From patchwork Wed Jun 27 11:38:39 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10491227 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 E28B960230 for ; Wed, 27 Jun 2018 11:39:00 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id D2B4A28C61 for ; Wed, 27 Jun 2018 11:39:00 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id C712028CA3; Wed, 27 Jun 2018 11:39:00 +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 5C94B28CA8 for ; Wed, 27 Jun 2018 11:39:00 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id DBC8A6E8BC; Wed, 27 Jun 2018 11:38:57 +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 8619D6E8BA for ; Wed, 27 Jun 2018 11:38:56 +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 12174373-1500050 for multiple; Wed, 27 Jun 2018 12:38:47 +0100 Received: by haswell.alporthouse.com (sSMTP sendmail emulation); Wed, 27 Jun 2018 12:38:46 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Wed, 27 Jun 2018 12:38:39 +0100 Message-Id: <20180627113843.7257-2-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.18.0 In-Reply-To: <20180627113843.7257-1-chris@chris-wilson.co.uk> References: <20180627113843.7257-1-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 2/6] drm/i915/execlists: Pull CSB reset under the timeline.lock 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 In the following patch, we will process the CSB events under the timeline.lock and not serialised by the tasklet. This also means that we will need to protect access to common variables such as execlists->csb_head with the timeline.lock during reset. v2: Move sync_irq to avoid deadlocks between taking timeline.lock from our interrupt handler. v3: Kill off the synchronize_hardirq as it raises more questions than answered; now we use the timeline.lock entirely for CSB serialisation between the irq and elsewhere, we don't need to be so heavy handed with flushing v4: Treat request cancellation (wedging after failed reset) similarly Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/intel_lrc.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 009db92b67d7..4b31e8f42aeb 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -871,7 +871,6 @@ static void reset_irq(struct intel_engine_cs *engine) { /* Mark all CS interrupts as complete */ smp_store_mb(engine->execlists.active, 0); - synchronize_hardirq(engine->i915->drm.irq); clear_gtiir(engine); @@ -908,14 +907,12 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) * submission's irq state, we also wish to remind ourselves that * it is irq state.) */ - local_irq_save(flags); + spin_lock_irqsave(&engine->timeline.lock, flags); /* Cancel the requests on the HW and clear the ELSP tracker. */ execlists_cancel_port_requests(execlists); reset_irq(engine); - spin_lock(&engine->timeline.lock); - /* Mark all executing requests as skipped. */ list_for_each_entry(rq, &engine->timeline.requests, link) { GEM_BUG_ON(!rq->global_seqno); @@ -949,9 +946,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) execlists->first = NULL; GEM_BUG_ON(port_isset(execlists->port)); - spin_unlock(&engine->timeline.lock); - - local_irq_restore(flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); } static void process_csb(struct intel_engine_cs *engine) @@ -1969,8 +1964,7 @@ static void execlists_reset(struct intel_engine_cs *engine, engine->name, request ? request->global_seqno : 0, intel_engine_get_seqno(engine)); - /* See execlists_cancel_requests() for the irq/spinlock split. */ - local_irq_save(flags); + spin_lock_irqsave(&engine->timeline.lock, flags); /* * Catch up with any missed context-switch interrupts. @@ -1985,14 +1979,12 @@ static void execlists_reset(struct intel_engine_cs *engine, reset_irq(engine); /* Push back any incomplete requests for replay after the reset. */ - spin_lock(&engine->timeline.lock); __unwind_incomplete_requests(engine); - spin_unlock(&engine->timeline.lock); /* Following the reset, we need to reload the CSB read/write pointers */ engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1; - local_irq_restore(flags); + spin_unlock_irqrestore(&engine->timeline.lock, flags); /* * If the request was innocent, we leave the request in the ELSP