dm: dec_pending needs locking to save error value

Multiple instances of dec_pending() can run concurrently so a lock is
needed when it saves the first error code.

I have never experienced actual problem without locking and just found
this during code inspection while implementing the barrier support
patch for request-based dm.

This patch adds the locking.
I've done compile, boot and basic I/O testings.

Cc: stable@kernel.org
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

1 files changed, 8 insertions, 2 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c5f9918dab24..724efc63904d 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -47,6 +47,7 @@ struct dm_io {
         atomic_t io_count;
         struct bio *bio;
         unsigned long start_time;
+        spinlock_t endio_lock;
 };
 
 /*
@@ -578,8 +579,12 @@ static void dec_pending(struct dm_io *io, int error)
         struct mapped_device *md = io->md;
 
         /* Push-back supersedes any I/O errors */
-        if (error && !(io->error > 0 && __noflush_suspending(md)))
-                io->error = error;
+        if (unlikely(error)) {
+                spin_lock_irqsave(&io->endio_lock, flags);
+                if (!(io->error > 0 && __noflush_suspending(md)))
+                        io->error = error;
+                spin_unlock_irqrestore(&io->endio_lock, flags);
+        }
 
         if (atomic_dec_and_test(&io->io_count)) {
                 if (io->error == DM_ENDIO_REQUEUE) {
@@ -1226,6 +1231,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
         atomic_set(&ci.io->io_count, 1);
         ci.io->bio = bio;
         ci.io->md = md;
+        spin_lock_init(&ci.io->endio_lock);
         ci.sector = bio->bi_sector;
         ci.sector_count = bio_sectors(bio);
         if (unlikely(bio_empty_barrier(bio)))