Re: softirqs are invoked while bottom halves are masked

2011-07-13 Thread Eric Dumazet
Le mercredi 13 juillet 2011 à 09:20 +0200, Thomas De Schampheleire a écrit : > I just want to mention that, although you seem to think that we > shouldn't have created this thread in the first place, your and Eric's > remarks have actually helped us in identifying the problem and > increasing our

Re: softirqs are invoked while bottom halves are masked

2011-07-13 Thread Thomas De Schampheleire
On Tue, Jul 12, 2011 at 2:13 PM, David Miller wrote: > From: David Miller > Date: Tue, 12 Jul 2011 05:08:17 -0700 (PDT) > >> From: Ronny Meeus >> Date: Tue, 12 Jul 2011 14:03:04 +0200 >> >>> but we still see the issue "BUG: sleeping function called from invalid >>> context": >>> >>> [   91.0159

Re: softirqs are invoked while bottom halves are masked (was: Re: [PATCH] [PATCH] Fix deadlock in af_packet while stressing raw ethernet socket interface)

2011-07-12 Thread Ronny Meeus
On Tue, Jul 12, 2011 at 5:27 PM, Eric Dumazet wrote: > Le mardi 12 juillet 2011 à 14:03 +0200, Ronny Meeus a écrit : > >> Sorry for not mentioning we were using a patched kernel. >> I was not aware that the code involved was patched by the FreeScale >> patches we applied. The code found in the sta

Re: softirqs are invoked while bottom halves are masked (was: Re: [PATCH] [PATCH] Fix deadlock in af_packet while stressing raw ethernet socket interface)

2011-07-12 Thread Ronny Meeus
On Tue, Jul 12, 2011 at 12:10 PM, Eric Dumazet wrote: > Le mardi 12 juillet 2011 à 11:23 +0200, Thomas De Schampheleire a > écrit : >> Hi, >> >> I'm adding the linuxppc-dev mailing list since this may be pointing to >> an irq/softirq problem in the powerpc architecture-specific code... > >> >> Not

Re: softirqs are invoked while bottom halves are masked (was: Re: [PATCH] [PATCH] Fix deadlock in af_packet while stressing raw ethernet socket interface)

2011-07-12 Thread Eric Dumazet
Le mardi 12 juillet 2011 à 14:03 +0200, Ronny Meeus a écrit : > Sorry for not mentioning we were using a patched kernel. > I was not aware that the code involved was patched by the FreeScale > patches we applied. The code found in the stack dumps is not > implemented in FSL specific files. > > Wh

Re: softirqs are invoked while bottom halves are masked

2011-07-12 Thread David Miller
From: David Miller Date: Tue, 12 Jul 2011 05:08:17 -0700 (PDT) > From: Ronny Meeus > Date: Tue, 12 Jul 2011 14:03:04 +0200 > >> but we still see the issue "BUG: sleeping function called from invalid >> context": >> >> [ 91.015989] BUG: sleeping function called from invalid context at >> inc

Re: softirqs are invoked while bottom halves are masked

2011-07-12 Thread David Miller
From: Ronny Meeus Date: Tue, 12 Jul 2011 14:03:04 +0200 > but we still see the issue "BUG: sleeping function called from invalid > context": > > [ 91.015989] BUG: sleeping function called from invalid context at > include/linux/skbuff.h:786 > [ 91.117096] in_atomic(): 1, irqs_disabled(): 0,

Re: softirqs are invoked while bottom halves are masked (was: Re: [PATCH] [PATCH] Fix deadlock in af_packet while stressing raw ethernet socket interface)

2011-07-12 Thread Eric Dumazet
Le mardi 12 juillet 2011 à 11:23 +0200, Thomas De Schampheleire a écrit : > Hi, > > I'm adding the linuxppc-dev mailing list since this may be pointing to > an irq/softirq problem in the powerpc architecture-specific code... > > Note that the reason we are seeing this problem, may be because the

Re: softirqs are invoked while bottom halves are masked

2011-07-12 Thread David Miller
From: Thomas De Schampheleire Date: Tue, 12 Jul 2011 11:23:28 +0200 > Note that the reason we are seeing this problem, may be because the > kernel we are using contains some patches from Freescale. > Specifically, in dev_queue_xmit(), support is added for hardware queue > handling, just before en

softirqs are invoked while bottom halves are masked (was: Re: [PATCH] [PATCH] Fix deadlock in af_packet while stressing raw ethernet socket interface)

2011-07-12 Thread Thomas De Schampheleire
Hi, I'm adding the linuxppc-dev mailing list since this may be pointing to an irq/softirq problem in the powerpc architecture-specific code... On Tue, Jul 12, 2011 at 8:58 AM, Eric Dumazet wrote: > Le mardi 12 juillet 2011 à 08:38 +0200, Ronny Meeus a écrit : >> On Tue, Jul 12, 2011 at 5:27 AM,