dm mpath: avoid that path removal can trigger an infinite loop

If blk_get_request() fails, check whether the failure is due to a path
being removed.  If that is the case, fail the path by triggering a call
to fail_path().  This avoids that the following scenario can be
encountered while removing paths:
* CPU usage of a kworker thread jumps to 100%.
* Removing the DM device becomes impossible.

Delay requeueing if blk_get_request() returns -EBUSY or -EWOULDBLOCK,
and the queue is not dying, because in these cases immediate requeuing
is inappropriate.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This commit is contained in:
Bart Van Assche 2017-04-27 10:11:15 -07:00 committed by Mike Snitzer
parent 89bfce763e
commit 7083abbbfc
1 changed files with 11 additions and 4 deletions

View File

@ -489,6 +489,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
struct pgpath *pgpath;
struct block_device *bdev;
struct dm_mpath_io *mpio = get_mpio(map_context);
struct request_queue *q;
struct request *clone;
/* Do we need to select a new pgpath? */
@ -511,12 +512,18 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
mpio->nr_bytes = nr_bytes;
bdev = pgpath->path.dev->bdev;
clone = blk_get_request(bdev_get_queue(bdev),
rq->cmd_flags | REQ_NOMERGE,
GFP_ATOMIC);
q = bdev_get_queue(bdev);
clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE, GFP_ATOMIC);
if (IS_ERR(clone)) {
/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
bool queue_dying = blk_queue_dying(q);
DMERR_LIMIT("blk_get_request() returned %ld%s - requeuing",
PTR_ERR(clone), queue_dying ? " (path offline)" : "");
if (queue_dying) {
atomic_inc(&m->pg_init_in_progress);
activate_or_offline_path(pgpath);
return DM_MAPIO_REQUEUE;
}
return DM_MAPIO_DELAY_REQUEUE;
}
clone->bio = clone->biotail = NULL;