[03/11] drm/i915: Use insert_page for pwrite_fast

Submitted by ankitprasad.r.sharma@intel.com on May 31, 2016, 6:19 a.m.

Details

Message ID 1464675564-11988-4-git-send-email-ankitprasad.r.sharma@intel.com
State New
Headers show
Series "Support for creating/using Stolen memory backed objects" ( rev: 15 ) in Intel GFX

Not browsing as part of any series.

Commit Message

ankitprasad.r.sharma@intel.com May 31, 2016, 6:19 a.m.
From: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com>

In pwrite_fast, map an object page by page if obj_ggtt_pin fails. First,
we try a nonblocking pin for the whole object (since that is fastest if
reused), then failing that we try to grab one page in the mappable
aperture. It also allows us to handle objects larger than the mappable
aperture (e.g. if we need to pwrite with vGPU restricting the aperture
to a measely 8MiB or something like that).

v2: Pin pages before starting pwrite, Combined duplicate loops (Chris)

v3: Combined loops based on local patch by Chris (Chris)

v4: Added i915 wrapper function for drm_mm_insert_node_in_range (Chris)

v5: Renamed wrapper function for drm_mm_insert_node_in_range (Chris)

v5: Added wrapper for drm_mm_remove_node() (Chris)

v6: Added get_pages call before pinning the pages (Tvrtko)
Added remove_mappable_node() wrapper for drm_mm_remove_node() (Chris)

v7: Added size argument for insert_mappable_node (Tvrtko)

v8: Do not put_pages after pwrite, do memset of node in the wrapper
function (insert_mappable_node) (Chris)

v9: Rebase (Ankit)

Signed-off-by: Ankitprasad Sharma <ankitprasad.r.sharma@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 90 +++++++++++++++++++++++++++++++----------
 1 file changed, 68 insertions(+), 22 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 89967f9..74346cf 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -60,6 +60,24 @@  static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 	return obj->pin_display;
 }
 
+static int
+insert_mappable_node(struct drm_i915_private *i915,
+                     struct drm_mm_node *node, u32 size)
+{
+	memset(node, 0, sizeof(*node));
+	return drm_mm_insert_node_in_range_generic(&i915->ggtt.base.mm, node,
+						   size, 0, 0, 0,
+						   i915->ggtt.mappable_end,
+						   DRM_MM_SEARCH_DEFAULT,
+						   DRM_MM_CREATE_DEFAULT);
+}
+
+static void
+remove_mappable_node(struct drm_mm_node *node)
+{
+	drm_mm_remove_node(node);
+}
+
 /* some bookkeeping */
 static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
 				  size_t size)
@@ -755,21 +773,34 @@  fast_user_write(struct io_mapping *mapping,
  * user into the GTT, uncached.
  */
 static int
-i915_gem_gtt_pwrite_fast(struct drm_device *dev,
+i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
 			 struct drm_i915_gem_object *obj,
 			 struct drm_i915_gem_pwrite *args,
 			 struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	ssize_t remain;
-	loff_t offset, page_base;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct drm_mm_node node;
+	uint64_t remain, offset;
 	char __user *user_data;
-	int page_offset, page_length, ret;
+	int ret;
 
 	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK);
-	if (ret)
-		goto out;
+	if (ret) {
+		ret = insert_mappable_node(i915, &node, PAGE_SIZE);
+		if (ret)
+			goto out;
+
+		ret = i915_gem_object_get_pages(obj);
+		if (ret) {
+			remove_mappable_node(&node);
+			goto out;
+		}
+
+		i915_gem_object_pin_pages(obj);
+	} else {
+		node.start = i915_gem_obj_ggtt_offset(obj);
+		node.allocated = false;
+	}
 
 	ret = i915_gem_object_set_to_gtt_domain(obj, true);
 	if (ret)
@@ -779,26 +810,32 @@  i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	if (ret)
 		goto out_unpin;
 
-	user_data = to_user_ptr(args->data_ptr);
-	remain = args->size;
-
-	offset = i915_gem_obj_ggtt_offset(obj) + args->offset;
-
 	intel_fb_obj_invalidate(obj, ORIGIN_GTT);
+	obj->dirty = true;
 
-	while (remain > 0) {
+	user_data = to_user_ptr(args->data_ptr);
+	offset = args->offset;
+	remain = args->size;
+	while (remain) {
 		/* Operation in this page
 		 *
 		 * page_base = page offset within aperture
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_base = offset & PAGE_MASK;
-		page_offset = offset_in_page(offset);
-		page_length = remain;
-		if ((page_offset + remain) > PAGE_SIZE)
-			page_length = PAGE_SIZE - page_offset;
-
+		u32 page_base = node.start;
+		unsigned page_offset = offset_in_page(offset);
+		unsigned page_length = PAGE_SIZE - page_offset;
+		page_length = remain < page_length ? remain : page_length;
+		if (node.allocated) {
+			wmb(); /* flush the write before we modify the GGTT */
+			ggtt->base.insert_page(&ggtt->base,
+					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					       node.start, I915_CACHE_NONE, 0);
+			wmb(); /* flush modifications to the GGTT (insert_page) */
+		} else {
+			page_base += offset & PAGE_MASK;
+		}
 		/* If we get a fault while copying data, then (presumably) our
 		 * source page isn't available.  Return the error and we'll
 		 * retry in the slow path.
@@ -817,7 +854,16 @@  i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 out_flush:
 	intel_fb_obj_flush(obj, false, ORIGIN_GTT);
 out_unpin:
-	i915_gem_object_ggtt_unpin(obj);
+	if (node.allocated) {
+		wmb();
+		ggtt->base.clear_range(&ggtt->base,
+				       node.start, node.size,
+				       true);
+		i915_gem_object_unpin_pages(obj);
+		remove_mappable_node(&node);
+	} else {
+		i915_gem_object_ggtt_unpin(obj);
+	}
 out:
 	return ret;
 }
@@ -1082,7 +1128,7 @@  i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 	if (obj->tiling_mode == I915_TILING_NONE &&
 	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
 	    cpu_write_needs_clflush(obj)) {
-		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
+		ret = i915_gem_gtt_pwrite_fast(dev_priv, obj, args, file);
 		/* Note that the gtt paths might fail with non-page-backed user
 		 * pointers (e.g. gtt mappings when moving data between
 		 * textures). Fallback to the shmem path in that case. */