From patchwork Fri Mar 8 18:11:22 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10845293 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 8BBF714E1 for ; Fri, 8 Mar 2019 18:18:34 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 782302F6EE for ; Fri, 8 Mar 2019 18:18:34 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 6CAEA2FA2D; Fri, 8 Mar 2019 18:18:34 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.2 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 6CA262F6EE for ; Fri, 8 Mar 2019 18:18:33 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id D9EA26E41B; Fri, 8 Mar 2019 18:18:31 +0000 (UTC) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from fireflyinternet.com (mail.fireflyinternet.com [109.228.58.192]) by gabe.freedesktop.org (Postfix) with ESMTPS id 5F0BD6E41B for ; Fri, 8 Mar 2019 18:18:25 +0000 (UTC) X-Default-Received-SPF: pass (skip=forwardok (res=PASS)) x-ip-name=78.156.65.138; Received: from haswell.alporthouse.com (unverified [78.156.65.138]) by fireflyinternet.com (Firefly Internet (M1)) with ESMTP id 15827704-1500050 for multiple; Fri, 08 Mar 2019 18:11:33 +0000 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Fri, 8 Mar 2019 18:11:22 +0000 Message-Id: <20190308181129.15562-12-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190308181129.15562-1-chris@chris-wilson.co.uk> References: <20190308181129.15562-1-chris@chris-wilson.co.uk> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH i-g-t 12/19] drm-uapi: Import i915_drm.h upto 364df3d04d51 X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP commit 364df3d04d51f0aad13b898f3dffca8c2d03d2b3 (HEAD) Author: Chris Wilson Date: Fri Jun 30 13:40:53 2017 +0100 drm/i915: Allow specification of parallel execbuf Signed-off-by: Chris Wilson --- include/drm-uapi/i915_drm.h | 352 ++++++++++++++++++++++++++++-------- 1 file changed, 279 insertions(+), 73 deletions(-) diff --git a/include/drm-uapi/i915_drm.h b/include/drm-uapi/i915_drm.h index 43fb8ede2..e606680a5 100644 --- a/include/drm-uapi/i915_drm.h +++ b/include/drm-uapi/i915_drm.h @@ -62,6 +62,26 @@ 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 boundary with pointers encapsulated inside u64. + */ +struct i915_user_extension { + __u64 next_extension; + __u64 name; +}; + /* * 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 +119,14 @@ 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 }; +#define I915_ENGINE_CLASS_INVALID_NONE -1 +#define I915_ENGINE_CLASS_INVALID_VIRTUAL 0 + /** * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915 * @@ -319,6 +344,9 @@ 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) @@ -367,6 +395,7 @@ 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 +406,8 @@ 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. @@ -476,6 +507,7 @@ 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_PARAM_HUC_STATUS 42 @@ -559,6 +591,14 @@ 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 +/* Must be kept compact -- no holes and well documented */ + typedef struct drm_i915_getparam { __s32 param; /* @@ -574,6 +614,7 @@ 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; @@ -972,7 +1013,7 @@ 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) @@ -1078,7 +1119,16 @@ 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) \ @@ -1120,32 +1170,34 @@ 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 @@ -1412,65 +1464,18 @@ struct drm_i915_gem_wait { }; struct drm_i915_gem_context_create { - /* output: id of new context*/ - __u32 ctx_id; - __u32 pad; -}; - -struct drm_i915_gem_context_destroy { - __u32 ctx_id; - __u32 pad; -}; - -struct drm_i915_reg_read { - /* - * Register offset. - * For 64bit wide registers where the upper 32bits don't immediately - * follow the lower 32bits, the offset of the lower 32bits must - * be specified - */ - __u64 offset; -#define I915_REG_READ_8B_WA (1ul << 0) - - __u64 val; /* Return value */ -}; -/* Known registers: - * - * Render engine timestamp - 0x2358 + 64bit - gen7+ - * - Note this register returns an invalid value if using the default - * single instruction 8byte read, in order to workaround that pass - * flag I915_REG_READ_8B_WA in offset field. - * - */ - -struct drm_i915_reset_stats { - __u32 ctx_id; - __u32 flags; - - /* All resets since boot/module reload, for all contexts */ - __u32 reset_count; - - /* Number of batches lost