fs: fix superblock iteration race

list_for_each_entry_safe is not suitable to protect against concurrent
modification of the list. a2f2501 introduced a race in sb walking.

list_for_each_entry can use the trick of pinning the current entry in
the list before we drop and retake the lock because it subsequently
follows cur->next. However list_for_each_entry_safe saves n=cur->next
for following before entering the loop body, so when the lock is
dropped, n may be deleted.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: John Stultz <johnstul@us.ibm.com>
Cc: Frank Mayhar <fmayhar@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/dcache.c b/fs/dcache.c
index d96047b4a633a86cb7ae711cb29362ac6cda061a..c8c78ba078271163f567c26045afff6cf0b5cd71 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -590,6 +590,8 @@ static void prune_dcache(int count)
                        up_read(&sb->s_umount);
                }
                spin_lock(&sb_lock);
+               /* lock was dropped, must reset next */
+               list_safe_reset_next(sb, n, s_list);
                count -= pruned;
                __put_super(sb);
                /* more work left to do? */

diff --git a/fs/super.c b/fs/super.c
index 5c35bc7a499e19c97b0f8eba3a91a8224a46ffe4..938119ab8dcbc28f3f9853bc0808d6d70cd51d55 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -374,6 +374,8 @@ void sync_supers(void)
                        up_read(&sb->s_umount);
 
                        spin_lock(&sb_lock);
+                       /* lock was dropped, must reset next */
+                       list_safe_reset_next(sb, n, s_list);
                        __put_super(sb);
                }
        }
@@ -405,6 +407,8 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
                up_read(&sb->s_umount);
 
                spin_lock(&sb_lock);
+               /* lock was dropped, must reset next */
+               list_safe_reset_next(sb, n, s_list);
                __put_super(sb);
        }
        spin_unlock(&sb_lock);
@@ -585,6 +589,8 @@ static void do_emergency_remount(struct work_struct *work)
                }
                up_write(&sb->s_umount);
                spin_lock(&sb_lock);
+               /* lock was dropped, must reset next */
+               list_safe_reset_next(sb, n, s_list);
                __put_super(sb);
        }
        spin_unlock(&sb_lock);

diff --git a/include/linux/list.h b/include/linux/list.h
index 8392884a2977cda6a5f004fed2511ad51a140aa5..5d57a3a1fa1b1b9143a5e80381ac7668b51bb677 100644 (file)
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -544,6 +544,21 @@ static inline void list_splice_tail_init(struct list_head *list,
             &pos->member != (head);                                    \
             pos = n, n = list_entry(n->member.prev, typeof(*n), member))
 
+/**
+ * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
+ * @pos:       the loop cursor used in the list_for_each_entry_safe loop
+ * @n:         temporary storage used in list_for_each_entry_safe
+ * @member:    the name of the list_struct within the struct.
+ *
+ * list_safe_reset_next is not safe to use in general if the list may be
+ * modified concurrently (eg. the lock is dropped in the loop body). An
+ * exception to this is if the cursor element (pos) is pinned in the list,
+ * and list_safe_reset_next is called after re-taking the lock and before
+ * completing the current iteration of the loop body.
+ */
+#define list_safe_reset_next(pos, n, member)                           \
+       n = list_entry(pos->member.next, typeof(*pos), member)
+
 /*
  * Double linked lists with a single pointer list head.
  * Mostly useful for hash tables where the two pointer list head is