* [PATCH v2 0/1] perf: Add --pmu-filter option for filtering PMUs
@ 2026-03-10 4:06 Qinxin Xia
2026-03-10 4:06 ` [PATCH v2 1/1] " Qinxin Xia
2026-03-27 21:01 ` [PATCH v2 0/1] " Namhyung Kim
0 siblings, 2 replies; 8+ messages in thread
From: Qinxin Xia @ 2026-03-10 4:06 UTC (permalink / raw)
To: namhyung, irogers, peterz, mingo, acme, wangyushan12, hejunhao3,
jonathan.cameron, xiaqinxin
Cc: linux-perf-users, linux-kernel, mark.rutland, alexander.shishkin,
jolsa, adrian.hunter, james.clark, linuxarm
This patch adds a new --pmu-filter option to perf-stat command to allow
filtering events on specific PMUs. This is useful when there are
multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
[root@localhost tmp]# perf stat -M cpa_p0_avg_bw
Performance counter stats for 'system wide':
19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
19.417734480 seconds time elapsed
[root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
Performance counter stats for 'system wide':
6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
50,548,465 cpa_p0_wr_dat
7,552,182 cpa_p0_rd_dat_64b
0 cpa_p0_rd_dat_32b
6.234139320 seconds time elapsed
wildcard match:
[root@localhost ~]# ./perf stat --pmu-filter hisi_sicl[2,8]_cpa0 -M cpa_p0_avg_bw
Performance counter stats for 'system wide':
18,505,025,031 hisi_sicl2_cpa0/cpa_cycles/ # 0.42 cpa_p0_avg_bw
80,007,944 hisi_sicl2_cpa0/cpa_p0_wr_dat/
42,014,906 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
18,504,957,351 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
18.504994880 seconds time elapsed
Changes since V1:
- Address the comments from Namhyung, the description of the event filter in commit
info is omitted, and wildcard matching is supported for pmu-filter.
- Link: https://lore.kernel.org/all/20260225034125.2157622-2-xiaqinxin@huawei.com/
Changes since RFC:
- Address the comments from Ian, replace '--uncorepmu' with '--pmu-filter'.
- Link: https://lore.kernel.org/linux-perf-users/20260120095058.2778834-1-xiaqinxin@huawei.com/
Qinxin Xia (1):
perf: Add --pmu-filter option for filtering PMUs
tools/perf/Documentation/perf-stat.txt | 4 ++++
tools/perf/builtin-stat.c | 19 +++++++++++++++++++
tools/perf/util/metricgroup.c | 18 +++++++++++++-----
tools/perf/util/parse-events.c | 2 +-
4 files changed, 37 insertions(+), 6 deletions(-)
--
2.33.0
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH v2 1/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-10 4:06 [PATCH v2 0/1] perf: Add --pmu-filter option for filtering PMUs Qinxin Xia
@ 2026-03-10 4:06 ` Qinxin Xia
2026-03-12 18:07 ` Namhyung Kim
2026-03-27 21:01 ` [PATCH v2 0/1] " Namhyung Kim
1 sibling, 1 reply; 8+ messages in thread
From: Qinxin Xia @ 2026-03-10 4:06 UTC (permalink / raw)
To: namhyung, irogers, peterz, mingo, acme, wangyushan12, hejunhao3,
jonathan.cameron, xiaqinxin
Cc: linux-perf-users, linux-kernel, mark.rutland, alexander.shishkin,
jolsa, adrian.hunter, james.clark, linuxarm
This patch adds a new --pmu-filter option to perf-stat command to allow
filtering events on specific PMUs. This is useful when there are
multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
[root@localhost tmp]# perf stat -M cpa_p0_avg_bw
Performance counter stats for 'system wide':
19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
19.417734480 seconds time elapsed
[root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
Performance counter stats for 'system wide':
6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
50,548,465 cpa_p0_wr_dat
7,552,182 cpa_p0_rd_dat_64b
0 cpa_p0_rd_dat_32b
6.234139320 seconds time elapsed
Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
---
tools/perf/Documentation/perf-stat.txt | 4 ++++
tools/perf/builtin-stat.c | 19 +++++++++++++++++++
tools/perf/util/metricgroup.c | 18 +++++++++++++-----
tools/perf/util/parse-events.c | 2 +-
4 files changed, 37 insertions(+), 6 deletions(-)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 7cccc3a847d1..b72a29c9223c 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
Only enable events on applying cpu with this type for hybrid platform
(e.g. core or atom)"
+--pmu-filter::
+Only enable events on applying pmu with specified for multiple
+pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
+
EXAMPLES
--------
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 73c2ba7e3076..69c83a5beb71 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
return 0;
}
+static int parse_pmu_filter(const struct option *opt,
+ const char *str,
+ int unset __maybe_unused)
+{
+ struct evlist *evlist = *(struct evlist **)opt->value;
+
+ if (!list_empty(&evlist->core.entries)) {
+ fprintf(stderr, "Must define pmu-filter before events/metrics\n");
+ return -1;
+ }
+
+ parse_events_option_args.pmu_filter = str;
+ return 0;
+}
+
static int parse_cache_level(const struct option *opt,
const char *str,
int unset __maybe_unused)
@@ -2561,6 +2576,10 @@ int cmd_stat(int argc, const char **argv)
"Only enable events on applying cpu with this type "
"for hybrid platform (e.g. core or atom)",
parse_cputype),
+ OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
+ "Only enable events on applying pmu with specified "
+ "for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
+ parse_pmu_filter),
#ifdef HAVE_LIBPFM
OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
"libpfm4 event selector. use 'perf list' to list available events",
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 46bf4dfeebc8..89b83ca38483 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
const char *metric_or_groups)
{
const char *pm_pmu = pm->pmu ?: "cpu";
+ struct perf_pmu *perf_pmu = NULL;
- if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
+ if (pm->pmu)
+ perf_pmu = perf_pmus__find(pm->pmu);
+
+ if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
+ (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
return false;
