From 5727347180ebc6b4a866fcbe00dcb39cc03acb37 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 6 Mar 2012 17:33:17 +0100 Subject: ARM: 7354/1: perf: limit sample_period to half max_period in non-sampling mode On ARM, the PMU does not stop counting after an overflow and therefore IRQ latency affects the new counter value read by the kernel. This is significant for non-sampling runs where it is possible for the new value to overtake the previous one, causing the delta to be out by up to max_period events. Commit a737823d ("ARM: 6835/1: perf: ensure overflows aren't missed due to IRQ latency") attempted to fix this problem by allowing interrupt handlers to pass an overflow flag to the event update function, causing the overflow calculation to assume that the counter passed through zero when going from prev to new. Unfortunately, this doesn't work when overflow occurs on the perf_task_tick path because we have the flag cleared and end up computing a large negative delta. This patch removes the overflow flag from armpmu_event_update and instead limits the sample_period to half of the max_period for non-sampling profiling runs. Cc: Signed-off-by: Ming Lei Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/perf_event.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'arch/arm/kernel/perf_event.c') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 5bb91bf3d47..56173ae1644 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -180,7 +180,7 @@ armpmu_event_set_period(struct perf_event *event, u64 armpmu_event_update(struct perf_event *event, struct hw_perf_event *hwc, - int idx, int overflow) + int idx) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); u64 delta, prev_raw_count, new_raw_count; @@ -193,13 +193,7 @@ again: new_raw_count) != prev_raw_count) goto again; - new_raw_count &= armpmu->max_period; - prev_raw_count &= armpmu->max_period; - - if (overflow) - delta = armpmu->max_period - prev_raw_count + new_raw_count + 1; - else - delta = new_raw_count - prev_raw_count; + delta = (new_raw_count - prev_raw_count) & armpmu->max_period; local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); @@ -216,7 +210,7 @@ armpmu_read(struct perf_event *event) if (hwc->idx < 0) return; - armpmu_event_update(event, hwc, hwc->idx, 0); + armpmu_event_update(event, hwc, hwc->idx); } static void @@ -232,7 +226,7 @@ armpmu_stop(struct perf_event *event, int flags) if (!(hwc->state & PERF_HES_STOPPED)) { armpmu->disable(hwc, hwc->idx); barrier(); /* why? */ - armpmu_event_update(event, hwc, hwc->idx, 0); + armpmu_event_update(event, hwc, hwc->idx); hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; } } @@ -518,7 +512,13 @@ __hw_perf_event_init(struct perf_event *event) hwc->config_base |= (unsigned long)mapping; if (!hwc->sample_period) { - hwc->sample_period = armpmu->max_period; + /* + * For non-sampling runs, limit the sample_period to half + * of the counter width. That way, the new counter value + * is far less likely to overtake the previous one unless + * you have some serious IRQ latency issues. + */ + hwc->sample_period = armpmu->max_period >> 1; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } -- cgit v1.2.3-70-g09d2 From a0feb6db0fe03326d7d2c7a4615ce3289615c023 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 6 Mar 2012 17:37:45 +0100 Subject: ARM: 7358/1: perf: add PMU hotplug notifier When a CPU is taken out of reset, either cold booted or hotplugged in, some of its PMU registers can contain UNKNOWN values. This patch adds a hotplug notifier to ARM core perf code so that upon CPU restart the PMU unit is reset and becomes ready to use again. Signed-off-by: Lorenzo Pieralisi Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/kernel/perf_event.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'arch/arm/kernel/perf_event.c') diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 56173ae1644..b2abfa18f13 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -679,6 +679,28 @@ static void __init cpu_pmu_init(struct arm_pmu *armpmu) armpmu->type = ARM_PMU_DEVICE_CPU; } +/* + * PMU hardware loses all context when a CPU goes offline. + * When a CPU is hotplugged back in, since some hardware registers are + * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading + * junk values out of them. + */ +static int __cpuinit pmu_cpu_notify(struct notifier_block *b, + unsigned long action, void *hcpu) +{ + if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING) + return NOTIFY_DONE; + + if (cpu_pmu && cpu_pmu->reset) + cpu_pmu->reset(NULL); + + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata pmu_cpu_notifier = { + .notifier_call = pmu_cpu_notify, +}; + /* * CPU PMU identification and registration. */ @@ -730,6 +752,7 @@ init_hw_perf_events(void) pr_info("enabled with %s PMU driver, %d counters available\n", cpu_pmu->name, cpu_pmu->num_events); cpu_pmu_init(cpu_pmu); + register_cpu_notifier(&pmu_cpu_notifier); armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW); } else { pr_info("no hardware support available\n"); -- cgit v1.2.3-70-g09d2