From: Ian Rogers <irogers@google.com>
To: Adrian Hunter <adrian.hunter@intel.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Benjamin Gray <bgray@linux.ibm.com>,
Caleb Biggers <caleb.biggers@intel.com>,
Edward Baker <edward.baker@intel.com>,
Ian Rogers <irogers@google.com>, Ingo Molnar <mingo@redhat.com>,
James Clark <james.clark@linaro.org>,
Jing Zhang <renyu.zj@linux.alibaba.com>,
Jiri Olsa <jolsa@kernel.org>,
John Garry <john.g.garry@oracle.com>, Leo Yan <leo.yan@arm.com>,
Namhyung Kim <namhyung@kernel.org>,
Perry Taylor <perry.taylor@intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Samantha Alt <samantha.alt@intel.com>,
Sandipan Das <sandipan.das@amd.com>,
Thomas Falcon <thomas.falcon@intel.com>,
Weilin Wang <weilin.wang@intel.com>, Xu Yang <xu.yang_2@nxp.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: [PATCH v8 01/52] perf python: Correct copying of metric_leader in an evsel
Date: Wed, 12 Nov 2025 19:19:49 -0800 [thread overview]
Message-ID: <20251113032040.1994090-2-irogers@google.com> (raw)
In-Reply-To: <20251113032040.1994090-1-irogers@google.com>
Ensure the metric_leader is copied and set up correctly. In
compute_metric determine the correct metric_leader event to match the
requested CPU. Fixes the handling of metrics particularly on hybrid
machines.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/util/evsel.c | 1 +
tools/perf/util/python.c | 82 +++++++++++++++++++++++++++++-----------
2 files changed, 61 insertions(+), 22 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 989c56d4a23f..0918afe5c009 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -538,6 +538,7 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig)
#endif
evsel->handler = orig->handler;
evsel->core.leader = orig->core.leader;
+ evsel->metric_leader = orig->metric_leader;
evsel->max_events = orig->max_events;
zfree(&evsel->unit);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index fa5e4270d182..cc1019d29a5d 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1340,27 +1340,48 @@ static int prepare_metric(const struct metric_expr *mexp,
struct metric_ref *metric_refs = mexp->metric_refs;
for (int i = 0; metric_events[i]; i++) {
- char *n = strdup(evsel__metric_id(metric_events[i]));
+ struct evsel *cur = metric_events[i];
double val, ena, run;
- int source_count = evsel__source_count(metric_events[i]);
- int ret;
+ int ret, source_count = 0;
struct perf_counts_values *old_count, *new_count;
+ char *n = strdup(evsel__metric_id(cur));
if (!n)
return -ENOMEM;
+ /*
+ * If there are multiple uncore PMUs and we're not reading the
+ * leader's stats, determine the stats for the appropriate
+ * uncore PMU.
+ */
+ if (evsel && evsel->metric_leader &&
+ evsel->pmu != evsel->metric_leader->pmu &&
+ cur->pmu == evsel->metric_leader->pmu) {
+ struct evsel *pos;
+
+ evlist__for_each_entry(evsel->evlist, pos) {
+ if (pos->pmu != evsel->pmu)
+ continue;
+ if (pos->metric_leader != cur)
+ continue;
+ cur = pos;
+ source_count = 1;
+ break;
+ }
+ }
+
if (source_count == 0)
- source_count = 1;
+ source_count = evsel__source_count(cur);
- ret = evsel__ensure_counts(metric_events[i]);
+ ret = evsel__ensure_counts(cur);
if (ret)
return ret;
/* Set up pointers to the old and newly read counter values. */
- old_count = perf_counts(metric_events[i]->prev_raw_counts, cpu_idx, thread_idx);
- new_count = perf_counts(metric_events[i]->counts, cpu_idx, thread_idx);
- /* Update the value in metric_events[i]->counts. */
- evsel__read_counter(metric_events[i], cpu_idx, thread_idx);
+ old_count = perf_counts(cur->prev_raw_counts, cpu_idx, thread_idx);
+ new_count = perf_counts(cur->counts, cpu_idx, thread_idx);
+ /* Update the value in cur->counts. */
+ evsel__read_counter(cur, cpu_idx, thread_idx);
val = new_count->val - old_count->val;
ena = new_count->ena - old_count->ena;
@@ -1392,6 +1413,7 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
struct metric_expr *mexp = NULL;
struct expr_parse_ctx *pctx;
double result = 0;
+ struct evsel *metric_evsel = NULL;
if (!PyArg_ParseTuple(args, "sii", &metric, &cpu, &thread))
return NULL;
@@ -1404,6 +1426,7 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
