[Intel-gfx] [PATCH 2/2] drm/i915: Use remap_pfn_range() to prefault all PTE in a single pass

[Chris Wilson]

On an Ivybridge i7-3720qm with 1600MHz DDR3, with 32 fences,
Upload rate for 2 linear surfaces:  8134MiB/s -> 8154MiB/s
Upload rate for 2 tiled surfaces:   8625MiB/s -> 8632MiB/s
Upload rate for 4 linear surfaces:  8127MiB/s -> 8134MiB/s
Upload rate for 4 tiled surfaces:   8602MiB/s -> 8629MiB/s
Upload rate for 8 linear surfaces:  8124MiB/s -> 8137MiB/s
Upload rate for 8 tiled surfaces:   8603MiB/s -> 8624MiB/s
Upload rate for 16 linear surfaces: 8123MiB/s -> 8128MiB/s
Upload rate for 16 tiled surfaces:  8606MiB/s -> 8618MiB/s
Upload rate for 32 linear surfaces: 8121MiB/s -> 8128MiB/s
Upload rate for 32 tiled surfaces:  8605MiB/s -> 8614MiB/s
Upload rate for 64 linear surfaces: 8121MiB/s -> 8127MiB/s
Upload rate for 64 tiled surfaces:  3017MiB/s -> 5127MiB/s

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e1f68f06c2ef..7128d389a6ff 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1709,21 +1709,19 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	pfn >>= PAGE_SHIFT;
 
 	if (!obj->fault_mappable) {
-		int i;
-
-		for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) {
-			ret = vm_insert_pfn(vma,
-					    (unsigned long)vma->vm_start + i * PAGE_SIZE,
-					    pfn + i);
-			if (ret)
-				break;
-		}
-
-		obj->fault_mappable = true;
-	} else
-		ret = vm_insert_pfn(vma,
-				    (unsigned long)vmf->virtual_address,
-				    pfn + page_offset);
+		ret = remap_pfn_range(vma,
+				      vma->vm_start,
+				      pfn,
+				      obj->base.size,
+				      vma->vm_page_prot);
+		obj->fault_mappable = ret == 0;
+	} else {
+		ret = remap_pfn_range(vma,
+				      (unsigned long)vmf->virtual_address,
+				      pfn + page_offset,
+				      PAGE_SIZE,
+				      vma->vm_page_prot);
+	}
 unpin:
 	i915_gem_object_ggtt_unpin(obj);
 unlock:
-- 
2.0.0