From patchwork Wed Jan 30 02:19:06 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10787575 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 E0CD41874 for ; Wed, 30 Jan 2019 02:19:44 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id D2BF92DDE5 for ; Wed, 30 Jan 2019 02:19:44 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id C4A4A2CF2F; Wed, 30 Jan 2019 02:19:44 +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 5F3A12CF2F for ; Wed, 30 Jan 2019 02:19:44 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id AEE986E433; Wed, 30 Jan 2019 02:19:43 +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 BBFED6E43D for ; Wed, 30 Jan 2019 02:19:36 +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 15397396-1500050 for multiple; Wed, 30 Jan 2019 02:19:22 +0000 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Wed, 30 Jan 2019 02:19:06 +0000 Message-Id: <20190130021906.17933-11-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190130021906.17933-1-chris@chris-wilson.co.uk> References: <20190130021906.17933-1-chris@chris-wilson.co.uk> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH 11/11] drm/i915: Prioritise non-busywait semaphore workloads 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 We don't want to busywait on the GPU if we have other work to do. If we give non-busywaiting workloads higher (initial) priority than workloads that require a busywait, we will prioritise work that is ready to run immediately. Testcase: igt/gem_exec_schedule/semaphore Signed-off-by: Chris Wilson --- drivers/gpu/drm/i915/i915_request.c | 8 +++++++- drivers/gpu/drm/i915/i915_scheduler.c | 2 +- drivers/gpu/drm/i915/i915_scheduler.h | 11 +++++++---- drivers/gpu/drm/i915/intel_lrc.c | 5 +++-- 4 files changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 6d825cd28ae6..30cd8724d39f 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -844,7 +844,7 @@ emit_semaphore_wait(struct i915_request *to, intel_ring_advance(to, cs); } - to->sched.semaphore = true; + to->sched.semaphore |= I915_SCHED_HAS_SEMAPHORE; return 0; } @@ -867,6 +867,9 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) return ret; } + if (from->sched.semaphore && !i915_request_started(from)) + to->sched.semaphore |= I915_SCHED_CHAIN_SEMAPHORE; + if (to->engine == from->engine) { ret = i915_sw_fence_await_sw_fence_gfp(&to->submit, &from->submit, @@ -1117,6 +1120,9 @@ void i915_request_add(struct i915_request *request) if (engine->schedule) { struct i915_sched_attr attr = request->gem_context->sched; + if (!request->sched.semaphore) + attr.priority |= I915_PRIORITY_NOSEMAPHORE; + /* * Boost priorities to new clients (new request flows). * diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index aa6c663dca09..4394763d10d8 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -29,7 +29,7 @@ void i915_sched_node_init(struct i915_sched_node *node) INIT_LIST_HEAD(&node->waiters_list); INIT_LIST_HEAD(&node->link); node->attr.priority = I915_PRIORITY_INVALID; - node->semaphore = false; + node->semaphore = 0; } static struct i915_dependency * diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h index d764cf10536f..d84f09e8c248 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.h +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -24,14 +24,15 @@ enum { I915_PRIORITY_INVALID = INT_MIN }; -#define I915_USER_PRIORITY_SHIFT 2 +#define I915_USER_PRIORITY_SHIFT 3 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT) #define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT) #define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1) -#define I915_PRIORITY_WAIT ((u8)BIT(0)) -#define I915_PRIORITY_NEWCLIENT ((u8)BIT(1)) +#define I915_PRIORITY_WAIT ((u8)BIT(0)) +#define I915_PRIORITY_NEWCLIENT ((u8)BIT(1)) +#define I915_PRIORITY_NOSEMAPHORE ((u8)BIT(2)) struct i915_sched_attr { /** @@ -72,7 +73,9 @@ struct i915_sched_node { struct list_head waiters_list; /* those after us, they depend upon us */ struct list_head link; struct i915_sched_attr attr; - bool semaphore; + unsigned long semaphore; +#define I915_SCHED_HAS_SEMAPHORE BIT(0) +#define I915_SCHED_CHAIN_SEMAPHORE BIT(1) }; struct i915_dependency { diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 80d17b75b2e6..5bb3964bb202 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -164,7 +164,7 @@ #define WA_TAIL_DWORDS 2 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS) -#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT) +#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT | I915_PRIORITY_NOSEMAPHORE) static int execlists_context_deferred_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine, @@ -614,7 +614,8 @@ static bool can_merge_rq(const struct i915_request *prev, * rules should mean that if this semaphore is preempted, its * dependency chain is preserved and suitably promoted via PI. */ - if (prev->sched.semaphore && !i915_request_started(prev)) + if (prev->sched.semaphore & I915_SCHED_HAS_SEMAPHORE && + !i915_request_started(prev)) return false; if (!can_merge_ctx(prev->hw_context, next->hw_context))