blk_mq_freeze_queue() never terminates if one or more bios are on the plug
list and if the block device driver defines a .submit_bio() method.
This is the case for device mapper drivers. The deadlock happens because
blk_mq_freeze_queue() waits for q_usage_counter to drop to zero, because
a queue reference is held by bios on the plug list and because the
__bio_queue_enter() call in __submit_bio() waits for the queue to be
unfrozen.
This patch fixes the following deadlock:
Workqueue: dm-51_zwplugs blk_zone_wplug_bio_work
Call trace:
__schedule+0xb08/0x1160
schedule+0x48/0xc8
__bio_queue_enter+0xcc/0x1d0
__submit_bio+0x100/0x1b0
submit_bio_noacct_nocheck+0x230/0x49c
blk_zone_wplug_bio_work+0x168/0x250
process_one_work+0x26c/0x65c
worker_thread+0x33c/0x498
kthread+0x110/0x134
ret_from_fork+0x10/0x20
Call trace:
__switch_to+0x230/0x410
__schedule+0xb08/0x1160
schedule+0x48/0xc8
blk_mq_freeze_queue_wait+0x78/0xb8
blk_mq_freeze_queue+0x90/0xa4
queue_attr_store+0x7c/0xf0
sysfs_kf_write+0x98/0xc8
kernfs_fop_write_iter+0x12c/0x1d4
vfs_write+0x340/0x3ac
ksys_write+0x78/0xe8
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Damien Le Moal <dlemoal@xxxxxxxxxx>
Cc: Yu Kuai <yukuai1@xxxxxxxxxxxxxxx>
Cc: Ming Lei <ming.lei@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Fixes: dd291d77cc90 ("block: Introduce zone write plugging")
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
---
Changes compared to v1: fixed a race condition. Call bio_zone_write_plugging()
only before submitting the bio and not after it has been submitted.
block/blk-core.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index b862c66018f2..713fb3865260 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -621,6 +621,13 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
return BLK_STS_OK;
}
+/*
+ * Do not call bio_queue_enter() if the BIO_ZONE_WRITE_PLUGGING flag has been
+ * set because this causes blk_mq_freeze_queue() to deadlock if
+ * blk_zone_wplug_bio_work() submits a bio. Calling bio_queue_enter() for bios
+ * on the plug list is not necessary since a q_usage_counter reference is held
+ * while a bio is on the plug list.
+ */
static void __submit_bio(struct bio *bio)
{
/* If plug is not used, add new plug here to cache nsecs time. */
@@ -633,8 +640,12 @@ static void __submit_bio(struct bio *bio)
if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) {
blk_mq_submit_bio(bio);
- } else if (likely(bio_queue_enter(bio) == 0)) {
+ } else {
struct gendisk *disk = bio->bi_bdev->bd_disk;
+ bool zwp = bio_zone_write_plugging(bio);
+
+ if (unlikely(!zwp && bio_queue_enter(bio) != 0))
+ goto finish_plug;
if ((bio->bi_opf & REQ_POLLED) &&
!(disk->queue->limits.features & BLK_FEAT_POLL)) {
@@ -643,9 +654,12 @@ static void __submit_bio(struct bio *bio)
} else {
disk->fops->submit_bio(bio);
}
- blk_queue_exit(disk->queue);
+
+ if (!zwp)
+ blk_queue_exit(disk->queue);
}
+finish_plug:
blk_finish_plug(&plug);
}
