8139too: RTNL and flush_scheduled_work deadlock]

PATCH In review Ben Greear 2 participants 3 messages Apr 6, 2007 – Apr 11, 2007

Subsystems (2)

Networking Network drivers

lore

Share & tools

lore

Ben Greear

author

2007-04-06 05:52 UTC #0 lore raw

PATCH 3/4 8139too: RTNL and flush_scheduled_work deadlock]

Please consider this for the 2.6.20 stable branch. This fixes a deadlock between the bridging code and the 8139too driver. I am not the author of this patch, but I have tested a slightly modified version (so that it works with the 2.6.18 kernel) extensively and it solves the deadlock. Mr. Romieu suggested I forward this to you...

Thanks,
Ben

-------- Original Message --------
Subject: [PATCH 3/4] 8139too: RTNL and flush_scheduled_work deadlock
Date: Thu, 15 Feb 2007 23:37:44 +0100
From: Francois Romieu <[email protected]>
To: [email protected]
CC: Stephen Hemminger <[email protected]>, [email protected], [email protected], Ben Greear <[email protected]>, Kyle Lucke <[email protected]>, Raghavendra Koushik <[email protected]>, Al Viro <[email protected]>

Your usual dont-flush_scheduled_work-with-RTNL-held stuff.

It is a bit different here since the thread runs permanently or is only occasionally kicked for recovery depending on the hardware revision.

Signed-off-by Francois Romieu <[email protected]>

---
drivers/net/8139too.c | 40 +++++++++++++++++-----------------------

1 files changed, 17 insertions(+), 23 deletions(-)

drivers/net/8139too.c +0 -0

index 35ad5cf..99304b2 100644
@@ -1109,6 +1109,8 @@ static void __devexit rtl8139_remove_one (struct pci_dev *pdev)

	assert (dev != NULL);

+ flush_scheduled_work();
+

	unregister_netdev (dev);

	__rtl8139_cleanup_dev (dev);
@@ -1603,18 +1605,21 @@ static void rtl8139_thread (struct work_struct *work)
	struct net_device *dev = tp->mii.dev;
	unsigned long thr_delay = next_tick;

+ rtnl_lock();
+
+ if (!netif_running(dev))
+ goto out_unlock;
+

	if (tp->watchdog_fired) {
		tp->watchdog_fired = 0;
		rtl8139_tx_timeout_task(work);

- } else if (rtnl_trylock()) {
- rtl8139_thread_iter (dev, tp, tp->mmio_addr);
- rtnl_unlock ();
- } else {
- /* unlikely race. mitigate with fast poll. */
- thr_delay = HZ / 2;
- }
+ } else
+ rtl8139_thread_iter(dev, tp, tp->mmio_addr);

- schedule_delayed_work(&tp->thread, thr_delay);
+ if (tp->have_thread)
+ schedule_delayed_work(&tp->thread, thr_delay);
+out_unlock:
+ rtnl_unlock ();
}

static void rtl8139_start_thread(struct rtl8139_private *tp)
@@ -1626,19 +1631,11 @@ static void rtl8139_start_thread(struct rtl8139_private *tp)

		return;

	tp->have_thread = 1;

+ tp->watchdog_fired = 0;

	schedule_delayed_work(&tp->thread, next_tick);
}

-static void rtl8139_stop_thread(struct rtl8139_private *tp) -{
- if (tp->have_thread) {
- cancel_rearming_delayed_work(&tp->thread);
- tp->have_thread = 0;
- } else
- flush_scheduled_work();
-}
-
static inline void rtl8139_tx_clear (struct rtl8139_private *tp)

{
	tp->cur_tx = 0;
@@ -1696,12 +1693,11 @@ static void rtl8139_tx_timeout (struct net_device *dev)
{
	struct rtl8139_private *tp = netdev_priv(dev);

+	tp->watchdog_fired = 1;
	if (!tp->have_thread) {
-		INIT_DELAYED_WORK(&tp->thread, rtl8139_tx_timeout_task);
+		INIT_DELAYED_WORK(&tp->thread, rtl8139_thread);
		schedule_delayed_work(&tp->thread, next_tick);

- } else
- tp->watchdog_fired = 1;
-
+ }
}

static int rtl8139_start_xmit (struct sk_buff *skb, struct net_device *dev) @@ -2233,8 +2229,6 @@ static int rtl8139_close (struct net_device *dev)

	netif_stop_queue (dev);

