@@ -523,8 +523,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
isw->inode = inode;
- atomic_inc(&isw_nr_in_flight);
-
/*
* In addition to synchronizing among switchers, I_WB_SWITCH tells
* the RCU protected stat update paths to grab the i_page
@@ -532,6 +530,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
* Let's continue after I_WB_SWITCH is guaranteed to be visible.
*/
call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
+
+ atomic_inc(&isw_nr_in_flight);
+
goto out_unlock;
out_free:
@@ -901,7 +902,11 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
void cgroup_writeback_umount(void)
{
if (atomic_read(&isw_nr_in_flight)) {
- synchronize_rcu();
+ /*
+ * Use rcu_barrier() to wait for all pending callbacks to
+ * ensure that all in-flight wb switches are in the workqueue.
+ */
+ rcu_barrier();
flush_workqueue(isw_wq);
}
}
synchronize_rcu() didn't wait for call_rcu() callbacks, so inode wb switch may not go to the workqueue after synchronize_rcu(). Thus previous scheduled switches was not finished even flushing the workqueue, which will cause a NULL pointer dereferenced followed below. VFS: Busy inodes after unmount of vdd. Self-destruct in 5 seconds. Have a nice day... BUG: unable to handle kernel NULL pointer dereference at 0000000000000278 [<ffffffff8126a303>] evict+0xb3/0x180 [<ffffffff8126a760>] iput+0x1b0/0x230 [<ffffffff8127c690>] inode_switch_wbs_work_fn+0x3c0/0x6a0 [<ffffffff810a5b2e>] worker_thread+0x4e/0x490 [<ffffffff810a5ae0>] ? process_one_work+0x410/0x410 [<ffffffff810ac056>] kthread+0xe6/0x100 [<ffffffff8173c199>] ret_from_fork+0x39/0x50 Replace the synchronize_rcu() call with a rcu_barrier() to wait for all pending callbacks to finish. And inc isw_nr_in_flight after call_rcu() in inode_switch_wbs() to make more sense. Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jiufei Xue <jiufei.xue@linux.alibaba.com> Cc: stable@kernel.org --- fs/fs-writeback.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)