perf/cgroups: Don't rotate events for cgroups unnecessarily

Currently perf_rotate_context assumes that if the context's nr_events !=
nr_active a rotation is necessary for perf event multiplexing. With
cgroups, nr_events is the total count of events for all cgroups and
nr_active will not include events in a cgroup other than the current
task's. This makes rotation appear necessary for cgroups when it is not.

Add a perf_event_context flag that is set when rotation is necessary.
Clear the flag during sched_out and set it when a flexible sched_in
fails due to resources.

Signed-off-by: Ian Rogers <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vince Weaver <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

include/linux/perf_event.h

@@ -749,6 +749,11 @@ struct perf_event_context {
 	int				nr_stat;
 	int				nr_freq;
 	int				rotate_disable;
+	/*
+	 * Set when nr_events != nr_active, except tolerant to events not
+	 * necessary to be active due to scheduling constraints, such as cgroups.
+	 */
+	int				rotate_necessary;
 	refcount_t			refcount;
 	struct task_struct		*task;
 

kernel/events/core.c

@@ -2952,6 +2952,12 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
+	/*
+	 * If we had been multiplexing, no rotations are necessary, now no events
+	 * are active.
+	 */
+	ctx->rotate_necessary = 0;
+
 	perf_pmu_disable(ctx->pmu);
 	if (is_active & EVENT_PINNED) {
 		list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list)
@@ -3319,10 +3325,13 @@ static int flexible_sched_in(struct perf_event *event, void *data)
 		return 0;
 
 	if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
-		if (!group_sched_in(event, sid->cpuctx, sid->ctx))
-			list_add_tail(&event->active_list, &sid->ctx->flexible_active);
-		else
+		int ret = group_sched_in(event, sid->cpuctx, sid->ctx);
+		if (ret) {
 			sid->can_add_hw = 0;
+			sid->ctx->rotate_necessary = 1;
+			return 0;
+		}
+		list_add_tail(&event->active_list, &sid->ctx->flexible_active);
 	}
 
 	return 0;
@@ -3690,24 +3699,17 @@ ctx_first_active(struct perf_event_context *ctx)
 static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
 	struct perf_event *cpu_event = NULL, *task_event = NULL;
-	bool cpu_rotate = false, task_rotate = false;
-	struct perf_event_context *ctx = NULL;
+	struct perf_event_context *task_ctx = NULL;
+	int cpu_rotate, task_rotate;
 
 	/*
 	 * Since we run this from IRQ context, nobody can install new
 	 * events, thus the event count values are stable.
 	 */
 
-	if (cpuctx->ctx.nr_events) {
-		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
-			cpu_rotate = true;
-	}
-
-	ctx = cpuctx->task_ctx;
-	if (ctx && ctx->nr_events) {
-		if (ctx->nr_events != ctx->nr_active)
-			task_rotate = true;
-	}
+	cpu_rotate = cpuctx->ctx.rotate_necessary;
+	task_ctx = cpuctx->task_ctx;
+	task_rotate = task_ctx ? task_ctx->rotate_necessary : 0;
 
 	if (!(cpu_rotate || task_rotate))
 		return false;
@@ -3716,7 +3718,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
 	if (task_rotate)
-		task_event = ctx_first_active(ctx);
+		task_event = ctx_first_active(task_ctx);
 	if (cpu_rotate)
 		cpu_event = ctx_first_active(&cpuctx->ctx);
 
@@ -3724,17 +3726,17 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	 * As per the order given at ctx_resched() first 'pop' task flexible
 	 * and then, if needed CPU flexible.
 	 */
-	if (task_event || (ctx && cpu_event))
-		ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+	if (task_event || (task_ctx && cpu_event))
+		ctx_sched_out(task_ctx, cpuctx, EVENT_FLEXIBLE);
 	if (cpu_event)
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
 	if (task_event)
-		rotate_ctx(ctx, task_event);
+		rotate_ctx(task_ctx, task_event);
 	if (cpu_event)
 		rotate_ctx(&cpuctx->ctx, cpu_event);
 
-	perf_event_sched_in(cpuctx, ctx, current);
+	perf_event_sched_in(cpuctx, task_ctx, current);
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);