From patchwork Mon Dec 10 13:41:48 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Mika Kuoppala X-Patchwork-Id: 1858091 Return-Path: X-Original-To: patchwork-intel-gfx@patchwork.kernel.org Delivered-To: patchwork-process-083081@patchwork2.kernel.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) by patchwork2.kernel.org (Postfix) with ESMTP id C912FDFB79 for ; Mon, 10 Dec 2012 13:43:28 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id BDA17E5D02 for ; Mon, 10 Dec 2012 05:43:28 -0800 (PST) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga14.intel.com (mga14.intel.com [143.182.124.37]) by gabe.freedesktop.org (Postfix) with ESMTP id 3FBB6E5FA8 for ; Mon, 10 Dec 2012 05:42:01 -0800 (PST) Received: from azsmga002.ch.intel.com ([10.2.17.35]) by azsmga102.ch.intel.com with ESMTP; 10 Dec 2012 05:42:00 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.84,252,1355126400"; d="scan'208";a="178912178" Received: from gaia.fi.intel.com (HELO gaia) ([10.237.72.78]) by AZSMGA002.ch.intel.com with ESMTP; 10 Dec 2012 05:41:59 -0800 Received: by gaia (Postfix, from userid 1000) id 5F99C41A88; Mon, 10 Dec 2012 15:41:58 +0200 (EET) From: Mika Kuoppala To: intel-gfx@lists.freedesktop.org Date: Mon, 10 Dec 2012 15:41:48 +0200 Message-Id: <1355146908-8645-1-git-send-email-mika.kuoppala@intel.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: References: Cc: chris@chris-wilson-co.uk Subject: [Intel-gfx] [PATCH 1/2] drm/i915: Don't emit semaphore wait if wrap happened X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.13 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: intel-gfx-bounces+patchwork-intel-gfx=patchwork.kernel.org@lists.freedesktop.org Errors-To: intel-gfx-bounces+patchwork-intel-gfx=patchwork.kernel.org@lists.freedesktop.org If wrap just happened we need to prevent emitting waits for pre wrap values. Detect this and emit no-ops instead. v2: Use olr > seqno to detect wrap instead of *seqno == 0 as suggested by Chris Wilson. v3: Use last used seqno to detect the wraparound. From Chris Wilson v4: Fixed unnecessary last_seqno assigment References: https://bugs.freedesktop.org/show_bug.cgi?id=57967 Signed-off-by: Mika Kuoppala --- drivers/gpu/drm/i915/i915_drv.h | 2 +- drivers/gpu/drm/i915/i915_gem.c | 2 +- drivers/gpu/drm/i915/intel_ringbuffer.c | 26 +++++++++++++++++++++----- 3 files changed, 23 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 2ab476d..9da6782 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -671,7 +671,7 @@ typedef struct drm_i915_private { struct pci_dev *bridge_dev; struct intel_ring_buffer ring[I915_NUM_RINGS]; - uint32_t next_seqno; + uint32_t last_seqno, next_seqno; drm_dma_handle_t *status_page_dmah; struct resource mch_res; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index e4b233d..a81b78a 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1969,7 +1969,7 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno) dev_priv->next_seqno = 1; } - *seqno = dev_priv->next_seqno++; + *seqno = dev_priv->last_seqno = dev_priv->next_seqno++; return 0; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 0d03dc6..69bbe7b 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -596,6 +596,13 @@ gen6_add_request(struct intel_ring_buffer *ring) return 0; } +static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev, + u32 seqno) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + return dev_priv->last_seqno < seqno; +} + /** * intel_ring_sync - sync the waiter to the signaller on seqno * @@ -626,11 +633,20 @@ gen6_ring_sync(struct intel_ring_buffer *waiter, if (ret) return ret; - intel_ring_emit(waiter, - dw1 | signaller->semaphore_register[waiter->id]); - intel_ring_emit(waiter, seqno); - intel_ring_emit(waiter, 0); - intel_ring_emit(waiter, MI_NOOP); + /* If seqno wrap happened, omit the wait with no-ops */ + if (likely(!i915_gem_has_seqno_wrapped(waiter->dev, seqno))) { + intel_ring_emit(waiter, + dw1 | + signaller->semaphore_register[waiter->id]); + intel_ring_emit(waiter, seqno); + intel_ring_emit(waiter, 0); + intel_ring_emit(waiter, MI_NOOP); + } else { + intel_ring_emit(waiter, MI_NOOP); + intel_ring_emit(waiter, MI_NOOP); + intel_ring_emit(waiter, MI_NOOP); + intel_ring_emit(waiter, MI_NOOP); + } intel_ring_advance(waiter); return 0;