blk-cgroup: don't nest queue_lock under blkcg->lock in blkcg_destroy_blkgs()

The correct lock order is q->queue_lock before blkcg->lock, and in order
to prevent deadlock from blkcg_destroy_blkgs(), trylock is used for
q->queue_lock while blkcg->lock is already held, this is hacky.

Refactor blkcg_destroy_blkgs() to hold blkcg->lock only long enough to
get the first blkg and then release it. Then take q->queue_lock and
blkcg->lock in the correct order to destroy the blkg. This is a very cold
path, so the extra lock/unlock cycles are acceptable.

Also prepare to convert protecting blkcg with blkcg_mutex instead of
queue_lock.

Signed-off-by: Yu Kuai <yukuai@fygo.io>
Link: https://patch.msgid.link/00b03cf74a9937cb4d6dd67a189ddc00a3de0451.1780621988.git.yukuai@fygo.io
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 26 insertions, 19 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e1bde48852ae..d2a1f5903f24 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1239,6 +1239,21 @@ struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css)
  *    This finally frees the blkcg.
  */
 
+static struct blkcg_gq *blkcg_get_first_blkg(struct blkcg *blkcg)
+{
+	struct blkcg_gq *blkg = NULL;
+
+	spin_lock_irq(&blkcg->lock);
+	if (!hlist_empty(&blkcg->blkg_list)) {
+		blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq,
+				   blkcg_node);
+		blkg_get(blkg);
+	}
+	spin_unlock_irq(&blkcg->lock);
+
+	return blkg;
+}
+
 /**
  * blkcg_destroy_blkgs - responsible for shooting down blkgs
  * @blkcg: blkcg of interest
@@ -1252,32 +1267,24 @@ struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css)
  */
 static void blkcg_destroy_blkgs(struct blkcg *blkcg)
 {
-	might_sleep();
+	struct blkcg_gq *blkg;
 
-	spin_lock_irq(&blkcg->lock);
+	might_sleep();
 
-	while (!hlist_empty(&blkcg->blkg_list)) {
-		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
-						struct blkcg_gq, blkcg_node);
+	while ((blkg = blkcg_get_first_blkg(blkcg))) {
 		struct request_queue *q = blkg->q;
 
-		if (need_resched() || !spin_trylock(&q->queue_lock)) {
-			/*
-			 * Given that the system can accumulate a huge number
-			 * of blkgs in pathological cases, check to see if we
-			 * need to rescheduling to avoid softlockup.
-			 */
-			spin_unlock_irq(&blkcg->lock);
-			cond_resched();
-			spin_lock_irq(&blkcg->lock);
-			continue;
-		}
+		spin_lock_irq(&q->queue_lock);
+		spin_lock(&blkcg->lock);
 
 		blkg_destroy(blkg);
-		spin_unlock(&q->queue_lock);
-	}
 
-	spin_unlock_irq(&blkcg->lock);
+		spin_unlock(&blkcg->lock);
+		spin_unlock_irq(&q->queue_lock);
+
+		blkg_put(blkg);
+		cond_resched();
+	}
 }
 
 /**