return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
@@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
static int parse_ids(bool metric_no_merge, bool fake_pmu,
struct expr_parse_ctx *ids, const char *modifier,
bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
- struct evlist **out_evlist)
+ struct evlist **out_evlist,
+ const char *filter_pmu)
{
struct parse_events_error parse_error;
struct evlist *parsed_evlist;
@@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
}
pr_debug("Parsing metric events '%s'\n", events.buf);
parse_events_error__init(&parse_error);
- ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
+ ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
&parse_error, fake_pmu, /*warn_if_reordered=*/false,
/*fake_tp=*/false);
if (ret) {
@@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
/*modifier=*/NULL,
/*group_events=*/false,
tool_events,
- &combined_evlist);
+ &combined_evlist,
+ (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
}
if (combined)
expr__ctx_free(combined);
@@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
}
if (!metric_evlist) {
ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
- m->group_events, tool_events, &m->evlist);
+ m->group_events, tool_events, &m->evlist,
+ (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
if (ret)
goto out;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index b9efb296bba5..789ff4d15e47 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
if (parse_state->pmu_filter == NULL)
return false;
- return strcmp(parse_state->pmu_filter, pmu->name) != 0;
+ return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
}
static int parse_events_add_pmu(struct parse_events_state *parse_state,
--
2.33.0
^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH v2 1/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-10 4:06 ` [PATCH v2 1/1] " Qinxin Xia
@ 2026-03-12 18:07 ` Namhyung Kim
2026-03-19 10:23 ` Qinxin Xia
0 siblings, 1 reply; 8+ messages in thread
From: Namhyung Kim @ 2026-03-12 18:07 UTC (permalink / raw)
To: Qinxin Xia, irogers
Cc: peterz, mingo, acme, wangyushan12, hejunhao3, jonathan.cameron,
linux-perf-users, linux-kernel, mark.rutland, alexander.shishkin,
jolsa, adrian.hunter, james.clark, linuxarm
On Tue, Mar 10, 2026 at 12:06:07PM +0800, Qinxin Xia wrote:
> This patch adds a new --pmu-filter option to perf-stat command to allow
> filtering events on specific PMUs. This is useful when there are
> multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
>
> [root@localhost tmp]# perf stat -M cpa_p0_avg_bw
> Performance counter stats for 'system wide':
>
> 19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> 0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
> 19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> 0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
> 19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
> 75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
> 18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
> 0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
> 19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> 0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
>
> 19.417734480 seconds time elapsed
>
> [root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
> Performance counter stats for 'system wide':
>
> 6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
> 50,548,465 cpa_p0_wr_dat
> 7,552,182 cpa_p0_rd_dat_64b
> 0 cpa_p0_rd_dat_32b
>
> 6.234139320 seconds time elapsed
Ian, can you please take a look at this?
Thanks,
Namhyung
>
> Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
> ---
> tools/perf/Documentation/perf-stat.txt | 4 ++++
> tools/perf/builtin-stat.c | 19 +++++++++++++++++++
> tools/perf/util/metricgroup.c | 18 +++++++++++++-----
> tools/perf/util/parse-events.c | 2 +-
> 4 files changed, 37 insertions(+), 6 deletions(-)
>
> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
> index 7cccc3a847d1..b72a29c9223c 100644
> --- a/tools/perf/Documentation/perf-stat.txt
> +++ b/tools/perf/Documentation/perf-stat.txt
> @@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
> Only enable events on applying cpu with this type for hybrid platform
> (e.g. core or atom)"
>
> +--pmu-filter::
> +Only enable events on applying pmu with specified for multiple
> +pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
> +
> EXAMPLES
> --------
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 73c2ba7e3076..69c83a5beb71 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
> return 0;
> }
>
> +static int parse_pmu_filter(const struct option *opt,
> + const char *str,
> + int unset __maybe_unused)
> +{
> + struct evlist *evlist = *(struct evlist **)opt->value;
> +
> + if (!list_empty(&evlist->core.entries)) {
> + fprintf(stderr, "Must define pmu-filter before events/metrics\n");
> + return -1;
> + }
> +
> + parse_events_option_args.pmu_filter = str;
> + return 0;
> +}
> +
> static int parse_cache_level(const struct option *opt,
> const char *str,
> int unset __maybe_unused)
> @@ -2561,6 +2576,10 @@ int cmd_stat(int argc, const char **argv)
> "Only enable events on applying cpu with this type "
> "for hybrid platform (e.g. core or atom)",
> parse_cputype),
> + OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
> + "Only enable events on applying pmu with specified "
> + "for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
> + parse_pmu_filter),
> #ifdef HAVE_LIBPFM
> OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
> "libpfm4 event selector. use 'perf list' to list available events",
> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> index 46bf4dfeebc8..89b83ca38483 100644
> --- a/tools/perf/util/metricgroup.c
> +++ b/tools/perf/util/metricgroup.c
> @@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
> const char *metric_or_groups)
> {
> const char *pm_pmu = pm->pmu ?: "cpu";
