1 files changed, 53 insertions, 17 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0274a44f8fb0..178d9c5feb62 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -642,9 +642,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
 
 static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cgroup *cgrp_out = cpuctx->cgrp;
-	if (cgrp_out)
-		__update_cgrp_time(cgrp_out);
+	struct perf_cgroup *cgrp = cpuctx->cgrp;
+	struct cgroup_subsys_state *css;
+
+	if (cgrp) {
+		for (css = &cgrp->css; css; css = css->parent) {
+			cgrp = container_of(css, struct perf_cgroup, css);
+			__update_cgrp_time(cgrp);
+		}
+	}
 }
 
 static inline void update_cgrp_time_from_event(struct perf_event *event)
@@ -672,6 +678,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 {
 	struct perf_cgroup *cgrp;
 	struct perf_cgroup_info *info;
+	struct cgroup_subsys_state *css;
 
 	/*
 	 * ctx->lock held by caller
@@ -682,8 +689,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 		return;
 
 	cgrp = perf_cgroup_from_task(task, ctx);
-	info = this_cpu_ptr(cgrp->info);
-	info->timestamp = ctx->timestamp;
+
+	for (css = &cgrp->css; css; css = css->parent) {
+		cgrp = container_of(css, struct perf_cgroup, css);
+		info = this_cpu_ptr(cgrp->info);
+		info->timestamp = ctx->timestamp;
+	}
 }
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
@@ -889,27 +900,39 @@ list_update_cgroup_event(struct perf_event *event,
 	if (!is_cgroup_event(event))
 		return;
 
-	if (add && ctx->nr_cgroups++)
-		return;
-	else if (!add && --ctx->nr_cgroups)
-		return;
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * this will always be called from the right CPU.
 	 */
 	cpuctx = __get_cpu_context(ctx);
-	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
-	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
-	if (add) {
+
+	/*
+	 * Since setting cpuctx->cgrp is conditional on the current @cgrp
+	 * matching the event's cgroup, we must do this for every new event,
+	 * because if the first would mismatch, the second would not try again
+	 * and we would leave cpuctx->cgrp unset.
+	 */
+	if (add && !cpuctx->cgrp) {
 		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
 
-		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
 		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 			cpuctx->cgrp = cgrp;
-	} else {
-		list_del(cpuctx_entry);
-		cpuctx->cgrp = NULL;
 	}
+
+	if (add && ctx->nr_cgroups++)
+		return;
+	else if (!add && --ctx->nr_cgroups)
+		return;
+
+	/* no cgroup running */
+	if (!add)
+		cpuctx->cgrp = NULL;
+
+	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
+	if (add)
+		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
+	else
+		list_del(cpuctx_entry);
 }
 
 #else /* !CONFIG_CGROUP_PERF */
@@ -2393,6 +2416,18 @@ static int  __perf_install_in_context(void *info)
 		raw_spin_lock(&task_ctx->lock);
 	}
 
+#ifdef CONFIG_CGROUP_PERF
+	if (is_cgroup_event(event)) {
+		/*
+		 * If the current cgroup doesn't match the event's
+		 * cgroup, we should not try to schedule it.
+		 */
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+		reprogram = cgroup_is_descendant(cgrp->css.cgroup,
+					event->cgrp->css.cgroup);
+	}
+#endif
+
 	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);
@@ -5802,7 +5837,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		values[n++] = running;
 
-	if (leader != event)
+	if ((leader != event) &&
+	    (leader->state == PERF_EVENT_STATE_ACTIVE))
 		leader->pmu->read(leader);
 
 	values[n++] = perf_event_count(leader);