1 files changed, 65 insertions, 42 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f5744010a8d2..f83a71a3e46d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
-		       PERF_FLAG_PID_CGROUP)
+		       PERF_FLAG_PID_CGROUP |\
+		       PERF_FLAG_FD_CLOEXEC)
 
 /*
  * branch priv levels that need permission checks
@@ -230,11 +231,29 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 #define NR_ACCUMULATED_SAMPLES 128
 static DEFINE_PER_CPU(u64, running_sample_length);
 
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
 {
+	u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
 	u64 avg_local_sample_len;
 	u64 local_samples_len;
+
+	local_samples_len = __get_cpu_var(running_sample_length);
+	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+	printk_ratelimited(KERN_WARNING
+			"perf interrupt took too long (%lld > %lld), lowering "
+			"kernel.perf_event_max_sample_rate to %d\n",
+			avg_local_sample_len, allowed_ns >> 1,
+			sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
 	u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+	u64 avg_local_sample_len;
+	u64 local_samples_len;
 
 	if (allowed_ns == 0)
 		return;
@@ -262,13 +281,14 @@ void perf_sample_event_took(u64 sample_len_ns)
 	sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
 	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 
-	printk_ratelimited(KERN_WARNING
-			"perf samples too long (%lld > %lld), lowering "
-			"kernel.perf_event_max_sample_rate to %d\n",
-			avg_local_sample_len, allowed_ns,
-			sysctl_perf_event_sample_rate);
-
 	update_perf_cpu_limits();
+
+	if (!irq_work_queue(&perf_duration_work)) {
+		early_printk("perf interrupt took too long (%lld > %lld), lowering "
+			     "kernel.perf_event_max_sample_rate to %d\n",
+			     avg_local_sample_len, allowed_ns >> 1,
+			     sysctl_perf_event_sample_rate);
+	}
 }
 
 static atomic64_t perf_event_id;
@@ -341,7 +361,7 @@ struct perf_cgroup {
 static inline struct perf_cgroup *
 perf_cgroup_from_task(struct task_struct *task)
 {
-	return container_of(task_css(task, perf_subsys_id),
+	return container_of(task_css(task, perf_event_cgrp_id),
 			    struct perf_cgroup, css);
 }
 
@@ -369,11 +389,6 @@ perf_cgroup_match(struct perf_event *event)
 				    event->cgrp->css.cgroup);
 }
 
-static inline bool perf_tryget_cgroup(struct perf_event *event)
-{
-	return css_tryget(&event->cgrp->css);
-}
-
 static inline void perf_put_cgroup(struct perf_event *event)
 {
 	css_put(&event->cgrp->css);
@@ -592,9 +607,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	if (!f.file)
 		return -EBADF;
 
-	rcu_read_lock();
-
-	css = css_from_dir(f.file->f_dentry, &perf_subsys);
+	css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
 		goto out;
@@ -603,13 +616,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
 
-	/* must be done before we fput() the file */
-	if (!perf_tryget_cgroup(event)) {
-		event->cgrp = NULL;
-		ret = -ENOENT;
-		goto out;
-	}
-
 	/*
 	 * all events in a group must monitor
 	 * the same cgroup because a task belongs
@@ -620,7 +626,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		ret = -EINVAL;
 	}
 out:
-	rcu_read_unlock();
 	fdput(f);
 	return ret;
 }
@@ -1713,7 +1718,7 @@ group_sched_in(struct perf_event *group_event,
 	       struct perf_event_context *ctx)
 {
 	struct perf_event *event, *partial_group = NULL;
-	struct pmu *pmu = group_event->pmu;
+	struct pmu *pmu = ctx->pmu;
 	u64 now = ctx->time;
 	bool simulate = false;
 
@@ -2562,8 +2567,6 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
 		if (cpuctx->ctx.nr_branch_stack > 0
 		    && pmu->flush_branch_stack) {
 
-			pmu = cpuctx->ctx.pmu;
-
 			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 
 			perf_pmu_disable(pmu);
@@ -3542,7 +3545,7 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	int ret = 0;
+	int ret = 0, active;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -3566,6 +3569,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->attr.sample_period = value;
 		event->hw.sample_period = value;
 	}
+
+	active = (event->state == PERF_EVENT_STATE_ACTIVE);
+	if (active) {
+		perf_pmu_disable(ctx->pmu);
+		event->pmu->stop(event, PERF_EF_UPDATE);
+	}
+
+	local64_set(&event->hw.period_left, 0);
+
+	if (active) {
+		event->pmu->start(event, PERF_EF_RELOAD);
+		perf_pmu_enable(ctx->pmu);
+	}
+
 unlock:
 	raw_spin_unlock_irq(&ctx->lock);
 
@@ -6279,7 +6296,7 @@ static int perf_event_idx_default(struct perf_event *event)
  * Ensures all contexts with the same task_ctx_nr have the same
  * pmu_cpu_context too.
  */
-static void *find_pmu_context(int ctxn)
+static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 {
 	struct pmu *pmu;
 
@@ -6670,6 +6687,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
+	INIT_LIST_HEAD(&event->active_entry);
+	INIT_HLIST_NODE(&event->hlist_entry);
+
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
@@ -6980,6 +7000,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int event_fd;
 	int move_group = 0;
 	int err;
+	int f_flags = O_RDWR;
 
 	/* for future expandability... */
 	if (flags & ~PERF_FLAG_ALL)
@@ -7008,7 +7029,10 @@ SYSCALL_DEFINE5(perf_event_open,
 	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
 		return -EINVAL;
 
-	event_fd = get_unused_fd();
+	if (flags & PERF_FLAG_FD_CLOEXEC)
+		f_flags |= O_CLOEXEC;
+
+	event_fd = get_unused_fd_flags(f_flags);
 	if (event_fd < 0)
 		return event_fd;
 
@@ -7130,7 +7154,8 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 	}
 
-	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
 		goto err_context;
@@ -7833,14 +7858,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 static void __perf_event_exit_context(void *__info)
 {
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event, *tmp;
+	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		__perf_remove_from_context(event);
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(event);
+	rcu_read_unlock();
 }
 
 static void perf_event_exit_cpu_context(int cpu)
@@ -7864,11 +7889,11 @@ static void perf_event_exit_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
+	perf_event_exit_cpu_context(cpu);
+
 	mutex_lock(&swhash->hlist_mutex);
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
-
-	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
@@ -8013,7 +8038,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset)
+	cgroup_taskset_for_each(task, tset)
 		task_function_call(task, __perf_cgroup_move, task);
 }
 
@@ -8032,9 +8057,7 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css,
 	task_function_call(task, __perf_cgroup_move, task);
 }
 
-struct cgroup_subsys perf_subsys = {
-	.name		= "perf_event",
-	.subsys_id	= perf_subsys_id,
+struct cgroup_subsys perf_event_cgrp_subsys = {
 	.css_alloc	= perf_cgroup_css_alloc,
 	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,