From patchwork Wed May 22 08:29:18 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10955315 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 1EC786C5 for ; Wed, 22 May 2019 08:29:36 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 11CAE28AB0 for ; Wed, 22 May 2019 08:29:36 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 034CC28B51; Wed, 22 May 2019 08:29:35 +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 5CD6628AB0 for ; Wed, 22 May 2019 08:29:35 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 8083D89801; Wed, 22 May 2019 08:29:34 +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 5E39089801; Wed, 22 May 2019 08:29:33 +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 16636903-1500050 for multiple; Wed, 22 May 2019 09:29:19 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Wed, 22 May 2019 09:29:18 +0100 Message-Id: <20190522082918.8343-1-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.20.1 MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH i-g-t] drm-uapi: Import i915_drm.h upto a88b6e4cbafd 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: , Cc: igt-dev@lists.freedesktop.org Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP commit a88b6e4cbafd6f23b3450c087acdbe23d90e7606 Author: Chris Wilson Date: Tue May 21 22:11:34 2019 +0100 drm/i915: Allow specification of parallel execbuf Signed-off-by: Chris Wilson --- include/drm-uapi/i915_drm.h | 164 +++++++++++++++++++++++++++++++++++- 1 file changed, 162 insertions(+), 2 deletions(-) diff --git a/include/drm-uapi/i915_drm.h b/include/drm-uapi/i915_drm.h index e01b3e1fd..72be2705e 100644 --- a/include/drm-uapi/i915_drm.h +++ b/include/drm-uapi/i915_drm.h @@ -136,6 +136,8 @@ enum drm_i915_gem_engine_class { 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 }; /** @@ -355,6 +357,8 @@ 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) @@ -415,6 +419,8 @@ 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. @@ -598,6 +604,12 @@ 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 { @@ -1120,7 +1132,16 @@ 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) \ @@ -1464,8 +1485,9 @@ 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_USE_EXTENSIONS << 1)) + (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) __u64 extensions; }; @@ -1507,6 +1529,41 @@ 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; @@ -1570,12 +1627,115 @@ 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 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;