[PATCH] md: use a mutex to protect a global list

[Cong Wang]

We saw a list corruption in the list all_detected_devices:

 WARNING: CPU: 16 PID: 226 at lib/list_debug.c:29 __list_add+0x3c/0xa9()
 list_add corruption. next->prev should be prev (ffff880859d58320), but was ffff880859ce74c0. (next=ffffffff81abfdb0).
 Modules linked in: ahci libahci libata sd_mod scsi_mod
 CPU: 16 PID: 226 Comm: kworker/u241:4 Not tainted 4.1.20 #1
 Hardware name: Dell Inc. PowerEdge C6220/04GD66, BIOS 2.2.3 11/07/2013
 Workqueue: events_unbound async_run_entry_fn
  0000000000000000 ffff880859a5baf8 ffffffff81502872 ffff880859a5bb48
  0000000000000009 ffff880859a5bb38 ffffffff810692a5 ffff880859ee8828
  ffffffff812ad02c ffff880859d58320 ffffffff81abfdb0 ffff880859eb90c0
 Call Trace:
  [<ffffffff81502872>] dump_stack+0x4d/0x63
  [<ffffffff810692a5>] warn_slowpath_common+0xa1/0xbb
  [<ffffffff812ad02c>] ? __list_add+0x3c/0xa9
  [<ffffffff81069305>] warn_slowpath_fmt+0x46/0x48
  [<ffffffff812ad02c>] __list_add+0x3c/0xa9
  [<ffffffff81406f28>] md_autodetect_dev+0x41/0x62
  [<ffffffff81285862>] rescan_partitions+0x25f/0x29d
  [<ffffffff81506372>] ? mutex_lock+0x13/0x31
  [<ffffffff811a090f>] __blkdev_get+0x1aa/0x3cd
  [<ffffffff811a0b91>] blkdev_get+0x5f/0x294
  [<ffffffff81377ceb>] ? put_device+0x17/0x19
  [<ffffffff8128227c>] ? disk_put_part+0x12/0x14
  [<ffffffff812836f3>] add_disk+0x29d/0x407
  [<ffffffff81384345>] ? __pm_runtime_use_autosuspend+0x5c/0x64
  [<ffffffffa004a724>] sd_probe_async+0x115/0x1af [sd_mod]
  [<ffffffff81083177>] async_run_entry_fn+0x72/0x12c
  [<ffffffff8107c44c>] process_one_work+0x198/0x2ce
  [<ffffffff8107cac7>] worker_thread+0x1dd/0x2bb
  [<ffffffff8107c8ea>] ? cancel_delayed_work_sync+0x15/0x15
  [<ffffffff8107c8ea>] ? cancel_delayed_work_sync+0x15/0x15
  [<ffffffff81080d9c>] kthread+0xae/0xb6
  [<ffffffff81080000>] ? param_array_set+0x40/0xfa
  [<ffffffff81080cee>] ? __kthread_parkme+0x61/0x61
  [<ffffffff81508152>] ret_from_fork+0x42/0x70
  [<ffffffff81080cee>] ? __kthread_parkme+0x61/0x61

I suspect it is because there is no lock protecting this
global list, autostart_arrays() is called in ioctl() path
where there is no lock.

Cc: Shaohua Li <shli@xxxxxxxxxx>
Signed-off-by: Cong Wang <xiyou.wangcong@xxxxxxxxx>
---
 drivers/md/md.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 866825f..f2f1912 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8799,6 +8799,7 @@ EXPORT_SYMBOL(md_reload_sb);
  * at boot time.
  */
 
+static DEFINE_MUTEX(detected_devices_mutex);
 static LIST_HEAD(all_detected_devices);
 struct detected_devices_node {
 	struct list_head list;
@@ -8812,7 +8813,9 @@ void md_autodetect_dev(dev_t dev)
 	node_detected_dev = kzalloc(sizeof(*node_detected_dev), GFP_KERNEL);
 	if (node_detected_dev) {
 		node_detected_dev->dev = dev;
+		mutex_lock(&detected_devices_mutex);
 		list_add_tail(&node_detected_dev->list, &all_detected_devices);
+		mutex_unlock(&detected_devices_mutex);
 	} else {
 		printk(KERN_CRIT "md: md_autodetect_dev: kzalloc failed"
 			", skipping dev(%d,%d)\n", MAJOR(dev), MINOR(dev));
@@ -8831,6 +8834,7 @@ static void autostart_arrays(int part)
 
 	printk(KERN_INFO "md: Autodetecting RAID arrays.\n");
 
+	mutex_lock(&detected_devices_mutex);
 	while (!list_empty(&all_detected_devices) && i_scanned < INT_MAX) {
 		i_scanned++;
 		node_detected_dev = list_entry(all_detected_devices.next,
@@ -8849,6 +8853,7 @@ static void autostart_arrays(int part)
 		list_add(&rdev->same_set, &pending_raid_disks);
 		i_passed++;
 	}
+	mutex_unlock(&detected_devices_mutex);
 
 	printk(KERN_INFO "md: Scanned %d and added %d devices.\n",
 						i_scanned, i_passed);
-- 
2.1.0