2 files changed, 54 insertions, 7 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8d5a646ebe6a..07e02c4bf5a8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -151,7 +151,7 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	atomic_dec(&bo->glob->bo_count);
 	if (bo->resv == &bo->ttm_resv)
 		reservation_object_fini(&bo->ttm_resv);
-
+	mutex_destroy(&bo->wu_mutex);
 	if (bo->destroy)
 		bo->destroy(bo);
 	else {
@@ -1123,6 +1123,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
 	INIT_LIST_HEAD(&bo->io_reserve_lru);
+	mutex_init(&bo->wu_mutex);
 	bo->bdev = bdev;
 	bo->glob = bdev->glob;
 	bo->type = type;
@@ -1704,3 +1705,35 @@ void ttm_bo_swapout_all(struct ttm_bo_device *bdev)
 		;
 }
 EXPORT_SYMBOL(ttm_bo_swapout_all);
+
+/**
+ * ttm_bo_wait_unreserved - interruptible wait for a buffer object to become
+ * unreserved
+ *
+ * @bo: Pointer to buffer
+ */
+int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo)
+{
+	int ret;
+
+	/*
+	 * In the absense of a wait_unlocked API,
+	 * Use the bo::wu_mutex to avoid triggering livelocks due to
+	 * concurrent use of this function. Note that this use of
+	 * bo::wu_mutex can go away if we change locking order to
+	 * mmap_sem -> bo::reserve.
+	 */
+	ret = mutex_lock_interruptible(&bo->wu_mutex);
+	if (unlikely(ret != 0))
+		return -ERESTARTSYS;
+	if (!ww_mutex_is_locked(&bo->resv->lock))
+		goto out_unlock;
+	ret = ttm_bo_reserve_nolru(bo, true, false, false, NULL);
+	if (unlikely(ret != 0))
+		goto out_unlock;
+	ww_mutex_unlock(&bo->resv->lock);
+
+out_unlock:
+	mutex_unlock(&bo->wu_mutex);
+	return ret;
+}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index ac617f3ecd0c..b249ab9b1eb2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -107,13 +107,28 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/*
 	 * Work around locking order reversal in fault / nopfn
 	 * between mmap_sem and bo_reserve: Perform a trylock operation
-	 * for reserve, and if it fails, retry the fault after scheduling.
+	 * for reserve, and if it fails, retry the fault after waiting
+	 * for the buffer to become unreserved.
 	 */
-
-	ret = ttm_bo_reserve(bo, true, true, false, 0);
+	ret = ttm_bo_reserve(bo, true, true, false, NULL);
 	if (unlikely(ret != 0)) {
-		if (ret == -EBUSY)
-			set_need_resched();
+		if (ret != -EBUSY)
+			return VM_FAULT_NOPAGE;
+
+		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				up_read(&vma->vm_mm->mmap_sem);
+				(void) ttm_bo_wait_unreserved(bo);
+			}
+
+			return VM_FAULT_RETRY;
+		}
+
+		/*
+		 * If we'd want to change locking order to
+		 * mmap_sem -> bo::reserve, we'd use a blocking reserve here
+		 * instead of retrying the fault...
+		 */
 		return VM_FAULT_NOPAGE;
 	}
 
@@ -123,7 +138,6 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		case 0:
 			break;
 		case -EBUSY:
-			set_need_resched();
 		case -ERESTARTSYS:
 			retval = VM_FAULT_NOPAGE;
 			goto out_unlock;