diff --git a/external/i915_drm.h b/external/i915_drm.h index 268b585..2e210cc 100644 --- a/external/i915_drm.h +++ b/external/i915_drm.h @@ -24,8 +24,8 @@ * */ -#ifndef _I915_DRM_H_ -#define _I915_DRM_H_ +#ifndef _UAPI_I915_DRM_H_ +#define _UAPI_I915_DRM_H_ #include "drm.h" @@ -62,6 +62,28 @@ extern "C" { #define I915_ERROR_UEVENT "ERROR" #define I915_RESET_UEVENT "RESET" +/* + * 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, + * as demonstrated by Vulkan's approach to providing extensions for forward + * and backward compatibility, is to use a list of optional structs to + * provide those extra details. + * + * The key advantage to using an extension chain is that it allows us to + * redefine the interface more easily than an ever growing struct of + * increasing complexity, and for large parts of that interface to be + * entirely optional. The downside is more pointer chasing; chasing across + * the __user boundary with pointers encapsulated inside u64. + */ +struct i915_user_extension { + __u64 next_extension; + __u32 name; + __u32 flags; /* All undefined bits must be zero. */ + __u32 rsvd[4]; /* Reserved for future use; must be zero. */ +}; + /* * MOCS indexes used for GPU surfaces, defining the cacheability of the * surface data and the coherency for this data wrt. CPU vs. GPU accesses. @@ -99,9 +121,25 @@ enum drm_i915_gem_engine_class { I915_ENGINE_CLASS_VIDEO = 2, I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + /* should be kept compact */ + I915_ENGINE_CLASS_INVALID = -1 }; +/* + * 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 { + __u16 engine_class; /* see enum drm_i915_gem_engine_class */ + __u16 engine_instance; +#define I915_ENGINE_CLASS_INVALID_NONE -1 +#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 +}; + /** * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 * @@ -319,6 +357,9 @@ 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 +/* Must be kept compact -- no holes */ #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -350,10 +391,12 @@ 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, 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) @@ -367,6 +410,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey) #define DRM_IOCTL_I915_GEM_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait) #define DRM_IOCTL_I915_GEM_CONTEXT_CREATE DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create) +#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext) #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy) #define DRM_IOCTL_I915_REG_READ DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read) #define DRM_IOCTL_I915_GET_RESET_STATS DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats) @@ -377,6 +421,8 @@ 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. @@ -412,6 +458,14 @@ typedef struct drm_i915_irq_wait { int irq_seq; } drm_i915_irq_wait_t; +/* + * Different modes of per-process Graphics Translation Table, + * see I915_PARAM_HAS_ALIASING_PPGTT + */ +#define I915_GEM_PPGTT_NONE 0 +#define I915_GEM_PPGTT_ALIASING 1 +#define I915_GEM_PPGTT_FULL 2 + /* Ioctl to query kernel params: */ #define I915_PARAM_IRQ_ACTIVE 1 @@ -468,6 +522,8 @@ typedef struct drm_i915_irq_wait { #define I915_SCHEDULER_CAP_ENABLED (1ul << 0) #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) #define I915_PARAM_HUC_STATUS 42 @@ -551,6 +607,21 @@ 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 + +/* Must be kept compact -- no holes and well documented */ + typedef struct drm_i915_getparam { __s32 param; /* @@ -566,6 +637,7 @@ typedef struct drm_i915_getparam { #define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY 2 #define I915_SETPARAM_ALLOW_BATCHBUFFER 3 #define I915_SETPARAM_NUM_USED_FENCES 4 +/* Must be kept compact -- no holes */ typedef struct drm_i915_setparam { int param; @@ -651,6 +723,27 @@ struct drm_i915_gem_create { __u32 pad; }; +struct drm_i915_gem_create_ext { + + /** + * Requested size for the object. + * + * The (page-aligned) allocated size for the object will be returned. + */ + __u64 size; + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + __u32 pad; +#define I915_GEM_CREATE_EXT_SETPARAM (1u << 0) +#define I915_GEM_CREATE_EXT_FLAGS_UNKNOWN \ + (-(I915_GEM_CREATE_EXT_SETPARAM << 1)) + __u64 extensions; +}; + struct drm_i915_gem_pread { /** Handle for the object being read. */ __u32 handle; @@ -723,6 +816,37 @@ struct drm_i915_gem_mmap_gtt { __u64 offset; }; +struct drm_i915_gem_mmap_offset { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** + * Fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; + + /** + * Flags for extended behaviour. + * + * It is mandatory that one of the MMAP_OFFSET types + * (GTT, WC, WB, UC, etc) should be included. + */ + __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 + + /* + * Zero-terminated chain of extensions. + * + * No current extensions defined; mbz. + */ + __u64 extensions; +}; + struct