[PATCH 3.8 040/152] dm mpath: fix race condition between multipath_dtr and pg_init_done

[Kamal Mostafa]

3.8.13.14 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Shiva Krishna Merla <shivakrishna.merla@xxxxxxxxxx>

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@xxxxxxxxxx>
Reviewed-by: Krishnasamy Somasundaram <somasundaram.krishnasamy@xxxxxxxxxx>
Tested-by: Speagle Andy <Andy.Speagle@xxxxxxxxxx>
Acked-by: Junichi Nomura <j-nomura@xxxxxxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
Signed-off-by: Kamal Mostafa <kamal@xxxxxxxxxxxxx>
---
 drivers/md/dm-mpath.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 9f330c1..9d11b4e 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -86,6 +86,7 @@ struct multipath {
 	unsigned queue_if_no_path:1;	/* Queue I/O if last path fails? */
 	unsigned saved_queue_if_no_path:1; /* Saved state during suspension */
 	unsigned retain_attached_hw_handler:1; /* If there's already a hw_handler present, don't change it. */
+	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 */
@@ -497,7 +498,8 @@ 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);
 
 	spin_unlock_irqrestore(&m->lock, flags);
@@ -941,10 +943,20 @@ 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(&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)
@@ -1163,7 +1175,7 @@ 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;
@@ -1689,7 +1701,7 @@ out:
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 5, 1},
+	.version = {1, 6, 0},
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
-- 
1.8.3.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/