[PATCH 08/10] blk-mq: fix blk_mq_tags double free while nr_requests grown

[Yu Kuai]

From: Yu Kuai <yukuai3@xxxxxxxxxx>

In the case user trigger tags grow by queue sysfs attribute nr_requests,
hctx->sched_tags will be freed directly and replaced with a new
allocated tags, see blk_mq_tag_update_depth().

The problem is that hctx->sched_tags is from elevator->et->tags, while
et->tags is still the freed tags, hence later elevator exist will try to
free the tags again, causing kernel panic.

Fix this problem by using new allocated elevator_tags, also convert
blk_mq_update_nr_requests to void since this helper will never fail now.

Meanwhile, there is a longterm problem can be fixed as well:

If blk_mq_tag_update_depth() succeed for previous hctx, then bitmap depth
is updated, however, if following hctx failed, q->nr_requests is not
updated and the previous hctx->sched_tags endup bigger than q->nr_requests.

Fixes: f5a6604f7a44 ("block: fix lockdep warning caused by lock dependency in elv_iosched_store")
Fixes: e3a2b3f931f5 ("blk-mq: allow changing of queue depth through sysfs")
Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
---
 block/blk-mq.c    | 19 ++++++-------------
 block/blk-mq.h    |  4 +++-
 block/blk-sysfs.c | 21 ++++++++++++++-------
 3 files changed, 23 insertions(+), 21 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 11c8baebb9a0..e9f037a25fe3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4917,12 +4917,12 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 }
 EXPORT_SYMBOL(blk_mq_free_tag_set);
 
-int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
+void blk_mq_update_nr_requests(struct request_queue *q,
+			       struct elevator_tags *et, unsigned int nr)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
-	int ret = 0;
 
 	blk_mq_quiesce_queue(q);
 
@@ -4946,24 +4946,17 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 				nr - hctx->sched_tags->nr_reserved_tags);
 		}
 	} else {
-		queue_for_each_hw_ctx(q, hctx, i) {
-			if (!hctx->tags)
-				continue;
-			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
-						      nr);
-			if (ret)
-				goto out;
-		}
+		blk_mq_free_sched_tags(q->elevator->et, set);
+		queue_for_each_hw_ctx(q, hctx, i)
+			hctx->sched_tags = et->tags[i];
+		q->elevator->et = et;
 	}
 
 	q->nr_requests = nr;
 	if (q->elevator && q->elevator->type->ops.depth_updated)
 		q->elevator->type->ops.depth_updated(q);
 
-out:
 	blk_mq_unquiesce_queue(q);
-
-	return ret;
 }
 
 /*
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 731f4578d9a8..98740f9c204e 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -6,6 +6,7 @@
 #include "blk-stat.h"
 
 struct blk_mq_tag_set;
+struct elevator_tags;
 
 struct blk_mq_ctxs {
 	struct kobject kobj;
@@ -45,7 +46,8 @@ void blk_mq_submit_bio(struct bio *bio);
 int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
 		unsigned int flags);
 void blk_mq_exit_queue(struct request_queue *q);
-int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
+void blk_mq_update_nr_requests(struct request_queue *q,
+			       struct elevator_tags *et, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *,
 			     bool);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 37eae7927b45..848648456255 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -64,11 +64,12 @@ static ssize_t queue_requests_show(struct gendisk *disk, char *page)
 static ssize_t
 queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 {
-	unsigned long nr;
-	int ret, err;
-	unsigned int memflags;
 	struct request_queue *q = disk->queue;
 	struct blk_mq_tag_set *set = q->tag_set;
+	struct elevator_tags *et = NULL;
+	unsigned int memflags;
+	unsigned long nr;
+	int ret;
 
 	ret = queue_var_store(&nr, page, count);
 	if (ret < 0)
@@ -90,12 +91,18 @@ queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 		goto unlock;
 	}
 
+	if (q->elevator && nr > q->elevator->et->nr_requests) {
+		/* allocate memory before freezing queue to prevent deadlock */
+		et = blk_mq_alloc_sched_tags(set, q->nr_hw_queues, nr);
+		if (!et) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
+	}
+
 	memflags = blk_mq_freeze_queue(q);
 	mutex_lock(&q->elevator_lock);
-	err = blk_mq_update_nr_requests(disk->queue, nr);
-	if (err)
-		ret = err;
-
+	blk_mq_update_nr_requests(disk->queue, et, nr);
 	mutex_unlock(&q->elevator_lock);
 	blk_mq_unfreeze_queue(q, memflags);
 
-- 
2.39.2