- rtl8139_stop_thread(tp);
-

	if (netif_msg_ifdown(tp))
		printk(KERN_DEBUG "%s: Shutting down ethercard, status was 0x%4.4x.\n",
			dev->name, RTL_R16 (IntrStatus));

Signature · 10 lines

1.4.4.4

-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html


-- 
Ben Greear <[email protected]> Candela Technologies Inc  http://www.candelatech.com

[email protected]

2007-04-11 18:53 UTC #1 lore raw

patch 8139too-rtnl-and-flush_scheduled_work-deadlock.patch queued to -stable tree

This is a note to let you know that we have just queued up the patch titled

Subject: 8139too: RTNL and flush_scheduled_work deadlock

to the 2.6.20-stable tree. Its filename is

8139too-rtnl-and-flush_scheduled_work-deadlock.patch

A git repo of this tree can be found at
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

Quoted 1 line

From [email protected] Thu Apr 5 22:52:18 2007

From: Francois Romieu <[email protected]>
Date: Thu, 05 Apr 2007 22:52:12 -0700
Subject: 8139too: RTNL and flush_scheduled_work deadlock
To: [email protected], NetDev <[email protected]>
Message-ID: <[email protected]>

From: Francois Romieu <[email protected]>

Your usual dont-flush_scheduled_work-with-RTNL-held stuff.

It is a bit different here since the thread runs permanently or is only occasionally kicked for recovery depending on the hardware revision.

Signed-off-by Francois Romieu <[email protected]>

Cc Ben Greear <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

drivers/net/8139too.c +17 ~~-23~~

@@ -1109,6 +1109,8 @@ static void __devexit rtl8139_remove_one (struct pci_dev *pdev)
 
 	assert (dev != NULL);
 
+	flush_scheduled_work();
+
 	unregister_netdev (dev);
 
 	__rtl8139_cleanup_dev (dev);

@@ -1603,18 +1605,21 @@ static void rtl8139_thread (struct work_struct *work)
 	struct net_device *dev = tp->mii.dev;
 	unsigned long thr_delay = next_tick;
 
+	rtnl_lock();
+
+	if (!netif_running(dev))
+		goto out_unlock;
+
 	if (tp->watchdog_fired) {
 		tp->watchdog_fired = 0;
 		rtl8139_tx_timeout_task(work);
-	} else if (rtnl_trylock()) {
-		rtl8139_thread_iter (dev, tp, tp->mmio_addr);
-		rtnl_unlock ();
-	} else {
-		/* unlikely race.  mitigate with fast poll. */
-		thr_delay = HZ / 2;
-	}
+	} else
+		rtl8139_thread_iter(dev, tp, tp->mmio_addr);
 
-	schedule_delayed_work(&tp->thread, thr_delay);
+	if (tp->have_thread)
+		schedule_delayed_work(&tp->thread, thr_delay);
+out_unlock:
+	rtnl_unlock ();
 }
 
 static void rtl8139_start_thread(struct rtl8139_private *tp)

@@ -1626,19 +1631,11 @@ static void rtl8139_start_thread(struct rtl8139_private *tp)
 		return;
 
 	tp->have_thread = 1;
+	tp->watchdog_fired = 0;
 
 	schedule_delayed_work(&tp->thread, next_tick);
 }
 
-static void rtl8139_stop_thread(struct rtl8139_private *tp)
-{
-	if (tp->have_thread) {
-		cancel_rearming_delayed_work(&tp->thread);
-		tp->have_thread = 0;
-	} else
-		flush_scheduled_work();
-}
-
 static inline void rtl8139_tx_clear (struct rtl8139_private *tp)
 {
 	tp->cur_tx = 0;

@@ -1696,12 +1693,11 @@ static void rtl8139_tx_timeout (struct net_device *dev)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
 
+	tp->watchdog_fired = 1;
 	if (!tp->have_thread) {
-		INIT_DELAYED_WORK(&tp->thread, rtl8139_tx_timeout_task);
+		INIT_DELAYED_WORK(&tp->thread, rtl8139_thread);
 		schedule_delayed_work(&tp->thread, next_tick);
-	} else
-		tp->watchdog_fired = 1;
-
+	}
 }
 
 static int rtl8139_start_xmit (struct sk_buff *skb, struct net_device *dev)

@@ -2233,8 +2229,6 @@ static int rtl8139_close (struct net_device *dev)
 
 	netif_stop_queue (dev);
 
-	rtl8139_stop_thread(tp);
-
 	if (netif_msg_ifdown(tp))
 		printk(KERN_DEBUG "%s: Shutting down ethercard, status was 0x%4.4x.\n",
 			dev->name, RTL_R16 (IntrStatus));

