From patchwork Fri Mar 30 10:39:02 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10317585 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 27B9E60212 for ; Fri, 30 Mar 2018 10:39:46 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 161DC286DF for ; Fri, 30 Mar 2018 10:39:46 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 0AAAE286E3; Fri, 30 Mar 2018 10:39:46 +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=-4.2 required=2.0 tests=BAYES_00, 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 5244E286E0 for ; Fri, 30 Mar 2018 10:39:45 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 92BDD6E404; Fri, 30 Mar 2018 10:39:44 +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 410746E3FD for ; Fri, 30 Mar 2018 10:39:41 +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 11213806-1500050 for multiple; Fri, 30 Mar 2018 11:39:28 +0100 Received: by haswell.alporthouse.com (sSMTP sendmail emulation); Fri, 30 Mar 2018 11:39:26 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Fri, 30 Mar 2018 11:39:02 +0100 Message-Id: <20180330103915.23018-5-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.16.3 In-Reply-To: <20180330103915.23018-1-chris@chris-wilson.co.uk> References: <20180330103915.23018-1-chris@chris-wilson.co.uk> MIME-Version: 1.0 X-Originating-IP: 78.156.65.138 X-Country: code=GB country="United Kingdom" ip=78.156.65.138 Subject: [Intel-gfx] [PATCH 04/17] drm/i915: Move engine reset prepare/finish to backends 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 In preparation to more carefully handling incomplete preemption during reset by execlists, we move the existing code wholesale to the backends under a couple of new reset vfuncs. Signed-off-by: Chris Wilson Cc: Michał Winiarski CC: Michel Thierry Cc: Jeff McGee Reviewed-by: Jeff McGee --- drivers/gpu/drm/i915/i915_gem.c | 47 +++----------------------- drivers/gpu/drm/i915/intel_lrc.c | 59 +++++++++++++++++++++++++++++++-- drivers/gpu/drm/i915/intel_ringbuffer.c | 23 +++++++++++-- drivers/gpu/drm/i915/intel_ringbuffer.h | 9 +++-- 4 files changed, 88 insertions(+), 50 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 9650a7b10c5f..038867c96809 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2917,7 +2917,7 @@ static bool engine_stalled(struct intel_engine_cs *engine) struct i915_request * i915_gem_reset_prepare_engine(struct intel_engine_cs *engine) { - struct i915_request *request = NULL; + struct i915_request *request; /* * During the reset sequence, we must prevent the engine from @@ -2940,40 +2940,7 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine) */ kthread_park(engine->breadcrumbs.signaler); - /* - * Prevent request submission to the hardware until we have - * completed the reset in i915_gem_reset_finish(). If a request - * is completed by one engine, it may then queue a request - * to a second via its execlists->tasklet *just* as we are - * calling engine->init_hw() and also writing the ELSP. - * Turning off the execlists->tasklet until the reset is over - * prevents the race. - * - * Note that this needs to be a single atomic operation on the - * tasklet (flush existing tasks, prevent new tasks) to prevent - * a race between reset and set-wedged. It is not, so we do the best - * we can atm and make sure we don't lock the machine up in the more - * common case of recursively being called from set-wedged from inside - * i915_reset. - */ - if (!atomic_read(&engine->execlists.tasklet.count)) - tasklet_kill(&engine->execlists.tasklet); - tasklet_disable(&engine->execlists.tasklet); - - /* - * We're using worker to queue preemption requests from the tasklet in - * GuC submission mode. - * Even though tasklet was disabled, we may still have a worker queued. - * Let's make sure that all workers scheduled before disabling the - * tasklet are completed before continuing with the reset. - */ - if (engine->i915->guc.preempt_wq) - flush_workqueue(engine->i915->guc.preempt_wq); - - if (engine->irq_seqno_barrier) - engine->irq_seqno_barrier(engine); - - request = i915_gem_find_active_request(engine); + request = engine->reset.prepare(engine); if (request && request->fence.error == -EIO) request = ERR_PTR(-EIO); /* Previous reset failed! */ @@ -3114,13 +3081,8 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine, if (request) request = i915_gem_reset_request(engine, request); - if (request) { - DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n", - engine->name, request->global_seqno); - } - /* Setup the CS to resume from the breadcrumb of the hung request */ - engine->reset_hw(engine, request); + engine->reset.reset(engine, request); } void i915_gem_reset(struct drm_i915_private *dev_priv) @@ -3172,7 +3134,8 @@ void i915_gem_reset(struct drm_i915_private *dev_priv) void i915_gem_reset_finish_engine(struct intel_engine_cs *engine) { - tasklet_enable(&engine->execlists.tasklet); + engine->reset.finish(engine); + kthread_unpark(engine->breadcrumbs.signaler); intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL); diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 51e930323626..42f9af625e88 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1732,8 +1732,48 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine) return