drm_i915_gem_set_domain { /** Handle for the object */ __u32 handle; @@ -964,7 +1088,7 @@ struct drm_i915_gem_execbuffer2 { * struct drm_i915_gem_exec_fence *fences. */ __u64 cliprects_ptr; -#define I915_EXEC_RING_MASK (7<<0) +#define I915_EXEC_RING_MASK (0x3f) #define I915_EXEC_DEFAULT (0<<0) #define I915_EXEC_RENDER (1<<0) #define I915_EXEC_BSD (2<<0) @@ -1070,7 +1194,16 @@ 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) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1112,32 +1245,34 @@ struct drm_i915_gem_busy { * as busy may become idle before the ioctl is completed. * * Furthermore, if the object is busy, which engine is busy is only - * provided as a guide. There are race conditions which prevent the - * report of which engines are busy from being always accurate. - * However, the converse is not true. If the object is idle, the - * result of the ioctl, that all engines are idle, is accurate. + * provided as a guide and only indirectly by reporting its class + * (there may be more than one engine in each class). There are race + * conditions which prevent the report of which engines are busy from + * being always accurate. However, the converse is not true. If the + * object is idle, the result of the ioctl, that all engines are idle, + * is accurate. * * The returned dword is split into two fields to indicate both - * the engines on which the object is being read, and the - * engine on which it is currently being written (if any). + * the engine classess on which the object is being read, and the + * engine class on which it is currently being written (if any). * * The low word (bits 0:15) indicate if the object is being written * to by any engine (there can only be one, as the GEM implicit * synchronisation rules force writes to be serialised). Only the - * engine for the last write is reported. + * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as + * 1 not 0 etc) for the last write is reported. * - * The high word (bits 16:31) are a bitmask of which engines are - * currently reading from the object. Multiple engines may be + * The high word (bits 16:31) are a bitmask of which engines classes + * are currently reading from the object. Multiple engines may be * reading from the object simultaneously. * - * The value of each engine is the same as specified in the - * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc. - * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to - * the I915_EXEC_RENDER engine for execution, and so it is never + * The value of each engine class is the same as specified in the + * I915_CONTEXT_SET_ENGINES 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 identifier in the EXECBUFFER2 ioctl and - * so are not separately reported for busyness. + * 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 @@ -1404,16 +1539,381 @@ struct drm_i915_gem_wait { }; struct drm_i915_gem_context_create { - /* output: id of new context*/ - __u32 ctx_id; + __u32 ctx_id; /* output: id of new context*/ __u32 pad; }; +struct drm_i915_gem_context_create_ext { + __u32 ctx_id; /* output: id of new context*/ + __u32 flags; +#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) +#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1) +#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ + (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) + __u64 extensions; +}; + +struct drm_i915_gem_context_param { + __u32 ctx_id; + __u32 size; + __u64 param; +#define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 +#define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2 +#define I915_CONTEXT_PARAM_GTT_SIZE 0x3 +#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 +#define I915_CONTEXT_PARAM_BANNABLE 0x5 +#define I915_CONTEXT_PARAM_PRIORITY 0x6 +#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ +#define I915_CONTEXT_DEFAULT_PRIORITY 0 +#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ + /* + * When using the following param, value should be a pointer to + * drm_i915_gem_context_param_sseu. + */ +#define I915_CONTEXT_PARAM_SSEU 0x7 + +/* + * Not all clients may want to attempt automatic recover of a context after + * a hang (for example, some clients may only submit very small incremental + * batches relying on known logical state of previous batches which will never + * recover correctly and each attempt will hang), and so would prefer that + * the context is forever banned instead. + * + * If set to false (0), after a reset, subsequent (and in flight) rendering + * from this context is discarded, and the client will need to create a new + * context to use instead. + * + * If set to true (1), the kernel will automatically attempt to recover the + * context by skipping the hanging batch and executing the next batch starting + * from the default context state (discarding the incomplete logical context + * state lost due to the reset). + * + * On creation, all new contexts are marked as