Signature · 14 lines

1.4.4.4

-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html


-- 
Ben Greear <[email protected]> 
Candela Technologies Inc  http://www.candelatech.com


Patches currently in stable-queue which might be from [email protected] are

[email protected]

2007-04-11 19:02 UTC #2 lore raw

patch 8139too-rtnl-and-flush_scheduled_work-deadlock.patch queued to -stable tree

In reply to Ben Greear

This is a note to let you know that we have just queued up the patch titled

Subject: 8139too: RTNL and flush_scheduled_work deadlock

to the 2.6.20-stable tree. Its filename is

8139too-rtnl-and-flush_scheduled_work-deadlock.patch

A git repo of this tree can be found at
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

Quoted 1 line

From [email protected] Thu Apr 5 22:52:18 2007

From: Francois Romieu <[email protected]>

Your usual dont-flush_scheduled_work-with-RTNL-held stuff.

It is a bit different here since the thread runs permanently or is only occasionally kicked for recovery depending on the hardware revision.

Signed-off-by Francois Romieu <[email protected]>

Cc Ben Greear <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

drivers/net/8139too.c +17 ~~-23~~

@@ -1109,6 +1109,8 @@ static void __devexit rtl8139_remove_one (struct pci_dev *pdev)
 
 	assert (dev != NULL);
 
+	flush_scheduled_work();
+
 	unregister_netdev (dev);
 
 	__rtl8139_cleanup_dev (dev);

@@ -1603,18 +1605,21 @@ static void rtl8139_thread (struct work_struct *work)
 	struct net_device *dev = tp->mii.dev;
 	unsigned long thr_delay = next_tick;
 
+	rtnl_lock();
+
+	if (!netif_running(dev))
+		goto out_unlock;
+
 	if (tp->watchdog_fired) {
 		tp->watchdog_fired = 0;
 		rtl8139_tx_timeout_task(work);
-	} else if (rtnl_trylock()) {
-		rtl8139_thread_iter (dev, tp, tp->mmio_addr);
-		rtnl_unlock ();
-	} else {
-		/* unlikely race.  mitigate with fast poll. */
-		thr_delay = HZ / 2;
-	}
+	} else
+		rtl8139_thread_iter(dev, tp, tp->mmio_addr);
 
-	schedule_delayed_work(&tp->thread, thr_delay);
+	if (tp->have_thread)
+		schedule_delayed_work(&tp->thread, thr_delay);
+out_unlock:
+	rtnl_unlock ();
 }
 
 static void rtl8139_start_thread(struct rtl8139_private *tp)

@@ -1626,19 +1631,11 @@ static void rtl8139_start_thread(struct rtl8139_private *tp)
 		return;
 
 	tp->have_thread = 1;
+	tp->watchdog_fired = 0;
 
 	schedule_delayed_work(&tp->thread, next_tick);
 }
 
-static void rtl8139_stop_thread(struct rtl8139_private *tp)
-{
-	if (tp->have_thread) {
-		cancel_rearming_delayed_work(&tp->thread);
-		tp->have_thread = 0;
-	} else
-		flush_scheduled_work();
-}
-
 static inline void rtl8139_tx_clear (struct rtl8139_private *tp)
 {
 	tp->cur_tx = 0;

@@ -1696,12 +1693,11 @@ static void rtl8139_tx_timeout (struct net_device *dev)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
 
+	tp->watchdog_fired = 1;
 	if (!tp->have_thread) {
-		INIT_DELAYED_WORK(&tp->thread, rtl8139_tx_timeout_task);
+		INIT_DELAYED_WORK(&tp->thread, rtl8139_thread);
 		schedule_delayed_work(&tp->thread, next_tick);
-	} else
-		tp->watchdog_fired = 1;
-
+	}
 }
 
 static int rtl8139_start_xmit (struct sk_buff *skb, struct net_device *dev)

@@ -2233,8 +2229,6 @@ static int rtl8139_close (struct net_device *dev)
 
 	netif_stop_queue (dev);
 
-	rtl8139_stop_thread(tp);
-
 	if (netif_msg_ifdown(tp))
 		printk(KERN_DEBUG "%s: Shutting down ethercard, status was 0x%4.4x.\n",
 			dev->name, RTL_R16 (IntrStatus));

Signature · 14 lines

1.4.4.4

-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html


-- 
Ben Greear <[email protected]> 
Candela Technologies Inc  http://www.candelatech.com


Patches currently in stable-queue which might be from [email protected] are