net/ncsi: Avoid channel_monitor hrtimer deadlock

[ Upstream commit 03cb4d05b4ea9a3491674ca40952adb708d549fa ]

Calling ncsi_stop_channel_monitor from channel_monitor is a guaranteed
deadlock on SMP because stop calls del_timer_sync on the timer that
invoked channel_monitor as its timer function.

Recognise the inherent race of marking the monitor disabled before
deleting the timer by just returning if enable was cleared.  After
a timeout (the default case -- reset to START when response received)
just mark the monitor.enabled false.

If the channel has an entry on the channel_queue list, or if the
state is not ACTIVE or INACTIVE, then warn and mark the timer stopped
and don't restart, as the locking is broken somehow.

Fixes: 0795fb2021f0 ("net/ncsi: Stop monitor if channel times out or is inactive")
Signed-off-by: Milton Miller <miltonm@us.ibm.com>
Signed-off-by: Eddie James <eajames@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 13 insertions, 7 deletions

diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 28c42b22b748..6b7f9e1f64d3 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -203,13 +203,20 @@ static void ncsi_channel_monitor(unsigned long data)
 	monitor_state = nc->monitor.state;
 	spin_unlock_irqrestore(&nc->lock, flags);
 
-	if (!enabled || chained) {
-		ncsi_stop_channel_monitor(nc);
-		return;
-	}
+	if (!enabled)
+		return;		/* expected race disabling timer */
+	if (WARN_ON_ONCE(chained))
+		goto bad_state;
+
 	if (state != NCSI_CHANNEL_INACTIVE &&
 	    state != NCSI_CHANNEL_ACTIVE) {
-		ncsi_stop_channel_monitor(nc);
+bad_state:
+		netdev_warn(ndp->ndev.dev,
+			    "Bad NCSI monitor state channel %d 0x%x %s queue\n",
+			    nc->id, state, chained ? "on" : "off");
+		spin_lock_irqsave(&nc->lock, flags);
+		nc->monitor.enabled = false;
+		spin_unlock_irqrestore(&nc->lock, flags);
 		return;
 	}
 
@@ -234,10 +241,9 @@ static void ncsi_channel_monitor(unsigned long data)
 			ndp->flags |= NCSI_DEV_RESHUFFLE;
 		}
 
-		ncsi_stop_channel_monitor(nc);
-
 		ncm = &nc->modes[NCSI_MODE_LINK];
 		spin_lock_irqsave(&nc->lock, flags);
+		nc->monitor.enabled = false;
 		nc->state = NCSI_CHANNEL_INVISIBLE;
 		ncm->data[2] &= ~0x1;
 		spin_unlock_irqrestore(&nc->lock, flags);