Messages in this thread | | | Date | Mon, 28 Dec 2009 12:55:46 +0300 | From | Cyrill Gorcunov <> | Subject | Re: [PATCH] x86, perfctr: remove unused func avail_to_resrv_perfctr_nmi() |
| |
On Mon, Dec 28, 2009 at 09:38:45AM +0100, Ingo Molnar wrote: > > * Cyrill Gorcunov <gorcunov@gmail.com> wrote: > > > On Thu, Dec 24, 2009 at 01:54:47AM +0000, Naga Chumbalkar wrote: > > > avail_to_resrv_perfctr_nmi() is neither EXPORT'd, nor used in the file. > > > So remove it. > > > > > > Signed-off-by: Naga Chumbalkar <nagananda.chumbalkar@hp.com> > > > --- > > > arch/x86/include/asm/nmi.h | 1 - > > > arch/x86/kernel/cpu/perfctr-watchdog.c | 11 ----------- > > > 2 files changed, 0 insertions(+), 12 deletions(-) > > > > > > > Hi Naga, this looks good to me! Thanks. > > > > Is there any plans to use this routine in future > > so we shouldn't touch this snippet? > > Not that i know of.
ok, then we could apply this patch I think, at least for a while.
> > In fact we should transform/migrate the NMI watchdog driver by making it based > on a kernel-internal created perf event. (which is what the NMI watchdog > really is: a periodic NMI event occuring once per second and running a > callback function.)
Yes, this would be great. I'll try to find out some time for this task, though no promises :) If someone get it done earlier I would really appreciate.
> > That would give us NMI watchdog support on all future x86 CPUs, automatically > - without having to extend the arch/x86/kernel/cpu/perfctr-watchdog.c code for > it. > > Ingo > -- Cyrill
| |