1 files changed, 63 insertions, 24 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4b1a35ab0ea4..37e6cc91d576 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -322,6 +322,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
+	blkg->iostat.blkg = blkg;
 #ifdef CONFIG_BLK_CGROUP_PUNT_BIO
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
@@ -618,12 +619,45 @@ restart:
 	spin_unlock_irq(&q->queue_lock);
 }
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void __blkg_clear_stat(struct blkg_iostat_set *bis)
+{
+	struct blkg_iostat cur = {0};
+	unsigned long flags;
+
+	flags = u64_stats_update_begin_irqsave(&bis->sync);
+	blkg_iostat_set(&bis->cur, &cur);
+	blkg_iostat_set(&bis->last, &cur);
+	u64_stats_update_end_irqrestore(&bis->sync, flags);
+}
+
+static void blkg_clear_stat(struct blkcg_gq *blkg)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu);
+
+		__blkg_clear_stat(s);
+	}
+	__blkg_clear_stat(&blkg->iostat);
+}
+
 static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 			     struct cftype *cftype, u64 val)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
-	int i, cpu;
+	int i;
 
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
@@ -634,18 +668,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	 * anyway.  If you get hit by a race, retry.
 	 */
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		for_each_possible_cpu(cpu) {
-			struct blkg_iostat_set *bis =
-				per_cpu_ptr(blkg->iostat_cpu, cpu);
-			memset(bis, 0, sizeof(*bis));
-
-			/* Re-initialize the cleared blkg_iostat_set */
-			u64_stats_init(&bis->sync);
-			bis->blkg = blkg;
-		}
-		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
-		u64_stats_init(&blkg->iostat.sync);
-
+		blkg_clear_stat(blkg);
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
 
@@ -948,16 +971,6 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(blkg_conf_exit);
 
-static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
-{
-	int i;
-
-	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
-		dst->bytes[i] = src->bytes[i];
-		dst->ios[i] = src->ios[i];
-	}
-}
-
 static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
 {
 	int i;
@@ -1023,7 +1036,19 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
 		struct blkg_iostat cur;
 		unsigned int seq;
 
+		/*
+		 * Order assignment of `next_bisc` from `bisc->lnode.next` in
+		 * llist_for_each_entry_safe and clearing `bisc->lqueued` for
+		 * avoiding to assign `next_bisc` with new next pointer added
+		 * in blk_cgroup_bio_start() in case of re-ordering.
+		 *
+		 * The pair barrier is implied in llist_add() in blk_cgroup_bio_start().
+		 */
+		smp_mb();
+
 		WRITE_ONCE(bisc->lqueued, false);
+		if (bisc == &blkg->iostat)
+			goto propagate_up; /* propagate up to parent only */
 
 		/* fetch the current per-cpu values */
 		do {
@@ -1033,10 +1058,24 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu)
 
 		blkcg_iostat_update(blkg, &cur, &bisc->last);
 
+propagate_up:
 		/* propagate global delta to parent (unless that's root) */
-		if (parent && parent->parent)
+		if (parent && parent->parent) {
 			blkcg_iostat_update(parent, &blkg->iostat.cur,
 					    &blkg->iostat.last);
+			/*
+			 * Queue parent->iostat to its blkcg's lockless
+			 * list to propagate up to the grandparent if the
+			 * iostat hasn't been queued yet.
+			 */
+			if (!parent->iostat.lqueued) {
+				struct llist_head *plhead;
+
+				plhead = per_cpu_ptr(parent->blkcg->lhead, cpu);
+				llist_add(&parent->iostat.lnode, plhead);
+				parent->iostat.lqueued = true;
+			}
+		}
 	}
 	raw_spin_unlock_irqrestore(&blkg_stat_lock, flags);
 out: