From c46e665f037743bbce7887e7c55750713eb7fb09 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 2 Sep 2014 11:44:14 -0700 Subject: [PATCH] perf/x86: Add INST_RETIRED.ALL workarounds On Broadwell INST_RETIRED.ALL cannot be used with any period that doesn't have the lowest 6 bits cleared. And the period should not be smaller than 128. Add a new callback to enforce this, and set it for Broadwell. This is erratum BDM57 and BDM11. How does this handle the case when an app requests a specific period with some of the bottom bits set The apps thinks it is sampling at X occurences per sample, when it is in fact at X - 63 (worst case). Short answer: Any useful instruction sampling period needs to be 4-6 orders of magnitude larger than 128, as an PMI every 128 instructions would instantly overwhelm the system and be throttled. So the +-64 error from this is really small compared to the period, much smaller than normal system jitter. Long answer: IFF we guarantee perf_event_attr::sample_period >= 128. Suppose we start out with sample_period=192; then we'll set period_left to 192, we'll end up with left = 128 (we truncate the lower bits). We get an interrupt, find that period_left = 64 (>0 so we return 0 and don't get an overflow handler), up that to 128. Then we trigger again, at n=256. Then we find period_left = -64 (<=0 so we return 1 and do get an overflow). We increment with sample_period so we get left = 128. We fire again, at n=384, period_left = 0 (<=0 so we return 1 and get an overflow). And on and on. So while the individual interrupts are 'wrong' we get then with interval=256,128 in exactly the right ratio to average out at 192. And this works for everything >=128. So the num_samples*fixed_period thing is still entirely correct +- 127, which is good enough I'd say, as you already have that error anyhow. So no need to 'fix' the tools, al we need to do is refuse to create INST_RETIRED:ALL events with sample_period < 128. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Andi Kleen Cc: Arnaldo Carvalho de Melo Cc: Kan Liang Cc: Maria Dimakopoulou Cc: Mark Davies Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1409683455-29168-4-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.c | 9 +++++++++ arch/x86/kernel/cpu/perf_event.h | 1 + arch/x86/kernel/cpu/perf_event_intel.c | 19 +++++++++++++++++++ 3 files changed, 29 insertions(+) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 0646d3b63b9d..918d75f77be7 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -443,6 +443,12 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + if (event->attr.sample_period && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, event->attr.sample_period) > + event->attr.sample_period) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -980,6 +986,9 @@ int x86_perf_event_set_period(struct perf_event *event) if (left > x86_pmu.max_period) left = x86_pmu.max_period; + if (x86_pmu.limit_period) + left = x86_pmu.limit_period(event, left); + per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index fc5eb390b368..d98a34d435d7 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -445,6 +445,7 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; + unsigned (*limit_period)(struct perf_event *event, unsigned l); /* * sysfs attrs diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 567156608613..bbcd0d2b157a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2034,6 +2034,24 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) return c; } +/* + * Broadwell: + * The INST_RETIRED.ALL period always needs to have lowest + * 6bits cleared (BDM57). It shall not use a period smaller + * than 100 (BDM11). We combine the two to enforce + * a min-period of 128. + */ +static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +{ + if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (left < 128) + left = 128; + left &= ~0x3fu; + } + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -2712,6 +2730,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.limit_period = bdw_limit_period; pr_cont("Broadwell events, "); break; -- 2.39.5