> + struct perf_pmu *perf_pmu = NULL;
>
> - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
> + if (pm->pmu)
> + perf_pmu = perf_pmus__find(pm->pmu);
> +
> + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
> + (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
> return false;
>
> return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
> @@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
> static int parse_ids(bool metric_no_merge, bool fake_pmu,
> struct expr_parse_ctx *ids, const char *modifier,
> bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
> - struct evlist **out_evlist)
> + struct evlist **out_evlist,
> + const char *filter_pmu)
> {
> struct parse_events_error parse_error;
> struct evlist *parsed_evlist;
> @@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
> }
> pr_debug("Parsing metric events '%s'\n", events.buf);
> parse_events_error__init(&parse_error);
> - ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
> + ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
> &parse_error, fake_pmu, /*warn_if_reordered=*/false,
> /*fake_tp=*/false);
> if (ret) {
> @@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
> /*modifier=*/NULL,
> /*group_events=*/false,
> tool_events,
> - &combined_evlist);
> + &combined_evlist,
> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
> }
> if (combined)
> expr__ctx_free(combined);
> @@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
> }
> if (!metric_evlist) {
> ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
> - m->group_events, tool_events, &m->evlist);
> + m->group_events, tool_events, &m->evlist,
> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
> if (ret)
> goto out;
>
> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> index b9efb296bba5..789ff4d15e47 100644
> --- a/tools/perf/util/parse-events.c
> +++ b/tools/perf/util/parse-events.c
> @@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
> if (parse_state->pmu_filter == NULL)
> return false;
>
> - return strcmp(parse_state->pmu_filter, pmu->name) != 0;
> + return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
> }
>
> static int parse_events_add_pmu(struct parse_events_state *parse_state,
> --
> 2.33.0
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 1/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-12 18:07 ` Namhyung Kim
@ 2026-03-19 10:23 ` Qinxin Xia
2026-03-20 22:56 ` Ian Rogers
0 siblings, 1 reply; 8+ messages in thread
From: Qinxin Xia @ 2026-03-19 10:23 UTC (permalink / raw)
To: Namhyung Kim, irogers
Cc: peterz, mingo, acme, wangyushan12, hejunhao3, jonathan.cameron,
linux-perf-users, linux-kernel, mark.rutland, alexander.shishkin,
jolsa, adrian.hunter, james.clark, linuxarm
On 2026/3/13 02:07:17, Namhyung Kim <namhyung@kernel.org> wrote:
> On Tue, Mar 10, 2026 at 12:06:07PM +0800, Qinxin Xia wrote:
>> This patch adds a new --pmu-filter option to perf-stat command to allow
>> filtering events on specific PMUs. This is useful when there are
>> multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
>>
>> [root@localhost tmp]# perf stat -M cpa_p0_avg_bw
>> Performance counter stats for 'system wide':
>>
>> 19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
>> 0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
>> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
>> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
>> 19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
>> 0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
>> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
>> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
>> 19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
>> 75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
>> 18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
>> 0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
>> 19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
>> 0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
>> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
>> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
>>
>> 19.417734480 seconds time elapsed
>>
>> [root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
>> Performance counter stats for 'system wide':
>>
>> 6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
>> 50,548,465 cpa_p0_wr_dat
>> 7,552,182 cpa_p0_rd_dat_64b
>> 0 cpa_p0_rd_dat_32b
>>
>> 6.234139320 seconds time elapsed
>
> Ian, can you please take a look at this?
>
> Thanks,
> Namhyung
>
>>
>> Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
>> ---
>> tools/perf/Documentation/perf-stat.txt | 4 ++++
>> tools/perf/builtin-stat.c | 19 +++++++++++++++++++
>> tools/perf/util/metricgroup.c | 18 +++++++++++++-----
>> tools/perf/util/parse-events.c | 2 +-
>> 4 files changed, 37 insertions(+), 6 deletions(-)
>>
>> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
>> index 7cccc3a847d1..b72a29c9223c 100644
>> --- a/tools/perf/Documentation/perf-stat.txt
>> +++ b/tools/perf/Documentation/perf-stat.txt
>> @@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
>> Only enable events on applying cpu with this type for hybrid platform
>> (e.g. core or atom)"
>>
>> +--pmu-filter::
>> +Only enable events on applying pmu with specified for multiple
>> +pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
>> +
>> EXAMPLES
>> --------
>>
>> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
>> index 73c2ba7e3076..69c83a5beb71 100644
>> --- a/tools/perf/builtin-stat.c
>> +++ b/tools/perf/builtin-stat.c
>> @@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
>> return 0;
>> }
>>
>> +static int parse_pmu_filter(const struct option *opt,
>> + const char *str,
>> + int unset __maybe_unused)
>> +{
>> + struct evlist *evlist = *(struct evlist **)opt->value;
>> +
>> + if (!list_empty(&evlist->core.entries)) {
>> + fprintf(stderr, "Must define pmu-filter before events/metrics\n");
>> + return -1;
>> + }
>> +
>> + parse_events_option_args.pmu_filter = str;
>> + return 0;
>> +}
>> +
>> static int parse_cache_level(const struct option *opt,
>> const char *str,
>> int unset __maybe_unused)
>> @@ -2561,6 +2576,10 @@ int cmd_stat(int argc, const char **argv)
>> "Only enable events on applying cpu with this type "
>> "for hybrid platform (e.g. core or atom)",
>> parse_cputype),
>> + OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
>> + "Only enable events on applying pmu with specified "
>> + "for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
>> + parse_pmu_filter),
>> #ifdef HAVE_LIBPFM
>> OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
>> "libpfm4 event selector. use 'perf list' to list available events",
>> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
>> index 46bf4dfeebc8..89b83ca38483 100644
>> --- a/tools/perf/util/metricgroup.c
>> +++ b/tools/perf/util/metricgroup.c
>> @@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
>> const char *metric_or_groups)
>> {
>> const char *pm_pmu = pm->pmu ?: "cpu";
>> + struct perf_pmu *perf_pmu = NULL;
>>
>> - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
>> + if (pm->pmu)
>> + perf_pmu = perf_pmus__find(pm->pmu);
>> +
>> + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
>> + (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
>> return false;
>>
>> return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
>> @@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
>> static int parse_ids(bool metric_no_merge, bool fake_pmu,
>> struct expr_parse_ctx *ids, const char *modifier,
>> bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
>> - struct evlist **out_evlist)
>> + struct evlist **out_evlist,
>> + const char *filter_pmu)
>> {
>> struct parse_events_error parse_error;
>> struct evlist *parsed_evlist;
>> @@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
>> }
>> pr_debug("Parsing metric events '%s'\n", events.buf);
>> parse_events_error__init(&parse_error);
>> - ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
>> + ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
>> &parse_error, fake_pmu, /*warn_if_reordered=*/false,
>> /*fake_tp=*/false);
>> if (ret) {
>> @@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
>> /*modifier=*/NULL,
>> /*group_events=*/false,
>> tool_events,
>> - &combined_evlist);
>> + &combined_evlist,
>> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
>> }
>> if (combined)
>> expr__ctx_free(combined);
>> @@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
>> }
>> if (!metric_evlist) {
>> ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
>> - m->group_events, tool_events, &m->evlist);
>> + m->group_events, tool_events, &m->evlist,
>> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
>> if (ret)
>> goto out;
>>
>> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
>> index b9efb296bba5..789ff4d15e47 100644
>> --- a/tools/perf/util/parse-events.c
>> +++ b/tools/perf/util/parse-events.c
>> @@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
>> if (parse_state->pmu_filter == NULL)
>> return false;
>>
>> - return strcmp(parse_state->pmu_filter, pmu->name) != 0;
>> + return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
>> }
>>
>> static int parse_events_add_pmu(struct parse_events_state *parse_state,
>> --
>> 2.33.0
>>
>
Gentle ping.
--
Thanks,
Qinxin
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 1/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-19 10:23 ` Qinxin Xia
@ 2026-03-20 22:56 ` Ian Rogers
2026-03-27 6:40 ` Qinxin Xia
0 siblings, 1 reply; 8+ messages in thread
From: Ian Rogers @ 2026-03-20 22:56 UTC (permalink / raw)
To: Qinxin Xia
Cc: Namhyung Kim, peterz, mingo, acme, wangyushan12, hejunhao3,
jonathan.cameron, linux-perf-users, linux-kernel, mark.rutland,
alexander.shishkin, jolsa, adrian.hunter, james.clark, linuxarm
On Thu, Mar 19, 2026 at 3:23 AM Qinxin Xia <xiaqinxin@huawei.com> wrote:
>
>
> On 2026/3/13 02:07:17, Namhyung Kim <namhyung@kernel.org> wrote:
> > On Tue, Mar 10, 2026 at 12:06:07PM +0800, Qinxin Xia wrote:
> >> This patch adds a new --pmu-filter option to perf-stat command to allow
> >> filtering events on specific PMUs. This is useful when there are
> >> multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
> >>
> >> [root@localhost tmp]# perf stat -M cpa_p0_avg_bw
> >> Performance counter stats for 'system wide':
> >>
> >> 19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> >> 0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
> >> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
> >> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
> >> 19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> >> 0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
> >> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
> >> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
> >> 19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
> >> 75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
> >> 18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
> >> 0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
> >> 19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> >> 0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
> >> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
> >> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
> >>
> >> 19.417734480 seconds time elapsed
> >>
> >> [root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
> >> Performance counter stats for 'system wide':
> >>
> >> 6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
> >> 50,548,465 cpa_p0_wr_dat
> >> 7,552,182 cpa_p0_rd_dat_64b
> >> 0 cpa_p0_rd_dat_32b
> >>
> >> 6.234139320 seconds time elapsed
> >
> > Ian, can you please take a look at this?
> >
> > Thanks,
> > Namhyung
> >
> >>
> >> Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
Sorry for the delay.
Reviewed-by: Ian Rogers <irogers@google.com>
Thanks,
Ian
> >> ---
> >> tools/perf/Documentation/perf-stat.txt | 4 ++++
> >> tools/perf/builtin-stat.c | 19 +++++++++++++++++++
> >> tools/perf/util/metricgroup.c | 18 +++++++++++++-----
> >> tools/perf/util/parse-events.c | 2 +-
> >> 4 files changed, 37 insertions(+), 6 deletions(-)
> >>
> >> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
> >> index 7cccc3a847d1..b72a29c9223c 100644
> >> --- a/tools/perf/Documentation/perf-stat.txt
> >> +++ b/tools/perf/Documentation/perf-stat.txt
> >> @@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
> >> Only enable events on applying cpu with this type for hybrid platform
> >> (e.g. core or atom)"
> >>
> >> +--pmu-filter::
> >> +Only enable events on applying pmu with specified for multiple
> >> +pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
> >> +
> >> EXAMPLES
> >> --------
> >>
> >> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> >> index 73c2ba7e3076..69c83a5beb71 100644
> >> --- a/tools/perf/builtin-stat.c
> >> +++ b/tools/perf/builtin-stat.c
> >> @@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
> >> return 0;
> >> }
> >>
> >> +static int parse_pmu_filter(const struct option *opt,
> >> + const char *str,
> >> + int unset __maybe_unused)
> >> +{
> >> + struct evlist *evlist = *(struct evlist **)opt->value;
> >> +
> >> + if (!list_empty(&evlist->core.entries)) {
> >> + fprintf(stderr, "Must define pmu-filter before events/metrics\n");
> >> + return -1;
> >> + }
> >> +
> >> + parse_events_option_args.pmu_filter = str;
> >> + return 0;
> >> +}
> >> +
> >> static int parse_cache_level(const struct option *opt,
> >> const char *str,
> >> int unset __maybe_unused)
> >> @@ -2561,6 +2576,10 @@ int cmd_stat(int argc, const char **argv)
> >> "Only enable events on applying cpu with this type "
> >> "for hybrid platform (e.g. core or atom)",
> >> parse_cputype),
> >> + OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
> >> + "Only enable events on applying pmu with specified "
> >> + "for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
> >> + parse_pmu_filter),
> >> #ifdef HAVE_LIBPFM
> >> OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
> >> "libpfm4 event selector. use 'perf list' to list available events",
> >> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> >> index 46bf4dfeebc8..89b83ca38483 100644
> >> --- a/tools/perf/util/metricgroup.c
> >> +++ b/tools/perf/util/metricgroup.c
> >> @@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
> >> const char *metric_or_groups)
> >> {
> >> const char *pm_pmu = pm->pmu ?: "cpu";
> >> + struct perf_pmu *perf_pmu = NULL;
> >>
> >> - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
> >> + if (pm->pmu)
> >> + perf_pmu = perf_pmus__find(pm->pmu);
> >> +
> >> + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
> >> + (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
> >> return false;
> >>
> >> return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
> >> @@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
> >> static int parse_ids(bool metric_no_merge, bool fake_pmu,
> >> struct expr_parse_ctx *ids, const char *modifier,
> >> bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
> >> - struct evlist **out_evlist)
> >> + struct evlist **out_evlist,
> >> + const char *filter_pmu)
> >> {
> >> struct parse_events_error parse_error;
> >> struct evlist *parsed_evlist;
> >> @@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
> >> }
> >> pr_debug("Parsing metric events '%s'\n", events.buf);
> >> parse_events_error__init(&parse_error);
> >> - ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
> >> + ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
> >> &parse_error, fake_pmu, /*warn_if_reordered=*/false,
> >> /*fake_tp=*/false);
> >> if (ret) {
> >> @@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
> >> /*modifier=*/NULL,
> >> /*group_events=*/false,
> >> tool_events,
> >> - &combined_evlist);
> >> + &combined_evlist,
> >> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
> >> }
> >> if (combined)
> >> expr__ctx_free(combined);
> >> @@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
> >> }
> >> if (!metric_evlist) {
> >> ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
> >> - m->group_events, tool_events, &m->evlist);
> >> + m->group_events, tool_events, &m->evlist,
> >> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
> >> if (ret)
> >> goto out;
> >>
> >> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> >> index b9efb296bba5..789ff4d15e47 100644
> >> --- a/tools/perf/util/parse-events.c
> >> +++ b/tools/perf/util/parse-events.c
> >> @@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
> >> if (parse_state->pmu_filter == NULL)
> >> return false;
> >>
> >> - return strcmp(parse_state->pmu_filter, pmu->name) != 0;
> >> + return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
> >> }
> >>
> >> static int parse_events_add_pmu(struct parse_events_state *parse_state,
> >> --
> >> 2.33.0
> >>
> >
>
> Gentle ping.
> --
> Thanks,
> Qinxin
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 1/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-20 22:56 ` Ian Rogers
@ 2026-03-27 6:40 ` Qinxin Xia
2026-03-27 6:52 ` Ian Rogers
0 siblings, 1 reply; 8+ messages in thread
From: Qinxin Xia @ 2026-03-27 6:40 UTC (permalink / raw)
To: Namhyung Kim
Cc: Ian Rogers, peterz, mingo, acme, wangyushan12, hejunhao3,
jonathan.cameron, linux-perf-users, linux-kernel, mark.rutland,
alexander.shishkin, jolsa, adrian.hunter, james.clark, linuxarm
On 2026/3/21 06:56:07, Ian Rogers <irogers@google.com> wrote:
> On Thu, Mar 19, 2026 at 3:23 AM Qinxin Xia <xiaqinxin@huawei.com> wrote:
>>
>>
>> On 2026/3/13 02:07:17, Namhyung Kim <namhyung@kernel.org> wrote:
>>> On Tue, Mar 10, 2026 at 12:06:07PM +0800, Qinxin Xia wrote:
>>>> This patch adds a new --pmu-filter option to perf-stat command to allow
>>>> filtering events on specific PMUs. This is useful when there are
>>>> multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
>>>>
>>>> [root@localhost tmp]# perf stat -M cpa_p0_avg_bw
>>>> Performance counter stats for 'system wide':
>>>>
>>>> 19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
>>>> 0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
>>>> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
>>>> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
>>>> 19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
>>>> 0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
>>>> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
>>>> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
>>>> 19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
>>>> 75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
>>>> 18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
>>>> 0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
>>>> 19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
>>>> 0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
>>>> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
>>>> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
>>>>
>>>> 19.417734480 seconds time elapsed
>>>>
>>>> [root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
>>>> Performance counter stats for 'system wide':
>>>>
>>>> 6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
>>>> 50,548,465 cpa_p0_wr_dat
>>>> 7,552,182 cpa_p0_rd_dat_64b
>>>> 0 cpa_p0_rd_dat_32b
>>>>
>>>> 6.234139320 seconds time elapsed
>>>
>>> Ian, can you please take a look at this?
