x86/sched/perf/AMD: Set sched_clock_stable
authorBorislav Petkov <bp@alien8.de>
Tue, 7 Feb 2012 12:08:52 +0000 (13:08 +0100)
committerIngo Molnar <mingo@elte.hu>
Tue, 7 Feb 2012 12:12:08 +0000 (13:12 +0100)
commitc98fdeaa92731308ed80386261fa2589addefa47
tree83faddb633c3a70d9eb6157266aa73e3336272c2
parent52fce956a7568504a1da90c14b9bf2deaad401bd
x86/sched/perf/AMD: Set sched_clock_stable

Stephane Eranian reported that doing a scheduler latency
measurements with perf on AMD doesn't work out as expected due
to the fact that the sched_clock() granularity is too coarse,
i.e. done in jiffies due to the sched_clock_stable not set,
which, if set, would mean that we get to use the TSC as sample
source which would give us much higher precision.

However, there's no reason not to set sched_clock_stable on AMD
because all families from F10h and upwards do have an invariant
TSC and have the CPUID flag to prove (CPUID_8000_0007_EDX[8]).

Make it so, #1.

Signed-off-by: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@amd64.org>
Cc: Venki Pallipadi <venki@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Link: http://lkml.kernel.org/r/20120206132546.GA30854@quad
[ Should any non-standard system break the TSC, we should
  mark them so explicitly, in their platform init handler, or
  in a DMI quirk. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
arch/x86/kernel/cpu/amd.c