From patchwork Fri Jun 15 19:10:54 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10467425 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 4EB8C60348 for ; Fri, 15 Jun 2018 19:11:38 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 3E0A628E41 for ; Fri, 15 Jun 2018 19:11:38 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 2FC7328E46; Fri, 15 Jun 2018 19:11:38 +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 D865028E41 for ; Fri, 15 Jun 2018 19:11:37 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 36A0B6EC37; Fri, 15 Jun 2018 19:11:37 +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 51A096EC31 for ; Fri, 15 Jun 2018 19:11:31 +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 12062440-1500050 for multiple; Fri, 15 Jun 2018 20:11:26 +0100 Received: by haswell.alporthouse.com (sSMTP sendmail emulation); Fri, 15 Jun 2018 20:11:27 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Fri, 15 Jun 2018 20:10:54 +0100 Message-Id: <20180615191105.17009-10-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20180615191105.17009-1-chris@chris-wilson.co.uk> References: <20180615191105.17009-1-chris@chris-wilson.co.uk> X-Originating-IP: 78.156.65.138 X-Country: code=GB country="United Kingdom" ip=78.156.65.138 Subject: [Intel-gfx] [PATCH 10/21] drm/i915: Reduce spinlock hold time during notify_ring() interrupt 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: , MIME-Version: 1.0 Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP By taking advantage of the RCU protection of the task struct, we can find the appropriate signaler under the spinlock and then release the spinlock before waking the task and signaling the fence. Signed-off-by: Chris Wilson --- drivers/gpu/drm/i915/i915_irq.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 2570262a268b..91f9357e6cf4 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1138,21 +1138,23 @@ static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv) static void notify_ring(struct intel_engine_cs *engine) { + const u32 seqno = intel_engine_get_seqno(engine); struct i915_request *rq = NULL; + struct task_struct *tsk = NULL; struct intel_wait *wait; - if (!engine->breadcrumbs.irq_armed) + if (unlikely(!engine->breadcrumbs.irq_armed)) return; atomic_inc(&engine->irq_count); - set_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); + + rcu_read_lock(); spin_lock(&engine->breadcrumbs.irq_lock); wait = engine->breadcrumbs.irq_wait; if (wait) { - bool wakeup = engine->irq_seqno_barrier; - - /* We use a callback from the dma-fence to submit + /* + * We use a callback from the dma-fence to submit * requests after waiting on our own requests. To * ensure minimum delay in queuing the next request to * hardware, signal the fence now rather than wait for @@ -1163,19 +1165,23 @@ static void notify_ring(struct intel_engine_cs *engine) * and to handle coalescing of multiple seqno updates * and many waiters. */ - if (i915_seqno_passed(intel_engine_get_seqno(engine), - wait->seqno)) { + if (i915_seqno_passed(seqno, wait->seqno)) { struct i915_request *waiter = wait->request; - wakeup = true; if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &waiter->fence.flags) && intel_wait_check_request(wait, waiter)) rq = i915_request_get(waiter); - } - if (wakeup) - wake_up_process(wait->tsk); + tsk = wait->tsk; + } else { + if (engine->irq_seqno_barrier && + i915_seqno_passed(seqno, wait->seqno - 1)) { + set_bit(ENGINE_IRQ_BREADCRUMB, + &engine->irq_posted); + tsk = wait->tsk; + } + } } else { if (engine->breadcrumbs.irq_armed) __intel_engine_disarm_breadcrumbs(engine); @@ -1188,6 +1194,11 @@ static void notify_ring(struct intel_engine_cs *engine) i915_request_put(rq); } + if (tsk && tsk->state & TASK_NORMAL) + wake_up_process(tsk); + + rcu_read_unlock(); + trace_intel_engine_notify(engine, wait); }