From patchwork Mon May 20 08:01:22 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10950185 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 6F12476 for ; Mon, 20 May 2019 08:02:32 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 6312F2845E for ; Mon, 20 May 2019 08:02:32 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 57C5128718; Mon, 20 May 2019 08:02:32 +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 563AF2870C for ; Mon, 20 May 2019 08:02:31 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id B9ACB89221; Mon, 20 May 2019 08:02:30 +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 473F38921C for ; Mon, 20 May 2019 08:02:04 +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 16610883-1500050 for multiple; Mon, 20 May 2019 09:01:36 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Mon, 20 May 2019 09:01:22 +0100 Message-Id: <20190520080127.18255-28-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190520080127.18255-1-chris@chris-wilson.co.uk> References: <20190520080127.18255-1-chris@chris-wilson.co.uk> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH 28/33] drm/i915: Stop retiring along engine 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 no longer track the execution order along the engine and so no longer need to enforce ordering of retire along the engine. Signed-off-by: Chris Wilson --- drivers/gpu/drm/i915/i915_request.c | 128 +++++++++++----------------- 1 file changed, 52 insertions(+), 76 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index eac7c6007846..195956a796a1 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -183,72 +183,23 @@ static void free_capture_list(struct i915_request *request) } } -static void __retire_engine_request(struct intel_engine_cs *engine, - struct i915_request *rq) -{ - GEM_TRACE("%s(%s) fence %llx:%lld, current %d\n", - __func__, engine->name, - rq->fence.context, rq->fence.seqno, - hwsp_seqno(rq)); - - GEM_BUG_ON(!i915_request_completed(rq)); - - local_irq_disable(); - - spin_lock(&engine->timeline.lock); - GEM_BUG_ON(!list_is_first(&rq->link, &engine->timeline.requests)); - list_del_init(&rq->link); - spin_unlock(&engine->timeline.lock); - - spin_lock(&rq->lock); - i915_request_mark_complete(rq); - if (!i915_request_signaled(rq)) - dma_fence_signal_locked(&rq->fence); - if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) - i915_request_cancel_breadcrumb(rq); - if (rq->waitboost) { - GEM_BUG_ON(!atomic_read(&rq->i915->gt_pm.rps.num_waiters)); - atomic_dec(&rq->i915->gt_pm.rps.num_waiters); - } - spin_unlock(&rq->lock); - - local_irq_enable(); -} - -static void __retire_engine_upto(struct intel_engine_cs *engine, - struct i915_request *rq) -{ - struct i915_request *tmp; - - if (list_empty(&rq->link)) - return; - - do { - tmp = list_first_entry(&engine->timeline.requests, - typeof(*tmp), link); - - GEM_BUG_ON(tmp->engine != engine); - __retire_engine_request(engine, tmp); - } while (tmp != rq); -} - -static void i915_request_retire(struct i915_request *request) +static bool i915_request_retire(struct i915_request *rq) { struct i915_active_request *active, *next; - GEM_TRACE("%s fence %llx:%lld, current %d\n", - request->engine->name, - request->fence.context, request->fence.seqno, - hwsp_seqno(request)); + lockdep_assert_held(&rq->i915->drm.struct_mutex); + if (!i915_request_completed(rq)) + return false; - lockdep_assert_held(&request->i915->drm.struct_mutex); - GEM_BUG_ON(!i915_sw_fence_signaled(&request->submit)); - GEM_BUG_ON(!i915_request_completed(request)); + GEM_TRACE("%s fence %llx:%lld, current %d\n", + rq->engine->name, + rq->fence.context, rq->fence.seqno, + hwsp_seqno(rq)); - trace_i915_request_retire(request); + GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit)); + trace_i915_request_retire(rq); - advance_ring(request); - free_capture_list(request); + advance_ring(rq); /* * Walk through the active list, calling retire on each. This allows @@ -260,7 +211,7 @@ static void i915_request_retire(struct i915_request *request) * pass along the auxiliary information (to avoid dereferencing * the node after the callback). */ - list_for_each_entry_safe(active, next, &request->active_list, link) { + list_for_each_entry_safe(active, next, &rq->active_list, link) { /* * In microbenchmarks or focusing upon time inside the kernel, * we may spend an inordinate amount of time simply handling @@ -276,18 +227,39 @@ static void i915_request_retire(struct i915_request *request) INIT_LIST_HEAD(&active->link); RCU_INIT_POINTER(active->request, NULL); - active->retire(active, request); + active->retire(active, rq); + } + + local_irq_disable(); + + spin_lock(&rq->engine->timeline.lock); + list_del(&rq->link); + spin_unlock(&rq->engine->timeline.lock); + + spin_lock(&rq->lock); + i915_request_mark_complete(rq); + if (!i915_request_signaled(rq)) + dma_fence_signal_locked(&rq->fence); + if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) + i915_request_cancel_breadcrumb(rq); + if (rq->waitboost) { + GEM_BUG_ON(!atomic_read(&rq->i915->gt_pm.rps.num_waiters)); + atomic_dec(&rq->i915->gt_pm.rps.num_waiters); } + spin_unlock(&rq->lock); + + local_irq_enable(); - i915_request_remove_from_client(request); + intel_context_exit(rq->hw_context); + intel_context_unpin(rq->hw_context); - __retire_engine_upto(request->engine, request); + i915_request_remove_from_client(rq); - intel_context_exit(request->hw_context); - intel_context_unpin(request->hw_context); + free_capture_list(rq); + i915_sched_node_fini(&rq->sched); + i915_request_put(rq); - i915_sched_node_fini(&request->sched); - i915_request_put(request); + return true; } void i915_request_retire_upto(struct i915_request *rq) @@ -309,9 +281,7 @@ void i915_request_retire_upto(struct i915_request *rq) do { tmp = list_first_entry(&ring->request_list, typeof(*tmp), ring_link); - - i915_request_retire(tmp); - } while (tmp != rq); + } while (i915_request_retire(tmp) && tmp != rq); } static void irq_execute_cb(struct irq_work *wrk) @@ -600,12 +570,9 @@ static void ring_retire_requests(struct intel_ring *ring) { struct i915_request *rq, *rn; - list_for_each_entry_safe(rq, rn, &ring->request_list, ring_link) { - if (!i915_request_completed(rq)) + list_for_each_entry_safe(rq, rn, &ring->request_list, ring_link) + if (!i915_request_retire(rq)) break; - - i915_request_retire(rq); - } } static noinline struct i915_request * @@ -620,6 +587,15 @@ request_alloc_slow(struct intel_context *ce, gfp_t gfp) if (!gfpflags_allow_blocking(gfp)) goto out; + /* Move our oldest request to the slab-cache (if not in use!) */ + rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link); + i915_request_retire(rq); + + rq = kmem_cache_alloc(global.slab_requests, + gfp | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); + if (rq) + return rq; + /* Ratelimit ourselves to prevent oom from malicious clients */ rq = list_last_entry(&ring->request_list, typeof(*rq), ring_link); cond_synchronize_rcu(rq->rcustate);