md: fix deadlock when stopping arrays
Resolve a deadlock when stopping redundant arrays, i.e. ones that
require a call to sysfs_remove_group when shutdown. The deadlock is
summarized below:
Thread1 Thread2
------- -------
read sysfs attribute stop array
take mddev lock
sysfs_remove_group
sysfs_get_active
wait for mddev lock
wait for active
Sysrq-w:
--------
mdmon S 00000017 2212 4163 1
f1982ea8 00000046 2dcf6b85 00000017 c0b23100 f2f83ed0 c0b23100 f2f8413c
c0b23100 c0b23100 c0b1fb98 f2f8413c 00000000 f2f8413c c0b23100 f2291ecc
00000002 c0b23100 00000000 00000017 f2f83ed0 f1982eac 00000046 c044d9dd
Call Trace:
[<c044d9dd>] ? debug_mutex_add_waiter+0x1d/0x58
[<c06ef451>] __mutex_lock_common+0x1d9/0x338
[<c06ef451>] ? __mutex_lock_common+0x1d9/0x338
[<c06ef5e3>] mutex_lock_interruptible_nested+0x33/0x3a
[<c0634553>] ? mddev_lock+0x14/0x16
[<c0634553>] mddev_lock+0x14/0x16
[<c0634eda>] md_attr_show+0x2a/0x49
[<c04e9997>] sysfs_read_file+0x93/0xf9
mdadm D 00000017 2812 4177 1
f0401d78 00000046 430456f8 00000017 f0401d58 f0401d20 c0b23100 f2da2c4c
c0b23100 c0b23100 c0b1fb98 f2da2c4c 0a10fc36 00000000 c0b23100 f0401d70
00000003 c0b23100 00000000 00000017 f2da29e0 00000001 00000002 00000000
Call Trace:
[<c06eed1b>] schedule_timeout+0x1b/0x95
[<c06eed1b>] ? schedule_timeout+0x1b/0x95
[<c06eeb97>] ? wait_for_common+0x34/0xdc
[<c044fa8a>] ? trace_hardirqs_on_caller+0x18/0x145
[<c044fbc2>] ? trace_hardirqs_on+0xb/0xd
[<c06eec03>] wait_for_common+0xa0/0xdc
[<c0428c7c>] ? default_wake_function+0x0/0x12
[<c06eeccc>] wait_for_completion+0x17/0x19
[<c04ea620>] sysfs_addrm_finish+0x19f/0x1d1
[<c04e920e>] sysfs_hash_and_remove+0x42/0x55
[<c04eb4db>] sysfs_remove_group+0x57/0x86
[<c0638086>] do_md_stop+0x13a/0x499
This has been there for a while, but is easier to trigger now that mdmon
is closely watching sysfs.
Cc: <stable@kernel.org>
Reported-by: Jacek Danecki <jacek.danecki@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 03b4cd0..a307f87 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -214,12 +214,7 @@
return mddev;
}
-static void mddev_delayed_delete(struct work_struct *ws)
-{
- mddev_t *mddev = container_of(ws, mddev_t, del_work);
- kobject_del(&mddev->kobj);
- kobject_put(&mddev->kobj);
-}
+static void mddev_delayed_delete(struct work_struct *ws);
static void mddev_put(mddev_t *mddev)
{
@@ -3542,6 +3537,21 @@
int mdp_major = 0;
+static void mddev_delayed_delete(struct work_struct *ws)
+{
+ mddev_t *mddev = container_of(ws, mddev_t, del_work);
+
+ if (mddev->private == &md_redundancy_group) {
+ sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+ if (mddev->sysfs_action)
+ sysfs_put(mddev->sysfs_action);
+ mddev->sysfs_action = NULL;
+ mddev->private = NULL;
+ }
+ kobject_del(&mddev->kobj);
+ kobject_put(&mddev->kobj);
+}
+
static int md_alloc(dev_t dev, char *name)
{
static DEFINE_MUTEX(disks_mutex);
@@ -4033,13 +4043,9 @@
mddev->queue->merge_bvec_fn = NULL;
mddev->queue->unplug_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
- if (mddev->pers->sync_request) {
- sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
- if (mddev->sysfs_action)
- sysfs_put(mddev->sysfs_action);
- mddev->sysfs_action = NULL;
- }
module_put(mddev->pers->owner);
+ if (mddev->pers->sync_request)
+ mddev->private = &md_redundancy_group;
mddev->pers = NULL;
/* tell userspace to handle 'inactive' */
sysfs_notify_dirent(mddev->sysfs_state);