md: fix deadlock between mddev_suspend() and md_write_start()
If mddev_suspend() races with md_write_start() we can deadlock
with mddev_suspend() waiting for the request that is currently
in md_write_start() to complete the ->make_request() call,
and md_write_start() waiting for the metadata to be updated
to mark the array as 'dirty'.
As metadata updates done by md_check_recovery() only happen then
the mddev_lock() can be claimed, and as mddev_suspend() is often
called with the lock held, these threads wait indefinitely for each
other.
We fix this by having md_write_start() abort if mddev_suspend()
is happening, and ->make_request() aborts if md_write_start()
aborted.
md_make_request() can detect this abort, decrease the ->active_io
count, and wait for mddev_suspend().
Reported-by: Nix <nix@esperi.org.uk>
Fix: 68866e425be2(MD: no sync IO while suspended)
Cc: stable@vger.kernel.org
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index d6c0bc7..94d9ae9 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -548,7 +548,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
bio_endio(bio);
}
-static void raid0_make_request(struct mddev *mddev, struct bio *bio)
+static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
{
struct strip_zone *zone;
struct md_rdev *tmp_dev;
@@ -559,12 +559,12 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
- return;
+ return true;
}
if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
raid0_handle_discard(mddev, bio);
- return;
+ return true;
}
bio_sector = bio->bi_iter.bi_sector;
@@ -599,6 +599,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
mddev_check_writesame(mddev, bio);
mddev_check_write_zeroes(mddev, bio);
generic_make_request(bio);
+ return true;
}
static void raid0_status(struct seq_file *seq, struct mddev *mddev)