backing-dev: fix wakeup timer races with bdi_unregister()

While 7a401a972df8e18 ("backing-dev: ensure wakeup_timer is deleted")
addressed the problem of the bdi being freed with a queued wakeup
timer, there are other races that could happen if the wakeup timer
expires after/during bdi_unregister(), before bdi_destroy() is called.

wakeup_timer_fn() could attempt to wakeup a task which has already has
been freed, or could access a NULL bdi->dev via the wake_forker_thread
tracepoint.

Cc: <stable@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Reported-by: Chanho Min <chanho.min@lge.com>
Reviewed-by: Namjae Jeon <linkinjeon@gmail.com>
Signed-off-by: Rabin Vincent <rabin@rab.in>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

1 files changed, 18 insertions, 5 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7ba8feae11b8..dd8e2aafb07e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -318,7 +318,7 @@ static void wakeup_timer_fn(unsigned long data)
         if (bdi->wb.task) {
                 trace_writeback_wake_thread(bdi);
                 wake_up_process(bdi->wb.task);
-        } else {
+        } else if (bdi->dev) {
                 /*
                  * When bdi tasks are inactive for long time, they are killed.
                  * In this case we have to wake-up the forker thread which
@@ -584,6 +584,8 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
+        struct task_struct *task;
+
         if (!bdi_cap_writeback_dirty(bdi))
                 return;
 
@@ -602,8 +604,13 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
          * Finally, kill the kernel thread. We don't need to be RCU
          * safe anymore, since the bdi is gone from visibility.
          */
-        if (bdi->wb.task)
-                kthread_stop(bdi->wb.task);
+        spin_lock_bh(&bdi->wb_lock);
+        task = bdi->wb.task;
+        bdi->wb.task = NULL;
+        spin_unlock_bh(&bdi->wb_lock);
+
+        if (task)
+                kthread_stop(task);
 }
 
 /*
@@ -623,7 +630,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-        if (bdi->dev) {
+        struct device *dev = bdi->dev;
+
+        if (dev) {
                 bdi_set_min_ratio(bdi, 0);
                 trace_writeback_bdi_unregister(bdi);
                 bdi_prune_sb(bdi);
@@ -632,8 +641,12 @@ void bdi_unregister(struct backing_dev_info *bdi)
                 if (!bdi_cap_flush_forker(bdi))
                         bdi_wb_shutdown(bdi);
                 bdi_debug_unregister(bdi);
-                device_unregister(bdi->dev);
+
+                spin_lock_bh(&bdi->wb_lock);
                 bdi->dev = NULL;
+                spin_unlock_bh(&bdi->wb_lock);
+
+                device_unregister(dev);
         }
 }
 EXPORT_SYMBOL(bdi_unregister);