From 2dbf0116aa8c7bfa900352d3f7b2609748fcc1c5 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 5 Sep 2013 20:37:38 -0700 Subject: [PATCH] perf/x86/intel: Avoid checkpointed counters causing excessive TSX aborts With checkpointed counters there can be a situation where the counter is overflowing, aborts the transaction, is set back to a non overflowing checkpoint, causes interupt. The interrupt doesn't see the overflow because it has been checkpointed. This is then a spurious PMI, typically with a ugly NMI message. It can also lead to excessive aborts. Avoid this problem by: - Using the full counter width for counting counters (earlier patch) - Forbid sampling for checkpointed counters. It's not too useful anyways, checkpointing is mainly for counting. The check is approximate (to still handle KVM), but should catch the majority of cases. - On a PMI always set back checkpointed counters to zero. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1378438661-24765-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel.c | 37 ++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9db76c31b3c3..57d64b75f15c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1282,6 +1282,11 @@ static void intel_pmu_enable_event(struct perf_event *event) __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } +static inline bool event_is_checkpointed(struct perf_event *event) +{ + return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0; +} + /* * Save and restart an expired event. Called by NMI contexts, * so it has to be careful about preempting normal event ops: @@ -1289,6 +1294,17 @@ static void intel_pmu_enable_event(struct perf_event *event) int intel_pmu_save_and_restart(struct perf_event *event) { x86_perf_event_update(event); + /* + * For a checkpointed counter always reset back to 0. This + * avoids a situation where the counter overflows, aborts the + * transaction and is then set back to shortly before the + * overflow, and overflows and aborts again. + */ + if (unlikely(event_is_checkpointed(event))) { + /* No race with NMIs because the counter should not be armed */ + wrmsrl(event->hw.event_base, 0); + local64_set(&event->hw.prev_count, 0); + } return x86_perf_event_set_period(event); } @@ -1372,6 +1388,13 @@ again: x86_pmu.drain_pebs(regs); } + /* + * To avoid spurious interrupts with perf stat always reset checkpointed + * counters. + */ + if (cpuc->events[2] && event_is_checkpointed(cpuc->events[2])) + status |= (1ULL << 2); + for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; @@ -1837,6 +1860,20 @@ static int hsw_hw_config(struct perf_event *event) event->attr.precise_ip > 0)) return -EOPNOTSUPP; + if (event_is_checkpointed(event)) { + /* + * Sampling of checkpointed events can cause situations where + * the CPU constantly aborts because of a overflow, which is + * then checkpointed back and ignored. Forbid checkpointing + * for sampling. + * + * But still allow a long sampling period, so that perf stat + * from KVM works. + */ + if (event->attr.sample_period > 0 && + event->attr.sample_period < 0x7fffffff) + return -EOPNOTSUPP; + } return 0; } -- 2.34.1