Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 41 insertions, 11 deletions

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 5bb91bf3d47f..186c8cb982c5 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);
 	}
@@ -539,6 +539,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
 	if (armpmu->map_event(event) == -ENOENT)
 		return -ENOENT;
 
@@ -680,6 +684,28 @@ static void __init cpu_pmu_init(struct arm_pmu *armpmu)
 }
 
 /*
+ * 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.
  */
 static int __init
@@ -712,6 +738,9 @@ init_hw_perf_events(void)
 		case 0xC0F0:	/* Cortex-A15 */
 			cpu_pmu = armv7_a15_pmu_init();
 			break;
+		case 0xC070:	/* Cortex-A7 */
+			cpu_pmu = armv7_a7_pmu_init();
+			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (0x69 == implementor) {
@@ -730,6 +759,7 @@ 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");