1 files changed, 100 insertions, 54 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ff93c385ba5a..9ed93d91d754 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -218,8 +218,7 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 
 	/* as long as there are pending bios, @blkg can't go away */
 	spin_lock(&blkg->async_bio_lock);
-	bio_list_merge(&bios, &blkg->async_bios);
-	bio_list_init(&blkg->async_bios);
+	bio_list_merge_init(&bios, &blkg->async_bios);
 	spin_unlock(&blkg->async_bio_lock);
 
 	/* start plug only when bio_list contains at least 2 bios */
@@ -323,6 +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);
@@ -619,12 +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);
@@ -635,18 +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];
 
@@ -949,16 +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;
@@ -1024,7 +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 {
@@ -1034,10 +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:
@@ -1100,6 +1138,7 @@ static void blkcg_fill_root_iostats(void)
 		blkg_iostat_set(&blkg->iostat.cur, &tmp);
 		u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
 	}
+	class_dev_iter_exit(&iter);
 }
 
 static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s)
@@ -1286,10 +1325,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css)
 	struct blkcg *blkcg = css_to_blkcg(blkcg_css);
 
 	do {
+		struct blkcg *parent;
+
 		if (!refcount_dec_and_test(&blkcg->online_pin))
 			break;
+
+		parent = blkcg_parent(blkcg);
 		blkcg_destroy_blkgs(blkcg);
-		blkcg = blkcg_parent(blkcg);
+		blkcg = parent;
 	} while (blkcg);
 }
 
@@ -1409,15 +1452,17 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
+void blkg_init_queue(struct request_queue *q)
+{
+	INIT_LIST_HEAD(&q->blkg_list);
+	mutex_init(&q->blkcg_mutex);
+}
+
 int blkcg_init_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *new_blkg, *blkg;
 	bool preloaded;
-	int ret;
-
-	INIT_LIST_HEAD(&q->blkg_list);
-	mutex_init(&q->blkcg_mutex);
 
 	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
@@ -1437,21 +1482,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_ioprio_init(disk);
-	if (ret)
-		goto err_destroy_all;
-
-	ret = blk_throtl_init(disk);
-	if (ret)
-		goto err_ioprio_exit;
-
 	return 0;
 
-err_ioprio_exit:
-	blk_ioprio_exit(disk);
-err_destroy_all:
-	blkg_destroy_all(disk);
-	return ret;
 err_unlock:
 	spin_unlock_irq(&q->queue_lock);
 	if (preloaded)
@@ -1514,13 +1546,22 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	struct request_queue *q = disk->queue;
 	struct blkg_policy_data *pd_prealloc = NULL;
 	struct blkcg_gq *blkg, *pinned_blkg = NULL;
+	unsigned int memflags;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
+	/*
+	 * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn,
+	 * for example, ioprio. Such policy will work on blkcg level, not disk
+	 * level, and don't need to be activated.
+	 */
+	if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn))
+		return -EINVAL;
+
 	if (queue_is_mq(q))
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 retry:
 	spin_lock_irq(&q->queue_lock);
 
@@ -1584,7 +1625,7 @@ retry:
 	spin_unlock_irq(&q->queue_lock);
 out:
 	if (queue_is_mq(q))
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 	if (pinned_blkg)
 		blkg_put(pinned_blkg);
 	if (pd_prealloc)
@@ -1628,12 +1669,13 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 {
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
+	unsigned int memflags;
 
 	if (!blkcg_policy_enabled(q, pol))
 		return;
 
 	if (queue_is_mq(q))
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 
 	mutex_lock(&q->blkcg_mutex);
 	spin_lock_irq(&q->queue_lock);
@@ -1657,7 +1699,7 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	mutex_unlock(&q->blkcg_mutex);
 
 	if (queue_is_mq(q))
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 
@@ -1698,9 +1740,12 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 		goto err_unlock;
 	}
 
-	/* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */
+	/*
+	 * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy
+	 * without pd_alloc_fn/pd_free_fn can't be activated.
+	 */
 	if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
-		(!pol->pd_alloc_fn ^ !pol->pd_free_fn))
+	    (!pol->pd_alloc_fn ^ !pol->pd_free_fn))
 		goto err_unlock;
 
 	/* register @pol */
@@ -1846,7 +1891,7 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
 	unsigned long pflags;
 	bool clamp;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	u64 exp;
 	u64 delay_nsec = 0;
 	int tok;
@@ -2147,12 +2192,13 @@ void blk_cgroup_bio_start(struct bio *bio)
 
 bool blk_cgroup_congested(void)
 {
-	struct cgroup_subsys_state *css;
+	struct blkcg *blkcg;
 	bool ret = false;
 
 	rcu_read_lock();
-	for (css = blkcg_css(); css; css = css->parent) {
-		if (atomic_read(&css->cgroup->congestion_count)) {
+	for (blkcg = css_to_blkcg(blkcg_css()); blkcg;
+	     blkcg = blkcg_parent(blkcg)) {
+		if (atomic_read(&blkcg->congestion_count)) {
 			ret = true;
 			break;
 		}