>>>
>>> Thanks,
>>> Namhyung
>>>
>>>>
>>>> Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
>
> Sorry for the delay.
>
> Reviewed-by: Ian Rogers <irogers@google.com>
>
> Thanks,
> Ian
>
Hi Namhyung!
Ian has already provided Reviewed-by. Could you please apply this
patch if everything looks good to you? :-)
--
Thanks,
Qinxin
>>>> ---
>>>> tools/perf/Documentation/perf-stat.txt | 4 ++++
>>>> tools/perf/builtin-stat.c | 19 +++++++++++++++++++
>>>> tools/perf/util/metricgroup.c | 18 +++++++++++++-----
>>>> tools/perf/util/parse-events.c | 2 +-
>>>> 4 files changed, 37 insertions(+), 6 deletions(-)
>>>>
>>>> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
>>>> index 7cccc3a847d1..b72a29c9223c 100644
>>>> --- a/tools/perf/Documentation/perf-stat.txt
>>>> +++ b/tools/perf/Documentation/perf-stat.txt
>>>> @@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
>>>> Only enable events on applying cpu with this type for hybrid platform
>>>> (e.g. core or atom)"
>>>>
>>>> +--pmu-filter::
>>>> +Only enable events on applying pmu with specified for multiple
>>>> +pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
>>>> +
>>>> EXAMPLES
>>>> --------
>>>>
>>>> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
>>>> index 73c2ba7e3076..69c83a5beb71 100644
>>>> --- a/tools/perf/builtin-stat.c
>>>> +++ b/tools/perf/builtin-stat.c
>>>> @@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
>>>> return 0;
>>>> }
>>>>
>>>> +static int parse_pmu_filter(const struct option *opt,
>>>> + const char *str,
>>>> + int unset __maybe_unused)
>>>> +{
>>>> + struct evlist *evlist = *(struct evlist **)opt->value;
>>>> +
>>>> + if (!list_empty(&evlist->core.entries)) {
>>>> + fprintf(stderr, "Must define pmu-filter before events/metrics\n");
>>>> + return -1;
>>>> + }
>>>> +
>>>> + parse_events_option_args.pmu_filter = str;
>>>> + return 0;
>>>> +}
>>>> +
>>>> static int parse_cache_level(const struct option *opt,
>>>> const char *str,
>>>> int unset __maybe_unused)
>>>> @@ -2561,6 +2576,10 @@ int cmd_stat(int argc, const char **argv)
>>>> "Only enable events on applying cpu with this type "
>>>> "for hybrid platform (e.g. core or atom)",
>>>> parse_cputype),
>>>> + OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
>>>> + "Only enable events on applying pmu with specified "
>>>> + "for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
>>>> + parse_pmu_filter),
>>>> #ifdef HAVE_LIBPFM
>>>> OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
>>>> "libpfm4 event selector. use 'perf list' to list available events",
>>>> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
>>>> index 46bf4dfeebc8..89b83ca38483 100644
>>>> --- a/tools/perf/util/metricgroup.c
>>>> +++ b/tools/perf/util/metricgroup.c
>>>> @@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
>>>> const char *metric_or_groups)
>>>> {
>>>> const char *pm_pmu = pm->pmu ?: "cpu";
>>>> + struct perf_pmu *perf_pmu = NULL;
>>>>
>>>> - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
>>>> + if (pm->pmu)
>>>> + perf_pmu = perf_pmus__find(pm->pmu);
>>>> +
>>>> + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
>>>> + (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
>>>> return false;
>>>>
>>>> return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
>>>> @@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
>>>> static int parse_ids(bool metric_no_merge, bool fake_pmu,
>>>> struct expr_parse_ctx *ids, const char *modifier,
>>>> bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
>>>> - struct evlist **out_evlist)
>>>> + struct evlist **out_evlist,
>>>> + const char *filter_pmu)
>>>> {
>>>> struct parse_events_error parse_error;
>>>> struct evlist *parsed_evlist;
>>>> @@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
>>>> }
>>>> pr_debug("Parsing metric events '%s'\n", events.buf);
>>>> parse_events_error__init(&parse_error);
>>>> - ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
>>>> + ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
>>>> &parse_error, fake_pmu, /*warn_if_reordered=*/false,
>>>> /*fake_tp=*/false);
>>>> if (ret) {
>>>> @@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
>>>> /*modifier=*/NULL,
>>>> /*group_events=*/false,
>>>> tool_events,
>>>> - &combined_evlist);
>>>> + &combined_evlist,
>>>> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
>>>> }
>>>> if (combined)
>>>> expr__ctx_free(combined);
>>>> @@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
>>>> }
>>>> if (!metric_evlist) {
>>>> ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
>>>> - m->group_events, tool_events, &m->evlist);
>>>> + m->group_events, tool_events, &m->evlist,
>>>> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
>>>> if (ret)
>>>> goto out;
>>>>
>>>> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
>>>> index b9efb296bba5..789ff4d15e47 100644
>>>> --- a/tools/perf/util/parse-events.c
>>>> +++ b/tools/perf/util/parse-events.c
>>>> @@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
>>>> if (parse_state->pmu_filter == NULL)
>>>> return false;
>>>>
>>>> - return strcmp(parse_state->pmu_filter, pmu->name) != 0;
>>>> + return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
>>>> }
>>>>
>>>> static int parse_events_add_pmu(struct parse_events_state *parse_state,
>>>> --
>>>> 2.33.0
>>>>
>>>
>>
>> Gentle ping.
