bcache: fix for data collapse after re-attaching an attached device

[ Upstream commit 73ac105 ]

back-end device sdm has already attached a cache_set with ID
f67ebe1f-f8bc-4d73-bfe5-9dc88607f119, then try to attach with
another cache set, and it returns with an error:
[root]# cd /sys/block/sdm/bcache
[root]# echo 5ccd0a63-148e-48b8-afa2-aca9cbd6279f > attach
-bash: echo: write error: Invalid argument

After that, execute a command to modify the label of bcache
device:
[root]# echo data_disk1 > label

Then we reboot the system, when the system power on, the back-end
device can not attach to cache_set, a messages show in the log:
Feb  5 12:05:52 ceph152 kernel: [922385.508498] bcache:
bch_cached_dev_attach() couldn't find uuid for sdm in set

In sysfs_attach(), dc->sb.set_uuid was assigned to the value
which input through sysfs, no matter whether it is success
or not in bch_cached_dev_attach(). For example, If the back-end
device has already attached to an cache set, bch_cached_dev_attach()
would fail, but dc->sb.set_uuid was changed. Then modify the
label of bcache device, it will call bch_write_bdev_super(),
which would write the dc->sb.set_uuid to the super block, so we
record a wrong cache set ID in the super block, after the system
reboot, the cache set couldn't find the uuid of the back-end
device, so the bcache device couldn't exist and use any more.

In this patch, we don't assigned cache set ID to dc->sb.set_uuid
in sysfs_attach() directly, but input it into bch_cached_dev_attach(),
and assigned dc->sb.set_uuid to the cache set ID after the back-end
device attached to the cache set successful.

Signed-off-by: Tang Junhui <[email protected]>
Reviewed-by: Michael Lyle <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Tang Junhui

drivers/md/bcache/bcache.h

@@ -906,7 +906,7 @@ void bcache_write_super(struct cache_set *);
 
 int bch_flash_dev_create(struct cache_set *c, uint64_t size);
 
-int bch_cached_dev_attach(struct cached_dev *, struct cache_set *);
+int bch_cached_dev_attach(struct cached_dev *, struct cache_set *, uint8_t *);
 void bch_cached_dev_detach(struct cached_dev *);
 void bch_cached_dev_run(struct cached_dev *);
 void bcache_device_stop(struct bcache_device *);

drivers/md/bcache/super.c

@@ -939,7 +939,8 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 	cached_dev_put(dc);
 }
 
-int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
+int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
+			  uint8_t *set_uuid)
 {
 	uint32_t rtime = cpu_to_le32(get_seconds());
 	struct uuid_entry *u;
@@ -948,7 +949,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
 
 	bdevname(dc->bdev, buf);
 
-	if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
+	if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
+	    (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
 		return -ENOENT;
 
 	if (dc->disk.c) {
@@ -1190,7 +1192,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 
 	list_add(&dc->list, &uncached_devices);
 	list_for_each_entry(c, &bch_cache_sets, list)
-		bch_cached_dev_attach(dc, c);
+		bch_cached_dev_attach(dc, c, NULL);
 
 	if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
 	    BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
@@ -1712,7 +1714,7 @@ static void run_cache_set(struct cache_set *c)
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
-		bch_cached_dev_attach(dc, c);
+		bch_cached_dev_attach(dc, c, NULL);
 
 	flash_devs_run(c);
 

drivers/md/bcache/sysfs.c

@@ -265,11 +265,13 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_attach) {
-		if (bch_parse_uuid(buf, dc->sb.set_uuid) < 16)
+		uint8_t		set_uuid[16];
+
+		if (bch_parse_uuid(buf, set_uuid) < 16)
 			return -EINVAL;
 
 		list_for_each_entry(c, &bch_cache_sets, list) {
-			v = bch_cached_dev_attach(dc, c);
+			v = bch_cached_dev_attach(dc, c, set_uuid);
 			if (!v)
 				return size;
 		}