dm cache: fix race when issuing a POLICY_REPLACE operation

There is a race between a policy deciding to replace a cache entry,
the core target writing back any dirty data from this block, and other
IO threads doing IO to the same block.

This sort of problem is avoided most of the time by the core target
grabbing a bio prison cell before making the request to the policy.
But for a demotion the core target doesn't know which block will be
demoted, so can't do this in advance.

Fix this demotion race by introducing a callback to the policy interface
that allows the policy to grab the cell on behalf of the core target.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org

1 files changed, 14 insertions, 1 deletions

diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h
index f50fe360c546..5524e21e4836 100644
--- a/drivers/md/dm-cache-policy.h
+++ b/drivers/md/dm-cache-policy.h
@@ -70,6 +70,18 @@ enum policy_operation {
 };
 
 /*
+ * When issuing a POLICY_REPLACE the policy needs to make a callback to
+ * lock the block being demoted.  This doesn't need to occur during a
+ * writeback operation since the block remains in the cache.
+ */
+struct policy_locker;
+typedef int (*policy_lock_fn)(struct policy_locker *l, dm_oblock_t oblock);
+
+struct policy_locker {
+	policy_lock_fn fn;
+};
+
+/*
  * This is the instruction passed back to the core target.
  */
 struct policy_result {
@@ -122,7 +134,8 @@ struct dm_cache_policy {
 	 */
 	int (*map)(struct dm_cache_policy *p, dm_oblock_t oblock,
 		   bool can_block, bool can_migrate, bool discarded_oblock,
-		   struct bio *bio, struct policy_result *result);
+		   struct bio *bio, struct policy_locker *locker,
+		   struct policy_result *result);
 
 	/*
 	 * Sometimes we want to see if a block is in the cache, without