>> --
>> Thanks,
>> Qinxin
>>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 1/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-27 6:40 ` Qinxin Xia
@ 2026-03-27 6:52 ` Ian Rogers
0 siblings, 0 replies; 8+ messages in thread
From: Ian Rogers @ 2026-03-27 6:52 UTC (permalink / raw)
To: Qinxin Xia
Cc: Namhyung Kim, peterz, mingo, acme, wangyushan12, hejunhao3,
jonathan.cameron, linux-perf-users, linux-kernel, mark.rutland,
alexander.shishkin, jolsa, adrian.hunter, james.clark, linuxarm
On Thu, Mar 26, 2026 at 11:41 PM Qinxin Xia <xiaqinxin@huawei.com> wrote:
>
>
>
> On 2026/3/21 06:56:07, Ian Rogers <irogers@google.com> wrote:
> > On Thu, Mar 19, 2026 at 3:23 AM Qinxin Xia <xiaqinxin@huawei.com> wrote:
> >>
> >>
> >> On 2026/3/13 02:07:17, Namhyung Kim <namhyung@kernel.org> wrote:
> >>> On Tue, Mar 10, 2026 at 12:06:07PM +0800, Qinxin Xia wrote:
> >>>> This patch adds a new --pmu-filter option to perf-stat command to allow
> >>>> filtering events on specific PMUs. This is useful when there are
> >>>> multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
> >>>>
> >>>> [root@localhost tmp]# perf stat -M cpa_p0_avg_bw
> >>>> Performance counter stats for 'system wide':
> >>>>
> >>>> 19,417,779,115 hisi_sicl0_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> >>>> 0 hisi_sicl0_cpa0/cpa_p0_wr_dat/
> >>>> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
> >>>> 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
> >>>> 19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> >>>> 0 hisi_sicl10_cpa0/cpa_p0_wr_dat/
> >>>> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
> >>>> 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
> >>>> 19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_avg_bw
> >>>> 75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/
> >>>> 18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
> >>>> 0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
> >>>> 19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_avg_bw
> >>>> 0 hisi_sicl8_cpa0/cpa_p0_wr_dat/
> >>>> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
> >>>> 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/
> >>>>
> >>>> 19.417734480 seconds time elapsed
> >>>>
> >>>> [root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
> >>>> Performance counter stats for 'system wide':
> >>>>
> >>>> 6,234,093,559 cpa_cycles # 0.60 cpa_p0_avg_bw
> >>>> 50,548,465 cpa_p0_wr_dat
> >>>> 7,552,182 cpa_p0_rd_dat_64b
> >>>> 0 cpa_p0_rd_dat_32b
> >>>>
> >>>> 6.234139320 seconds time elapsed
> >>>
> >>> Ian, can you please take a look at this?
> >>>
> >>> Thanks,
> >>> Namhyung
> >>>
> >>>>
> >>>> Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
> >
> > Sorry for the delay.
> >
> > Reviewed-by: Ian Rogers <irogers@google.com>
> >
> > Thanks,
> > Ian
> >
>
> Hi Namhyung!
>
> Ian has already provided Reviewed-by. Could you please apply this
> patch if everything looks good to you? :-)
>
> --
> Thanks,
> Qinxin
Hi Qinxin,
I see it queued up on tmp.perf-tools-next:
https://web.git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/log/?h=tmp.perf-tools-next
which is where patches are tested prior to landing in perf-tools-next :-)
Thanks,
Ian
> >>>> ---
> >>>> tools/perf/Documentation/perf-stat.txt | 4 ++++
> >>>> tools/perf/builtin-stat.c | 19 +++++++++++++++++++
> >>>> tools/perf/util/metricgroup.c | 18 +++++++++++++-----
> >>>> tools/perf/util/parse-events.c | 2 +-
> >>>> 4 files changed, 37 insertions(+), 6 deletions(-)
> >>>>
> >>>> diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
> >>>> index 7cccc3a847d1..b72a29c9223c 100644
> >>>> --- a/tools/perf/Documentation/perf-stat.txt
> >>>> +++ b/tools/perf/Documentation/perf-stat.txt
> >>>> @@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
> >>>> Only enable events on applying cpu with this type for hybrid platform
> >>>> (e.g. core or atom)"
> >>>>
> >>>> +--pmu-filter::
> >>>> +Only enable events on applying pmu with specified for multiple
> >>>> +pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
> >>>> +
> >>>> EXAMPLES
> >>>> --------
> >>>>
> >>>> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> >>>> index 73c2ba7e3076..69c83a5beb71 100644
> >>>> --- a/tools/perf/builtin-stat.c
> >>>> +++ b/tools/perf/builtin-stat.c
> >>>> @@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
> >>>> return 0;
> >>>> }
> >>>>
> >>>> +static int parse_pmu_filter(const struct option *opt,
> >>>> + const char *str,
> >>>> + int unset __maybe_unused)
> >>>> +{
> >>>> + struct evlist *evlist = *(struct evlist **)opt->value;
> >>>> +
> >>>> + if (!list_empty(&evlist->core.entries)) {
> >>>> + fprintf(stderr, "Must define pmu-filter before events/metrics\n");
> >>>> + return -1;
> >>>> + }
> >>>> +
> >>>> + parse_events_option_args.pmu_filter = str;
> >>>> + return 0;
> >>>> +}
> >>>> +
> >>>> static int parse_cache_level(const struct option *opt,
> >>>> const char *str,
> >>>> int unset __maybe_unused)
> >>>> @@ -2561,6 +2576,10 @@ int cmd_stat(int argc, const char **argv)
