[tip:perf/pebs] perf, x86: Fix pebs drains
in [Kernel]
|
Prev: [tip:perf/pebs] perf, x86: Robustify PEBS fixup
Next: [PATCH] Route kbd LEDs through the generic LEDs layer (5th version)
From: tip-bot for Peter Zijlstra on 10 Mar 2010 08:30 Commit-ID: 8f4aebd2be9892bf8fb79a2d8576d3f3ee7f00f6 Gitweb: http://git.kernel.org/tip/8f4aebd2be9892bf8fb79a2d8576d3f3ee7f00f6 Author: Peter Zijlstra <a.p.zijlstra(a)chello.nl> AuthorDate: Sat, 6 Mar 2010 13:26:11 +0100 Committer: Ingo Molnar <mingo(a)elte.hu> CommitDate: Wed, 10 Mar 2010 13:23:36 +0100 perf, x86: Fix pebs drains I overlooked the perf_disable()/perf_enable() calls in intel_pmu_handle_irq(), (pointed out by Markus) so we should not explicitly disable_all/enable_all pebs counters in the drain functions, these are already disabled and enabling them early is confusing. Signed-off-by: Peter Zijlstra <a.p.zijlstra(a)chello.nl> Cc: Arnaldo Carvalho de Melo <acme(a)infradead.org> Cc: paulus(a)samba.org Cc: eranian(a)google.com Cc: robert.richter(a)amd.com Cc: fweisbec(a)gmail.com LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo(a)elte.hu> --- arch/x86/kernel/cpu/perf_event_intel_ds.c | 15 +++------------ 1 files changed, 3 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index a7401e4..66c6962 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -476,18 +476,16 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event || !ds || !x86_pmu.pebs) return; - intel_pmu_pebs_disable_all(); - at = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_core *)(unsigned long)ds->pebs_index; if (top <= at) - goto out; + return; ds->pebs_index = ds->pebs_buffer_base; if (!intel_pmu_save_and_restart(event)) - goto out; + return; perf_sample_data_init(&data, 0); data.period = event->hw.last_period; @@ -528,9 +526,6 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (perf_event_overflow(event, 1, &data, ®s)) x86_pmu_stop(event); - -out: - intel_pmu_pebs_enable_all(); } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) @@ -547,13 +542,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) if (!ds || !x86_pmu.pebs) return; - intel_pmu_pebs_disable_all(); - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; if (top <= at) - goto out; + return; ds->pebs_index = ds->pebs_buffer_base; @@ -604,8 +597,6 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) if (perf_event_overflow(event, 1, &data, ®s)) x86_pmu_stop(event); } -out: - intel_pmu_pebs_enable_all(); } /* -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |