dm mpath: fix race condition between multipath_dtr and pg_init_done

commit 954a73d5d3073df2231820c718fdd2f18b0fe4c9 upstream.

Whenever multipath_dtr() is happening we must prevent queueing any
further path activation work.  Implement this by adding a new
'pg_init_disabled' flag to the multipath structure that denotes future
path activation work should be skipped if it is set.  By disabling
pg_init and then re-enabling in flush_multipath_work() we also avoid the
potential for pg_init to be initiated while suspending an mpath device.

Without this patch a race condition exists that may result in a kernel
panic:

1) If after pg_init_done() decrements pg_init_in_progress to 0, a call
   to wait_for_pg_init_completion() assumes there are no more pending path
   management commands.
2) If pg_init_required is set by pg_init_done(), due to retryable
   mode_select errors, then process_queued_ios() will again queue the
   path activation work.
3) If free_multipath() completes before activate_path() work is called a
   NULL pointer dereference like the following can be seen when
   accessing members of the recently destructed multipath:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000090
RIP: 0010:[<ffffffffa003db1b>]  [<ffffffffa003db1b>] activate_path+0x1b/0x30 [dm_multipath]
[<ffffffff81090ac0>] worker_thread+0x170/0x2a0
[<ffffffff81096c80>] ? autoremove_wake_function+0x0/0x40

[switch to disabling pg_init in flush_multipath_work & header edits by Mike Snitzer]
Signed-off-by: Shiva Krishna Merla <shivakrishna.merla@netapp.com>
Reviewed-by: Krishnasamy Somasundaram <somasundaram.krishnasamy@netapp.com>
Tested-by: Speagle Andy <Andy.Speagle@netapp.com>
Acked-by: Junichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
[bwh: Backported to 3.2:
 - Adjust context
 - Bump version to 1.3.2 not 1.6.0]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
[xr: Backported to 3.4: Adjust context]
Signed-off-by: Rui Xiang <rui.xiang@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 15 insertions, 3 deletions

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 9147569545e..d5fc3ec3639 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -84,6 +84,7 @@ struct multipath {
 	unsigned queue_io;		/* Must we queue all I/O? */
 	unsigned queue_if_no_path;	/* Queue I/O if last path fails? */
 	unsigned saved_queue_if_no_path;/* Saved state during suspension */
+	unsigned pg_init_disabled:1;	/* pg_init is not currently allowed */
 	unsigned pg_init_retries;	/* Number of times to retry pg_init */
 	unsigned pg_init_count;		/* Number of times pg_init called */
 	unsigned pg_init_delay_msecs;	/* Number of msecs before pg_init retry */
@@ -493,7 +494,8 @@ static void process_queued_ios(struct work_struct *work)
 	    (!pgpath && !m->queue_if_no_path))
 		must_queue = 0;
 
-	if (m->pg_init_required && !m->pg_init_in_progress && pgpath)
+	if (m->pg_init_required && !m->pg_init_in_progress && pgpath &&
+	    !m->pg_init_disabled)
 		__pg_init_all_paths(m);
 
 out:
@@ -907,10 +909,20 @@ static void multipath_wait_for_pg_init_completion(struct multipath *m)
 
 static void flush_multipath_work(struct multipath *m)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&m->lock, flags);
+	m->pg_init_disabled = 1;
+	spin_unlock_irqrestore(&m->lock, flags);
+
 	flush_workqueue(kmpath_handlerd);
 	multipath_wait_for_pg_init_completion(m);
 	flush_workqueue(kmultipathd);
 	flush_work_sync(&m->trigger_event);
+
+	spin_lock_irqsave(&m->lock, flags);
+	m->pg_init_disabled = 0;
+	spin_unlock_irqrestore(&m->lock, flags);
 }
 
 static void multipath_dtr(struct dm_target *ti)
@@ -1129,7 +1141,7 @@ static int pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath)
 
 	spin_lock_irqsave(&m->lock, flags);
 
-	if (m->pg_init_count <= m->pg_init_retries)
+	if (m->pg_init_count <= m->pg_init_retries && !m->pg_init_disabled)
 		m->pg_init_required = 1;
 	else
 		limit_reached = 1;
@@ -1644,7 +1656,7 @@ out:
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 3, 0},
+	.version = {1, 3, 2},
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,