list_for_each(pos, &me->head) {
struct metric_expr *e = container_of(pos, struct metric_expr, nd);
+ struct evsel *pos2;
if (strcmp(e->metric_name, metric))
continue;
@@ -1411,20 +1434,24 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
if (e->metric_events[0] == NULL)
continue;
- cpu_idx = perf_cpu_map__idx(e->metric_events[0]->core.cpus,
- (struct perf_cpu){.cpu = cpu});
- if (cpu_idx < 0)
- continue;
-
- thread_idx = perf_thread_map__idx(e->metric_events[0]->core.threads,
- thread);
- if (thread_idx < 0)
- continue;
-
- mexp = e;
- break;
+ evlist__for_each_entry(&pevlist->evlist, pos2) {
+ if (pos2->metric_leader != e->metric_events[0])
+ continue;
+ cpu_idx = perf_cpu_map__idx(pos2->core.cpus,
+ (struct perf_cpu){.cpu = cpu});
+ if (cpu_idx < 0)
+ continue;
+
+ thread_idx = perf_thread_map__idx(pos2->core.threads, thread);
+ if (thread_idx < 0)
+ continue;
+ metric_evsel = pos2;
+ mexp = e;
+ goto done;
+ }
}
}
+done:
if (!mexp) {
PyErr_Format(PyExc_TypeError, "Unknown metric '%s' for CPU '%d' and thread '%d'",
metric, cpu, thread);
@@ -1435,7 +1462,7 @@ static PyObject *pyrf_evlist__compute_metric(struct pyrf_evlist *pevlist,
if (!pctx)
return PyErr_NoMemory();
- ret = prepare_metric(mexp, mexp->metric_events[0], pctx, cpu_idx, thread_idx);
+ ret = prepare_metric(mexp, metric_evsel, pctx, cpu_idx, thread_idx);
if (ret) {
expr__ctx_free(pctx);
errno = -ret;
@@ -1996,6 +2023,17 @@ static PyObject *pyrf_evlist__from_evlist(struct evlist *evlist)
else if (leader == NULL)
evsel__set_leader(pos, pos);
}
+
+ leader = pos->metric_leader;
+
+ if (pos != leader) {
+ int idx = evlist__pos(evlist, leader);
+
+ if (idx >= 0)
+ pos->metric_leader = evlist__at(&pevlist->evlist, idx);
+ else if (leader == NULL)
+ pos->metric_leader = pos;
+ }
}
metricgroup__copy_metric_events(&pevlist->evlist, /*cgrp=*/NULL,
&pevlist->evlist.metric_events,
--
2.51.2.1041.gc1ab5b90ca-goog
next prev parent reply other threads:[~2025-11-13 3:20 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-13 3:19 [PATCH v8 00/52] AMD, ARM, Intel metric generation with Python Ian Rogers
2025-11-13 3:19 ` Ian Rogers [this message]
2025-11-13 3:19 ` [PATCH v8 02/52] perf ilist: Be tolerant of reading a metric on the wrong CPU Ian Rogers
2025-11-13 3:19 ` [PATCH v8 03/52] perf jevents: Allow multiple metricgroups.json files Ian Rogers
2025-11-13 3:19 ` [PATCH v8 04/52] perf jevents: Update metric constraint support Ian Rogers
2025-11-13 3:19 ` [PATCH v8 05/52] perf jevents: Add descriptions to metricgroup abstraction Ian Rogers
2025-11-13 3:19 ` [PATCH v8 06/52] perf jevents: Allow metric groups not to be named Ian Rogers
2025-11-13 3:19 ` [PATCH v8 07/52] perf jevents: Support parsing negative exponents Ian Rogers
2025-11-13 3:19 ` [PATCH v8 08/52] perf jevents: Term list fix in event parsing Ian Rogers
2025-11-13 3:19 ` [PATCH v8 09/52] perf jevents: Add threshold expressions to Metric Ian Rogers
2025-11-13 3:19 ` [PATCH v8 10/52] perf jevents: Move json encoding to its own functions Ian Rogers
2025-11-13 3:19 ` [PATCH v8 11/52] perf jevents: Drop duplicate pending metrics Ian Rogers
2025-11-13 3:20 ` [PATCH v8 12/52] perf jevents: Skip optional metrics in metric group list Ian Rogers
2025-11-13 3:20 ` [PATCH v8 13/52] perf jevents: Build support for generating metrics from python Ian Rogers
2025-11-13 3:20 ` [PATCH v8 14/52] perf jevents: Add load event json to verify and allow fallbacks Ian Rogers
2025-11-13 3:20 ` [PATCH v8 15/52] perf jevents: Add RAPL event metric for AMD zen models Ian Rogers
2025-11-26 5:05 ` Sandipan Das
2025-11-28 9:20 ` Ian Rogers
2025-11-28 11:33 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 16/52] perf jevents: Add idle " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 17/52] perf jevents: Add upc metric for uops per cycle for AMD Ian Rogers
2025-11-13 3:20 ` [PATCH v8 18/52] perf jevents: Add br metric group for branch statistics on AMD Ian Rogers
2025-11-13 3:20 ` [PATCH v8 19/52] perf jevents: Add software prefetch (swpf) metric group for AMD Ian Rogers
2025-11-26 10:05 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 20/52] perf jevents: Add hardware prefetch (hwpf) " Ian Rogers