when active in GPU, for this context */ - __u32 batch_active; - - /* Number of batches lost pending for execution, for this context */ - __u32 batch_pending; - + __u32 ctx_id; /* output: id of new context*/ __u32 pad; }; -struct drm_i915_gem_userptr { - __u64 user_ptr; - __u64 user_size; +struct drm_i915_gem_context_create_ext { + __u32 ctx_id; /* output: id of new context*/ __u32 flags; -#define I915_USERPTR_READ_ONLY 0x1 -#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 - /** - * Returned handle for the object. - * - * Object handles are nonzero. - */ - __u32 handle; +#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 { @@ -1511,6 +1516,43 @@ struct drm_i915_gem_context_param { * 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 +/* Must be kept compact -- no holes and well documented */ + __u64 value; }; @@ -1543,9 +1585,10 @@ struct drm_i915_gem_context_param_sseu { __u16 engine_instance; /* - * 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 @@ -1573,6 +1616,168 @@ struct drm_i915_gem_context_param_sseu { __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 mbz16; /* reserved for future use; must be zero */ + __u32 flags; /* all undefined flags must be zero */ + + __u64 engines_mask; /* selection mask of engines[] */ + + __u64 mbz64[4]; /* reserved for future use; must be zero */ +}; + +/* + * i915_context_engines_bond: + * + */ +struct i915_context_engines_bond { + struct i915_user_extension base; + + __u16 engine_index; + __u16 mbz; + + __u16 master_class; + __u16 master_instance; + + __u64 sibling_mask; + __u64 flags; /* all undefined flags must be zero */ +}; + +struct i915_context_param_engines { + __u64 extensions; /* linked chain of extension blocks, 0 terminates */ +#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 +#define I915_CONTEXT_ENGINES_EXT_BOND 1 + + struct { + __u16 engine_class; /* see enum drm_i915_gem_engine_class */ + __u16 engine_instance; + } class_instance[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ + __u64 extensions; \ + struct { \ + __u16 engine_class; \ + __u16 engine_instance; \ + } class_instance[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 setparam; +}; + +struct drm_i915_gem_context_create_ext_clone { +#define I915_CONTEXT_CREATE_EXT_CLONE 1 + struct i915_user_extension base; + __u32 clone; + __u32 flags; +#define I915_CONTEXT_CLONE_FLAGS (1u << 0) +#define I915_CONTEXT_CLONE_SCHED (1u << 1) +#define I915_CONTEXT_CLONE_SSEU (1u << 2) +#define I915_CONTEXT_CLONE_TIMELINE (1u << 3) +#define I915_CONTEXT_CLONE_VM (1u << 4) +#define I915_CONTEXT_CLONE_ENGINES (1u << 5) +#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_ENGINES << 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. + * + * DRM_I915_GEM_VM_DESTROY - + * + * Destroys a previously created VM id. + */ +struct drm_i915_gem_vm_control { + __u64 extensions; + __u32 flags; + __u32 id; +}; + +struct drm_i915_reg_read { + /* + * Register offset. + * For 64bit wide registers where the upper 32bits don't immediately + * follow the lower 32bits, the offset of the lower 32bits must + * be specified + */ + __u64 offset; +#define I915_REG_READ_8B_WA (1ul << 0) + + __u64 val; /* Return value */ +}; + +/* Known registers: + * + * Render engine timestamp - 0x2358 + 64bit - gen7+ + * - Note this register returns an invalid value if using the default + * single instruction 8byte read, in order to workaround that pass + * flag I915_REG_READ_8B_WA in offset field. + * + */ + +struct drm_i915_reset_stats { + __u32 ctx_id; + __u32 flags; + + /* All resets since boot/module reload, for all contexts */ + __u32 reset_count; + + /* Number of batches lost when active in GPU, for this context */ + __u32 batch_active; + + /* Number of batches lost pending for execution, for this context */ + __u32 batch_pending; + + __u32 pad; +}; + +struct drm_i915_gem_userptr { + __u64 user_ptr; + __u64 user_size; + __u32 flags; +#define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; +}; + enum drm_i915_oa_format { I915_OA_FORMAT_A13 = 1, /* HSW only */ I915_OA_FORMAT_A29, /* HSW only */ @@ -1734,6 +1939,7 @@ struct drm_i915_perf_oa_config { struct drm_i915_query_item { __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 +/* Must be kept compact -- no holes and well documented */ /* * When set to zero by userspace, this is filled with the size of the