recoverable. + */ +#define I915_CONTEXT_PARAM_RECOVERABLE 0x8 + + /* + * 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 + +/* + * I915_CONTEXT_PARAM_ENGINES: + * + * 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. + * + * 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) + */ +#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 + + /* + * I915_CONTEXT_PARAM_ACC: + * + * To be able to change the access counter thresholds and configurations. + * + * By default: access counter feature is disabled. + */ +#define I915_CONTEXT_PARAM_ACC 0xd + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * If set to true (1) PXP content protection is enabled. + * When enabled, the context is marked unrecoverable and may + * become invalid due to PXP teardown event or other error. + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xe + +/* Must be kept compact -- no holes and well documented */ + + __u64 value; +}; + +struct drm_i915_gem_object_param { + /* Object handle (0 for I915_GEM_CREATE_EXT_SETPARAM) */ + __u32 handle; + + /* Data pointer size */ + __u32 size; + +/* + * I915_OBJECT_PARAM: + * + * Select object namespace for the param. + */ +#define I915_OBJECT_PARAM (1ull<<32) + +/* + * I915_PARAM_MEMORY_REGIONS: + * + * Set the data pointer with the desired set of placements in priority + * order(each entry must be unique and supported by the device), as an array of + * drm_i915_gem_memory_class_instance, or an equivalent layout of class:instance + * pair encodings. See DRM_I915_QUERY_MEMORY_REGIONS for how to query the + * supported regions. + * + * Note that this requires the I915_OBJECT_PARAM namespace: + * .param = I915_OBJECT_PARAM | I915_PARAM_MEMORY_REGIONS + */ +#define I915_PARAM_MEMORY_REGIONS 0x1 + +/* + * I915_PARAM_PROTECTED_CONTENT: + * + * If set to true (1) buffer contents is expected to be protected by + * PXP encryption and requires decryption for scan out and processing. + * Protected buffers can only be used in PXP protected contexts. + * A protected buffer may become invalid as a result of PXP teardown. + */ +#define I915_PARAM_PROTECTED_CONTENT 0x2 + + __u64 param; + + /* Data value or pointer */ + __u64 data; +}; + +struct drm_i915_gem_create_ext_setparam { + struct i915_user_extension base; + struct drm_i915_gem_object_param param; +}; + +/** + * 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 + * code -ENODEV will be returned. + * + * Also, flexibility of possible SSEU configuration permutations varies between + * GPU generations and software imposed limitations. Requesting such a + * combination will return an error code of -EINVAL. + * + * NOTE: When perf/OA is active the context's SSEU configuration is ignored in + * favour of a single global setting. + */ +struct drm_i915_gem_context_param_sseu { + /* + * Engine class & instance to be configured or queried. + */ + struct i915_engine_class_instance engine; + + /* + * 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 + * of the bitmask value returned for I915_PARAM_SLICE_MASK. + */ + __u64 slice_mask; + + /* + * Mask of subslices to enable for the context. Valid values are a + * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK. + */ + __u64 subslice_mask; + + /* + * Minimum/Maximum number of EUs to enable per subslice for the + * context. min_eus_per_subslice must be inferior or equal to + * max_eus_per_subslice. + */ + __u16 min_eus_per_subslice; + __u16 max_eus_per_subslice; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 rsvd; +}; + +/* + * 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[0]; +} __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[0]; +} __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_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 */ + 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 { +#define I915_CONTEXT_CREATE_EXT_SETPARAM 0 + struct i915_user_extension base; + struct drm_i915_gem_context_param param; +}; + +struct drm_i915_gem_context_create_ext_clone { +#define I915_CONTEXT_CREATE_EXT_CLONE 1 + struct i915_user_extension base; + __u32 clone_id; + __u32 flags; +#define I915_CONTEXT_CLONE_ENGINES (1u << 0) +#define I915_CONTEXT_CLONE_FLAGS (1u << 1) +#define I915_CONTEXT_CLONE_SCHEDATTR (1u << 2) +#define I915_CONTEXT_CLONE_SSEU (1u << 3) +#define I915_CONTEXT_CLONE_TIMELINE (1u << 4) +#define I915_CONTEXT_CLONE_VM (1u << 5) +#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1) + __u64 rsvd; +}; + struct drm_i915_gem_context_destroy { __u32 ctx_id; __u32 pad; }; +/* + * DRM_I915_GEM_VM_CREATE - + * + * Create a new virtual memory address space (ppGTT) for use within a context + * on the same file. Extensions can be provided to configure exactly how the + * address space is setup upon creation. + * + * 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. + * + * No extensions or flags are allowed currently, and so must be zero. + */ +struct drm_i915_gem_vm_control { + __u64 