dm cache: prevent BUG_ON by blocking retries on failed device resumes

[ Upstream commit 5da692e ]

A cache device failing to resume due to mapping errors should not be
retried, as the failure leaves a partially initialized policy object.
Repeating the resume operation risks triggering BUG_ON when reloading
cache mappings into the incomplete policy object.

Reproduce steps:

1. create a cache metadata consisting of 512 or more cache blocks,
   with some mappings stored in the first array block of the mapping
   array. Here we use cache_restore v1.0 to build the metadata.

cat <<EOF >> cmeta.xml
<superblock uuid="" block_size="128" nr_cache_blocks="512" \
policy="smq" hint_width="4">
  <mappings>
    <mapping cache_block="0" origin_block="0" dirty="false"/>
  </mappings>
</superblock>
EOF
dmsetup create cmeta --table "0 8192 linear /dev/sdc 0"
cache_restore -i cmeta.xml -o /dev/mapper/cmeta --metadata-version=2
dmsetup remove cmeta

2. wipe the second array block of the mapping array to simulate
   data degradations.

mapping_root=$(dd if=/dev/sdc bs=1c count=8 skip=192 \
2>/dev/null | hexdump -e '1/8 "%u\n"')
ablock=$(dd if=/dev/sdc bs=1c count=8 skip=$((4096*mapping_root+2056)) \
2>/dev/null | hexdump -e '1/8 "%u\n"')
dd if=/dev/zero of=/dev/sdc bs=4k count=1 seek=$ablock

3. try bringing up the cache device. The resume is expected to fail
   due to the broken array block.

dmsetup create cmeta --table "0 8192 linear /dev/sdc 0"
dmsetup create cdata --table "0 65536 linear /dev/sdc 8192"
dmsetup create corig --table "0 524288 linear /dev/sdc 262144"
dmsetup create cache --notable
dmsetup load cache --table "0 524288 cache /dev/mapper/cmeta \
/dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0"
dmsetup resume cache

4. try resuming the cache again. An unexpected BUG_ON is triggered
   while loading cache mappings.

dmsetup resume cache

Kernel logs:

(snip)
------------[ cut here ]------------
kernel BUG at drivers/md/dm-cache-policy-smq.c:752!
Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 332 Comm: dmsetup Not tainted 6.13.4 #3
RIP: 0010:smq_load_mapping+0x3e5/0x570

Fix by disallowing resume operations for devices that failed the
initial attempt.

Signed-off-by: Ming-Hung Tsai <[email protected]>
Signed-off-by: Mikulas Patocka <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>

Author: mingnus

drivers/md/dm-cache-target.c

@@ -2903,6 +2903,27 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache)
 	return to_cblock(size);
 }
 
+static bool can_resume(struct cache *cache)
+{
+	/*
+	 * Disallow retrying the resume operation for devices that failed the
+	 * first resume attempt, as the failure leaves the policy object partially
+	 * initialized. Retrying could trigger BUG_ON when loading cache mappings
+	 * into the incomplete policy object.
+	 */
+	if (cache->sized && !cache->loaded_mappings) {
+		if (get_cache_mode(cache) != CM_WRITE)
+			DMERR("%s: unable to resume a failed-loaded cache, please check metadata.",
+			      cache_device_name(cache));
+		else
+			DMERR("%s: unable to resume cache due to missing proper cache table reload",
+			      cache_device_name(cache));
+		return false;
+	}
+
+	return true;
+}
+
 static bool can_resize(struct cache *cache, dm_cblock_t new_size)
 {
 	if (from_cblock(new_size) > from_cblock(cache->cache_size)) {
@@ -2951,6 +2972,9 @@ static int cache_preresume(struct dm_target *ti)
 	struct cache *cache = ti->private;
 	dm_cblock_t csize = get_cache_dev_size(cache);
 
+	if (!can_resume(cache))
+		return -EINVAL;
+
 	/*
 	 * Check to see if the cache has resized.
 	 */