perf evlist: Reduce affinity use and move into iterator, fix no affinity

The evlist__for_each_cpu iterator will call sched_setaffitinity when
moving between CPUs to avoid IPIs.

If only 1 IPI is saved then this may be unprofitable as the delay to get
scheduled may be considerable.

This may be particularly true if reading an event group in `perf stat`
in interval mode.

Move the affinity handling completely into the iterator so that a single
evlist__use_affinity can determine whether CPU affinities will be used.

For `perf record` the change is minimal as the dummy event and the real
event will always make the use of affinities the thing to do.

In `perf stat`, tool events are ignored and affinities only used if >1
event on the same CPU occur.

Determining if affinities are useful is done by evlist__use_affinity
which tests per-event whether the event's PMU benefits from affinity use
- it is assumed only perf event using PMUs do.

Fix a bug where when there are no affinities that the CPU map iterator
may reference a CPU not present in the initial evsel. Fix by making the
iterator and non-iterator code common.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andres Freund <andres@anarazel.de>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: captain5050

tools/perf/builtin-stat.c

@@ -369,19 +369,11 @@ static int read_counter_cpu(struct evsel *counter, int cpu_map_idx)
 static int read_counters_with_affinity(void)
 {
 	struct evlist_cpu_iterator evlist_cpu_itr;
-	struct affinity saved_affinity, *affinity;
 
 	if (all_counters_use_bpf)
 		return 0;
 
-	if (!target__has_cpu(&target) || target__has_per_thread(&target))
-		affinity = NULL;
-	else if (affinity__setup(&saved_affinity) < 0)
-		return -1;
-	else
-		affinity = &saved_affinity;
-
-	evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+	evlist__for_each_cpu(evlist_cpu_itr, evsel_list) {
 		struct evsel *counter = evlist_cpu_itr.evsel;
 
 		if (evsel__is_bpf(counter))
@@ -393,8 +385,6 @@ static int read_counters_with_affinity(void)
 		if (!counter->err)
 			counter->err = read_counter_cpu(counter, evlist_cpu_itr.cpu_map_idx);
 	}
-	if (affinity)
-		affinity__cleanup(&saved_affinity);
 
 	return 0;
 }
@@ -793,7 +783,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
 	struct evlist_cpu_iterator evlist_cpu_itr;
-	struct affinity saved_affinity, *affinity = NULL;
 	int err, open_err = 0;
 	bool second_pass = false, has_supported_counters;
 
@@ -805,14 +794,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		child_pid = evsel_list->workload.pid;
 	}
 
-	if (!cpu_map__is_dummy(evsel_list->core.user_requested_cpus)) {
-		if (affinity__setup(&saved_affinity) < 0) {
-			err = -1;
-			goto err_out;
-		}
-		affinity = &saved_affinity;
-	}
-
 	evlist__for_each_entry(evsel_list, counter) {
 		counter->reset_group = false;
 		if (bpf_counter__load(counter, &target)) {
@@ -825,57 +806,56 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	evlist__reset_aggr_stats(evsel_list);
 
-	evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
-		counter = evlist_cpu_itr.evsel;
+	/*
+	 * bperf calls evsel__open_per_cpu() in bperf__load(), so
+	 * no need to call it again here.
+	 */
+	if (!target.use_bpf) {
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list) {
+			counter = evlist_cpu_itr.evsel;
 
-		/*
-		 * bperf calls evsel__open_per_cpu() in bperf__load(), so
-		 * no need to call it again here.
-		 */
-		if (target.use_bpf)
-			break;
+			if (counter->reset_group || !counter->supported)
+				continue;
+			if (evsel__is_bperf(counter))
+				continue;
 
-		if (counter->reset_group || !counter->supported)
-			continue;
-		if (evsel__is_bperf(counter))
-			continue;
+			while (true) {
+				if (create_perf_stat_counter(counter, &stat_config,
+							      evlist_cpu_itr.cpu_map_idx) == 0)
+					break;
 
-		while (true) {
-			if (create_perf_stat_counter(counter, &stat_config,
-						     evlist_cpu_itr.cpu_map_idx) == 0)
-				break;
+				open_err = errno;
+				/*
+				 * 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 ((open_err == EINVAL || open_err == EBADF) &&
+					evsel__leader(counter) != counter &&
+					counter->weak_group) {
+					evlist__reset_weak_group(evsel_list, counter, false);
+					assert(counter->reset_group);
+					counter->supported = true;
+					second_pass = true;
+					break;
+				}
 
-			open_err = errno;
-			/*
-			 * 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 ((open_err == EINVAL || open_err == EBADF) &&
-				evsel__leader(counter) != counter &&
-				counter->weak_group) {
-				evlist__reset_weak_group(evsel_list, counter, false);
-				assert(counter->reset_group);
-				counter->supported = true;
-				second_pass = true;
-				break;
+				if (stat_handle_error(counter, open_err) != COUNTER_RETRY)
+					break;
 			}
-
-			if (stat_handle_error(counter, open_err) != COUNTER_RETRY)
-				break;
 		}
 	}
-
 	if (second_pass) {
 		/*
 		 * Now redo all the weak group after closing them,
 		 * and also close errored counters.
 		 */
 
 		/* First close errored or weak retry */
-		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list) {
 			counter = evlist_cpu_itr.evsel;
 
 			if (!counter->reset_group && counter->supported)
@@ -884,7 +864,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx);
 		}
 		/* Now reopen weak */
-		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list) {
 			counter = evlist_cpu_itr.evsel;
 
 			if (!counter->reset_group)
@@ -893,17 +873,18 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			while (true) {
 				pr_debug2("reopening weak %s\n", evsel__name(counter));
 				if (create_perf_stat_counter(counter, &stat_config,
-							     evlist_cpu_itr.cpu_map_idx) == 0)
+							     evlist_cpu_itr.cpu_map_idx) == 0) {
+					evlist_cpu_iterator__exit(&evlist_cpu_itr);
 					break;
-
+				}
 				open_err = errno;
-				if (stat_handle_error(counter, open_err) != COUNTER_RETRY)
+				if (stat_handle_error(counter, open_err) != COUNTER_RETRY) {
+					evlist_cpu_iterator__exit(&evlist_cpu_itr);
 					break;
+				}
 			}
 		}
 	}
-	affinity__cleanup(affinity);
-	affinity = NULL;
 
 	has_supported_counters = false;
 	evlist__for_each_entry(evsel_list, counter) {
@@ -1065,7 +1046,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (forks)
 		evlist__cancel_workload(evsel_list);
 
-	affinity__cleanup(affinity);
 	return err;
 }