From patchwork Fri May 25 22:24:03 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Wilson X-Patchwork-Id: 10428689 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 5E5CE602D6 for ; Fri, 25 May 2018 22:24:13 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 4EE4B297ED for ; Fri, 25 May 2018 22:24:13 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 415252981B; Fri, 25 May 2018 22:24:13 +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 E2E4D297ED for ; Fri, 25 May 2018 22:24:12 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id AE1D96EB02; Fri, 25 May 2018 22:24:11 +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 193606E1E1 for ; Fri, 25 May 2018 22:24:09 +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 11848416-1500050 for ; Fri, 25 May 2018 23:24:06 +0100 Received: by haswell.alporthouse.com (sSMTP sendmail emulation); Fri, 25 May 2018 23:24:06 +0100 From: Chris Wilson To: intel-gfx@lists.freedesktop.org Date: Fri, 25 May 2018 23:24:03 +0100 Message-Id: <20180525222403.28357-2-chris@chris-wilson.co.uk> X-Mailer: git-send-email 2.17.0 In-Reply-To: <20180525222403.28357-1-chris@chris-wilson.co.uk> References: <20180525222403.28357-1-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] [CI 2/2] drm/i915: "Race-to-idle" after switching to the kernel context 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 During suspend we want to flush out all active contexts and their rendering. To do so we queue a request from the kernel's context, once we know that request is done, we know the GPU is completely idle. To speed up that switch bump the GPU clocks. Switching to the kernel context prior to idling is also used to enforce a barrier before changing OA properties, and when evicting active rendering from the global GTT. All cases where we do want to race-to-idle. v2: Limit the boosting to only the switch before suspend. v3: Limit it to the wait-for-idle on suspend. Signed-off-by: Chris Wilson Cc: David Weinehall Cc: Mika Kuoppala Tested-by: David Weinehall #v1 Reviewed-by: Mika Kuoppala --- drivers/gpu/drm/i915/i915_gem.c | 27 +++++++++++++++++++++++++-- drivers/gpu/drm/i915/i915_request.h | 1 + 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c93f5dcb1d82..7b5544efa0ba 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3704,7 +3704,29 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags) { - return i915_gem_active_wait(&tl->last_request, flags); + struct i915_request *rq; + long ret; + + rq = i915_gem_active_get_unlocked(&tl->last_request); + if (!rq) + return 0; + + /* + * "Race-to-idle". + * + * Switching to the kernel context is often used a synchronous + * step prior to idling, e.g. in suspend for flushing all + * current operations to memory before sleeping. These we + * want to complete as quickly as possible to avoid prolonged + * stalls, so allow the gpu to boost to maximum clocks. + */ + if (flags & I915_WAIT_FOR_IDLE_BOOST) + gen6_rps_boost(rq, NULL); + + ret = i915_request_wait(rq, flags, MAX_SCHEDULE_TIMEOUT); + i915_request_put(rq); + + return ret < 0 ? ret : 0; } static int wait_for_engines(struct drm_i915_private *i915) @@ -4979,7 +5001,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv) ret = i915_gem_wait_for_idle(dev_priv, I915_WAIT_INTERRUPTIBLE | - I915_WAIT_LOCKED); + I915_WAIT_LOCKED | + I915_WAIT_FOR_IDLE_BOOST); if (ret && ret != -EIO) goto err_unlock; diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 1bbbb7a9fa03..491ff81d0fea 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -267,6 +267,7 @@ long i915_request_wait(struct i915_request *rq, #define I915_WAIT_INTERRUPTIBLE BIT(0) #define I915_WAIT_LOCKED BIT(1) /* struct_mutex held, handle GPU reset */ #define I915_WAIT_ALL BIT(2) /* used by i915_gem_object_wait() */ +#define I915_WAIT_FOR_IDLE_BOOST BIT(3) static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine);