summaryrefslogtreecommitdiffstats
path: root/fs/reiserfs/super.c
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2014-08-06 19:43:56 +0200
committerJan Kara <jack@suse.cz>2014-08-12 12:46:30 +0200
commit01777836c87081e4f68c4a43c9abe6114805f91e (patch)
tree249981494b2563e689b091fe4e67929e4ddc113c /fs/reiserfs/super.c
parentreiserfs: fix corruption introduced by balance_leaf refactor (diff)
downloadlinux-01777836c87081e4f68c4a43c9abe6114805f91e.tar.xz
linux-01777836c87081e4f68c4a43c9abe6114805f91e.zip
reiserfs: Fix use after free in journal teardown
If do_journal_release() races with do_journal_end() which requeues delayed works for transaction flushing, we can leave work items for flushing outstanding transactions queued while freeing them. That results in use after free and possible crash in run_timers_softirq(). Fix the problem by not requeueing works if superblock is being shut down (MS_ACTIVE not set) and using cancel_delayed_work_sync() in do_journal_release(). CC: stable@vger.kernel.org Signed-off-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'fs/reiserfs/super.c')
-rw-r--r--fs/reiserfs/super.c6
1 files changed, 5 insertions, 1 deletions
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index a392cef6acc6..5fd8f57e07fc 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -100,7 +100,11 @@ void reiserfs_schedule_old_flush(struct super_block *s)
struct reiserfs_sb_info *sbi = REISERFS_SB(s);
unsigned long delay;
- if (s->s_flags & MS_RDONLY)
+ /*
+ * Avoid scheduling flush when sb is being shut down. It can race
+ * with journal shutdown and free still queued delayed work.
+ */
+ if (s->s_flags & MS_RDONLY || !(s->s_flags & MS_ACTIVE))
return;
spin_lock(&sbi->old_work_lock);