blk-cgroup: prevent rcu_sched detected stalls warnings while iteratin…

…g blkgs

We run a test that create millions of cgroups and blkgs, and then trigger
blkg_destroy_all(). blkg_destroy_all() will hold spin lock for a long
time in such situation. Thus release the lock when a batch of blkgs are
destroyed.

blkcg_activate_policy() and blkcg_deactivate_policy() might have the
same problem, however, as they are basically only called from module
init/exit paths, let's leave them alone for now.

Signed-off-by: Yu Kuai <[email protected]>
Acked-by: Tejun Heo <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

block/blk-cgroup.c

@@ -56,6 +56,8 @@ static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 bool blkcg_debug_stats = false;
 static struct workqueue_struct *blkcg_punt_bio_wq;
 
+#define BLKG_DESTROY_BATCH_SIZE  64
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -422,14 +424,27 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 static void blkg_destroy_all(struct request_queue *q)
 {
 	struct blkcg_gq *blkg, *n;
+	int count = BLKG_DESTROY_BATCH_SIZE;
 
+restart:
 	spin_lock_irq(&q->queue_lock);
 	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);
+
+		/*
+		 * in order to avoid holding the spin lock for too long, release
+		 * it when a batch of blkgs are destroyed.
+		 */
+		if (!(--count)) {
+			count = BLKG_DESTROY_BATCH_SIZE;
+			spin_unlock_irq(&q->queue_lock);
+			cond_resched();
+			goto restart;
+		}
 	}
 
 	q->root_blkg = NULL;