Skip to contentSkip to conversation

perf tools: Add cached probe type detection for evsel

PATCH Superseded Arnaldo Carvalho de Melo 3 participants 5 messages Jun 16 perf events

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore

Arnaldo Carvalho de Melo

author maintainer
#0 lore raw

cover perf tools: Add cached probe type detection for evsel

Hi,

Checking whether an evsel is a kprobe or uprobe currently requires walking the PMU list via evsel__find_pmu() on every call. This is wasteful when the same evsel is checked repeatedly in hot paths like trace__fprintf_tp_fields().

Patch 1 adds evsel__is_kprobe(), evsel__is_uprobe(), and evsel__is_probe() helpers that resolve the probe type on first call and cache the result in a 2-bit field that fits in existing struct padding.

Patch 2 is the first user: it guards the __probe_ip field name comparison in perf trace with evsel__is_probe(), so the strcmp is skipped entirely for the common case of non-probe tracepoint events.

Build-tested with gcc and clang.

Arnaldo Carvalho de Melo (2):
perf evsel: Add lazy-initialized probe type detection helpers perf trace: Guard __probe_ip suppression with evsel__is_probe()

 tools/perf/builtin-trace.c |  2 +-
 tools/perf/util/evsel.c    | 44 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evsel.h    |  5 +++++
 3 files changed, 50 insertions(+), 1 deletion(-)

Developed with AI assistance (Claude), tagged in commits.

Thanks,

- Arnaldo

author maintainer
#1 lore raw

PATCH 1/2 perf evsel: Add lazy-initialized probe type detection helpers

From: Arnaldo Carvalho de Melo <[email protected]>

Several places in perf need to check whether an evsel is a kprobe or uprobe, which requires looking up the PMU by name via evsel__find_pmu(). This lookup walks the PMU list each time, which is wasteful when the same evsel is checked repeatedly.

Add evsel__is_kprobe(), evsel__is_uprobe(), and evsel__is_probe() that resolve the probe type on first call via evsel__pmu_name() and cache the result in a 2-bit field (probe_type) in struct evsel. The field fits in existing padding after the bool fields, so struct size does not grow.

The enum uses PROBE__UNKNOWN (0) as the uninitialized sentinel — explicitly set in evsel__init() — so the lookup happens on first use. PROBE__NOPE (1) caches "not a probe" to avoid repeated negative lookups.

Assisted-by Claude Opus 4.6 <[email protected]>
---
 tools/perf/util/evsel.c | 44 +++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/evsel.h |  5 +++++
 2 files changed, 49 insertions(+)
tools/perf/util/evsel.c +44 -0
index 05fa0010c858a51e..223571091f09f9ee 100644
@@ -254,6 +254,49 @@ const char *evsel__pmu_name(const struct evsel *evsel)
 	return event_type(evsel->core.attr.type);
 }
 
+enum evsel_probe_type {
+	PROBE__UNKNOWN	= 0,
+	PROBE__NOPE	= 1,
+	PROBE__KPROBE	= 2,
+	PROBE__UPROBE	= 3,
+};
+
+static void evsel__resolve_probe_type(struct evsel *evsel)
+{
+	const char *name = evsel__pmu_name(evsel);
+
+	if (!strcmp(name, "kprobe"))
+		evsel->probe_type = PROBE__KPROBE;
+	else if (!strcmp(name, "uprobe"))
+		evsel->probe_type = PROBE__UPROBE;
+	else
+		evsel->probe_type = PROBE__NOPE;
+}
+
+bool evsel__is_probe(struct evsel *evsel)
+{
+	if (evsel->probe_type == PROBE__UNKNOWN)
+		evsel__resolve_probe_type(evsel);
+
+	return evsel->probe_type > PROBE__NOPE;
+}
+
+bool evsel__is_kprobe(struct evsel *evsel)
+{
+	if (evsel->probe_type == PROBE__UNKNOWN)
+		evsel__resolve_probe_type(evsel);
+
+	return evsel->probe_type == PROBE__KPROBE;
+}
+
+bool evsel__is_uprobe(struct evsel *evsel)
+{
+	if (evsel->probe_type == PROBE__UNKNOWN)
+		evsel__resolve_probe_type(evsel);
+
+	return evsel->probe_type == PROBE__UPROBE;
+}
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
 
 int __evsel__sample_size(u64 sample_type)
@@ -413,6 +456,7 @@ void evsel__init(struct evsel *evsel,
 	evsel->supported     = true;
 	evsel->alternate_hw_config = PERF_COUNT_HW_MAX;
 	evsel->script_output_type = -1; // FIXME: OUTPUT_TYPE_UNSET, see builtin-script.c
+	evsel->probe_type = PROBE__UNKNOWN;
 }
 
 struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
tools/perf/util/evsel.h +5 -0
index 8009be22cc3f1055..bf75381526147f92 100644
@@ -126,6 +126,7 @@ struct evsel {
 	bool			needs_uniquify;
 	bool			fallenback_eacces;
 	bool			fallenback_eopnotsupp;
+	u8			probe_type:2;
 	struct hashmap		*per_pkg_mask;
 	int			err;
 	int			script_output_type;
@@ -259,6 +260,10 @@ struct perf_pmu *evsel__find_pmu(const struct evsel *evsel);
 const char *evsel__pmu_name(const struct evsel *evsel);
 bool evsel__is_aux_event(const struct evsel *evsel);
 
+bool evsel__is_probe(struct evsel *evsel);
+bool evsel__is_kprobe(struct evsel *evsel);
+bool evsel__is_uprobe(struct evsel *evsel);
+
 struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx);
 
 static inline struct evsel *evsel__new(struct perf_event_attr *attr)
Signature · 1 line
2.54.0
author maintainer
#2 lore raw

PATCH 2/2 perf trace: Guard __probe_ip suppression with evsel__is_probe()

In reply to Arnaldo Carvalho de Melo

From: Arnaldo Carvalho de Melo <[email protected]>

trace__fprintf_tp_fields() compares every field name against "__probe_ip" for all tracepoint events, but this field is only implicitly added by the Ftrace subsystem to bare dynamic probes.

Add an evsel__is_probe() check before the strcmp so the string comparison is skipped entirely for non-probe events.

---
 tools/perf/builtin-trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-trace.c +1 -1
index a8492da23a9cc178..57f3f14c5d435805 100644
@@ -3267,7 +3267,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct perf_sample *
 		 * If verbose mode is enabled, ensure it is formatted as a
 		 * hexadecimal memory address rather than a signed integer.
 		 */
-		if (!strcmp(field->name, "__probe_ip")) {
+		if (evsel__is_probe(evsel) && !strcmp(field->name, "__probe_ip")) {
 			if (!verbose)
 				continue;
 
Signature · 1 line
2.54.0
#3 lore raw

Re: [PATCH 2/2] perf trace: Guard __probe_ip suppression with evsel__is_probe()

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [High] The `evsel__is_probe()` check evaluates to false for Ftrace dynamic probes, breaking the intended…

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The evsel__is_probe() check evaluates to false for Ftrace dynamic probes, breaking the intended suppression of the __probe_ip field. --

commit 0e15cda4a40a59d474ee0a3a5cdae64267b1f3b2
Author: Arnaldo Carvalho de Melo <[email protected]>

perf trace: Guard __probe_ip suppression with evsel__is_probe()

This commit adds an evsel__is_probe() check to trace__fprintf_tp_fields() to skip the string comparison of __probe_ip for non-probe events.

tools/perf/builtin-trace.c static size_t trace__fprintf_tp_fields(struct trace *trace, struct perf_sample * · line 3270

Quoted 10 lines
tools/perf/builtin-trace.c +1 -1
index a8492da23a9cc..57f3f14c5d435 100644
@@ -3267,7 +3267,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct perf_sample *
 		 * If verbose mode is enabled, ensure it is formatted as a
 		 * hexadecimal memory address rather than a signed integer.
 		 */
-		if (!strcmp(field->name, "__probe_ip")) {
+		if (evsel__is_probe(evsel) && !strcmp(field->name, "__probe_ip")) {

[Severity: High]
Does this check accidentally disable the suppression entirely for Ftrace dynamic probes?

Since trace__fprintf_tp_fields() processes fields specifically for tracepoint events (where evsel__tp_format() succeeds), the event has type PERF_TYPE_TRACEPOINT. For these events, the PMU name is "tracepoint".

However, evsel__is_probe() resolves the probe type by checking if the PMU name is "kprobe" or "uprobe". If it evaluates to false here because the PMU is "tracepoint", the condition short-circuits and the __probe_ip field is no longer suppressed.

Will this cause __probe_ip to be erroneously printed for all dynamic probes instead of being suppressed by default as intended?

Quoted 3 lines
tools/perf/builtin-trace.c +0 -0
 			if (!verbose)
 				continue;
 
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=2
Reviewed-by on v1 2/2
#4 lore raw

Re: [PATCH 2/2] perf trace: Guard __probe_ip suppression with evsel__is_probe()

In reply to Arnaldo Carvalho de Melo
Quoted 32 lines · Arnaldo Carvalho de Melo

From: Arnaldo Carvalho de Melo <[email protected]>

trace__fprintf_tp_fields() compares every field name against "__probe_ip" for all tracepoint events, but this field is only implicitly added by the Ftrace subsystem to bare dynamic probes.

Add an evsel__is_probe() check before the strcmp so the string comparison is skipped entirely for non-probe events.

---
 tools/perf/builtin-trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-trace.c +1 -1
index a8492da23a9cc178..57f3f14c5d435805 100644
@@ -3267,7 +3267,7 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct perf_sample *
 		 * If verbose mode is enabled, ensure it is formatted as a
 		 * hexadecimal memory address rather than a signed integer.
 		 */
-		if (!strcmp(field->name, "__probe_ip")) {
+		if (evsel__is_probe(evsel) && !strcmp(field->name, "__probe_ip")) {
 			if (!verbose)
 				continue;
 
Signature · 1 line
2.54.0

LGTM.

Signature · 1 line
Aaron Tomlin