perf inject: Lazily allocate event_copy

The event_copy is 64kb (PERF_SAMPLE_SIZE_MAX) and stack allocated in
struct perf_inject. It is used for aux events that may not exist in a
file. Make the array allocation lazy to cut down on the stack usage.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230527034324.2597593-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index d19a1b8..2023b7a 100644 (file)
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -122,7 +122,7 @@ struct perf_inject {
        u64                     aux_id;
        struct list_head        samples;
        struct itrace_synth_opts itrace_synth_opts;
-       char                    event_copy[PERF_SAMPLE_MAX_SIZE];
+       char                    *event_copy;
        struct perf_file_section secs[HEADER_FEAT_BITS];
        struct guest_session    guest_session;
        struct strlist          *known_build_ids;
@@ -320,8 +320,14 @@ perf_inject__cut_auxtrace_sample(struct perf_inject *inject,
 {
        size_t sz1 = sample->aux_sample.data - (void *)event;
        size_t sz2 = event->header.size - sample->aux_sample.size - sz1;
-       union perf_event *ev = (union perf_event *)inject->event_copy;
+       union perf_event *ev;
 
+       if (inject->event_copy == NULL) {
+               inject->event_copy = malloc(PERF_SAMPLE_MAX_SIZE);
+               if (!inject->event_copy)
+                       return ERR_PTR(-ENOMEM);
+       }
+       ev = (union perf_event *)inject->event_copy;
        if (sz1 > event->header.size || sz2 > event->header.size ||
            sz1 + sz2 > event->header.size ||
            sz1 < sizeof(struct perf_event_header) + sizeof(u64))
@@ -357,8 +363,11 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 
        build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-       if (inject->itrace_synth_opts.set && sample->aux_sample.size)
+       if (inject->itrace_synth_opts.set && sample->aux_sample.size) {
                event = perf_inject__cut_auxtrace_sample(inject, event, sample);
+               if (IS_ERR(event))
+                       return PTR_ERR(event);
+       }
 
        return perf_event__repipe_synth(tool, event);
 }
@@ -2391,5 +2400,6 @@ out_close_output:
        if (!inject.in_place_update)
                perf_data__close(&inject.output);
        free(inject.itrace_synth_opts.vm_tm_corr_args);
+       free(inject.event_copy);
        return ret;
 }