From 6b567085c1bdbacea217dd628f0dbf26dd67db3f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 8 Jun 2017 12:14:05 +0100 Subject: [PATCH] drm/i915: Remove the spin-request during execbuf await_request Originally we would enable and disable the breadcrumb interrupt immediately on demand. This was slow enough to have a large impact (>30%) on tasks that hopped between engines. However, by using a shadow to keep the irq alive for an extra interrupt (see commit 67b807a89230 ("drm/i915: Delay disabling the user interrupt for breadcrumbs")) and by recently reducing the cost in adding ourselves to the signal tree, we no longer need to spin-request during await_request to avoid delays in throughput tests. Without the earlier patches to stop the wakeup when signaling if the irq was already active, we saw no improvement in execbuf overhead (and corresponding contention in other clients) despite the removal of the spinner in a simple test like glxgears. This means there will be scenarios where now we spend longer enabling the interrupt than we would have spent spinning, but these are not likely to have as noticeable an impact as the high frequency test cases (where there should not be any regression). Ulterior motive: generalising the engine->sync_to to handle different types of semaphores and non-semaphores. Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: Tvrtko Ursulin Cc: Oscar Mateo Reviewed-by: Tvrtko Ursulin Reviewed-by: Joonas Lahtinen Link: http://patchwork.freedesktop.org/patch/msgid/20170608111405.16466-4-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/i915_gem_request.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index 46d869e26b4d..8c59c79cbd8b 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -683,7 +683,6 @@ static int i915_gem_request_await_request(struct drm_i915_gem_request *to, struct drm_i915_gem_request *from) { - u32 seqno; int ret; GEM_BUG_ON(to == from); @@ -707,18 +706,14 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to, return ret < 0 ? ret : 0; } - seqno = i915_gem_request_global_seqno(from); - if (!seqno) - goto await_dma_fence; + if (to->engine->semaphore.sync_to) { + u32 seqno; - if (!to->engine->semaphore.sync_to) { - if (!__i915_gem_request_started(from, seqno)) - goto await_dma_fence; + GEM_BUG_ON(!from->engine->semaphore.signal); - if (!__i915_spin_request(from, seqno, TASK_INTERRUPTIBLE, 2)) + seqno = i915_gem_request_global_seqno(from); + if (!seqno) goto await_dma_fence; - } else { - GEM_BUG_ON(!from->engine->semaphore.signal); if (seqno <= to->timeline->global_sync[from->engine->id]) return 0; @@ -729,10 +724,9 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to, return ret; to->timeline->global_sync[from->engine->id] = seqno; + return 0; } - return 0; - await_dma_fence: ret = i915_sw_fence_await_dma_fence(&to->submit, &from->fence, 0, -- 2.30.2