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 patch 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 because in these cases immediate requeuing is
inappropriate.
Signed-off-by: Bart Van Assche <bart.vanassche@xxxxxxxxxxx>
Cc: Hannes Reinecke <hare@xxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
---
drivers/md/dm-mpath.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index eff7ecea1d2a..cc41e34607c3 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -490,6 +490,7 @@ 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? */
@@ -512,13 +513,19 @@ 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 */
- return r;
+ pr_debug("blk_get_request() returned %ld%s - requeuing\n",
+ PTR_ERR(clone), blk_queue_dying(q) ?
+ " (path offline)" : "");
+ if (blk_queue_dying(q)) {
+ 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;
clone->rq_disk = bdev->bd_disk;
--
2.12.2