> >>>> "Only enable events on applying cpu with this type "
> >>>> "for hybrid platform (e.g. core or atom)",
> >>>> parse_cputype),
> >>>> + OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
> >>>> + "Only enable events on applying pmu with specified "
> >>>> + "for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
> >>>> + parse_pmu_filter),
> >>>> #ifdef HAVE_LIBPFM
> >>>> OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
> >>>> "libpfm4 event selector. use 'perf list' to list available events",
> >>>> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> >>>> index 46bf4dfeebc8..89b83ca38483 100644
> >>>> --- a/tools/perf/util/metricgroup.c
> >>>> +++ b/tools/perf/util/metricgroup.c
> >>>> @@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
> >>>> const char *metric_or_groups)
> >>>> {
> >>>> const char *pm_pmu = pm->pmu ?: "cpu";
> >>>> + struct perf_pmu *perf_pmu = NULL;
> >>>>
> >>>> - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
> >>>> + if (pm->pmu)
> >>>> + perf_pmu = perf_pmus__find(pm->pmu);
> >>>> +
> >>>> + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
> >>>> + (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
> >>>> return false;
> >>>>
> >>>> return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
> >>>> @@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
> >>>> static int parse_ids(bool metric_no_merge, bool fake_pmu,
> >>>> struct expr_parse_ctx *ids, const char *modifier,
> >>>> bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
> >>>> - struct evlist **out_evlist)
> >>>> + struct evlist **out_evlist,
> >>>> + const char *filter_pmu)
> >>>> {
> >>>> struct parse_events_error parse_error;
> >>>> struct evlist *parsed_evlist;
> >>>> @@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
> >>>> }
> >>>> pr_debug("Parsing metric events '%s'\n", events.buf);
> >>>> parse_events_error__init(&parse_error);
> >>>> - ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
> >>>> + ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
> >>>> &parse_error, fake_pmu, /*warn_if_reordered=*/false,
> >>>> /*fake_tp=*/false);
> >>>> if (ret) {
> >>>> @@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
> >>>> /*modifier=*/NULL,
> >>>> /*group_events=*/false,
> >>>> tool_events,
> >>>> - &combined_evlist);
> >>>> + &combined_evlist,
> >>>> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
> >>>> }
> >>>> if (combined)
> >>>> expr__ctx_free(combined);
> >>>> @@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
> >>>> }
> >>>> if (!metric_evlist) {
> >>>> ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
> >>>> - m->group_events, tool_events, &m->evlist);
> >>>> + m->group_events, tool_events, &m->evlist,
> >>>> + (pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
> >>>> if (ret)
> >>>> goto out;
> >>>>
> >>>> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> >>>> index b9efb296bba5..789ff4d15e47 100644
> >>>> --- a/tools/perf/util/parse-events.c
> >>>> +++ b/tools/perf/util/parse-events.c
> >>>> @@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
> >>>> if (parse_state->pmu_filter == NULL)
> >>>> return false;
> >>>>
> >>>> - return strcmp(parse_state->pmu_filter, pmu->name) != 0;
> >>>> + return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
> >>>> }
> >>>>
> >>>> static int parse_events_add_pmu(struct parse_events_state *parse_state,
> >>>> --
> >>>> 2.33.0
> >>>>
> >>>
> >>
> >> Gentle ping.
> >> --
> >> Thanks,
> >> Qinxin
> >>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 0/1] perf: Add --pmu-filter option for filtering PMUs
2026-03-10 4:06 [PATCH v2 0/1] perf: Add --pmu-filter option for filtering PMUs Qinxin Xia
2026-03-10 4:06 ` [PATCH v2 1/1] " Qinxin Xia
@ 2026-03-27 21:01 ` Namhyung Kim
1 sibling, 0 replies; 8+ messages in thread
From: Namhyung Kim @ 2026-03-27 21:01 UTC (permalink / raw)
To: irogers, peterz, mingo, acme, wangyushan12, hejunhao3,
jonathan.cameron, Qinxin Xia
Cc: linux-perf-users, linux-kernel, mark.rutland, alexander.shishkin,
jolsa, adrian.hunter, james.clark, linuxarm
On Tue, 10 Mar 2026 12:06:06 +0800, Qinxin Xia wrote:
> This patch adds a new --pmu-filter option to perf-stat command to allow
> filtering events on specific PMUs. This is useful when there are
> multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).
>
> [root@localhost tmp]# perf stat -M cpa_p0_avg_bw
> Performance counter stats for 'system wide':
>
> [...]
Applied to perf-tools-next, thanks!
Best regards,
Namhyung
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2026-03-27 21:01 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-03-10 4:06 [PATCH v2 0/1] perf: Add --pmu-filter option for filtering PMUs Qinxin Xia
2026-03-10 4:06 ` [PATCH v2 1/1] " Qinxin Xia
2026-03-12 18:07 ` Namhyung Kim
2026-03-19 10:23 ` Qinxin Xia
2026-03-20 22:56 ` Ian Rogers
2026-03-27 6:40 ` Qinxin Xia
2026-03-27 6:52 ` Ian Rogers
2026-03-27 21:01 ` [PATCH v2 0/1] " Namhyung Kim
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox