[Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Jan Kiszka
Hi guys, we are currently trying to catch an ugly Linux pipeline state corruption on x86-64. Conceptual question: If a Xenomai task causes a fault, we enter ipipe_trap_notify over the primary domain and leave it over the root domain, right? Now, if the root domain happened to be stalled when the

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Jan Kiszka
Jan Kiszka wrote: > Hi guys, > > we are currently trying to catch an ugly Linux pipeline state corruption > on x86-64. > > Conceptual question: If a Xenomai task causes a fault, we enter > ipipe_trap_notify over the primary domain and leave it over the root > domain, right? Now, if the root domai

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Philippe Gerum
On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: > Hi guys, > > we are currently trying to catch an ugly Linux pipeline state corruption > on x86-64. > > Conceptual question: If a Xenomai task causes a fault, we enter > ipipe_trap_notify over the primary domain and leave it over the root > d

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Gilles Chanteperdrix
Philippe Gerum wrote: > On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: >> Hi guys, >> >> we are currently trying to catch an ugly Linux pipeline state corruption >> on x86-64. >> >> Conceptual question: If a Xenomai task causes a fault, we enter >> ipipe_trap_notify over the primary domain a

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Gilles Chanteperdrix
Jan Kiszka wrote: > Hi guys, > > we are currently trying to catch an ugly Linux pipeline state corruption > on x86-64. > > Conceptual question: If a Xenomai task causes a fault, we enter > ipipe_trap_notify over the primary domain and leave it over the root > domain, right? Now, if the root domai

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Jan Kiszka
Gilles Chanteperdrix wrote: > Philippe Gerum wrote: >> On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: >>> Hi guys, >>> >>> we are currently trying to catch an ugly Linux pipeline state corruption >>> on x86-64. >>> >>> Conceptual question: If a Xenomai task causes a fault, we enter >>> ipipe

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Jan Kiszka
Philippe Gerum wrote: > On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: >> Hi guys, >> >> we are currently trying to catch an ugly Linux pipeline state corruption >> on x86-64. >> >> Conceptual question: If a Xenomai task causes a fault, we enter >> ipipe_trap_notify over the primary domain a

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Jan Kiszka
Jan Kiszka wrote: > Philippe Gerum wrote: >> On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: >>> Hi guys, >>> >>> we are currently trying to catch an ugly Linux pipeline state corruption >>> on x86-64. >>> >>> Conceptual question: If a Xenomai task causes a fault, we enter >>> ipipe_trap_noti

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Philippe Gerum
On Fri, 2010-01-22 at 18:41 +0100, Jan Kiszka wrote: > Gilles Chanteperdrix wrote: > > Philippe Gerum wrote: > >> On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: > >>> Hi guys, > >>> > >>> we are currently trying to catch an ugly Linux pipeline state corruption > >>> on x86-64. > >>> > >>> Co

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Jan Kiszka
Philippe Gerum wrote: > On Fri, 2010-01-22 at 18:41 +0100, Jan Kiszka wrote: >> Gilles Chanteperdrix wrote: >>> Philippe Gerum wrote: On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: > Hi guys, > > we are currently trying to catch an ugly Linux pipeline state corruption >

Re: [Xenomai-core] Domain switch during page fault handling

2010-01-22 Thread Philippe Gerum
On Fri, 2010-01-22 at 19:03 +0100, Jan Kiszka wrote: > Philippe Gerum wrote: > > On Fri, 2010-01-22 at 18:41 +0100, Jan Kiszka wrote: > >> Gilles Chanteperdrix wrote: > >>> Philippe Gerum wrote: > On Fri, 2010-01-22 at 17:58 +0100, Jan Kiszka wrote: > > Hi guys, > > > > we are cur