From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Vetter Subject: [PATCH] drm/i915: fixup seqno allocation logic for lazy_request Date: Wed, 25 Jan 2012 16:32:49 +0100 Message-ID: <1327505569-14984-1-git-send-email-daniel.vetter@ffwll.ch> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail-we0-f177.google.com (mail-we0-f177.google.com [74.125.82.177]) by gabe.freedesktop.org (Postfix) with ESMTP id F00159ED43 for ; Wed, 25 Jan 2012 07:35:41 -0800 (PST) Received: by wera10 with SMTP id a10so1541850wer.36 for ; Wed, 25 Jan 2012 07:35:40 -0800 (PST) In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org Errors-To: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org To: Intel Graphics Development Cc: Daniel Vetter List-Id: intel-gfx@lists.freedesktop.org Currently we reserve seqnos only when we emit the request to the ring (by bumping dev_priv->next_seqno), but start using it much earlier for ring->oustanding_lazy_request. When 2 threads compete for the gpu and run on two different rings (e.g. ddx on blitter vs. compositor) hilarity ensued, especially when we get constantly interrupted while reserving buffers. Breakage seems to have been introduced in commit 6f392d548658a17600da7faaf8a5df25ee5f01f6 Author: Chris Wilson Date: Sat Aug 7 11:01:22 2010 +0100 drm/i915: Use a common seqno for all rings. This patch fixes up the seqno reservation logic by moving it into i915_gem_next_request_seqno. The ring->add_request functions now superflously still return the new seqno through a pointer, that will be refactored in the next patch. Note that with this change we now unconditionally allocate a seqno, even when ->add_request might fail because the rings are full and the gpu died. But this does not open up a new can of worms because we can already leave behind an outstanding_request_seqno if e.g. the caller gets interrupted with a signal while stalling for the gpu in the eviciton paths. And with the bugfix we only ever have one seqno allocated per ring (and only that ring), so there are no ordering issues with multiple outstanding seqnos on the same ring. v2: Keep i915_gem_get_seqno (but move it to i915_gem.c) to make it clear that we only have one seqno counter for all rings. Suggested by Chris Wilson. v3: As suggested by Chris Wilson use i915_gem_next_request_seqno instead of ring->oustanding_lazy_request to make the follow-up refactoring more clearly correct. Also improve the commit message with issues discussed on irc. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45181 Tested-by: Nicolas Kalkhof nkalkhof()at()web.de Signed-Off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.h | 7 +------ drivers/gpu/drm/i915/i915_gem.c | 23 +++++++++++++++++++++++ drivers/gpu/drm/i915/intel_ringbuffer.c | 24 ++++-------------------- 3 files changed, 28 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 32737a3..2f102ad 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1159,12 +1159,7 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2) return (int32_t)(seq1 - seq2) >= 0; } -static inline u32 -i915_gem_next_request_seqno(struct intel_ring_buffer *ring) -{ - drm_i915_private_t *dev_priv = ring->dev->dev_private; - return ring->outstanding_lazy_request = dev_priv->next_seqno; -} +u32 i915_gem_next_request_seqno(struct intel_ring_buffer *ring); int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj, struct intel_ring_buffer *pipelined); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 8f01c3d..dc8e45f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1647,6 +1647,28 @@ i915_gem_process_flushing_list(struct intel_ring_buffer *ring, } } +static u32 +i915_gem_get_seqno(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + u32 seqno = dev_priv->next_seqno; + + /* reserve 0 for non-seqno */ + if (++dev_priv->next_seqno == 0) + dev_priv->next_seqno = 1; + + return seqno; +} + +u32 +i915_gem_next_request_seqno(struct intel_ring_buffer *ring) +{ + if (ring->outstanding_lazy_request == 0) + ring->outstanding_lazy_request = i915_gem_get_seqno(ring->dev); + + return ring->outstanding_lazy_request; +} + int i915_add_request(struct intel_ring_buffer *ring, struct drm_file *file, @@ -1658,6 +1680,7 @@ i915_add_request(struct intel_ring_buffer *ring, int ret; BUG_ON(request == NULL); + seqno = i915_gem_next_request_seqno(ring); ret = ring->add_request(ring, &seqno); if (ret) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 1ab842c..7a107c9 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -52,20 +52,6 @@ static inline int ring_space(struct intel_ring_buffer *ring) return space; } -static u32 i915_gem_get_seqno(struct drm_device *dev) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - u32 seqno; - - seqno = dev_priv->next_seqno; - - /* reserve 0 for non-seqno */ - if (++dev_priv->next_seqno == 0) - dev_priv->next_seqno = 1; - - return seqno; -} - static int render_ring_flush(struct intel_ring_buffer *ring, u32 invalidate_domains, @@ -467,7 +453,7 @@ gen6_add_request(struct intel_ring_buffer *ring, mbox1_reg = ring->signal_mbox[0]; mbox2_reg = ring->signal_mbox[1]; - *seqno = i915_gem_get_seqno(ring->dev); + *seqno = i915_gem_next_request_seqno(ring); update_mboxes(ring, *seqno, mbox1_reg); update_mboxes(ring, *seqno, mbox2_reg); @@ -565,8 +551,7 @@ static int pc_render_add_request(struct intel_ring_buffer *ring, u32 *result) { - struct drm_device *dev = ring->dev; - u32 seqno = i915_gem_get_seqno(dev); + u32 seqno = i915_gem_next_request_seqno(ring); struct pipe_control *pc = ring->private; u32 scratch_addr = pc->gtt_offset + 128; int ret; @@ -617,8 +602,7 @@ static int render_ring_add_request(struct intel_ring_buffer *ring, u32 *result) { - struct drm_device *dev = ring->dev; - u32 seqno = i915_gem_get_seqno(dev); + u32 seqno = i915_gem_next_request_seqno(ring); int ret; ret = intel_ring_begin(ring, 4); @@ -792,7 +776,7 @@ ring_add_request(struct intel_ring_buffer *ring, if (ret) return ret; - seqno = i915_gem_get_seqno(ring->dev); + seqno = i915_gem_next_request_seqno(ring); intel_ring_emit(ring, MI_STORE_DWORD_INDEX); intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT); -- 1.7.7.5