drm/i915: Update write_domains on active list after flush.

commit 99fcb766a3a50466fe31d743260a3400c1aee855 upstream.

Before changing the status of a buffer with a pending write we will await
upon a new flush for that buffer. So we can take advantage of any flushes
posted whilst the buffer is active and pending processing by the GPU, by
clearing its write_domain and updating its last_rendering_seqno -- thus
saving a potential flush in deep queues and improves flushing behaviour
upon eviction for both GTT space and fences.

In order to reduce the time spent searching the active list for matching
write_domains, we move those to a separate list whose elements are
the buffers belong to the active/flushing list with pending writes.

Orignal patch by Chris Wilson <chris@chris-wilson.co.uk>, forward-ported
by me.

In addition to better performance, this also fixes a real bug. Before
this changes, i915_gem_evict_everything didn't work as advertised. When
the gpu was actually busy and processing request, the flush and subsequent
wait would not move active and dirty buffers to the inactive list, but
just to the flushing list. Which triggered the BUG_ON at the end of this
function. With the more tight dirty buffer tracking, all currently busy and
dirty buffers get moved to the inactive list by one i915_gem_flush operation.

I've left the BUG_ON I've used to prove this in there.

References:
  Bug 25911 - 2.10.0 causes kernel oops and system hangs
  http://bugs.freedesktop.org/show_bug.cgi?id=25911

  Bug 26101 - [i915] xf86-video-intel 2.10.0 (and git) triggers kernel oops
              within seconds after login
  http://bugs.freedesktop.org/show_bug.cgi?id=26101

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Adam Lantos <hege@playma.org>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

1 files changed, 19 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8ad244ae7fa3..07345cacd0cc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1552,6 +1552,8 @@ i915_gem_object_move_to_inactive(struct drm_gem_object *obj)
 	else
 		list_move_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
 
+	BUG_ON(!list_empty(&obj_priv->gpu_write_list));
+
 	obj_priv->last_rendering_seqno = 0;
 	if (obj_priv->active) {
 		obj_priv->active = 0;
@@ -1622,7 +1624,8 @@ i915_add_request(struct drm_device *dev, struct drm_file *file_priv,
 		struct drm_i915_gem_object *obj_priv, *next;
 
 		list_for_each_entry_safe(obj_priv, next,
-					 &dev_priv->mm.flushing_list, list) {
+					 &dev_priv->mm.gpu_write_list,
+					 gpu_write_list) {
 			struct drm_gem_object *obj = obj_priv->obj;
 
 			if ((obj->write_domain & flush_domains) ==
@@ -1630,6 +1633,7 @@ i915_add_request(struct drm_device *dev, struct drm_file *file_priv,
 				uint32_t old_write_domain = obj->write_domain;
 
 				obj->write_domain = 0;
+				list_del_init(&obj_priv->gpu_write_list);
 				i915_gem_object_move_to_active(obj, seqno);
 
 				trace_i915_gem_object_change_domain(obj,
@@ -2073,8 +2077,8 @@ static int
 i915_gem_evict_everything(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	uint32_t seqno;
 	int ret;
+	uint32_t seqno;
 	bool lists_empty;
 
 	spin_lock(&dev_priv->mm.active_list_lock);
@@ -2096,6 +2100,8 @@ i915_gem_evict_everything(struct drm_device *dev)
 	if (ret)
 		return ret;
 
+	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
+
 	ret = i915_gem_evict_from_inactive_list(dev);
 	if (ret)
 		return ret;
@@ -2690,7 +2696,7 @@ i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj)
 	old_write_domain = obj->write_domain;
 	i915_gem_flush(dev, 0, obj->write_domain);
 	seqno = i915_add_request(dev, NULL, obj->write_domain);
-	obj->write_domain = 0;
+	BUG_ON(obj->write_domain);
 	i915_gem_object_move_to_active(obj, seqno);
 
 	trace_i915_gem_object_change_domain(obj,
@@ -3710,16 +3716,23 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 		i915_gem_flush(dev,
 			       dev->invalidate_domains,
 			       dev->flush_domains);
-		if (dev->flush_domains)
+		if (dev->flush_domains & I915_GEM_GPU_DOMAINS)
 			(void)i915_add_request(dev, file_priv,
 					       dev->flush_domains);
 	}
 
 	for (i = 0; i < args->buffer_count; i++) {
 		struct drm_gem_object *obj = object_list[i];
+		struct drm_i915_gem_object *obj_priv = obj->driver_private;
 		uint32_t old_write_domain = obj->write_domain;
 
 		obj->write_domain = obj->pending_write_domain;
+		if (obj->write_domain)
+			list_move_tail(&obj_priv->gpu_write_list,
+				       &dev_priv->mm.gpu_write_list);
+		else
+			list_del_init(&obj_priv->gpu_write_list);
+
 		trace_i915_gem_object_change_domain(obj,
 						    obj->read_domains,
 						    old_write_domain);
@@ -4112,6 +4125,7 @@ int i915_gem_init_object(struct drm_gem_object *obj)
 	obj_priv->obj = obj;
 	obj_priv->fence_reg = I915_FENCE_REG_NONE;
 	INIT_LIST_HEAD(&obj_priv->list);
+	INIT_LIST_HEAD(&obj_priv->gpu_write_list);
 	INIT_LIST_HEAD(&obj_priv->fence_list);
 	obj_priv->madv = I915_MADV_WILLNEED;
 
@@ -4563,6 +4577,7 @@ i915_gem_load(struct drm_device *dev)
 	spin_lock_init(&dev_priv->mm.active_list_lock);
 	INIT_LIST_HEAD(&dev_priv->mm.active_list);
 	INIT_LIST_HEAD(&dev_priv->mm.flushing_list);
+	INIT_LIST_HEAD(&dev_priv->mm.gpu_write_list);
 	INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
 	INIT_LIST_HEAD(&dev_priv->mm.request_list);
 	INIT_LIST_HEAD(&dev_priv->mm.fence_list);