dm: skip second flush on bio unsupported error

When processing barriers, skip the second flush if processing the bio
failed with -EOPNOTSUPP.  This can happen with discard+barrier requests.
If the device doesn't support discard, there would be two useless
SYNCHRONIZE CACHE commands.  The first dm_flush cannot be so easily
optimized out, so we leave it there.

Previously, -EOPNOTSUPP could be received in dec_pending only with empty
barriers and we ignored that error, assuming the device not supporting
cache flushes has cache always consistent.  With the addition of discard
barriers, this -EOPNOTSUPP can also be generated by discards and we
must record it in md->barrier_error for process_barrier.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

1 files changed, 13 insertions, 2 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a503b95ecbf..f3cc5d99fe8 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -639,8 +639,14 @@ static void dec_pending(struct dm_io *io, int error)
                          * There can be just one barrier request so we use
                          * a per-device variable for error reporting.
                          * Note that you can't touch the bio after end_io_acct
+                         *
+                         * We ignore -EOPNOTSUPP for empty flush reported by
+                         * underlying devices. We assume that if the device
+                         * doesn't support empty barriers, it doesn't need
+                         * cache flushing commands.
                          */
-                        if (!md->barrier_error && io_error != -EOPNOTSUPP)
+                        if (!md->barrier_error &&
+                            !(bio_empty_barrier(bio) && io_error == -EOPNOTSUPP))
                                 md->barrier_error = io_error;
                         end_io_acct(io);
                         free_io(md, io);
@@ -2284,7 +2290,12 @@ static void process_barrier(struct mapped_device *md, struct bio *bio)
 
         if (!bio_empty_barrier(bio)) {
                 __split_and_process_bio(md, bio);
-                dm_flush(md);
+                /*
+                 * If the request isn't supported, don't waste time with
+                 * the second flush.
+                 */
+                if (md->barrier_error != -EOPNOTSUPP)
+                        dm_flush(md);
         }
 
         if (md->barrier_error != DM_ENDIO_REQUEUE)