[v2] perf tools: Ensure event leader stays at head of evlist after sorting

[RESEND PATCH v2] perf tools: Ensure event leader stays at head of evlist after sorting

Posted by Chun-Tse Shao 1 month, 1 week ago

From: Ian Rogers <irogers@google.com>

For evlist of a certain event/metric, the HEAD should be the event
leader. In some scenarios where uncore_xxx_0 does not exist, the event
leader is not the first element after sorting. For example, on my test
machine uncore_iio_0 does not exist, the event leader is uncore_iio_2.

However, in `evlist__cmp`, it was reordered based on the PMU name, which
makes uncore_iio_1 the HEAD of evlist, breaking the following merge
logic in `evsel__merge_aliases`.

The patch adds a loop at the end of
`parse_events__sort_events_and_fix_groups` to make sure the first
wildcard match is the earliest entry in the list, updating pointers
accordingly without breaking reordering detection.

Tested on device lacks uncore_iio_0, and `perf test` looks good.

Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
v2:
  Adding missing Signed-off-by from Ian Rogers.
  Renaming variable `l` to `orig_leader`.

v1: lore.kernel.org/20260501043532.790711-1-ctshao@google.com

 tools/perf/util/parse-events.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1497e1f2a08c..943569e82b82 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2251,6 +2251,33 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list)
 		}
 		last_event_was_forced_leader = (force_grouped_leader == pos);
 	}
+
+	/*
+	 * Make sure the first wildcard match is the earliest entry in the list.
+	 * Since list_sort might have reordered the aliases, the original leader
+	 * might not be at the head of the list anymore. We find the first
+	 * alias in the sorted list and make it the new leader, and redirect
+	 * all other aliases to it.
+	 */
+	list_for_each_entry(pos, list, core.node) {
+		struct evsel *orig_leader = pos->first_wildcard_match;
+
+		if (!orig_leader)
+			continue;
+
+		if (orig_leader->first_wildcard_match) {
+			/* Original leader was redirected to a new leader */
+			pos->first_wildcard_match = orig_leader->first_wildcard_match;
+		} else if (pos->core.idx < orig_leader->core.idx) {
+			/*
+			 * We are earlier than the original leader in sorted order,
+			 * and no earlier alias has claimed leadership yet.
+			 */
+			orig_leader->first_wildcard_match = pos;
+			pos->first_wildcard_match = NULL;
+		}
+	}
+
 	list_for_each_entry(pos, list, core.node) {
 		struct evsel *pos_leader = evsel__leader(pos);

--
2.54.0.545.g6539524ca2-goog

Re: [RESEND PATCH v2] perf tools: Ensure event leader stays at head of evlist after sorting

Posted by Namhyung Kim 1 month ago

Hello,

On Tue, May 05, 2026 at 02:19:00PM -0700, Chun-Tse Shao wrote:
> From: Ian Rogers <irogers@google.com>
> 
> For evlist of a certain event/metric, the HEAD should be the event
> leader. In some scenarios where uncore_xxx_0 does not exist, the event
> leader is not the first element after sorting. For example, on my test
> machine uncore_iio_0 does not exist, the event leader is uncore_iio_2.
> 
> However, in `evlist__cmp`, it was reordered based on the PMU name, which
> makes uncore_iio_1 the HEAD of evlist, breaking the following merge
> logic in `evsel__merge_aliases`.
> 
> The patch adds a loop at the end of
> `parse_events__sort_events_and_fix_groups` to make sure the first
> wildcard match is the earliest entry in the list, updating pointers
> accordingly without breaking reordering detection.
> 
> Tested on device lacks uncore_iio_0, and `perf test` looks good.
> 
> Signed-off-by: Ian Rogers <irogers@google.com>
> Signed-off-by: Chun-Tse Shao <ctshao@google.com>

Acked-by: Namhyung Kim <namhyung@kernel.org>

Thanks,
Namhyung

> ---
> v2:
>   Adding missing Signed-off-by from Ian Rogers.
>   Renaming variable `l` to `orig_leader`.
> 
> v1: lore.kernel.org/20260501043532.790711-1-ctshao@google.com
> 
>  tools/perf/util/parse-events.c | 27 +++++++++++++++++++++++++++
>  1 file changed, 27 insertions(+)
> 
> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> index 1497e1f2a08c..943569e82b82 100644
> --- a/tools/perf/util/parse-events.c
> +++ b/tools/perf/util/parse-events.c
> @@ -2251,6 +2251,33 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list)
>  		}
>  		last_event_was_forced_leader = (force_grouped_leader == pos);
>  	}
> +
> +	/*
> +	 * Make sure the first wildcard match is the earliest entry in the list.
> +	 * Since list_sort might have reordered the aliases, the original leader
> +	 * might not be at the head of the list anymore. We find the first
> +	 * alias in the sorted list and make it the new leader, and redirect
> +	 * all other aliases to it.
> +	 */
> +	list_for_each_entry(pos, list, core.node) {
> +		struct evsel *orig_leader = pos->first_wildcard_match;
> +
> +		if (!orig_leader)
> +			continue;
> +
> +		if (orig_leader->first_wildcard_match) {
> +			/* Original leader was redirected to a new leader */
> +			pos->first_wildcard_match = orig_leader->first_wildcard_match;
> +		} else if (pos->core.idx < orig_leader->core.idx) {
> +			/*
> +			 * We are earlier than the original leader in sorted order,
> +			 * and no earlier alias has claimed leadership yet.
> +			 */
> +			orig_leader->first_wildcard_match = pos;
> +			pos->first_wildcard_match = NULL;
> +		}
> +	}
> +
>  	list_for_each_entry(pos, list, core.node) {
>  		struct evsel *pos_leader = evsel__leader(pos);
> 
> --
> 2.54.0.545.g6539524ca2-goog
>

Re: [RESEND PATCH v2] perf tools: Ensure event leader stays at head of evlist after sorting

Posted by Arnaldo Carvalho de Melo 1 week, 2 days ago

On Sat, May 09, 2026 at 11:52:44PM -0700, Namhyung Kim wrote:
> Hello,
> 
> On Tue, May 05, 2026 at 02:19:00PM -0700, Chun-Tse Shao wrote:
> > From: Ian Rogers <irogers@google.com>
> > 
> > For evlist of a certain event/metric, the HEAD should be the event
> > leader. In some scenarios where uncore_xxx_0 does not exist, the event
> > leader is not the first element after sorting. For example, on my test
> > machine uncore_iio_0 does not exist, the event leader is uncore_iio_2.
> > 
> > However, in `evlist__cmp`, it was reordered based on the PMU name, which
> > makes uncore_iio_1 the HEAD of evlist, breaking the following merge
> > logic in `evsel__merge_aliases`.
> > 
> > The patch adds a loop at the end of
> > `parse_events__sort_events_and_fix_groups` to make sure the first
> > wildcard match is the earliest entry in the list, updating pointers
> > accordingly without breaking reordering detection.
> > 
> > Tested on device lacks uncore_iio_0, and `perf test` looks good.
> > 
> > Signed-off-by: Ian Rogers <irogers@google.com>
> > Signed-off-by: Chun-Tse Shao <ctshao@google.com>
> 
> Acked-by: Namhyung Kim <namhyung@kernel.org>

Thanks, applied to perf-tools-next, for v7.2.

- Arnaldo