diff mbox

[v2] drm/ttm: Don't evict BOs outside of the requested placement range

Message ID 1412931829-8963-1-git-send-email-michel@daenzer.net (mailing list archive)
State New, archived
Headers show

Commit Message

Michel Dänzer Oct. 10, 2014, 9:03 a.m. UTC
From: Michel Dänzer <michel.daenzer@amd.com>

The radeon driver uses placement range restrictions for several reasons,
in particular to make sure BOs in VRAM can be accessed by the CPU, e.g.
during a page fault.

Without this change, TTM could evict other BOs while trying to satisfy
the requested placement, even if the evicted BOs were outside of the
requested placement range. Doing so didn't free up any space in the
requested placement range, so the (potentially high) eviction cost was
incurred for no benefit.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=84662
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
---

v2: Dropped Cc: stable, will need to backport manually because the code
    has changed since 3.17

 drivers/gpu/drm/ttm/ttm_bo.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)
diff mbox

Patch

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8f5cec6..407fa2d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -709,6 +709,7 @@  out:
 
 static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 				uint32_t mem_type,
+				const struct ttm_place *place,
 				bool interruptible,
 				bool no_wait_gpu)
 {
@@ -720,8 +721,21 @@  static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &man->lru, lru) {
 		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
-		if (!ret)
+		if (!ret) {
+			if (place && (place->fpfn || place->lpfn)) {
+				/* Don't evict this BO if it's outside of the
+				 * requested placement range
+				 */
+				if (place->fpfn >= (bo->mem.start + bo->mem.size) ||
+				    (place->lpfn && place->lpfn <= bo->mem.start)) {
+					__ttm_bo_unreserve(bo);
+					ret = -EBUSY;
+					continue;
+				}
+			}
+
 			break;
+		}
 	}
 
 	if (ret) {
@@ -782,7 +796,7 @@  static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 			return ret;
 		if (mem->mm_node)
 			break;
-		ret = ttm_mem_evict_first(bdev, mem_type,
+		ret = ttm_mem_evict_first(bdev, mem_type, place,
 					  interruptible, no_wait_gpu);
 		if (unlikely(ret != 0))
 			return ret;
@@ -1233,7 +1247,7 @@  static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 	spin_lock(&glob->lru_lock);
 	while (!list_empty(&man->lru)) {
 		spin_unlock(&glob->lru_lock);
-		ret = ttm_mem_evict_first(bdev, mem_type, false, false);
+		ret = ttm_mem_evict_first(bdev, mem_type, NULL, false, false);
 		if (ret) {
 			if (allow_errors) {
 				return ret;