[tip:perfcounters/core] Revert "perf_counter, x86: speed up the scheduling fast-path"

[tip-bot for Ingo Molnar <mingo@elte.hu>]

Commit-ID:  53b441a565bf4036ab49c8ea04c5ad06ace7dd6b
Gitweb:     http://git.kernel.org/tip/53b441a565bf4036ab49c8ea04c5ad06ace7dd6b
Author:     Ingo Molnar <mingo@elte.hu>
AuthorDate: Mon, 25 May 2009 21:41:28 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 25 May 2009 21:41:28 +0200

Revert "perf_counter, x86: speed up the scheduling fast-path"

This reverts commit b68f1d2e7aa21029d73c7d453a8046e95d351740.

It is causing problems (stuck/stuttering profiling) - when mixed
NMI and non-NMI counters are used.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
LKML-Reference: <20090525153931.703093461@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 arch/x86/kernel/cpu/perf_counter.c |    5 +++--
 1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index c4b543d..189bf9d 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -293,7 +293,6 @@ static int __hw_perf_counter_init(struct perf_counter *counter)
 			return -EACCES;
 		hwc->nmi = 1;
 	}
-	perf_counters_lapic_init(hwc->nmi);
 
 	if (!hwc->irq_period)
 		hwc->irq_period = x86_pmu.max_period;
@@ -612,6 +611,8 @@ try_generic:
 		hwc->counter_base = x86_pmu.perfctr;
 	}
 
+	perf_counters_lapic_init(hwc->nmi);
+
 	x86_pmu.disable(hwc, idx);
 
 	cpuc->counters[idx] = counter;
@@ -1037,7 +1038,7 @@ void __init init_hw_perf_counters(void)
 
 	pr_info("... counter mask:    %016Lx\n", perf_counter_mask);
 
-	perf_counters_lapic_init(1);
+	perf_counters_lapic_init(0);
 	register_die_notifier(&perf_counter_nmi_notifier);
 }