From 0f0cd472062eca6f9fac8be0cd5585f9a2df1ab2 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 11 Dec 2015 11:32:59 +0000 Subject: [PATCH] drm/i915: Only spin whilst waiting on the current request Limit busywaiting only to the request currently being processed by the GPU. If the request is not currently being processed by the GPU, there is a very low likelihood of it being completed within the 2 microsecond spin timeout and so we will just be wasting CPU cycles. v2: Check for logical inversion when rebasing - we were incorrectly checking for this request being active, and instead busywaiting for when the GPU was not yet processing the request of interest. v3: Try another colour for the seqno names. v4: Another colour for the function names. v5: Remove the forced coherency when checking for the active request. On reflection and plenty of recent experimentation, the issue is not a cache coherency problem - but an irq/seqno ordering problem (timing issue). Here, we do not need the w/a to force ordering of the read with an interrupt. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Cc: "Rogozhkin, Dmitry V" Cc: Daniel Vetter Cc: Tvrtko Ursulin Cc: Eero Tamminen Cc: "Rantala, Valtteri" Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1449833608-22125-4-git-send-email-chris@chris-wilson.co.uk (cherry picked from commit 821485dc2ad665f136c57ee589bf7a8210160fe2) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 27 +++++++++++++++++++-------- drivers/gpu/drm/i915/i915_gem.c | 8 +++++++- 2 files changed, 26 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 037a650d6565..f4af19a0d569 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2193,8 +2193,17 @@ struct drm_i915_gem_request { struct drm_i915_private *i915; struct intel_engine_cs *ring; - /** GEM sequence number associated with this request. */ - uint32_t seqno; + /** GEM sequence number associated with the previous request, + * when the HWS breadcrumb is equal to this the GPU is processing + * this request. + */ + u32 previous_seqno; + + /** GEM sequence number associated with this request, + * when the HWS breadcrumb is equal or greater than this the GPU + * has finished processing this request. + */ + u32 seqno; /** Position in the ringbuffer of the start of the request */ u32 head; @@ -2911,15 +2920,17 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2) return (int32_t)(seq1 - seq2) >= 0; } +static inline bool i915_gem_request_started(struct drm_i915_gem_request *req, + bool lazy_coherency) +{ + u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency); + return i915_seqno_passed(seqno, req->previous_seqno); +} + static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req, bool lazy_coherency) { - u32 seqno; - - BUG_ON(req == NULL); - - seqno = req->ring->get_seqno(req->ring, lazy_coherency); - + u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency); return i915_seqno_passed(seqno, req->seqno); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 8719fa2ae7e7..f56af0aaafde 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1193,9 +1193,13 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state) * takes to sleep on a request, on the order of a microsecond. */ - if (i915_gem_request_get_ring(req)->irq_refcount) + if (req->ring->irq_refcount) return -EBUSY; + /* Only spin if we know the GPU is processing this request */ + if (!i915_gem_request_started(req, true)) + return -EAGAIN; + timeout = local_clock_us(&cpu) + 5; while (!need_resched()) { if (i915_gem_request_completed(req, true)) @@ -1209,6 +1213,7 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state) cpu_relax_lowlatency(); } + if (i915_gem_request_completed(req, false)) return 0; @@ -2600,6 +2605,7 @@ void __i915_add_request(struct drm_i915_gem_request *request, request->batch_obj = obj; request->emitted_jiffies = jiffies; + request->previous_seqno = ring->last_submitted_seqno; ring->last_submitted_seqno = request->seqno; list_add_tail(&request->list, &ring->request_list);