From nobody Sat Feb 7 23:33:59 2026 Received: from canpmsgout05.his.huawei.com (canpmsgout05.his.huawei.com [113.46.200.220]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5A230335066; Tue, 20 Jan 2026 09:51:06 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=113.46.200.220 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768902672; cv=none; b=u8rLj8fpiXL2/ziQ5WC2+RdHPWqE+Wfvp5p/o/8BXBbCrnZzoSoTOQF/1Yay6tQf+7xdAcinOhCgwc+zWpIEUYeq6wjM5BmfiyNisYlJdkBJvikKn4f0Gxt7w8Mu2y/uw9Glq9s35Pk8xsV4ejX09eKPT16jzQeEbxUqEanwipI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768902672; c=relaxed/simple; bh=sjgjuzNZ01vPQT5EGfQigj4qjU1ryOBzaiAooaIjlWg=; h=From:To:CC:Subject:Date:Message-ID:MIME-Version:Content-Type; b=TSef0Jbhap2PU9x8mQPzKen5B9RLm76wWxJHd8ZNBkPcpo+d7S+g09j0fEQj4CcnJYCJbw1tEoWTB71KYmiqrYmunw702hfFdLYfaJiZW9kFHOLpcI9Wr2BpfZcpgNs6HTXchFGoYiPvv8zYjJRl6t7V7GNN7qxNaE8qL5y3a9o= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com; spf=pass smtp.mailfrom=huawei.com; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b=0peX5yex; arc=none smtp.client-ip=113.46.200.220 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huawei.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b="0peX5yex" dkim-signature: v=1; a=rsa-sha256; d=huawei.com; s=dkim; c=relaxed/relaxed; q=dns/txt; h=From; bh=42MOztteCtilGOJ/7kcSahBhslYQw7ZPCwuPIdQb/r4=; b=0peX5yex0o58xHiHGYa/LL582bGxk5wOBM/A6LYbu/SBTlh5IRxl9DW05cnqnkzkriW9vjFsj g7iwFlNeypdfbtj+E4NfeW/dzxxnGNgpnKL0/+iWuEfOUz0Jlvm7OY8xu/HcQfYsEcUJ9nVapAQ H93eYOdOVx/cULGC2yJ3vsU= Received: from mail.maildlp.com (unknown [172.19.162.144]) by canpmsgout05.his.huawei.com (SkyGuard) with ESMTPS id 4dwMtG3VLxz12LFy; Tue, 20 Jan 2026 17:47:02 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id 656DA40567; Tue, 20 Jan 2026 17:51:01 +0800 (CST) Received: from localhost.huawei.com (10.90.31.46) by kwepemj200003.china.huawei.com (7.202.194.15) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1544.11; Tue, 20 Jan 2026 17:51:00 +0800 From: Qinxin Xia To: , , , , , , , CC: , , , , , , , , Subject: [RFC PATCH] perf: Add --uncorepmu option for filtering uncore PMUs Date: Tue, 20 Jan 2026 17:50:58 +0800 Message-ID: <20260120095058.2778834-1-xiaqinxin@huawei.com> X-Mailer: git-send-email 2.33.0 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-ClientProxiedBy: kwepems500002.china.huawei.com (7.221.188.17) To kwepemj200003.china.huawei.com (7.202.194.15) Content-Type: text/plain; charset="utf-8" This patch adds a new --uncorepmu option to perf-stat command to allow filtering events on specific uncore PMUs. This is useful when there are multiple uncore PMUs with the same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0). eg: [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 =20 0 hisi_sicl0_cpa0/cpa_p0_wr_dat/ = =20 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/ = =20 0 hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/ = =20 19,417,751,103 hisi_sicl10_cpa0/cpa_cycles/ # 0.00 cpa_p0_= avg_bw =20 0 hisi_sicl10_cpa0/cpa_p0_wr_dat/ = =20 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/ = =20 0 hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/ = =20 19,417,730,679 hisi_sicl2_cpa0/cpa_cycles/ # 0.31 cpa_p0_= avg_bw =20 75,635,749 hisi_sicl2_cpa0/cpa_p0_wr_dat/ = =20 18,520,640 hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/ = =20 0 hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/ = =20 19,417,674,227 hisi_sicl8_cpa0/cpa_cycles/ # 0.00 cpa_p0_= avg_bw =20 0 hisi_sicl8_cpa0/cpa_p0_wr_dat/ = =20 