[PATCH] bcm43xx: Fix cancellation of work queue crashes

A crash upon booting that is caused by bcm43xx has been reported [1] and
found to be due to a work queue being reinitialized while work on that
queue is still pending. This fix modifies the shutdown of work queues and
prevents periodic work from being requeued during shutdown. With this patch,
no more crashes on reboot were observed by the original reporter. I do not
get that particular failure on my system; however, when running a large
number of ifdown/ifup sequences, my system would kernel panic with the
'caps lock' light blinking at roughly a 1 Hz rate. In addition, there were
infrequent failures in the firmware that resulted in 'IRQ READY TIMEOUT'
errors. With this patch, no more of the first type of failure occur, and
incidence of the second type is greatly reduced.

[1] http://bugzilla.kernel.org/show_bug.cgi?id=8937

Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Acked-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

1 files changed, 20 insertions, 8 deletions

diff --git a/drivers/net/wireless/bcm43xx/bcm43xx_main.c b/drivers/net/wireless/bcm43xx/bcm43xx_main.c
index c5d6753a55e..dfbd01eaaf3 100644
--- a/drivers/net/wireless/bcm43xx/bcm43xx_main.c
+++ b/drivers/net/wireless/bcm43xx/bcm43xx_main.c
@@ -3183,6 +3183,9 @@ static void bcm43xx_periodic_work_handler(struct work_struct *work)
 	unsigned long orig_trans_start = 0;
 
 	mutex_lock(&bcm->mutex);
+	/* keep from doing and rearming periodic work if shutting down */
+	if (bcm43xx_status(bcm) == BCM43xx_STAT_UNINIT)
+		goto unlock_mutex;
 	if (unlikely(bcm->periodic_state % 60 == 0)) {
 		/* Periodic work will take a long time, so we want it to
 		 * be preemtible.
@@ -3228,14 +3231,10 @@ static void bcm43xx_periodic_work_handler(struct work_struct *work)
 	mmiowb();
 	bcm->periodic_state++;
 	spin_unlock_irqrestore(&bcm->irq_lock, flags);
+unlock_mutex:
 	mutex_unlock(&bcm->mutex);
 }
 
-void bcm43xx_periodic_tasks_delete(struct bcm43xx_private *bcm)
-{
-	cancel_rearming_delayed_work(&bcm->periodic_work);
-}
-
 void bcm43xx_periodic_tasks_setup(struct bcm43xx_private *bcm)
 {
 	struct delayed_work *work = &bcm->periodic_work;
@@ -3285,6 +3284,14 @@ static int bcm43xx_rng_init(struct bcm43xx_private *bcm)
 	return err;
 }
 
+void bcm43xx_cancel_work(struct bcm43xx_private *bcm)
+{
+	/* The system must be unlocked when this routine is entered.
+	 * If not, the next 2 steps may deadlock */
+	cancel_work_sync(&bcm->restart_work);
+	cancel_delayed_work_sync(&bcm->periodic_work);
+}
+
 static int bcm43xx_shutdown_all_wireless_cores(struct bcm43xx_private *bcm)
 {
 	int ret = 0;
@@ -3321,7 +3328,12 @@ static void bcm43xx_free_board(struct bcm43xx_private *bcm)
 {
 	bcm43xx_rng_exit(bcm);
 	bcm43xx_sysfs_unregister(bcm);
-	bcm43xx_periodic_tasks_delete(bcm);
+
+	mutex_lock(&(bcm)->mutex);
+	bcm43xx_set_status(bcm, BCM43xx_STAT_UNINIT);
+	mutex_unlock(&(bcm)->mutex);
+
+	bcm43xx_cancel_work(bcm);
 
 	mutex_lock(&(bcm)->mutex);
 	bcm43xx_shutdown_all_wireless_cores(bcm);
@@ -4016,7 +4028,7 @@ static int bcm43xx_net_stop(struct net_device *net_dev)
 	err = bcm43xx_disable_interrupts_sync(bcm);
 	assert(!err);
 	bcm43xx_free_board(bcm);
-	flush_scheduled_work();
+	bcm43xx_cancel_work(bcm);
 
 	return 0;
 }
@@ -4148,9 +4160,9 @@ static void bcm43xx_chip_reset(struct work_struct *work)
 	struct bcm43xx_phyinfo *phy;
 	int err = -ENODEV;
 
+	bcm43xx_cancel_work(bcm);
 	mutex_lock(&(bcm)->mutex);
 	if (bcm43xx_status(bcm) == BCM43xx_STAT_INITIALIZED) {
-		bcm43xx_periodic_tasks_delete(bcm);
 		phy = bcm43xx_current_phy(bcm);
 		err = bcm43xx_select_wireless_core(bcm, phy->type);
 		if (!err)