This fixes a regression added with:
commit e9e006f5fcf2bab59149cb38a48a4817c1b538b4
Author: Mike Christie <mchristi@xxxxxxxxxx>
Date: Sun Aug 4 14:10:06 2019 -0500
nbd: fix max number of supported devs
where we can deadlock during device shutdown. The problem will occur if
userpsace has done a NBD_CLEAR_SOCK call, then does close() before the
recv_work work has done its nbd_config_put() call. If recv_work does the
last call then it will do destroy_workqueue which will then be stuck
waiting for the work we are running from.
This fixes the issue by having nbd_start_device_ioctl flush the work
queue on both the failure and success cases and has a refcount on the
nbd_device while it is flushing the work queue.
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Mike Christie <mchristi@xxxxxxxxxx>
---
drivers/block/nbd.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 57532465fb83..f8597d2fb365 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1293,13 +1293,15 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
if (max_part)
bdev->bd_invalidated = 1;
+
+ refcount_inc(&nbd->config_refs);
mutex_unlock(&nbd->config_lock);
ret = wait_event_interruptible(config->recv_wq,
atomic_read(&config->recv_threads) == 0);
- if (ret) {
+ if (ret)
sock_shutdown(nbd);
- flush_workqueue(nbd->recv_workq);
- }
+ flush_workqueue(nbd->recv_workq);
+
mutex_lock(&nbd->config_lock);
nbd_bdev_reset(bdev);
/* user requested, ignore socket errors */
@@ -1307,6 +1309,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
ret = 0;
if (test_bit(NBD_RT_TIMEDOUT, &config->runtime_flags))
ret = -ETIMEDOUT;
+ nbd_config_put(nbd);
return ret;
}
--
2.20.1