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/ = =20 0 hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/ = =20 19.417734480 seconds time elapsed [root@localhost tmp]# ./perf stat --uncorepmu 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 =20 50,548,465 cpa_p0_wr_dat = =20 7,552,182 cpa_p0_rd_dat_64b = =20 0 cpa_p0_rd_dat_32b = =20 6.234139320 seconds time elapsed Signed-off-by: Qinxin Xia --- tools/perf/Documentation/perf-stat.txt | 4 ++++ tools/perf/builtin-stat.c | 26 ++++++++++++++++++++++++++ tools/perf/util/metricgroup.c | 18 +++++++++++++----- 3 files changed, 43 insertions(+), 5 deletions(-) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentat= ion/perf-stat.txt index 1a766d4a2233..9c0952b43a57 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -573,6 +573,10 @@ $ perf config stat.no-csv-summary=3Dtrue Only enable events on applying cpu with this type for hybrid platform (e.g. core or atom)" =20 +--uncorepmu:: +Only enable events on applying uncore pmu with specified for multiple +uncore pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0) + EXAMPLES -------- =20 diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index ab40d85fb125..3f34bfc79179 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1235,6 +1235,28 @@ static int parse_cputype(const struct option *opt, return 0; } =20 +static int parse_uncorepmu(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + const struct perf_pmu *pmu; + struct evlist *evlist =3D *(struct evlist **)opt->value; + + if (!list_empty(&evlist->core.entries)) { + fprintf(stderr, "Must define uncorepmu before events/metrics\n"); + return -1; + } + + pmu =3D perf_pmus__pmu_for_pmu_filter(str); + if (!pmu || pmu->is_core) { + fprintf(stderr, "--uncorepmu %s is not supported!\n", str); + return -1; + } + parse_events_option_args.pmu_filter =3D pmu->name; + + return 0; +} + static int parse_cache_level(const struct option *opt, const char *str, int unset __maybe_unused) @@ -2579,6 +2601,10 @@ 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, "uncorepmu", &evsel_list, "uncore pmu", + "Only enable events on applying uncore pmu with specified " + "for multiple uncore pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_s= icl0_cpa0)", + parse_uncorepmu), #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 25c75fdbfc52..59ef71df20bd 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 =3D pm->pmu ?: "cpu"; + struct perf_pmu *perf_pmu =3D NULL; =20 - if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu)) + if (pm->pmu) + perf_pmu =3D 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; =20 return match_metric_or_groups(pm->metric_group, metric_or_groups) || @@ -1260,7 +1265,8 @@ 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; @@ -1314,7 +1320,7 @@ 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 =3D __parse_events(parsed_evlist, events.buf, /*pmu_filter=3D*/NULL, + ret =3D __parse_events(parsed_evlist, events.buf, filter_pmu, &parse_error, fake_pmu, /*warn_if_reordered=3D*/false, /*fake_tp=3D*/false); if (ret) { @@ -1417,7 +1423,8 @@ static int parse_groups(struct evlist *perf_evlist, /*modifier=3D*/NULL, /*group_events=3D*/false, tool_events, - &combined_evlist); + &combined_evlist, + (pmu && strcmp(pmu, "all") =3D=3D 0) ? NULL : pmu); } if (combined) expr__ctx_free(combined); @@ -1472,7 +1479,8 @@ static int parse_groups(struct evlist *perf_evlist, } if (!metric_evlist) { ret =3D 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") =3D=3D 0) ? NULL : pmu); if (ret) goto out; =20 --=20 2.33.0