Revert "dm mirror: use all available legs on multiple failures"

snitm · snitm · commit cd15fb64ee56 · 2017-06-15T08:39:15.000-04:00
This reverts commit 12a7cf5. This commit apparently attempted to fix an issue that didn't really exist, furthermore: this commit is the source of deadlocks and crashes seen in multiple cases related to failing the primary mirror dev while syncing. Reported-by: Jonathan Brassow <jbrassow@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
@@ -145,6 +145,7 @@ static void dispatch_bios(void *context, struct bio_list *bio_list)
 
 struct dm_raid1_bio_record {
 	struct mirror *m;
+	/* if details->bi_bdev == NULL, details were not saved */
 	struct dm_bio_details details;
 	region_t write_region;
 };
@@ -1198,6 +1199,8 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 	struct dm_raid1_bio_record *bio_record =
 	  dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record));
 
+	bio_record->details.bi_bdev = NULL;
+
 	if (rw == WRITE) {
 		/* Save region for mirror_end_io() handler */
 		bio_record->write_region = dm_rh_bio_to_region(ms->rh, bio);
@@ -1256,12 +1259,22 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 	}
 
 	if (error == -EOPNOTSUPP)
-		return error;
+		goto out;
 
 	if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
-		return error;
+		goto out;
 
 	if (unlikely(error)) {
+		if (!bio_record->details.bi_bdev) {
+			/*
+			 * There wasn't enough memory to record necessary
+			 * information for a retry or there was no other
+			 * mirror in-sync.
+			 */
+			DMERR_LIMIT("Mirror read failed.");
+			return -EIO;
+		}
+
 		m = bio_record->m;
 
 		DMERR("Mirror read failed from %s. Trying alternative device.",
@@ -1277,6 +1290,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 			bd = &bio_record->details;
 
 			dm_bio_restore(bd, bio);
+			bio_record->details.bi_bdev = NULL;
 			bio->bi_error = 0;
 
 			queue_bio(ms, bio, rw);
@@ -1285,6 +1299,9 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 		DMERR("All replicated volumes dead, failing I/O");
 	}
 
+out:
+	bio_record->details.bi_bdev = NULL;
+
 	return error;
 }
 
