1 files changed, 152 insertions, 16 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b8785e26ee1..d1a1bee3522 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -29,6 +29,7 @@
 #include <linux/hardirq.h>
 #include <linux/rculist.h>
 #include <linux/uaccess.h>
+#include <linux/suspend.h>
 #include <linux/syscalls.h>
 #include <linux/anon_inodes.h>
 #include <linux/kernel_stat.h>
@@ -399,14 +400,54 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 	local_irq_restore(flags);
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task)
+static inline void perf_cgroup_sched_out(struct task_struct *task,
+					 struct task_struct *next)
 {
-	perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+	struct perf_cgroup *cgrp1;
+	struct perf_cgroup *cgrp2 = NULL;
+
+	/*
+	 * we come here when we know perf_cgroup_events > 0
+	 */
+	cgrp1 = perf_cgroup_from_task(task);
+
+	/*
+	 * next is NULL when called from perf_event_enable_on_exec()
+	 * that will systematically cause a cgroup_switch()
+	 */
+	if (next)
+		cgrp2 = perf_cgroup_from_task(next);
+
+	/*
+	 * only schedule out current cgroup events if we know
+	 * that we are switching to a different cgroup. Otherwise,
+	 * do no touch the cgroup events.
+	 */
+	if (cgrp1 != cgrp2)
+		perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
 }
 
-static inline void perf_cgroup_sched_in(struct task_struct *task)
+static inline void perf_cgroup_sched_in(struct task_struct *prev,
+					struct task_struct *task)
 {
-	perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+	struct perf_cgroup *cgrp1;
+	struct perf_cgroup *cgrp2 = NULL;
+
+	/*
+	 * we come here when we know perf_cgroup_events > 0
+	 */
+	cgrp1 = perf_cgroup_from_task(task);
+
+	/* prev can never be NULL */
+	cgrp2 = perf_cgroup_from_task(prev);
+
+	/*
+	 * only need to schedule in cgroup events if we are changing
+	 * cgroup during ctxsw. Cgroup events were not scheduled
+	 * out of ctxsw out if that was not the case.
+	 */
+	if (cgrp1 != cgrp2)
+		perf_cgroup_switch(task, PERF_CGROUP_SWIN);
 }
 
 static inline int perf_cgroup_connect(int fd, struct perf_event *event,
@@ -518,11 +559,13 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task)
+static inline void perf_cgroup_sched_out(struct task_struct *task,
+					 struct task_struct *next)
 {
 }
 
-static inline void perf_cgroup_sched_in(struct task_struct *task)
+static inline void perf_cgroup_sched_in(struct task_struct *prev,
+					struct task_struct *task)
 {
 }
 
@@ -1988,7 +2031,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * cgroup event are system-wide mode only
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
-		perf_cgroup_sched_out(task);
+		perf_cgroup_sched_out(task, next);
 }
 
 static void task_ctx_sched_out(struct perf_event_context *ctx)
@@ -2153,7 +2196,8 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
  * accessing the event control register. If a NMI hits, then it will
  * keep the event running.
  */
-void __perf_event_task_sched_in(struct task_struct *task)
+void __perf_event_task_sched_in(struct task_struct *prev,
+				struct task_struct *task)
 {
 	struct perf_event_context *ctx;
 	int ctxn;
@@ -2171,7 +2215,7 @@ void __perf_event_task_sched_in(struct task_struct *task)
 	 * cgroup event are system-wide mode only
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
-		perf_cgroup_sched_in(task);
+		perf_cgroup_sched_in(prev, task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2427,7 +2471,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 	 * ctxswin cgroup events which are already scheduled
 	 * in.
 	 */
-	perf_cgroup_sched_out(current);
+	perf_cgroup_sched_out(current, NULL);
 
 	raw_spin_lock(&ctx->lock);
 	task_ctx_sched_out(ctx);
@@ -3353,8 +3397,8 @@ static int perf_event_index(struct perf_event *event)
 }
 
 static void calc_timer_values(struct perf_event *event,
-				u64 *running,
-				u64 *enabled)
+				u64 *enabled,
+				u64 *running)
 {
 	u64 now, ctx_time;
 
@@ -5715,6 +5759,7 @@ struct pmu *perf_init_event(struct perf_event *event)
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
 	if (pmu) {
+		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (ret)
 			pmu = ERR_PTR(ret);
@@ -5722,6 +5767,7 @@ struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (!ret)
 			goto unlock;
@@ -5848,8 +5894,6 @@ done:
 		return ERR_PTR(err);
 	}
 
-	event->pmu = pmu;
-
 	if (!event->parent) {
 		if (event->attach_state & PERF_ATTACH_TASK)
 			jump_label_inc(&perf_sched_events);
@@ -6809,7 +6853,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0) {
+	if (swhash->hlist_refcount > 0 && !swhash->swevent_hlist) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -6898,7 +6942,14 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
-	switch (action & ~CPU_TASKS_FROZEN) {
+	/*
+	 * Ignore suspend/resume action, the perf_pm_notifier will
+	 * take care of that.
+	 */
+	if (action & CPU_TASKS_FROZEN)
+		return NOTIFY_OK;
+
+	switch (action) {
 
 	case CPU_UP_PREPARE:
 	case CPU_DOWN_FAILED:
@@ -6917,6 +6968,90 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
+static void perf_pm_resume_cpu(void *unused)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int idx;
+
+	idx = srcu_read_lock(&pmus_srcu);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		ctx = cpuctx->task_ctx;
+
+		perf_ctx_lock(cpuctx, ctx);
+		perf_pmu_disable(cpuctx->ctx.pmu);
+
+		cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+		if (ctx)
+			ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+
+		perf_pmu_enable(cpuctx->ctx.pmu);
+		perf_ctx_unlock(cpuctx, ctx);
+	}
+	srcu_read_unlock(&pmus_srcu, idx);
+}
+
+static void perf_pm_suspend_cpu(void *unused)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int idx;
+
+	idx = srcu_read_lock(&pmus_srcu);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		ctx = cpuctx->task_ctx;
+
+		perf_ctx_lock(cpuctx, ctx);
+		perf_pmu_disable(cpuctx->ctx.pmu);
+
+		perf_event_sched_in(cpuctx, ctx, current);
+
+		perf_pmu_enable(cpuctx->ctx.pmu);
+		perf_ctx_unlock(cpuctx, ctx);
+	}
+	srcu_read_unlock(&pmus_srcu, idx);
+}
+
+static int perf_resume(void)
+{
+	get_online_cpus();
+	smp_call_function(perf_pm_resume_cpu, NULL, 1);
+	put_online_cpus();
+
+	return NOTIFY_OK;
+}
+
+static int perf_suspend(void)
+{
+	get_online_cpus();
+	smp_call_function(perf_pm_suspend_cpu, NULL, 1);
+	put_online_cpus();
+
+	return NOTIFY_OK;
+}
+
+static int perf_pm(struct notifier_block *self, unsigned long action, void *ptr)
+{
+	switch (action) {
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		return perf_resume();
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		return perf_suspend();
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block perf_pm_notifier = {
+	.notifier_call = perf_pm,
+};
+
 void __init perf_event_init(void)
 {
 	int ret;
@@ -6931,6 +7066,7 @@ void __init perf_event_init(void)
 	perf_tp_register();
 	perf_cpu_notifier(perf_cpu_notify);
 	register_reboot_notifier(&perf_reboot_notifier);
+	register_pm_notifier(&perf_pm_notifier);
 
 	ret = init_hw_breakpoint();
 	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);