Skip to contentSkip to conversation

ixgbe: backport bug fix for tx panic

PATCH In review Jeff Kirsher 3 participants 7 messages May 11, 2010 – Jul 3, 2010

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 ixgbe: backport bug fix for tx panic

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f

Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

ixgbe: Fix return of invalid txq

a developer had complained of getting lots of warnings:

"eth16 selects TX queue 98, but real number of TX queues is 64"

http://www.mail-archive.com/[email protected]/msg02200.html

As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

---

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--
 1 files changed, 6 insertions(+), 2 deletions(-)
drivers/net/ixgbe/ixgbe_main.c +6 -2
index 6339d65..a873c5d 100644
@@ -5241,9 +5241,13 @@ static int ixgbe_maybe_stop_tx(struct net_device *netdev,
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	int txq = smp_processor_id();
 
-	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)
-		return smp_processor_id();
+	if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
+		while (unlikely(txq >= dev->real_num_tx_queues))
+			txq -= dev->real_num_tx_queues;
+		return txq;
+	}
 
 	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
 		return (skb->vlan_tci & IXGBE_TX_FLAGS_VLAN_PRIO_MASK) >> 13;
#1 lore raw
Quoted 26 lines · Jeff Kirsher

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f
Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

   ixgbe: Fix return of invalid txq

   a developer had complained of getting lots of warnings:

   "eth16 selects TX queue 98, but real number of TX queues is 64"

   http://www.mail-archive.com/[email protected]/msg02200.html

   As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

Quoted 7 lines

---

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--

 1 files changed, 6 insertions(+), 2 deletions(-)

Greg - status? Did you queue this patch for the stable release and I missed it?

Signature · 2 lines
Cheers,
Jeff
#2 lore raw
Quoted 31 lines · Jeff Kirsher
Quoted 30 lines · Jeff Kirsher

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f
Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

   ixgbe: Fix return of invalid txq

   a developer had complained of getting lots of warnings:

   "eth16 selects TX queue 98, but real number of TX queues is 64"

   http://www.mail-archive.com/[email protected]/msg02200.html

   As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

---

Quoted 5 lines
Quoted 3 lines

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--

 1 files changed, 6 insertions(+), 2 deletions(-)

Greg - status? Did you queue this patch for the stable release and I missed it?

Maybe we didn't say (and we should have) that this fixes a panic on machines with > 64 cores. Please apply to -stable 32.

#3 lore raw
Quoted 35 lines · Jesse
Quoted 31 lines · Jeff Kirsher
Quoted 30 lines · Jeff Kirsher

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f
Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

   ixgbe: Fix return of invalid txq

   a developer had complained of getting lots of warnings:

   "eth16 selects TX queue 98, but real number of TX queues is 64"

   http://www.mail-archive.com/[email protected]/msg02200.html

   As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

---

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--

 1 files changed, 6 insertions(+), 2 deletions(-)

Greg - status? Did you queue this patch for the stable release and I missed it?

Maybe we didn't say (and we should have) that this fixes a panic on machines with > 64 cores. Please apply to -stable 32.

I'll get to it for the next release after this one, if that's ok.

thanks,

greg k-h

#4 lore raw
Quoted 45 lines · Greg KH
Quoted 35 lines · Jesse
Quoted 31 lines · Jeff Kirsher
Quoted 30 lines · Jeff Kirsher

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f
Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

   ixgbe: Fix return of invalid txq

   a developer had complained of getting lots of warnings:

   "eth16 selects TX queue 98, but real number of TX queues is 64"

   http://www.mail-archive.com/[email protected]/msg02200.html

   As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

---

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--

 1 files changed, 6 insertions(+), 2 deletions(-)

Greg - status?  Did you queue this patch for the stable release and I missed it?

Maybe we didn't say (and we should have) that this fixes a panic on machines with > 64 cores.  Please apply to -stable 32.

Quoted 6 lines

I'll get to it for the next release after this one, if that's ok.

thanks,

greg k-h
--

I did not see this patch in the list of patches for the next release of the stable kernel. Just want to make sure this patch makes it this time... :)

Signature · 2 lines
Cheers,
Jeff
#5 lore raw
Quoted 48 lines · Jeff Kirsher
Quoted 47 lines · Greg KH
Quoted 35 lines · Jesse
Quoted 31 lines · Jeff Kirsher
Quoted 30 lines · Jeff Kirsher

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f
Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

   ixgbe: Fix return of invalid txq

   a developer had complained of getting lots of warnings:

   "eth16 selects TX queue 98, but real number of TX queues is 64"

   http://www.mail-archive.com/[email protected]/msg02200.html

   As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

---

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--

 1 files changed, 6 insertions(+), 2 deletions(-)

Greg - status?  Did you queue this patch for the stable release and I missed it?

Maybe we didn't say (and we should have) that this fixes a panic on machines with > 64 cores.  Please apply to -stable 32.

I'll get to it for the next release after this one, if that's ok.

Quoted 8 lines
Quoted 4 lines

thanks,

greg k-h
--

I did not see this patch in the list of patches for the next release of the stable kernel. Just want to make sure this patch makes it this time... :)

Ick, I missed it, let me go queue it up right now, sorry about that.

greg k-h

#6 lore raw
In reply to Jeff Kirsher
Quoted 31 lines · Jeff Kirsher
Quoted 30 lines · Jeff Kirsher

From: Jesse Brandeburg <[email protected]>

backporting this commit:

commit fdd3d631cddad20ad9d3e1eb7dbf26825a8a121f
Author: Krishna Kumar <[email protected]>
Date:   Wed Feb 3 13:13:10 2010 +0000

   ixgbe: Fix return of invalid txq

   a developer had complained of getting lots of warnings:

   "eth16 selects TX queue 98, but real number of TX queues is 64"

   http://www.mail-archive.com/[email protected]/msg02200.html

   As there was no follow up on that bug, I am submitting this patch assuming that the other return points will not return invalid txq's, and also that this fixes the bug (not tested).

---

Quoted 5 lines
Quoted 3 lines

 drivers/net/ixgbe/ixgbe_main.c |    8 ++++++--

 1 files changed, 6 insertions(+), 2 deletions(-)

Greg - status? Did you queue this patch for the stable release and I missed it?

Nope, I missed it, sorry.

I'll make sure to get it for the next .32 round.

thanks,

greg k-h