From 2d1f7b65f5deedd2e6b09fdc6ea27f8375f24b45 Mon Sep 17 00:00:00 2001 From: Ming-Hung Tsai Date: Mon, 9 Feb 2026 15:54:08 +0800 Subject: [PATCH] dm cache policy smq: fix missing locks in invalidating cache blocks In passthrough mode, the policy invalidate_mapping operation is called simultaneously from multiple workers, thus it should be protected by a lock. Otherwise, we might end up with data races on the allocated blocks counter, or even use-after-free issues with internal data structures when doing concurrent writes. Note that the existing FIXME in smq_invalidate_mapping() doesn't affect passthrough mode since migration tasks don't exist there, but would need attention if supporting fast device shrinking via suspend/resume without target reloading. Reproduce steps: 1. Create a cache device consisting of 1024 cache entries dmsetup create cmeta --table "0 8192 linear /dev/sdc 0" dmsetup create cdata --table "0 131072 linear /dev/sdc 8192" dmsetup create corig --table "0 262144 linear /dev/sdc 262144" dd if=/dev/zero of=/dev/mapper/cmeta bs=4k count=1 oflag=direct dmsetup create cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 writethrough smq 0" 2. Populate the cache, and record the number of cached blocks fio --name=populate --filename=/dev/mapper/cache --rw=randwrite --bs=4k \ --size=64m --direct=1 nr_cached=$(dmsetup status cache | awk '{split($7, a, "/"); print a[1]}') 3. Reload the cache into passthrough mode dmsetup suspend cache dmsetup reload cache --table "0 262144 cache /dev/mapper/cmeta \ /dev/mapper/cdata /dev/mapper/corig 128 2 metadata2 passthrough smq 0" dmsetup resume cache 4. Write to the passthrough cache. By setting multiple jobs with I/O size equal to the cache block size, cache blocks are invalidated concurrently from different workers. fio --filename=/dev/mapper/cache --name=test --rw=randwrite --bs=64k \ --direct=1 --numjobs=2 --randrepeat=0 --size=64m 5. Check if demoted matches cached block count. These numbers should match but may differ due to the data race. nr_demoted=$(dmsetup status cache | awk '{print $12}') echo "$nr_cached, $nr_demoted" Fixes: b29d4986d0da ("dm cache: significant rework to leverage dm-bio-prison-v2") Signed-off-by: Ming-Hung Tsai Signed-off-by: Mikulas Patocka --- drivers/md/dm-cache-policy-smq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index b328d9601046..dd77a93fd68d 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1589,14 +1589,18 @@ static int smq_invalidate_mapping(struct dm_cache_policy *p, dm_cblock_t cblock) { struct smq_policy *mq = to_smq_policy(p); struct entry *e = get_entry(&mq->cache_alloc, from_cblock(cblock)); + unsigned long flags; if (!e->allocated) return -ENODATA; + spin_lock_irqsave(&mq->lock, flags); // FIXME: what if this block has pending background work? del_queue(mq, e); h_remove(&mq->table, e); free_entry(&mq->cache_alloc, e); + spin_unlock_irqrestore(&mq->lock, flags); + return 0; }