[Intel-gfx] [PATCH v2 4/4] drm/i915: Kill i915_gem_execbuffer_wait_for_flips()

[ville.syrjala at linux.intel.com]

From: Ville Syrjälä <ville.syrjala at linux.intel.com>

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 <ville.syrjala at linux.intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h            |    7 ----
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |   42 ----------------------------
 drivers/gpu/drm/i915/intel_display.c       |    7 ----
 3 files changed, 0 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8a9856c..2c052bd 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1119,13 +1119,6 @@ struct drm_i915_gem_object {
 
 	/** for phy allocated objects */
 	struct drm_i915_gem_phys_object *phys_obj;
-
-	/**
-	 * Number of crtcs where this object is currently the fb, but
-	 * will be page flipped away on the next vblank.  When it
-	 * reaches 0, dev_priv->pending_flip_queue will be woken up.
-	 */
-	atomic_t pending_flip;
 };
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 48e4317..19d084c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -602,44 +602,11 @@ err:
 }
 
 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);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index ea710af..c7f7295 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6947,8 +6947,6 @@ static void do_intel_finish_page_flip(struct drm_device *dev,
 
 	obj = work->old_fb_obj;
 
-	atomic_clear_mask(1 << intel_crtc->plane,
-			  &obj->pending_flip.counter);
 	wake_up(&dev_priv->pending_flip_queue);
 
 	queue_work(dev_priv->wq, &work->work);
@@ -7294,10 +7292,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	work->enable_stall_check = true;
 
-	/* Block clients from rendering to the new back buffer until
-	 * the flip occurs and the object is no longer visible.
-	 */
-	atomic_add(1 << intel_crtc->plane, &work->old_fb_obj->pending_flip);
 	atomic_inc(&intel_crtc->unpin_work_count);
 
 	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj);
@@ -7314,7 +7308,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 cleanup_pending:
 	atomic_dec(&intel_crtc->unpin_work_count);
-	atomic_sub(1 << intel_crtc->plane, &work->old_fb_obj->pending_flip);
 	drm_gem_object_unreference(&work->old_fb_obj->base);
 	drm_gem_object_unreference(&obj->base);
 	mutex_unlock(&dev->struct_mutex);
-- 
1.7.8.6