[PATCH v8 3/4] perf script: Fix perf script -F +metric

[Andi Kleen <ak@linux.intel.com>]

This fixes a regression with perf script -F +metric originally caused by :

commit 37cc8ad77cf81f3ffd226856c367b0e15333a738
Author: Ian Rogers <irogers@google.com>
Date:   Sun Feb 19 01:28:46 2023 -0800

    perf metric: Directly use counts rather than saved_value

In the perf script environment the evsel wouldn't allocate an aggr
values array, which led to a -1 reference because the metric
evaluation would try to reference NULL - 1 (for aggr_idx)

Give the perf script evsels a single CPU aggr setup. That's
enough because the groups are always contiguous, so no need
to store more than one CPU's worth of values.

Before

% perf record -e '{cycles,instructions}:S' perf bench  mem memcpy
% perf script -F +metric
Segmentation fault (core dumped)

After:

% perf record -e '{cycles,instructions}:S' perf bench  mem memcpy
...
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.028 MB perf.data (90 samples) ]
% perf script -F +metric
       perf-exec 1847557 264658.180789:       3009       cycles:  ffffffff990a579a native_write_msr+0xa ([kernel.kallsyms])
       perf-exec 1847557 264658.180789:        382 instructions:  ffffffff990a579a native_write_msr+0xa ([kernel.kallsyms])
       perf-exec 1847557 264658.180789:         metric:    0.13  insn per cycle
...

Fixes: 37cc8ad77cf8 ("perf metric: Directly use counts rather ...")
Signed-off-by: Andi Kleen <ak@linux.intel.com>

----

v2: Reformat code
v3: Work around bogus warning
v4: Set up aggr map only for metrics case to keep perf stat record
working
v5: Broken version
v6: Only set up limited aggregation mode with -F +metric. Add conflict
checks with perf stat record files.
v7: Remove some unnecessary conflict checks. Fix buffer overflow. Minor cleanups.
v8: Add check for leader sampling. Update some comments.
---
 tools/perf/builtin-script.c | 50 +++++++++++++++++++++++++++++++++----
 1 file changed, 45 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c16224b1fef3..04378615b2ad 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -335,7 +335,6 @@ struct evsel_script {
        FILE *fp;
        u64  samples;
        /* For metric output */
-       u64  val;
        int  gnum;
 };
 
@@ -2127,18 +2126,30 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	};
 	struct evsel *ev2;
 	u64 val;
+	static int printed;
 
 	if (!evsel->stats)
 		evlist__alloc_stats(&stat_config, script->session->evlist, /*alloc_raw=*/false);
 	if (evsel_script(leader)->gnum++ == 0)
 		perf_stat__reset_shadow_stats();
-	val = sample->period * evsel->scale;
-	evsel_script(evsel)->val = val;
+	val = sample->period;
+	if (!(evsel->core.attr.sample_type & PERF_SAMPLE_READ)) {
+		if (!printed)
+			fprintf(stderr, "perf script: -F metric requires {}:S for groups leader sampling\n");
+		printed = 1;
+		return;
+	}
+	/*
+	 * Always use the first entry as storage because the leader sampling
+	 * groups are contiguous and there's no need to handle multiple indexes
+	 * for anything.
+	 */
+	evsel->stats->aggr[0].counts.val = val;
 	if (evsel_script(leader)->gnum == leader->core.nr_members) {
 		for_each_group_member (ev2, leader) {
 			perf_stat__print_shadow_stats(&stat_config, ev2,
-						      evsel_script(ev2)->val,
-						      sample->cpu,
+						      evsel->stats->aggr[0].counts.val,
+						      0,
 						      &ctx,
 						      NULL);
 		}
@@ -2325,6 +2336,20 @@ static void process_event(struct perf_script *script,
 		fflush(fp);
 }
 
+static void check_metric_conflict(void)
+{
+	int i;
+	/*
+	 * Avoid conflict with the aggregation mode used for the metric printing.
+	 */
+	for (i = 0; i < OUTPUT_TYPE_MAX; i++) {
+		if (output[i].fields & PERF_OUTPUT_METRIC) {
+			fprintf(stderr, "perf stat record files are not supported with -F metric\n");
+			exit(1);
+		}
+	}
+}
+
 static struct scripting_ops	*scripting_ops;
 
 static void __process_stat(struct evsel *counter, u64 tstamp)
@@ -2334,6 +2359,8 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
 	struct perf_cpu cpu;
 	static int header_printed;
 
+	check_metric_conflict();
+
 	if (!header_printed) {
 		printf("%3s %8s %15s %15s %15s %15s %s\n",
 		       "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT");
@@ -3725,6 +3752,8 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused
 {
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
+	check_metric_conflict();
+
 	/*
 	 * Aggregation modes are not used since post-processing scripts are
 	 * supposed to take care of such requirements
@@ -4088,6 +4117,17 @@ int cmd_script(int argc, const char **argv)
 
 	argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
+	for (i = 0; i < OUTPUT_TYPE_MAX; i++) {
+		if (output[i].fields & PERF_OUTPUT_METRIC) {
+			stat_config.aggr_map = cpu_aggr_map__empty_new(1);
+			err = -ENOMEM;
+			if (!stat_config.aggr_map)
+				goto out;
+			err = 0;
+			stat_config.aggr_map->nr = 1;
+			break;
+		}
+	}
 
 	if (symbol_conf.guestmount ||
 	    symbol_conf.default_guest_vmlinux_name ||
-- 
2.45.2