[PATCH] dm: fix rh_dec()/rh_inc() race in dm-raid1.c

Fix another bug in dm-raid1.c that the dirty region may stay in or be moved
to clean list and freed while in use.

It happens as follows:

   CPU0                                   CPU1
   ------------------------------------------------------------------------------
   rh_dec()
     if (atomic_dec_and_test(pending))
        <the region is still marked dirty>
                                          rh_inc()
                                            if the region is clean
                                               mark the region dirty
                                               and remove from clean list
        mark the region clean
        and move to clean list
                                                  atomic_inc(pending)

At this stage, the region is in clean list and will be mistakenly reclaimed
by rh_update_states() later.

Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 9 insertions, 3 deletions

diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index b08df8b..8632825 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -375,16 +375,18 @@ static void rh_inc(struct region_hash *rh, region_t region)
 
 	read_lock(&rh->hash_lock);
 	reg = __rh_find(rh, region);
+
+	atomic_inc(&reg->pending);
+
+	spin_lock_irq(&rh->region_lock);
 	if (reg->state == RH_CLEAN) {
 		rh->log->type->mark_region(rh->log, reg->key);
 
-		spin_lock_irq(&rh->region_lock);
 		reg->state = RH_DIRTY;
 		list_del_init(&reg->list);	/* take off the clean list */
-		spin_unlock_irq(&rh->region_lock);
 	}
+	spin_unlock_irq(&rh->region_lock);
 
-	atomic_inc(&reg->pending);
 	read_unlock(&rh->hash_lock);
 }
 
@@ -408,6 +410,10 @@ static void rh_dec(struct region_hash *rh, region_t region)
 
 	if (atomic_dec_and_test(&reg->pending)) {
 		spin_lock_irqsave(&rh->region_lock, flags);
+		if (atomic_read(&reg->pending)) { /* check race */
+			spin_unlock_irqrestore(&rh->region_lock, flags);
+			return;
+		}
 		if (reg->state == RH_RECOVERING) {
 			list_add_tail(&reg->list, &rh->quiesced_regions);
 		} else {