Re: [PATCH 1/4] perf record: Split --data-mmap option

[Ian Rogers <irogers@google.com>]

On Tue, Dec 9, 2025 at 6:33 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> Currently -d/--data option controls both PERF_SAMPLE_ADDR bit and
> perf_event_attr.mmap_data flag.  Separate them using new --data-mmap
> option to support recording only one of them.
>
> For data-type profiling, data MMAP is unnecessary but it wastes a lot
> of space in the ring buffer and data file.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>

Reviewed-by: Ian Rogers <irogers@google.com>

Thanks,
Ian

> ---
>  tools/perf/Documentation/perf-record.txt |  8 +++++++-
>  tools/perf/builtin-record.c              | 19 +++++++++++++------
>  tools/perf/util/evsel.c                  |  5 +++--
>  tools/perf/util/record.h                 |  2 ++
>  4 files changed, 25 insertions(+), 9 deletions(-)
>
> diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
> index e8b9aadbbfa50574..c402e74172f6a22d 100644
> --- a/tools/perf/Documentation/perf-record.txt
> +++ b/tools/perf/Documentation/perf-record.txt
> @@ -344,7 +344,8 @@ OPTIONS
>
>  -d::
>  --data::
> -       Record the sample virtual addresses.  Implies --sample-mem-info.
> +       Record the sample virtual addresses.  Implies --sample-mem-info and
> +       --data-mmap.
>
>  --phys-data::
>         Record the sample physical addresses.
> @@ -861,6 +862,11 @@ filtered through the mask provided by -C option.
>         Prepare BPF filter to be used by regular users.  The action should be
>         either "pin" or "unpin".  The filter can be used after it's pinned.
>
> +--data-mmap::
> +       Enable recording MMAP events for non-executable mappings.  Basically
> +       perf only records executable mappings but data mmaping can be useful
> +       when you analyze data access with sample addresses.  So using -d option
> +       would enable this unless you specify --no-data-mmap manually.
>
>  include::intel-hybrid.txt[]
>
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index 2584d0d8bc820676..cbfbd9bb10634093 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -1881,7 +1881,7 @@ static int record__synthesize_workload(struct record *rec, bool tail)
>                                                  process_synthesized_event,
>                                                  &rec->session->machines.host,
>                                                  needs_mmap,
> -                                                rec->opts.sample_address);
> +                                                rec->opts.record_data_mmap);
>         perf_thread_map__put(thread_map);
>         return err;
>  }
> @@ -2191,7 +2191,7 @@ static int record__synthesize(struct record *rec, bool tail)
>
>                 err = __machine__synthesize_threads(machine, tool, &opts->target,
>                                                     rec->evlist->core.threads,
> -                                                   f, needs_mmap, opts->sample_address,
> +                                                   f, needs_mmap, opts->record_data_mmap,
>                                                     rec->opts.nr_threads_synthesize);
>         }
>
> @@ -3006,8 +3006,9 @@ int record_opts__parse_callchain(struct record_opts *record,
>         ret = parse_callchain_record_opt(arg, callchain);
>         if (!ret) {
>                 /* Enable data address sampling for DWARF unwind. */
> -               if (callchain->record_mode == CALLCHAIN_DWARF)
> -                       record->sample_address = true;
> +               if (callchain->record_mode == CALLCHAIN_DWARF &&
> +                   !record->record_data_mmap_set)
> +                       record->record_data_mmap = true;
>                 callchain_debug(callchain);
>         }
>
> @@ -3686,6 +3687,9 @@ static struct option __record_options[] = {
>         OPT_CALLBACK(0, "off-cpu-thresh", &record.opts, "ms",
>                      "Dump off-cpu samples if off-cpu time exceeds this threshold (in milliseconds). (Default: 500ms)",
>                      record__parse_off_cpu_thresh),
> +       OPT_BOOLEAN_SET(0, "data-mmap", &record.opts.record_data_mmap,
> +                       &record.opts.record_data_mmap_set,
> +                       "Record mmap events for non-executable mappings"),
>         OPT_END()
>  };
>
> @@ -4249,9 +4253,12 @@ int cmd_record(int argc, const char **argv)
>                 goto out_opts;
>         }
>
> -       /* For backward compatibility, -d implies --mem-info */
> -       if (rec->opts.sample_address)
> +       /* For backward compatibility, -d implies --mem-info and --data-mmap */
> +       if (rec->opts.sample_address) {
>                 rec->opts.sample_data_src = true;
> +               if (!rec->opts.record_data_mmap_set)
> +                       rec->opts.record_data_mmap = true;
> +       }
>
>         /*
>          * Allow aliases to facilitate the lookup of symbols for address
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 9cd706f6279313c2..ec6552a6f667fec6 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1445,10 +1445,11 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
>                 attr->inherit_stat = 1;
>         }
>
> -       if (opts->sample_address) {
> +       if (opts->sample_address)
>                 evsel__set_sample_bit(evsel, ADDR);
> +
> +       if (opts->record_data_mmap)
>                 attr->mmap_data = track;
> -       }
>
>         /*
>          * We don't allow user space callchains for  function trace
> diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
> index ea3a6c4657eefb74..93627c9a73387ddd 100644
> --- a/tools/perf/util/record.h
> +++ b/tools/perf/util/record.h
> @@ -40,6 +40,8 @@ struct record_opts {
>         bool          record_cgroup;
>         bool          record_switch_events;
>         bool          record_switch_events_set;
> +       bool          record_data_mmap;
> +       bool          record_data_mmap_set;
>         bool          all_kernel;
>         bool          all_user;
>         bool          kernel_callchains;
> --
> 2.52.0.223.gf5cc29aaa4-goog
>