summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
authorIan Rogers <irogers@google.com>2025-11-13 10:05:13 -0800
committerNamhyung Kim <namhyung@kernel.org>2025-11-17 18:43:09 -0800
commitd8d8a0b3603a9a8fa207cf9e4f292e81dc5d1008 (patch)
tree1c4619d45ce616b6739935963150a3e745f218f9 /tools/perf
parentd702c0f4af6e065846e67ff89b34aec2cca7ffa7 (diff)
perf tool_pmu: More accurately set the cpus for tool events
The user and system time events can record on different CPUs, but for all other events a single CPU map of just CPU 0 makes sense. In parse-events detect a tool PMU and then pass the perf_event_attr so that the tool_pmu can return CPUs specific for the event. This avoids a CPU map of all online CPUs being used for events like duration_time. Avoiding this avoids the evlist CPUs containing CPUs for which duration_time just gives 0. Minimizing the evlist CPUs can remove unnecessary sched_setaffinity syscalls that delay metric calculations. Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/util/parse-events.c9
-rw-r--r--tools/perf/util/tool_pmu.c19
-rw-r--r--tools/perf/util/tool_pmu.h1
3 files changed, 27 insertions, 2 deletions
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e522082c5a21..5ffeb7b416d9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -30,6 +30,7 @@
#include "util/event.h"
#include "util/bpf-filter.h"
#include "util/stat.h"
+#include "util/tool_pmu.h"
#include "util/util.h"
#include "tracepoint.h"
#include <api/fs/tracing_path.h>
@@ -227,8 +228,12 @@ __add_event(struct list_head *list, int *idx,
if (pmu) {
is_pmu_core = pmu->is_core;
pmu_cpus = perf_cpu_map__get(pmu->cpus);
- if (perf_cpu_map__is_empty(pmu_cpus))
- pmu_cpus = cpu_map__online();
+ if (perf_cpu_map__is_empty(pmu_cpus)) {
+ if (perf_pmu__is_tool(pmu))
+ pmu_cpus = tool_pmu__cpus(attr);
+ else
+ pmu_cpus = cpu_map__online();
+ }
} else {
is_pmu_core = (attr->type == PERF_TYPE_HARDWARE ||
attr->type == PERF_TYPE_HW_CACHE);
diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c
index 6a9df3dc0e07..37c4eae0bef1 100644
--- a/tools/perf/util/tool_pmu.c
+++ b/tools/perf/util/tool_pmu.c
@@ -2,6 +2,7 @@
#include "cgroup.h"
#include "counts.h"
#include "cputopo.h"
+#include "debug.h"
#include "evsel.h"
#include "pmu.h"
#include "print-events.h"
@@ -13,6 +14,7 @@
#include <api/fs/fs.h>
#include <api/io.h>
#include <internal/threadmap.h>
+#include <perf/cpumap.h>
#include <perf/threadmap.h>
#include <fcntl.h>
#include <strings.h>
@@ -109,6 +111,23 @@ const char *evsel__tool_pmu_event_name(const struct evsel *evsel)
return tool_pmu__event_to_str(evsel->core.attr.config);
}
+struct perf_cpu_map *tool_pmu__cpus(struct perf_event_attr *attr)
+{
+ static struct perf_cpu_map *cpu0_map;
+ enum tool_pmu_event event = (enum tool_pmu_event)attr->config;
+
+ if (event <= TOOL_PMU__EVENT_NONE || event >= TOOL_PMU__EVENT_MAX) {
+ pr_err("Invalid tool PMU event config %llx\n", attr->config);
+ return NULL;
+ }
+ if (event == TOOL_PMU__EVENT_USER_TIME || event == TOOL_PMU__EVENT_SYSTEM_TIME)
+ return cpu_map__online();
+
+ if (!cpu0_map)
+ cpu0_map = perf_cpu_map__new_int(0);
+ return perf_cpu_map__get(cpu0_map);
+}
+
static bool read_until_char(struct io *io, char e)
{
int c;
diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h
index f1714001bc1d..ea343d1983d3 100644
--- a/tools/perf/util/tool_pmu.h
+++ b/tools/perf/util/tool_pmu.h
@@ -46,6 +46,7 @@ bool tool_pmu__read_event(enum tool_pmu_event ev,
u64 tool_pmu__cpu_slots_per_cycle(void);
bool perf_pmu__is_tool(const struct perf_pmu *pmu);
+struct perf_cpu_map *tool_pmu__cpus(struct perf_event_attr *attr);
bool evsel__is_tool(const struct evsel *evsel);
enum tool_pmu_event evsel__tool_event(const struct evsel *evsel);