From: Akilesh Kailash akailash@google.com
stable inclusion from linux-4.19.169 commit aef593d2c87598839d6200772c5aee8a9ecdcd9f
--------------------------------
commit fcc42338375a1e67b8568dbb558f8b784d0f3b01 upstream.
If the origin device has a volatile write-back cache and the following events occur:
1: After finishing merge operation of one set of exceptions, merge_callback() is invoked. 2: Update the metadata in COW device tracking the merge completion. This update to COW device is flushed cleanly. 3: System crashes and the origin device's cache where the recent merge was completed has not been flushed.
During the next cycle when we read the metadata from the COW device, we will skip reading those metadata whose merge was completed in step (1). This will lead to data loss/corruption.
To address this, flush the origin device post merge IO before updating the metadata.
Cc: stable@vger.kernel.org Signed-off-by: Akilesh Kailash akailash@google.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: Cheng Jian cj.chengjian@huawei.com --- drivers/md/dm-snap.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index d3f28a9e3fd9..9e930a150aa2 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -137,6 +137,11 @@ struct dm_snapshot { * for them to be committed. */ struct bio_list bios_queued_during_merge; + + /* + * Flush data after merge. + */ + struct bio flush_bio; };
/* @@ -1061,6 +1066,17 @@ static void snapshot_merge_next_chunks(struct dm_snapshot *s)
static void error_bios(struct bio *bio);
+static int flush_data(struct dm_snapshot *s) +{ + struct bio *flush_bio = &s->flush_bio; + + bio_reset(flush_bio); + bio_set_dev(flush_bio, s->origin->bdev); + flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + return submit_bio_wait(flush_bio); +} + static void merge_callback(int read_err, unsigned long write_err, void *context) { struct dm_snapshot *s = context; @@ -1074,6 +1090,11 @@ static void merge_callback(int read_err, unsigned long write_err, void *context) goto shut; }
+ if (flush_data(s) < 0) { + DMERR("Flush after merge failed: shutting down merge"); + goto shut; + } + if (s->store->type->commit_merge(s->store, s->num_merging_chunks) < 0) { DMERR("Write error in exception store: shutting down merge"); @@ -1198,6 +1219,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) s->first_merging_chunk = 0; s->num_merging_chunks = 0; bio_list_init(&s->bios_queued_during_merge); + bio_init(&s->flush_bio, NULL, 0);
/* Allocate hash table for COW data */ if (init_hash_tables(s)) { @@ -1391,6 +1413,8 @@ static void snapshot_dtr(struct dm_target *ti)
mutex_destroy(&s->lock);
+ bio_uninit(&s->flush_bio); + dm_put_device(ti, s->cow);
dm_put_device(ti, s->origin);