dm cache: fix race affecting dirty block count

commit 44fa816bb778edbab6b6ddaaf24908dd6295937e upstream.

nr_dirty is updated without locking, causing it to drift so that it is
non-zero (either a small positive integer, or a very large one when an
underflow occurs) even when there are no actual dirty blocks.  This was
due to a race between the workqueue and map function accessing nr_dirty
in parallel without proper protection.

People were seeing under runs due to a race on increment/decrement of
nr_dirty, see: https://lkml.org/lkml/2014/6/3/648

Fix this by using an atomic_t for nr_dirty.

Reported-by: roma1390@gmail.com
Signed-off-by: Anssi Hannula <anssi.hannula@iki.fi>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index c0ad90d..735e939 100644 (file)
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -231,7 +231,7 @@ struct cache {
        /*
         * cache_size entries, dirty if set
         */
-       dm_cblock_t nr_dirty;
+       atomic_t nr_dirty;
        unsigned long *dirty_bitset;
 
        /*
@@ -493,7 +493,7 @@ static bool is_dirty(struct cache *cache, dm_cblock_t b)
 static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
 {
        if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) {
-               cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1);
+               atomic_inc(&cache->nr_dirty);
                policy_set_dirty(cache->policy, oblock);
        }
 }
@@ -502,8 +502,7 @@ static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cbl
 {
        if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) {
                policy_clear_dirty(cache->policy, oblock);
-               cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1);
-               if (!from_cblock(cache->nr_dirty))
+               if (atomic_dec_return(&cache->nr_dirty) == 0)
                        dm_table_event(cache->ti->table);
        }
 }
@@ -2286,7 +2285,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
        atomic_set(&cache->quiescing_ack, 0);
 
        r = -ENOMEM;
-       cache->nr_dirty = 0;
+       atomic_set(&cache->nr_dirty, 0);
        cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
        if (!cache->dirty_bitset) {
                *error = "could not allocate dirty bitset";
@@ -2828,7 +2827,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 
                residency = policy_residency(cache->policy);
 
-               DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %llu ",
+               DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
                       (unsigned)(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT),
                       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
                       (unsigned long long)nr_blocks_metadata,
@@ -2841,7 +2840,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
                       (unsigned) atomic_read(&cache->stats.write_miss),
                       (unsigned) atomic_read(&cache->stats.demotion),
                       (unsigned) atomic_read(&cache->stats.promotion),
-                      (unsigned long long) from_cblock(cache->nr_dirty));
+                      (unsigned long) atomic_read(&cache->nr_dirty));
 
                if (writethrough_mode(&cache->features))
                        DMEMIT("1 writethrough ");