drm/i915: Only pwrite through the GTT if there is space in the aperture

Avoid stalling and waiting for the GPU by checking to see if there is
sufficient inactive space in the aperture for us to bind the buffer
prior to writing through the GTT. If there is inadequate space we will
have to stall waiting for the GPU, and incur overheads moving objects
about. Instead, only incur the clflush overhead on the target object by
writing through shmem.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 16 insertions, 13 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e1ec587c42c8..1ec5f7ef2cc2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -41,7 +41,8 @@ static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *o
 static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj);
 static __must_check int i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 						    unsigned alignment,
-						    bool map_and_fenceable);
+						    bool map_and_fenceable,
+						    bool nonblocking);
 static int i915_gem_phys_pwrite(struct drm_device *dev,
 				struct drm_i915_gem_object *obj,
 				struct drm_i915_gem_pwrite *args,
@@ -609,7 +610,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	char __user *user_data;
 	int page_offset, page_length, ret;
 
-	ret = i915_gem_object_pin(obj, 0, true);
+	ret = i915_gem_object_pin(obj, 0, true, true);
 	if (ret)
 		goto out;
 
@@ -925,10 +926,8 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	if (obj->gtt_space &&
-	    obj->cache_level == I915_CACHE_NONE &&
+	if (obj->cache_level == I915_CACHE_NONE &&
 	    obj->tiling_mode == I915_TILING_NONE &&
-	    obj->map_and_fenceable &&
 	    obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
 		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
 		/* Note that the gtt paths might fail with non-page-backed user
@@ -936,7 +935,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		 * textures). Fallback to the shmem path in that case. */
 	}
 
-	if (ret == -EFAULT)
+	if (ret == -EFAULT || ret == -ENOSPC)
 		ret = i915_gem_shmem_pwrite(dev, obj, args, file);
 
 out:
@@ -1115,7 +1114,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 			goto unlock;
 	}
 	if (!obj->gtt_space) {
-		ret = i915_gem_object_bind_to_gtt(obj, 0, true);
+		ret = i915_gem_object_bind_to_gtt(obj, 0, true, false);
 		if (ret)
 			goto unlock;
 
@@ -2772,7 +2771,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 static int
 i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 			    unsigned alignment,
-			    bool map_and_fenceable)
+			    bool map_and_fenceable,
+			    bool nonblocking)
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -2848,7 +2848,8 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	if (obj->gtt_space == NULL) {
 		ret = i915_gem_evict_something(dev, size, alignment,
 					       obj->cache_level,
-					       map_and_fenceable);
+					       map_and_fenceable,
+					       nonblocking);
 		if (ret)
 			return ret;
 
@@ -3188,7 +3189,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_object_pin(obj, alignment, true);
+	ret = i915_gem_object_pin(obj, alignment, true, false);
 	if (ret)
 		return ret;
 
@@ -3325,7 +3326,8 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 int
 i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		    uint32_t alignment,
-		    bool map_and_fenceable)
+		    bool map_and_fenceable,
+		    bool nonblocking)
 {
 	int ret;
 
@@ -3349,7 +3351,8 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 
 	if (obj->gtt_space == NULL) {
 		ret = i915_gem_object_bind_to_gtt(obj, alignment,
-						  map_and_fenceable);
+						  map_and_fenceable,
+						  nonblocking);
 		if (ret)
 			return ret;
 	}
@@ -3407,7 +3410,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	obj->user_pin_count++;
 	obj->pin_filp = file;
 	if (obj->user_pin_count == 1) {
-		ret = i915_gem_object_pin(obj, args->alignment, true);
+		ret = i915_gem_object_pin(obj, args->alignment, true, false);
 		if (ret)
 			goto out;
 	}