tools/perf/arch/x86/util/evlist.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
If slots isn't with a topdown event then moving it is unnecessary. For
example {instructions, slots} is re-ordered:
$ perf stat -e '{instructions,slots}' -a sleep 1
Performance counter stats for 'system wide':
936,600,825 slots
144,440,968 instructions
1.006061423 seconds time elapsed
Which can break tools expecting the command line order to match the
printed order. It is necessary to move the slots event first when it
appears with topdown events. Add extra checking so that the slots event
is only moved in the case of there being a topdown event like:
$ perf stat -e '{instructions,slots,topdown-fe-bound}' -a sleep 1
Performance counter stats for 'system wide':
2427568570 slots
300927614 instructions
551021649 topdown-fe-bound
1.001771803 seconds time elapsed
Fixes: 94dbfd6781a0 ("perf parse-events: Architecture specific leader override")
Reported-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/x86/util/evlist.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 8d9b55959256..cfc208d71f00 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -20,17 +20,27 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
struct evsel *arch_evlist__leader(struct list_head *list)
{
- struct evsel *evsel, *first;
+ struct evsel *evsel, *first, *slots = NULL;
+ bool has_topdown = false;
first = list_first_entry(list, struct evsel, core.node);
if (!pmu_have_event("cpu", "slots"))
return first;
+ /* If there is a slots event and a topdown event then the slots event comes first. */
__evlist__for_each_entry(list, evsel) {
- if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
- evsel->name && strcasestr(evsel->name, "slots"))
- return evsel;
+ if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
+ if (strcasestr(evsel->name, "slots")) {
+ slots = evsel;
+ if (slots == first)
+ return first;
+ }
+ if (!strncasecmp(evsel->name, "topdown", 7))
+ has_topdown = true;
+ if (slots && has_topdown)
+ return slots;
+ }
}
return first;
}
--
2.35.1.894.gb6a874cedc-goog
On 3/21/2022 6:33 PM, Ian Rogers wrote:
> If slots isn't with a topdown event then moving it is unnecessary. For
> example {instructions, slots} is re-ordered:
>
> $ perf stat -e '{instructions,slots}' -a sleep 1
>
> Performance counter stats for 'system wide':
>
> 936,600,825 slots
> 144,440,968 instructions
>
> 1.006061423 seconds time elapsed
>
> Which can break tools expecting the command line order to match the
> printed order. It is necessary to move the slots event first when it
> appears with topdown events. Add extra checking so that the slots event
> is only moved in the case of there being a topdown event like:
>
> $ perf stat -e '{instructions,slots,topdown-fe-bound}' -a sleep 1
>
> Performance counter stats for 'system wide':
>
> 2427568570 slots
> 300927614 instructions
> 551021649 topdown-fe-bound
>
> 1.001771803 seconds time elapsed
>
> Fixes: 94dbfd6781a0 ("perf parse-events: Architecture specific leader override")
> Reported-by: Kan Liang <kan.liang@linux.intel.com>
> Signed-off-by: Ian Rogers <irogers@google.com>
Thanks Ian. The patch works well.
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Thanks,
Kan
> ---
> tools/perf/arch/x86/util/evlist.c | 18 ++++++++++++++----
> 1 file changed, 14 insertions(+), 4 deletions(-)
>
> diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
> index 8d9b55959256..cfc208d71f00 100644
> --- a/tools/perf/arch/x86/util/evlist.c
> +++ b/tools/perf/arch/x86/util/evlist.c
> @@ -20,17 +20,27 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
>
> struct evsel *arch_evlist__leader(struct list_head *list)
> {
> - struct evsel *evsel, *first;
> + struct evsel *evsel, *first, *slots = NULL;
> + bool has_topdown = false;
>
> first = list_first_entry(list, struct evsel, core.node);
>
> if (!pmu_have_event("cpu", "slots"))
> return first;
>
> + /* If there is a slots event and a topdown event then the slots event comes first. */
> __evlist__for_each_entry(list, evsel) {
> - if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
> - evsel->name && strcasestr(evsel->name, "slots"))
> - return evsel;
> + if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
> + if (strcasestr(evsel->name, "slots")) {
> + slots = evsel;
> + if (slots == first)
> + return first;
> + }
> + if (!strncasecmp(evsel->name, "topdown", 7))
> + has_topdown = true;
> + if (slots && has_topdown)
> + return slots;
> + }
> }
> return first;
> }
Em Tue, Mar 22, 2022 at 07:48:48AM -0400, Liang, Kan escreveu:
> On 3/21/2022 6:33 PM, Ian Rogers wrote:
> > If slots isn't with a topdown event then moving it is unnecessary. For
> > example {instructions, slots} is re-ordered:
> >
> > $ perf stat -e '{instructions,slots}' -a sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 936,600,825 slots
> > 144,440,968 instructions
> >
> > 1.006061423 seconds time elapsed
> >
> > Which can break tools expecting the command line order to match the
> > printed order. It is necessary to move the slots event first when it
> > appears with topdown events. Add extra checking so that the slots event
> > is only moved in the case of there being a topdown event like:
> >
> > $ perf stat -e '{instructions,slots,topdown-fe-bound}' -a sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 2427568570 slots
> > 300927614 instructions
> > 551021649 topdown-fe-bound
> >
> > 1.001771803 seconds time elapsed
> >
> > Fixes: 94dbfd6781a0 ("perf parse-events: Architecture specific leader override")
> > Reported-by: Kan Liang <kan.liang@linux.intel.com>
> > Signed-off-by: Ian Rogers <irogers@google.com>
>
> Thanks Ian. The patch works well.
>
> Tested-by: Kan Liang <kan.liang@linux.intel.com>
Thanks, applied.
- Arnaldo
© 2016 - 2026 Red Hat, Inc.