perf stat: Use affinity for opening events

Restructure the event opening in perf stat to cycle through the events
by CPU after setting affinity to that CPU.

This eliminates IPI overhead in the perf API.

We have to loop through the CPU in the outter builtin-stat code instead
of leaving that to low level functions.

It has to change the weak group fallback strategy slightly.  Since we
cannot easily undo the opens for other CPUs move the weak group retry to
a separate loop.

Before with a large test case with 94 CPUs:

  % time     seconds  usecs/call     calls    errors syscall
  ------ ----------- ----------- --------- --------- ----------------
   42.75    4.050910          67     60046       110 perf_event_open

After:

   26.86    0.944396          16     58069       110 perf_event_open

(the number changes slightly because the weak group retries
work differently and the test case relies on weak groups)

Committer notes:

Added one of the hunks in a patch provided by Andi after I noticed that
the "event times" 'perf test' entry was segfaulting.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-10-andi@firstfloor.org
Link: http://lore.kernel.org/lkml/20191127232657.GL84886@tassilo.jf.intel.com # Fix
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 102 insertions, 19 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1d9d7161815e..cf8516e701e2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
 #include "util/target.h"
 #include "util/time-utils.h"
 #include "util/top.h"
+#include "util/affinity.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -440,6 +441,11 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 			ui__warning("%s event is not supported by the kernel.\n",
 				    perf_evsel__name(counter));
 		counter->supported = false;
+		/*
+		 * errored is a sticky flag that means one of the counter's
+		 * cpu event had a problem and needs to be reexamined.
+		 */
+		counter->errored = true;
 
 		if ((counter->leader != counter) ||
 		    !(counter->leader->core.nr_members > 1))
@@ -484,6 +490,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	int status = 0;
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
+	struct affinity affinity;
+	int i, cpu;
+	bool second_pass = false;
 
 	if (interval) {
 		ts.tv_sec  = interval / USEC_PER_MSEC;
@@ -508,30 +517,104 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (group)
 		perf_evlist__set_leader(evsel_list);
 
-	evlist__for_each_entry(evsel_list, counter) {
+	if (affinity__setup(&affinity) < 0)
+		return -1;
+
+	evlist__for_each_cpu (evsel_list, i, cpu) {
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evsel_list, counter) {
+			if (evsel__cpu_iter_skip(counter, cpu))
+				continue;
+			if (counter->reset_group || counter->errored)
+				continue;
 try_again:
-		if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
-
-			/* Weak group failed. Reset the group. */
-			if ((errno == EINVAL || errno == EBADF) &&
-			    counter->leader != counter &&
-			    counter->weak_group) {
-				counter = perf_evlist__reset_weak_group(evsel_list, counter);
-				goto try_again;
+			if (create_perf_stat_counter(counter, &stat_config, &target,
+						     counter->cpu_iter - 1) < 0) {
+
+				/*
+				 * Weak group failed. We cannot just undo this here
+				 * because earlier CPUs might be in group mode, and the kernel
+				 * doesn't support mixing group and non group reads. Defer
+				 * it to later.
+				 * Don't close here because we're in the wrong affinity.
+				 */
+				if ((errno == EINVAL || errno == EBADF) &&
+				    counter->leader != counter &&
+				    counter->weak_group) {
+					perf_evlist__reset_weak_group(evsel_list, counter, false);
+					assert(counter->reset_group);
+					second_pass = true;
+					continue;
+				}
+
+				switch (stat_handle_error(counter)) {
+				case COUNTER_FATAL:
+					return -1;
+				case COUNTER_RETRY:
+					goto try_again;
+				case COUNTER_SKIP:
+					continue;
+				default:
+					break;
+				}
+
 			}
+			counter->supported = true;
+		}
+	}
 
-			switch (stat_handle_error(counter)) {
-			case COUNTER_FATAL:
-				return -1;
-			case COUNTER_RETRY:
-				goto try_again;
-			case COUNTER_SKIP:
-				continue;
-			default:
-				break;
+	if (second_pass) {
+		/*
+		 * Now redo all the weak group after closing them,
+		 * and also close errored counters.
+		 */
+
+		evlist__for_each_cpu(evsel_list, i, cpu) {
+			affinity__set(&affinity, cpu);
+			/* First close errored or weak retry */
+			evlist__for_each_entry(evsel_list, counter) {
+				if (!counter->reset_group && !counter->errored)
+					continue;
+				if (evsel__cpu_iter_skip_no_inc(counter, cpu))
+					continue;
+				perf_evsel__close_cpu(&counter->core, counter->cpu_iter);
+			}
+			/* Now reopen weak */
+			evlist__for_each_entry(evsel_list, counter) {
+				if (!counter->reset_group && !counter->errored)
+					continue;
+				if (evsel__cpu_iter_skip(counter, cpu))
+					continue;
+				if (!counter->reset_group)
+					continue;
+try_again_reset:
+				pr_debug2("reopening weak %s\n", perf_evsel__name(counter));
+				if (create_perf_stat_counter(counter, &stat_config, &target,
+							     counter->cpu_iter - 1) < 0) {
+
+					switch (stat_handle_error(counter)) {
+					case COUNTER_FATAL:
+						return -1;
+					case COUNTER_RETRY:
+						goto try_again_reset;
+					case COUNTER_SKIP:
+						continue;
+					default:
+						break;
+					}
+				}
+				counter->supported = true;
 			}
 		}
-		counter->supported = true;
+	}
+	affinity__cleanup(&affinity);
+
+	evlist__for_each_entry(evsel_list, counter) {
+		if (!counter->supported) {
+			perf_evsel__free_fd(&counter->core);
+			continue;
+		}
 
 		l = strlen(counter->unit);
 		if (l > stat_config.unit_width)