ceph: correctly handle releasing an embedded cap flush

The ceph_cap_flush structures are usually dynamically allocated, but
the ceph_cap_snap has an embedded one.

When force umounting, the client will try to remove all the session
caps. During this, it will free them, but that should not be done
with the ones embedded in a capsnap.

Fix this by adding a new boolean that indicates that the cap flush is
embedded in a capsnap, and skip freeing it if that's set.

At the same time, switch to using list_del_init() when detaching the
i_list and g_list heads.  It's possible for a forced umount to remove
these objects but then handle_cap_flushsnap_ack() races in and does the
list_del_init() again, corrupting memory.

Cc: stable@vger.kernel.org
URL: https://tracker.ceph.com/issues/52283
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 13 insertions, 8 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 2a2900903f8c..39db97f149b9 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1743,7 +1743,11 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask,
 
 struct ceph_cap_flush *ceph_alloc_cap_flush(void)
 {
-	return kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
+	struct ceph_cap_flush *cf;
+
+	cf = kmem_cache_alloc(ceph_cap_flush_cachep, GFP_KERNEL);
+	cf->is_capsnap = false;
+	return cf;
 }
 
 void ceph_free_cap_flush(struct ceph_cap_flush *cf)
@@ -1778,7 +1782,7 @@ static bool __detach_cap_flush_from_mdsc(struct ceph_mds_client *mdsc,
 		prev->wake = true;
 		wake = false;
 	}
-	list_del(&cf->g_list);
+	list_del_init(&cf->g_list);
 	return wake;
 }
 
@@ -1793,7 +1797,7 @@ static bool __detach_cap_flush_from_ci(struct ceph_inode_info *ci,
 		prev->wake = true;
 		wake = false;
 	}
-	list_del(&cf->i_list);
+	list_del_init(&cf->i_list);
 	return wake;
 }
 
@@ -2352,7 +2356,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 	ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
 
 	list_for_each_entry_reverse(cf, &ci->i_cap_flush_list, i_list) {
-		if (!cf->caps) {
+		if (cf->is_capsnap) {
 			last_snap_flush = cf->tid;
 			break;
 		}
@@ -2371,7 +2375,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 
 		first_tid = cf->tid + 1;
 
-		if (cf->caps) {
+		if (!cf->is_capsnap) {
 			struct cap_msg_args arg;
 
 			dout("kick_flushing_caps %p cap %p tid %llu %s\n",
@@ -3516,7 +3520,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
 			cleaned = cf->caps;
 
 		/* Is this a capsnap? */
-		if (cf->caps == 0)
+		if (cf->is_capsnap)
 			continue;
 
 		if (cf->tid <= flush_tid) {
@@ -3589,8 +3593,9 @@ out:
 	while (!list_empty(&to_remove)) {
 		cf = list_first_entry(&to_remove,
 				      struct ceph_cap_flush, i_list);
-		list_del(&cf->i_list);
-		ceph_free_cap_flush(cf);
+		list_del_init(&cf->i_list);
+		if (!cf->is_capsnap)
+			ceph_free_cap_flush(cf);
 	}
 
 	if (wake_ci)