Re: igb and bnx2: "NETDEV WATCHDOG: transmit queue timed out" whenskb has huge linear buffer

[Zoltan Kiss]

On 05/02/14 20:43, Andrew Cooper wrote:
> On 05/02/2014 20:23, Zoltan Kiss wrote:
> > On 04/02/14 19:47, Michael Chan wrote:
> > > On Fri, 2014-01-31 at 14:29 +0100, Zoltan Kiss wrote:
> > > > [ 5417.275472] WARNING: at net/sched/sch_generic.c:255
> > > > dev_watchdog+0x156/0x1f0()
> > > > [ 5417.275474] NETDEV WATCHDOG: eth1 (bnx2): transmit queue 2 timed out
> > >
> > > The dump shows an internal IRQ pending on MSIX vector 2 which matches
> > > the the queue number that is timing out.  I don't know what happened to
> > > the MSIX and why the driver is not seeing it.  Do you see an IRQ error
> > > message from the kernel a few seconds before the tx timeout message?
> >
> > I haven't seen any IRQ related error message. Note, this is on Xen
> > 4.3.1. Now I have new results with a reworked version of the patch,
> > unfortunately it still has this issue. Here is a bnx2 dump, lspci
> > output and some Xen debug output (MSI and interrupt bindings, I have
> > more if needed).
>
> You need debug-keys 'Q' as well to map between the PCI devices and Xen IRQs
>
> ~Andrew

I could have it after reboot:

(XEN) [2014-02-06 09:44:34] 0000:02:00.0 - dom 0   - MSIs < 64 65 66 67 
68 69 >

So the relevant MSI informations:

(XEN) [2014-02-05 20:15:20]  MSI-X   64 vec=d7  fixed  edge   assert 
phys    cpu dest=00000022 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   65 vec=ba  fixed  edge   assert 
phys    cpu dest=00000000 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   66 vec=92  fixed  edge   assert 
phys    cpu dest=00000022 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   67 vec=3a  fixed  edge   assert 
phys    cpu dest=00000021 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   68 vec=b8  fixed  edge   assert 
phys    cpu dest=00000022 mask=1/0/0
(XEN) [2014-02-05 20:15:20]  MSI-X   69 vec=2a  fixed  edge   assert 
phys    cpu dest=00000020 mask=1/1/1
...
(XEN) [2014-02-05 20:15:22]    IRQ:  64 affinity:00000004 vec:d7 
type=PCI-MSI/-X      status=00000030 in-flight=0 domain-list=0:304(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  65 affinity:00000100 vec:ba 
type=PCI-MSI/-X      status=00000010 in-flight=0 domain-list=0:303(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  66 affinity:00000004 vec:92 
type=PCI-MSI/-X      status=00000010 in-flight=0 domain-list=0:302(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  67 affinity:00000002 vec:3a 
type=PCI-MSI/-X      status=00000010 in-flight=0 domain-list=0:301(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  68 affinity:00000004 vec:b8 
type=PCI-MSI/-X      status=00000030 in-flight=0 domain-list=0:300(---),
(XEN) [2014-02-05 20:15:22]    IRQ:  69 affinity:00000001 vec:2a 
type=PCI-MSI/-X      status=00000002 mapped, unbound


Zoli
--
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/