1 files changed, 33 insertions, 20 deletions

diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index e815d165cccc..89fe85778115 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -94,8 +94,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 				  struct btrfs_block_group *block_group)
 {
 	lockdep_assert_held(&discard_ctl->lock);
-	if (!btrfs_run_discard_work(discard_ctl))
-		return;
 
 	if (list_empty(&block_group->discard_list) ||
 	    block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) {
@@ -118,6 +116,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl,
 	if (!btrfs_is_block_group_data_only(block_group))
 		return;
 
+	if (!btrfs_run_discard_work(discard_ctl))
+		return;
+
 	spin_lock(&discard_ctl->lock);
 	__add_to_discard_list(discard_ctl, block_group);
 	spin_unlock(&discard_ctl->lock);
@@ -167,13 +168,7 @@ static bool remove_from_discard_list(struct btrfs_discard_ctl *discard_ctl,
 	block_group->discard_eligible_time = 0;
 	queued = !list_empty(&block_group->discard_list);
 	list_del_init(&block_group->discard_list);
-	/*
-	 * If the block group is currently running in the discard workfn, we
-	 * don't want to deref it, since it's still being used by the workfn.
-	 * The workfn will notice this case and deref the block group when it is
-	 * finished.
-	 */
-	if (queued && !running)
+	if (queued)
 		btrfs_put_block_group(block_group);
 
 	spin_unlock(&discard_ctl->lock);
@@ -250,6 +245,20 @@ again:
 		    block_group->used != 0) {
 			if (btrfs_is_block_group_data_only(block_group)) {
 				__add_to_discard_list(discard_ctl, block_group);
+				/*
+				 * The block group must have been moved to other
+				 * discard list even if discard was disabled in
+				 * the meantime or a transaction abort happened,
+				 * otherwise we can end up in an infinite loop,
+				 * always jumping into the 'again' label and
+				 * keep getting this block group over and over
+				 * in case there are no other block groups in
+				 * the discard lists.
+				 */
+				ASSERT(block_group->discard_index !=
+				       BTRFS_DISCARD_INDEX_UNUSED,
+				       "discard_index=%d",
+				       block_group->discard_index);
 			} else {
 				list_del_init(&block_group->discard_list);
 				btrfs_put_block_group(block_group);
@@ -260,9 +269,10 @@ again:
 			block_group->discard_cursor = block_group->start;
 			block_group->discard_state = BTRFS_DISCARD_EXTENTS;
 		}
-		discard_ctl->block_group = block_group;
 	}
 	if (block_group) {
+		btrfs_get_block_group(block_group);
+		discard_ctl->block_group = block_group;
 		*discard_state = block_group->discard_state;
 		*discard_index = block_group->discard_index;
 	}
@@ -493,9 +503,20 @@ static void btrfs_discard_workfn(struct work_struct *work)
 
 	block_group = peek_discard_list(discard_ctl, &discard_state,
 					&discard_index, now);
-	if (!block_group || !btrfs_run_discard_work(discard_ctl))
+	if (!block_group)
+		return;
+	if (!btrfs_run_discard_work(discard_ctl)) {
+		spin_lock(&discard_ctl->lock);
+		btrfs_put_block_group(block_group);
+		discard_ctl->block_group = NULL;
+		spin_unlock(&discard_ctl->lock);
 		return;
+	}
 	if (now < block_group->discard_eligible_time) {
+		spin_lock(&discard_ctl->lock);
+		btrfs_put_block_group(block_group);
+		discard_ctl->block_group = NULL;
+		spin_unlock(&discard_ctl->lock);
 		btrfs_discard_schedule_work(discard_ctl, false);
 		return;
 	}
@@ -547,15 +568,7 @@ static void btrfs_discard_workfn(struct work_struct *work)
 	spin_lock(&discard_ctl->lock);
 	discard_ctl->prev_discard = trimmed;
 	discard_ctl->prev_discard_time = now;
-	/*
-	 * If the block group was removed from the discard list while it was
-	 * running in this workfn, then we didn't deref it, since this function
-	 * still owned that reference. But we set the discard_ctl->block_group
-	 * back to NULL, so we can use that condition to know that now we need
-	 * to deref the block_group.
-	 */
-	if (discard_ctl->block_group == NULL)
-		btrfs_put_block_group(block_group);
+	btrfs_put_block_group(block_group);
 	discard_ctl->block_group = NULL;
 	__btrfs_discard_schedule_work(discard_ctl, now, false);
 	spin_unlock(&discard_ctl->lock);