Re: [PATCH] Separate performance counter reservation from nmi watchdog

2007-06-18 Thread Björn Steinbrink
On 2007.06.18 02:52:38 -0700, Stephane Eranian wrote: > Hello Bjorn, > > Sorry for the delay in my reponse. > > > > From: Björn Steinbrink <[EMAIL PROTECTED]> > > > > > > Separate the performance counter reservation system from the nmi > > > watchdog to allow usage of all performance counters ev

Re: [PATCH] Separate performance counter reservation from nmi watchdog

2007-06-18 Thread Stephane Eranian
Hello Bjorn, Sorry for the delay in my reponse. > > From: Björn Steinbrink <[EMAIL PROTECTED]> > > > > Separate the performance counter reservation system from the nmi > > watchdog to allow usage of all performance counters even if the nmi > > watchdog is not used. > > I think it is a good ide

Re: [PATCH] Separate performance counter reservation from nmi watchdog

2007-06-13 Thread Björn Steinbrink
On 2007.06.13 03:41:36 +0200, Björn Steinbrink wrote: > On 2007.06.12 21:07:30 +0200, Björn Steinbrink wrote: > > On 2007.06.12 08:02:46 -0700, Stephane Eranian wrote: > > > * the fill_in_addresses() callback for X86 invokes the NMI watchdog > > >reserve_*_nmi() register allocation routines. T

[PATCH] Separate performance counter reservation from nmi watchdog

2007-06-12 Thread Björn Steinbrink
On 2007.06.12 21:07:30 +0200, Björn Steinbrink wrote: > On 2007.06.12 08:02:46 -0700, Stephane Eranian wrote: > > * the fill_in_addresses() callback for X86 invokes the NMI watchdog > >reserve_*_nmi() register allocation routines. This is done regardless > >of whether the NMI watchdog is a