[PATCH 03/14] perf/x86: output multiplexing overhead

[kan.liang@intel.com]

From: Kan Liang <kan.liang@intel.com>

Multiplexing overhead is one of the key overhead when the number of
events is more than available counters.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 include/linux/perf_event.h      |  2 ++
 include/uapi/linux/perf_event.h |  1 +
 kernel/events/core.c            | 16 ++++++++++++++++
 3 files changed, 19 insertions(+)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 632647f..f72b97a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -793,6 +793,8 @@ struct perf_cpu_context {
 
 	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
+
+	struct perf_overhead_entry	mux_overhead;
 };
 
 struct perf_output_handle {
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 071323d..9124c7c 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -993,6 +993,7 @@ struct perf_branch_entry {
 
 enum perf_record_overhead_type {
 	PERF_NMI_OVERHEAD	= 0,
+	PERF_MUX_OVERHEAD,
 
 	PERF_OVERHEAD_MAX,
 };
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d82e6ca..9934059 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1829,6 +1829,11 @@ event_sched_out(struct perf_event *event,
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
 
+	if (log_overhead && cpuctx->mux_overhead.nr) {
+		cpuctx->mux_overhead.cpu = smp_processor_id();
+		perf_log_overhead(event, PERF_MUX_OVERHEAD, &cpuctx->mux_overhead);
+	}
+
 	perf_pmu_enable(event->pmu);
 }
 
@@ -3330,9 +3335,17 @@ static void rotate_ctx(struct perf_event_context *ctx)
 		list_rotate_left(&ctx->flexible_groups);
 }
 
+static void
+perf_caculate_mux_overhead(struct perf_cpu_context *cpuctx, u64 time)
+{
+	cpuctx->mux_overhead.nr++;
+	cpuctx->mux_overhead.time += time;
+}
+
 static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
 	struct perf_event_context *ctx = NULL;
+	u64 start_clock, end_clock;
 	int rotate = 0;
 
 	if (cpuctx->ctx.nr_events) {
@@ -3349,6 +3362,7 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 	if (!rotate)
 		goto done;
 
+	start_clock = perf_clock();
 	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
@@ -3364,6 +3378,8 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+	end_clock = perf_clock();
+	perf_caculate_mux_overhead(cpuctx, end_clock - start_clock);
 done:
 
 	return rotate;
-- 
2.5.5