From ca9c46c5c77987acf1bf7137bf85e9221bc459ba Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Tue, 27 Nov 2012 20:34:58 +0200 Subject: drm/i915: Kill i915_gem_execbuffer_wait_for_flips() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As per Chris Wilson's suggestion make i915_gem_execbuffer_wait_for_flips() go away. This was used to stall the GPU ring while there are pending page flips involving the relevant BO. Ie. while the BO is still being scanned out by the display controller. The recommended alternative is to use the page flip events to wait for the page flips to fully complete before reusing the BO of the old front buffer. Or use more buffers. Signed-off-by: Ville Syrjälä Reviewed-by: Chris Wilson Acked-by: Kristian Høgsberg Acked-by: Jesse Barnes [danvet: don't remove obj->pending_flips, still required due to reorder patches.] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 42 ------------------------------ 1 file changed, 42 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_gem_execbuffer.c') diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index ee8f97f0539..802d925b2b5 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -601,45 +601,12 @@ err: return ret; } -static int -i915_gem_execbuffer_wait_for_flips(struct intel_ring_buffer *ring, u32 flips) -{ - u32 plane, flip_mask; - int ret; - - /* Check for any pending flips. As we only maintain a flip queue depth - * of 1, we can simply insert a WAIT for the next display flip prior - * to executing the batch and avoid stalling the CPU. - */ - - for (plane = 0; flips >> plane; plane++) { - if (((flips >> plane) & 1) == 0) - continue; - - if (plane) - flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; - else - flip_mask = MI_WAIT_FOR_PLANE_A_FLIP; - - ret = intel_ring_begin(ring, 2); - if (ret) - return ret; - - intel_ring_emit(ring, MI_WAIT_FOR_EVENT | flip_mask); - intel_ring_emit(ring, MI_NOOP); - intel_ring_advance(ring); - } - - return 0; -} - static int i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, struct list_head *objects) { struct drm_i915_gem_object *obj; uint32_t flush_domains = 0; - uint32_t flips = 0; int ret; list_for_each_entry(obj, objects, exec_list) { @@ -650,18 +617,9 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) i915_gem_clflush_object(obj); - if (obj->base.pending_write_domain) - flips |= atomic_read(&obj->pending_flip); - flush_domains |= obj->base.write_domain; } - if (flips) { - ret = i915_gem_execbuffer_wait_for_flips(ring, flips); - if (ret) - return ret; - } - if (flush_domains & I915_GEM_DOMAIN_CPU) i915_gem_chipset_flush(ring->dev); -- cgit v1.2.3-70-g09d2 From c1f093e09c4ceb583b04d11e767bb3201812e4d2 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 3 Dec 2012 11:49:07 +0000 Subject: drm/i915: Remove check for conflicting relocation write-domains Simply use the last write-domain set for the object in the batch, trusting userspace to have correctly flushed the caches between usage as a write target. This check dates back from the golden age of having only a single operation per batch with the kernel repeating it for each cliprect, and conflicts both with userspace trying to efficiently batch multiple operations and with reducing the kernel overhead of relocation processing. Signed-off-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_gem_execbuffer.c') diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 802d925b2b5..6cd3e1c1629 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -150,17 +150,6 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, reloc->write_domain); return ret; } - if (unlikely(reloc->write_domain && target_obj->pending_write_domain && - reloc->write_domain != target_obj->pending_write_domain)) { - DRM_DEBUG("Write domain conflict: " - "obj %p target %d offset %d " - "new %08x old %08x\n", - obj, reloc->target_handle, - (int) reloc->offset, - reloc->write_domain, - target_obj->pending_write_domain); - return ret; - } target_obj->pending_read_domains |= reloc->read_domains; target_obj->pending_write_domain |= reloc->write_domain; -- cgit v1.2.3-70-g09d2