dm: fix queue start/stop imbalance under suspend/load/resume races

When suspend and load run concurrently, before q->mq_ops is set in
blk_mq_init_allocated_queue(), __dm_suspend() skip dm_stop_queue(). As a
result, the queue's quiesce depth is not incremented.

Later, once table load has finished and __dm_resume() runs, which triggers
q->quiesce_depth ==0 warning in blk_mq_unquiesce_queue():
Call Trace:
 <TASK>
 dm_start_queue+0x16/0x20 [dm_mod]
 __dm_resume+0xac/0xb0 [dm_mod]
 dm_resume+0x12d/0x150 [dm_mod]
 do_resume+0x2c2/0x420 [dm_mod]
 dev_suspend+0x30/0x130 [dm_mod]
 ctl_ioctl+0x402/0x570 [dm_mod]
 dm_ctl_ioctl+0x23/0x30 [dm_mod]

Fix this by explicitly tracking whether the request queue was
stopped in __dm_suspend() via a new DMF_QUEUE_STOPPED flag.
Only call dm_start_queue() in __dm_resume() if the queue was
actually stopped.

Fixes: e70feb8b3e68 ("blk-mq: support concurrent queue quiesce/unquiesce")
Cc: stable@vger.kernel.org
Signed-off-by: Zheng Qixing <zhengqixing@huawei.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index c889332e533bcaf08479b4ed8e3078d864c2b797..0070e4462ee2fe6d832748e1e8b8b3a1b2039c59 100644 (file)
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -162,6 +162,7 @@ struct mapped_device {
 #define DMF_SUSPENDED_INTERNALLY 7
 #define DMF_POST_SUSPENDING 8
 #define DMF_EMULATE_ZONE_APPEND 9
+#define DMF_QUEUE_STOPPED 10
 
 static inline sector_t dm_get_size(struct mapped_device *md)
 {

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a44e8c2dccee4ed2a41614d037e824afc79762e4..7222f20c1a83215b8bb4502258a0503a87919f00 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2960,8 +2960,10 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
         * Stop md->queue before flushing md->wq in case request-based
         * dm defers requests to md->wq from md->queue.
         */
-       if (dm_request_based(md))
+       if (dm_request_based(md)) {
                dm_stop_queue(md->queue);
+               set_bit(DMF_QUEUE_STOPPED, &md->flags);
+       }
 
        flush_workqueue(md->wq);
 
@@ -2983,7 +2985,7 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
        if (r < 0) {
                dm_queue_flush(md);
 
-               if (dm_request_based(md))
+               if (test_and_clear_bit(DMF_QUEUE_STOPPED, &md->flags))
                        dm_start_queue(md->queue);
 
                unlock_fs(md);
@@ -3067,7 +3069,7 @@ static int __dm_resume(struct mapped_device *md, struct dm_table *map)
         * so that mapping of targets can work correctly.
         * Request-based dm is queueing the deferred I/Os in its request_queue.
         */
-       if (dm_request_based(md))
+       if (test_and_clear_bit(DMF_QUEUE_STOPPED, &md->flags))
                dm_start_queue(md->queue);
 
        unlock_fs(md);