extensions; + __u32 flags; + __u32 vm_id; +}; + struct drm_i915_reg_read { /* * Register offset. @@ -1426,6 +1926,7 @@ struct drm_i915_reg_read { __u64 val; /* Return value */ }; + /* Known registers: * * Render engine timestamp - 0x2358 + 64bit - gen7+ @@ -1465,22 +1966,6 @@ struct drm_i915_gem_userptr { __u32 handle; }; -struct drm_i915_gem_context_param { - __u32 ctx_id; - __u32 size; - __u64 param; -#define I915_CONTEXT_PARAM_BAN_PERIOD 0x1 -#define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2 -#define I915_CONTEXT_PARAM_GTT_SIZE 0x3 -#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 -#define I915_CONTEXT_PARAM_BANNABLE 0x5 -#define I915_CONTEXT_PARAM_PRIORITY 0x6 -#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ -#define I915_CONTEXT_DEFAULT_PRIORITY 0 -#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ - __u64 value; -}; - enum drm_i915_oa_format { I915_OA_FORMAT_A13 = 1, /* HSW only */ I915_OA_FORMAT_A29, /* HSW only */ @@ -1503,23 +1988,31 @@ 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. + * + * 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, @@ -1529,9 +2022,22 @@ 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, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; @@ -1560,6 +2066,8 @@ 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) @@ -1567,9 +2075,24 @@ struct drm_i915_perf_open_param { * 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 */ @@ -1642,6 +2165,10 @@ struct drm_i915_perf_oa_config { struct drm_i915_query_item { __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 +/* Must be kept compact -- no holes and well documented */ /* * When set to zero by userspace, this is filled with the size of the @@ -1652,9 +2179,18 @@ struct drm_i915_query_item { __s32 length; /* - * Unused for now. Must be cleared to zero. + * 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 */ __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 @@ -1690,8 +2226,10 @@ struct drm_i915_query { * (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 : + * 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 + @@ -1739,8 +2277,156 @@ struct drm_i915_query_topology_info { __u8 data[]; }; +/** + * struct drm_i915_engine_info + * + * Describes one engine and it's capabilities as known to the driver. + */ +struct drm_i915_engine_info { + /** Engine class and instance. */ + struct i915_engine_class_instance engine; + + /** Reserved field. */ + __u32 rsvd0; + + /** Engine flags. */ + __u64 flags; + + /** Capabilities of this engine. */ + __u64 capabilities; +#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) +#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + + /** Reserved fields. */ + __u64 rsvd1[4]; +}; + +/** + * 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 { + /** Number of struct drm_i915_engine_info structs following. */ + __u32 num_engines; + + /** MBZ */ + __u32 rsvd[3]; + + /** Marker for drm_i915_engine_info structures. */ + struct drm_i915_engine_info engines[]; +}; + +/* + * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG. + */ +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. + */ + __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. + */ + __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. + * + * String formatted like "%08x-%04x-%04x-%04x-%012x" + */ + char uuid[36]; + }; + + /* + * 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. + * + * 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 + * configuration was created : + * + * - n_mux_regs + * - n_boolean_regs + * - n_flex_regs + */ + __u8 data[]; +}; + +enum drm_i915_gem_memory_class { + I915_MEMORY_CLASS_SYSTEM = 0, + I915_MEMORY_CLASS_DEVICE, + I915_MEMORY_CLASS_STOLEN_SYSTEM, + I915_MEMORY_CLASS_STOLEN_DEVICE, +}; + +struct drm_i915_gem_memory_class_instance { + __u16 memory_class; /* see enum drm_i915_gem_memory_class */ + __u16 memory_instance; +}; + +/** + * struct drm_i915_memory_region_info + * + * Describes one region as known to the driver. + */ +struct drm_i915_memory_region_info { + /** class:instance pair encoding */ + struct drm_i915_gem_memory_class_instance region; + + /** MBZ */ + __u32 rsvd0; + + /** MBZ */ + __u64 caps; + + /** MBZ */ + __u64 flags; + + /** Memory probed by the driver (-1 = unknown) */ + __u64 probed_size; + + /** Estimate of memory remaining (-1 = unknown) */ + __u64 unallocated_size; + + /** MBZ */ + __u64 rsvd1[8]; +}; + +/** + * struct drm_i915_query_memory_regions + * + * Region info query enumerates all regions known to the driver by filling in + * an array of struct drm_i915_memory_region_info structures. + */ +struct drm_i915_query_memory_regions { + /** Number of supported regions */ + __u32 num_regions; + + /** MBZ */ + __u32 rsvd[3]; + + /* Info about each supported region */ + struct drm_i915_memory_region_info regions[]; +}; + #if defined(__cplusplus) } #endif -#endif /* _I915_DRM_H_ */ +#endif /* _UAPI_I915_DRM_H_ */