init_workarounds_ring(engine); } -static void reset_common_ring(struct intel_engine_cs *engine, - struct i915_request *request) +static struct i915_request * +execlists_reset_prepare(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists * const execlists = &engine->execlists; + + GEM_TRACE("%s\n", engine->name); + + /* + * Prevent request submission to the hardware until we have + * completed the reset in i915_gem_reset_finish(). If a request + * is completed by one engine, it may then queue a request + * to a second via its execlists->tasklet *just* as we are + * calling engine->init_hw() and also writing the ELSP. + * Turning off the execlists->tasklet until the reset is over + * prevents the race. + * + * Note that this needs to be a single atomic operation on the + * tasklet (flush existing tasks, prevent new tasks) to prevent + * a race between reset and set-wedged. It is not, so we do the best + * we can atm and make sure we don't lock the machine up in the more + * common case of recursively being called from set-wedged from inside + * i915_reset. + */ + if (!atomic_read(&execlists->tasklet.count)) + tasklet_kill(&execlists->tasklet); + tasklet_disable(&execlists->tasklet); + + /* + * We're using worker to queue preemption requests from the tasklet in + * GuC submission mode. + * Even though tasklet was disabled, we may still have a worker queued. + * Let's make sure that all workers scheduled before disabling the + * tasklet are completed before continuing with the reset. + */ + if (engine->i915->guc.preempt_wq) + flush_workqueue(engine->i915->guc.preempt_wq); + + return i915_gem_find_active_request(engine); +} + +static void execlists_reset(struct intel_engine_cs *engine, + struct i915_request *request) { struct intel_engine_execlists * const execlists = &engine->execlists; struct intel_context *ce; @@ -1742,6 +1782,9 @@ static void reset_common_ring(struct intel_engine_cs *engine, GEM_TRACE("%s seqno=%x\n", engine->name, request ? request->global_seqno : 0); + /* The submission tasklet must be disabled, engine->reset.prepare(). */ + GEM_BUG_ON(!atomic_read(&execlists->tasklet.count)); + /* See execlists_cancel_requests() for the irq/spinlock split. */ local_irq_save(flags); @@ -1802,6 +1845,13 @@ static void reset_common_ring(struct intel_engine_cs *engine, unwind_wa_tail(request); } +static void execlists_reset_finish(struct intel_engine_cs *engine) +{ + tasklet_enable(&engine->execlists.tasklet); + + GEM_TRACE("%s\n", engine->name); +} + static int intel_logical_ring_emit_pdps(struct i915_request *rq) { struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt; @@ -2126,7 +2176,10 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) { /* Default vfuncs which can be overriden by each engine. */ engine->init_hw = gen8_init_common_ring; - engine->reset_hw = reset_common_ring; + + engine->reset.prepare = execlists_reset_prepare; + engine->reset.reset = execlists_reset; + engine->reset.finish = execlists_reset_finish; engine->context_pin = execlists_context_pin; engine->context_unpin = execlists_context_unpin; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 04d9d9a946a7..5dadbc435c0e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -530,9 +530,20 @@ static int init_ring_common(struct intel_engine_cs *engine) return ret; } -static void reset_ring_common(struct intel_engine_cs *engine, - struct i915_request *request) +static struct i915_request *reset_prepare(struct intel_engine_cs *engine) { + if (engine->irq_seqno_barrier) + engine->irq_seqno_barrier(engine); + + return i915_gem_find_active_request(engine); +} + +static void reset_ring(struct intel_engine_cs *engine, + struct i915_request *request) +{ + GEM_TRACE("%s seqno=%x\n", + engine->name, request ? request->global_seqno : 0); + /* * RC6 must be prevented until the reset is complete and the engine * reinitialised. If it occurs in the middle of this sequence, the @@ -595,6 +606,10 @@ static void reset_ring_common(struct intel_engine_cs *engine, } } +static void reset_finish(struct intel_engine_cs *engine) +{ +} + static int intel_rcs_ctx_init(struct i915_request *rq) { int ret; @@ -1987,7 +2002,9 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv, intel_ring_init_semaphores(dev_priv, engine); engine->init_hw = init_ring_common; - engine->reset_hw = reset_ring_common; + engine->reset.prepare = reset_prepare; + engine->reset.reset = reset_ring; + engine->reset.finish = reset_finish; engine->context_pin = intel_ring_context_pin; engine->context_unpin = intel_ring_context_unpin; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 2e20627e254b..15d624925594 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -418,8 +418,13 @@ struct intel_engine_cs { void (*irq_disable)(struct intel_engine_cs *engine); int (*init_hw)(struct intel_engine_cs *engine); - void (*reset_hw)(struct intel_engine_cs *engine, - struct i915_request *rq); + + struct { + struct i915_request *(*prepare)(struct intel_engine_cs *engine); + void (*reset)(struct intel_engine_cs *engine, + struct i915_request *rq); + void (*finish)(struct intel_engine_cs *engine); + } reset; void (*park)(struct intel_engine_cs *engine); void (*unpark)(struct intel_engine_cs *engine);