2025-11-26 10:17 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 21/52] perf jevents: Add itlb " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 22/52] perf jevents: Add dtlb " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 23/52] perf jevents: Add uncore l3 " Ian Rogers
2025-11-26 5:20 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 24/52] perf jevents: Add load store breakdown metrics ldst " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 25/52] perf jevents: Add ILP metrics " Ian Rogers
2025-11-26 6:26 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 26/52] perf jevents: Add context switch " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 27/52] perf jevents: Add uop cache hit/miss rates " Ian Rogers
2025-11-26 5:42 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 28/52] perf jevents: Add RAPL metrics for all Intel models Ian Rogers
2025-11-13 3:20 ` [PATCH v8 29/52] perf jevents: Add idle metric for " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 30/52] perf jevents: Add CheckPmu to see if a PMU is in loaded json events Ian Rogers
2025-11-13 3:20 ` [PATCH v8 31/52] perf jevents: Add smi metric group for Intel models Ian Rogers
2025-11-13 3:20 ` [PATCH v8 32/52] perf jevents: Mark metrics with experimental events as experimental Ian Rogers
2025-11-13 3:20 ` [PATCH v8 33/52] perf jevents: Add tsx metric group for Intel models Ian Rogers
2025-11-13 3:20 ` [PATCH v8 34/52] perf jevents: Add br metric group for branch statistics on Intel Ian Rogers
2025-11-13 3:20 ` [PATCH v8 35/52] perf jevents: Add software prefetch (swpf) metric group for Intel Ian Rogers
2025-11-13 3:20 ` [PATCH v8 36/52] perf jevents: Add ports metric group giving utilization on Intel Ian Rogers
2025-11-13 3:20 ` [PATCH v8 37/52] perf jevents: Add L2 metrics for Intel Ian Rogers
2025-11-13 3:20 ` [PATCH v8 38/52] perf jevents: Add load store breakdown metrics ldst " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 39/52] perf jevents: Add ILP metrics " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 40/52] perf jevents: Add context switch " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 41/52] perf jevents: Add FPU " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 42/52] perf jevents: Add Miss Level Parallelism (MLP) metric " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 43/52] perf jevents: Add mem_bw " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 44/52] perf jevents: Add local/remote "mem" breakdown metrics " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 45/52] perf jevents: Add dir " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 46/52] perf jevents: Add C-State metrics from the PCU PMU " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 47/52] perf jevents: Add local/remote miss latency metrics " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 48/52] perf jevents: Add upi_bw metric " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 49/52] perf jevents: Add mesh bandwidth saturation " Ian Rogers
2025-11-13 3:20 ` [PATCH v8 50/52] perf jevents: Add collection of topdown like metrics for arm64 Ian Rogers
2025-11-13 3:20 ` [PATCH v8 51/52] perf jevents: Add cycles breakdown metric for arm64/AMD/Intel Ian Rogers
2025-11-26 6:32 ` Sandipan Das
2025-11-13 3:20 ` [PATCH v8 52/52] perf jevents: Validate that all names given an Event Ian Rogers
2025-11-19 18:30 ` [PATCH v8 00/52] AMD, ARM, Intel metric generation with Python Ian Rogers
2025-11-20 20:32 ` Falcon, Thomas
2025-11-20 21:10 ` Namhyung Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251113032040.1994090-2-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=bgray@linux.ibm.com \
--cc=caleb.biggers@intel.com \
--cc=edward.baker@intel.com \
--cc=james.clark@linaro.org \
--cc=john.g.garry@oracle.com \
--cc=jolsa@kernel.org \
--cc=leo.yan@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=perry.taylor@intel.com \
--cc=peterz@infradead.org \
--cc=renyu.zj@linux.alibaba.com \
--cc=samantha.alt@intel.com \
--cc=sandipan.das@amd.com \
--cc=thomas.falcon@intel.com \
--cc=weilin.wang@intel.com \
--cc=xu.yang_2@nxp.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).