Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Misc fixes: PMU driver corner cases, tooling fixes, and an 'AUX'
  (Intel PT) race related core fix"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler
  perf/x86/intel: Fix memory leak on hot-plug allocation fail
  perf: Fix PERF_EVENT_IOC_PERIOD migration race
  perf: Fix double-free of the AUX buffer
  perf: Fix fasync handling on inherited events
  perf tools: Fix test build error when bindir contains double slash
  perf stat: Fix transaction lenght metrics
  perf: Fix running time accounting

arch/x86/kernel/cpu/perf_event_intel.c

@@ -2534,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
-			return NOTIFY_BAD;
+			goto err;
 	}
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
@@ -2542,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu)
 
 		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
 		if (!cpuc->constraint_list)
-			return NOTIFY_BAD;
+			goto err_shared_regs;
 
 		cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
-		if (!cpuc->excl_cntrs) {
-			kfree(cpuc->constraint_list);
-			kfree(cpuc->shared_regs);
-			return NOTIFY_BAD;
-		}
+		if (!cpuc->excl_cntrs)
+			goto err_constraint_list;
+
 		cpuc->excl_thread_id = 0;
 	}
 
 	return NOTIFY_OK;
+
+err_constraint_list:
+	kfree(cpuc->constraint_list);
+	cpuc->constraint_list = NULL;
+
+err_shared_regs:
+	kfree(cpuc->shared_regs);
+	cpuc->shared_regs = NULL;
+
+err:
+	return NOTIFY_BAD;
 }
 
 static void intel_pmu_cpu_starting(int cpu)

arch/x86/kernel/cpu/perf_event_intel_cqm.c

@@ -1255,7 +1255,7 @@ static inline void cqm_pick_event_reader(int cpu)
 	cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
-static void intel_cqm_cpu_prepare(unsigned int cpu)
+static void intel_cqm_cpu_starting(unsigned int cpu)
 {
 	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1296,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb,
 	unsigned int cpu  = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		intel_cqm_cpu_prepare(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
 		intel_cqm_cpu_exit(cpu);
 		break;
 	case CPU_STARTING:
+		intel_cqm_cpu_starting(cpu);
 		cqm_pick_event_reader(cpu);
 		break;
 	}
@@ -1373,7 +1371,7 @@ static int __init intel_cqm_init(void)
 		goto out;
 
 	for_each_online_cpu(i) {
-		intel_cqm_cpu_prepare(i);
+		intel_cqm_cpu_starting(i);
 		cqm_pick_event_reader(i);
 	}
 

kernel/events/core.c

@@ -1868,8 +1868,6 @@ event_sched_in(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
-	event->tstamp_running += tstamp - event->tstamp_stopped;
-
 	perf_set_shadow_time(event, ctx, tstamp);
 
 	perf_log_itrace_start(event);
@@ -1881,6 +1879,8 @@ event_sched_in(struct perf_event *event,
 		goto out;
 	}
 
+	event->tstamp_running += tstamp - event->tstamp_stopped;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	if (!ctx->nr_active++)
@@ -3958,28 +3958,21 @@ static void perf_event_for_each(struct perf_event *event,
 		perf_event_for_each_child(sibling, func);
 }
 
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
-{
-	struct perf_event_context *ctx = event->ctx;
-	int ret = 0, active;
+struct period_event {
+	struct perf_event *event;
 	u64 value;
+};
 
-	if (!is_sampling_event(event))
-		return -EINVAL;
+static int __perf_event_period(void *info)
+{
+	struct period_event *pe = info;
+	struct perf_event *event = pe->event;
+	struct perf_event_context *ctx = event->ctx;
+	u64 value = pe->value;
+	bool active;
 
-	if (copy_from_user(&value, arg, sizeof(value)))
-		return -EFAULT;
-
-	if (!value)
-		return -EINVAL;
-
-	raw_spin_lock_irq(&ctx->lock);
+	raw_spin_lock(&ctx->lock);
 	if (event->attr.freq) {
-		if (value > sysctl_perf_event_sample_rate) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-
 		event->attr.sample_freq = value;
 	} else {
 		event->attr.sample_period = value;
@@ -3998,11 +3991,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->pmu->start(event, PERF_EF_RELOAD);
 		perf_pmu_enable(ctx->pmu);
 	}
+	raw_spin_unlock(&ctx->lock);
 
-unlock:
+	return 0;
+}
+
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
+{
+	struct period_event pe = { .event = event, };
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task;
+	u64 value;
+
+	if (!is_sampling_event(event))
+		return -EINVAL;
+
+	if (copy_from_user(&value, arg, sizeof(value)))
+		return -EFAULT;
+
+	if (!value)
+		return -EINVAL;
+
+	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
+		return -EINVAL;
+
+	task = ctx->task;
+	pe.value = value;
+
+	if (!task) {
+		cpu_function_call(event->cpu, __perf_event_period, &pe);
+		return 0;
+	}
+
+retry:
+	if (!task_function_call(task, __perf_event_period, &pe))
+		return 0;
+
+	raw_spin_lock_irq(&ctx->lock);
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		task = ctx->task;
+		goto retry;
+	}
+
+	__perf_event_period(&pe);
 	raw_spin_unlock_irq(&ctx->lock);
 
-	return ret;
+	return 0;
 }
 
 static const struct file_operations perf_fops;
@@ -4740,12 +4775,20 @@ static const struct file_operations perf_fops = {
  * to user-space before waking everybody up.
  */
 
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+	/* only the parent has fasync state */
+	if (event->parent)
+		event = event->parent;
+	return &event->fasync;
+}
+
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
-		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
 		event->pending_kill = 0;
 	}
 }
@@ -6124,7 +6167,7 @@ static int __perf_event_overflow(struct perf_event *event,
 	else
 		perf_event_output(event, data, regs);
 
-	if (event->fasync && event->pending_kill) {
+	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending);
 	}

kernel/events/ring_buffer.c

@@ -559,11 +559,13 @@ static void __rb_free_aux(struct ring_buffer *rb)
 		rb->aux_priv = NULL;
 	}
 
-	for (pg = 0; pg < rb->aux_nr_pages; pg++)
-		rb_free_aux_page(rb, pg);
+	if (rb->aux_nr_pages) {
+		for (pg = 0; pg < rb->aux_nr_pages; pg++)
+			rb_free_aux_page(rb, pg);
 
-	kfree(rb->aux_pages);
-	rb->aux_nr_pages = 0;
+		kfree(rb->aux_pages);
+		rb->aux_nr_pages = 0;
+	}
 }
 
 void rb_free_aux(struct ring_buffer *rb)

tools/perf/config/Makefile

@@ -638,7 +638,7 @@ ifndef DESTDIR
 prefix ?= $(HOME)
 endif
 bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core

tools/perf/util/stat-shadow.c

@@ -85,7 +85,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
 		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
@@ -398,20 +398,18 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				" #   %5.2f%% aborted cycles         ",
 				100.0 * ((total2-avg) / total));
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   avg > 0 &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-		if (total)
+		if (avg)
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   avg > 0 &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-		if (total)
+		if (avg)
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);