1 files changed, 38 insertions, 2 deletions

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 16f93d7356b7..e5970ecdfd58 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -58,6 +58,32 @@ static kmem_zone_t *xfs_buf_zone;
 #define xb_to_gfp(flags) \
 	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)
 
+/*
+ * Locking orders
+ *
+ * xfs_buf_ioacct_inc:
+ * xfs_buf_ioacct_dec:
+ *	b_sema (caller holds)
+ *	  b_lock
+ *
+ * xfs_buf_stale:
+ *	b_sema (caller holds)
+ *	  b_lock
+ *	    lru_lock
+ *
+ * xfs_buf_rele:
+ *	b_lock
+ *	  pag_buf_lock
+ *	    lru_lock
+ *
+ * xfs_buftarg_wait_rele
+ *	lru_lock
+ *	  b_lock (trylock due to inversion)
+ *
+ * xfs_buftarg_isolate
+ *	lru_lock
+ *	  b_lock (trylock due to inversion)
+ */
 
 static inline int
 xfs_buf_is_vmapped(
@@ -983,8 +1009,18 @@ xfs_buf_rele(
 
 	ASSERT(atomic_read(&bp->b_hold) > 0);
 
-	release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock);
+	/*
+	 * We grab the b_lock here first to serialise racing xfs_buf_rele()
+	 * calls. The pag_buf_lock being taken on the last reference only
+	 * serialises against racing lookups in xfs_buf_find(). IOWs, the second
+	 * to last reference we drop here is not serialised against the last
+	 * reference until we take bp->b_lock. Hence if we don't grab b_lock
+	 * first, the last "release" reference can win the race to the lock and
+	 * free the buffer before the second-to-last reference is processed,
+	 * leading to a use-after-free scenario.
+	 */
 	spin_lock(&bp->b_lock);
+	release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock);
 	if (!release) {
 		/*
 		 * Drop the in-flight state if the buffer is already on the LRU
@@ -1702,7 +1738,7 @@ xfs_buftarg_isolate(
 	 * zero. If the value is already zero, we need to reclaim the
 	 * buffer, otherwise it gets another trip through the LRU.
 	 */
-	if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
+	if (atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
 		spin_unlock(&bp->b_lock);
 		return LRU_ROTATE;
 	}