Pointer to an array of struct drm_i915_query_item. The number of + * array elements is @num_items. */ __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. 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[]; +}; + +/** + * DOC: Engine Discovery uAPI + * + * Engine discovery uAPI is a way of enumerating physical engines present in a + * GPU associated with an open i915 DRM file descriptor. This supersedes the old + * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like + * `I915_PARAM_HAS_BLT`. + * + * The need for this interface came starting with Icelake and newer GPUs, which + * started to establish a pattern of having multiple engines of a same class, + * where not all instances were always completely functionally equivalent. + * + * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the + * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id. + * + * Example for getting the list of engines: + * + * .. code-block:: C + * + * struct drm_i915_query_engine_info *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_ENGINE_INFO; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of engines. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * // + * // Alternatively a large buffer can be allocated straight away enabling + * // querying in one pass, in which case item.length should contain the + * // length of the provided buffer. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with info on all engines. + * item.data_ptr = (uintptr_t)&info, + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each engine in the array + * for (i = 0; i < info->num_engines; i++) { + * struct drm_i915_engine_info einfo = info->engines[i]; + * u16 class = einfo.engine.class; + * u16 instance = einfo.engine.instance; + * .... + * } + * + * free(info); + * + * Each of the enumerated engines, apart from being defined by its class and + * instance (see `struct i915_engine_class_instance`), also can have flags and + * capabilities defined as documented in i915_drm.h. + * + * For instance video engines which support HEVC encoding will have the + * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set. + * + * Engine discovery only fully comes to its own when combined with the new way + * of addressing engines when submitting batch buffers using contexts with + * engine maps configured. + */ + +/** + * struct drm_i915_engine_info + * + * Describes one engine and it's capabilities as known to the driver. + */ +struct drm_i915_engine_info { + /** @engine: Engine class and instance. */ + struct i915_engine_class_instance engine; + + /** @rsvd0: Reserved field. */ + __u32 rsvd0; + + /** @flags: Engine flags. */ + __u64 flags; +#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0) + + /** @capabilities: Capabilities of this engine. */ + __u64 capabilities; +#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) +#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + + /** @logical_instance: Logical instance of engine */ + __u16 logical_instance; + + /** @rsvd1: Reserved fields. */ + __u16 rsvd1[3]; + /** @rsvd2: Reserved fields. */ + __u64 rsvd2[3]; +}; + +/** + * struct drm_i915_query_engine_info + * + * Engine info query enumerates all engines known to the driver by filling in + * an array of struct drm_i915_engine_info structures. + */ +struct drm_i915_query_engine_info { + /** @num_engines: Number of struct drm_i915_engine_info structs following. */ + __u32 num_engines; + + /** @rsvd: MBZ */ + __u32 rsvd[3]; + + /** @engines: Marker for drm_i915_engine_info structures. */ + struct drm_i915_engine_info engines[]; +}; + +/** + * 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 { + /** + * @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; + + /** + * @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; + + /** + * @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; + + /** + * @data: + * + * 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 : + * + * - &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[]; }; +/** + * enum drm_i915_gem_memory_class - Supported memory classes + */ +enum drm_i915_gem_memory_class { + /** @I915_MEMORY_CLASS_SYSTEM: System memory */ + I915_MEMORY_CLASS_SYSTEM = 0, + /** @I915_MEMORY_CLASS_DEVICE: Device local-memory */ + I915_MEMORY_CLASS_DEVICE, +}; + +/** + * struct drm_i915_gem_memory_class_instance - Identify particular memory region + */ +struct drm_i915_gem_memory_class_instance { + /** @memory_class: See enum drm_i915_gem_memory_class */ + __u16 memory_class; + + /** @memory_instance: Which instance */ + __u16 memory_instance; +}; + +/** + * struct drm_i915_memory_region_info - Describes one region as known to the + * driver. + * + * 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. + */ +struct drm_i915_memory_region_info { + /** @region: The class:instance pair encoding */ + struct drm_i915_gem_memory_class_instance region; + + /** @rsvd0: MBZ */ + __u32 rsvd0; + + /** + * @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 + * + * 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; + + 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; + }; + }; +}; + +/** + * struct drm_i915_query_memory_regions + * + * The region info query enumerates all regions known to the driver by filling + * in an array of struct drm_i915_memory_region_info structures. + * + * Example for getting the list of supported regions: + * + * .. code-block:: C + * + * struct drm_i915_query_memory_regions *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_MEMORY_REGIONS; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of regions. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with the all the region info. + * item.data_ptr = (uintptr_t)&info, + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each region in the array + * for (i = 0; i < info->num_regions; i++) { + * struct drm_i915_memory_region_info mr = info->regions[i]; + * u16 class = mr.region.class; + * u16 instance = mr.region.instance; + * + * .... + * } + * + * free(info); + */ +struct drm_i915_query_memory_regions { + /** @num_regions: Number of supported regions */ + __u32 num_regions; + + /** @rsvd: MBZ */ + __u32 rsvd[3]; + + /** @regions: Info about each supported region */ + struct drm_i915_memory_region_info 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. + * + * 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 { + /** + * @size: Requested size for the object. + * + * 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 + * 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. 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: + * + * 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; + + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + + /** + * @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. + * + * This will be useful in the future when we need to support several + * different extensions, and we need to apply more than one when + * creating the object. See struct i915_user_extension. + * + * If we don't supply any extensions then we get the same old gem_create + * behaviour. + * + * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see + * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. + */ +#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 + __u64 extensions; +}; + +/** + * struct drm_i915_gem_create_ext_memory_regions - The + * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension. + * + * Set the object with the desired set of placements/regions in priority + * order. Each entry must be unique and supported by the device. + * + * This is provided as an array of struct drm_i915_gem_memory_class_instance, or + * an equivalent layout of class:instance pair encodings. See struct + * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to + * query the supported regions for a device. + * + * As an example, on discrete devices, if we wish to set the placement as + * device local-memory we can do something like: + * + * .. code-block:: C + * + * struct drm_i915_gem_memory_class_instance region_lmem = { + * .memory_class = I915_MEMORY_CLASS_DEVICE, + * .memory_instance = 0, + * }; + * struct drm_i915_gem_create_ext_memory_regions regions = { + * .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS }, + * .regions = (uintptr_t)®ion_lmem, + * .num_regions = 1, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = 16 * PAGE_SIZE, + * .extensions = (uintptr_t)®ions, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + * + * 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. */ + struct i915_user_extension base; + + /** @pad: MBZ */ + __u32 pad; + /** @num_regions: Number of elements in the @regions array. */ + __u32 num_regions; + /** + * @regions: The regions/placements array. + * + * An array of struct drm_i915_gem_memory_class_instance. + */ + __u64 regions; +}; + +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + #if defined(__cplusplus) } #endif