Skip to contentSkip to conversation

perf parse-event: Release cpu_map if evsel alloc failed

PATCH In review Namhyung Kim 3 participants 7 messages Sep 17, 2020 – Sep 18, 2020 perf events

lore
Share & tools
lore

Namhyung Kim

author maintainer
#0 lore raw

PATCH v2 1/2 perf parse-event: Release cpu_map if evsel alloc failed

---
 tools/perf/util/parse-events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/parse-events.c +3 -1
index 667cbca1547a..176a51698a64 100644
@@ -360,8 +360,10 @@ __add_event(struct list_head *list, int *idx,
 		event_attr_init(attr);
 
 	evsel = evsel__new_idx(attr, *idx);
-	if (!evsel)
+	if (!evsel) {
+		perf_cpu_map__put(cpus);
 		return NULL;
+	}
 
 	(*idx)++;
 	evsel->core.cpus   = perf_cpu_map__get(cpus);
Signature · 1 line
2.28.0.618.gf4bc123cb7-goog
author maintainer
#1 lore raw

PATCH v2 2/2 perf parse-event: Fix cpu map leaks

Like evlist cpu map, evsel's cpu map should have a proper refcount. As it's created with a refcount, we don't need to get an extra count. Thanks to Arnaldo for the simpler suggestion.

This fixes the following ASAN report:

Direct leak of 840 byte(s) in 70 object(s) allocated from:

    #0 0x7fe36703f628 in malloc (/lib/x86_64-linux-gnu/libasan.so.5+0x107628)
    #1 0x559fbbf611ca in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x559fbbf6229c in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:237
    #3 0x559fbbcc6c6d in __add_event util/parse-events.c:357
    #4 0x559fbbcc6c6d in add_event_tool util/parse-events.c:408
    #5 0x559fbbcc6c6d in parse_events_add_tool util/parse-events.c:1414
    #6 0x559fbbd8474d in parse_events_parse util/parse-events.y:439
    #7 0x559fbbcc95da in parse_events__scanner util/parse-events.c:2096
    #8 0x559fbbcc95da in __parse_events util/parse-events.c:2141
    #9 0x559fbbc2788b in check_parse_id tests/pmu-events.c:406
    #10 0x559fbbc2788b in check_parse_id tests/pmu-events.c:393
    #11 0x559fbbc2788b in check_parse_fake tests/pmu-events.c:436
    #12 0x559fbbc2788b in metric_parse_fake tests/pmu-events.c:553
    #13 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:599
    #14 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:574
    #15 0x559fbbc0109b in run_test tests/builtin-test.c:410
    #16 0x559fbbc0109b in test_and_print tests/builtin-test.c:440
    #17 0x559fbbc03e69 in __cmd_test tests/builtin-test.c:695
    #18 0x559fbbc03e69 in cmd_test tests/builtin-test.c:807
    #19 0x559fbbc691f4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:312
    #20 0x559fbbb071a8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:364
    #21 0x559fbbb071a8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:408
    #22 0x559fbbb071a8 in main /home/namhyung/project/linux/tools/perf/perf.c:538
    #23 0x7fe366b68cc9 in __libc_start_main ../csu/libc-start.c:308

And I've failed which commit introduced this bug as the code was heavily changed since then. ;-/

---
 tools/perf/util/parse-events.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
tools/perf/util/parse-events.c +2 -2
index 176a51698a64..fbe0d3143353 100644
@@ -353,7 +353,7 @@ __add_event(struct list_head *list, int *idx,
 	    const char *cpu_list)
 {
 	struct evsel *evsel;
-	struct perf_cpu_map *cpus = pmu ? pmu->cpus :
+	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
 	if (init_attr)
@@ -366,7 +366,7 @@ __add_event(struct list_head *list, int *idx,
 	}
 
 	(*idx)++;
-	evsel->core.cpus   = perf_cpu_map__get(cpus);
+	evsel->core.cpus = cpus;
 	evsel->core.own_cpus = perf_cpu_map__get(cpus);
 	evsel->core.system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
Signature · 1 line
2.28.0.618.gf4bc123cb7-goog
#2 lore raw

Re: [PATCH v2 2/2] perf parse-event: Fix cpu map leaks

Em Thu, Sep 17, 2020 at 03:02:19PM +0900, Namhyung Kim escreveu:

Quoted 5 lines

Like evlist cpu map, evsel's cpu map should have a proper refcount. As it's created with a refcount, we don't need to get an extra count. Thanks to Arnaldo for the simpler suggestion.

This fixes the following ASAN report:

This one should come first, and the patch summary is:

"perf parse-events Fix cpu map refcounting"

Then the next patch fixes the refcoutnt leak on the error path.

I'm fixing this up,

Thanks,

- Arnaldo

Quoted 60 lines

Direct leak of 840 byte(s) in 70 object(s) allocated from:

    #0 0x7fe36703f628 in malloc (/lib/x86_64-linux-gnu/libasan.so.5+0x107628)
    #1 0x559fbbf611ca in cpu_map__trim_new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:79
    #2 0x559fbbf6229c in perf_cpu_map__new /home/namhyung/project/linux/tools/lib/perf/cpumap.c:237
    #3 0x559fbbcc6c6d in __add_event util/parse-events.c:357
    #4 0x559fbbcc6c6d in add_event_tool util/parse-events.c:408
    #5 0x559fbbcc6c6d in parse_events_add_tool util/parse-events.c:1414
    #6 0x559fbbd8474d in parse_events_parse util/parse-events.y:439
    #7 0x559fbbcc95da in parse_events__scanner util/parse-events.c:2096
    #8 0x559fbbcc95da in __parse_events util/parse-events.c:2141
    #9 0x559fbbc2788b in check_parse_id tests/pmu-events.c:406
    #10 0x559fbbc2788b in check_parse_id tests/pmu-events.c:393
    #11 0x559fbbc2788b in check_parse_fake tests/pmu-events.c:436
    #12 0x559fbbc2788b in metric_parse_fake tests/pmu-events.c:553
    #13 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:599
    #14 0x559fbbc27e2d in test_parsing_fake tests/pmu-events.c:574
    #15 0x559fbbc0109b in run_test tests/builtin-test.c:410
    #16 0x559fbbc0109b in test_and_print tests/builtin-test.c:440
    #17 0x559fbbc03e69 in __cmd_test tests/builtin-test.c:695
    #18 0x559fbbc03e69 in cmd_test tests/builtin-test.c:807
    #19 0x559fbbc691f4 in run_builtin /home/namhyung/project/linux/tools/perf/perf.c:312
    #20 0x559fbbb071a8 in handle_internal_command /home/namhyung/project/linux/tools/perf/perf.c:364
    #21 0x559fbbb071a8 in run_argv /home/namhyung/project/linux/tools/perf/perf.c:408
    #22 0x559fbbb071a8 in main /home/namhyung/project/linux/tools/perf/perf.c:538
    #23 0x7fe366b68cc9 in __libc_start_main ../csu/libc-start.c:308

And I've failed which commit introduced this bug as the code was heavily changed since then. ;-/

---
 tools/perf/util/parse-events.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
tools/perf/util/parse-events.c +2 -2
index 176a51698a64..fbe0d3143353 100644
@@ -353,7 +353,7 @@ __add_event(struct list_head *list, int *idx,
 	    const char *cpu_list)
 {
 	struct evsel *evsel;
-	struct perf_cpu_map *cpus = pmu ? pmu->cpus :
+	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
 	if (init_attr)
@@ -366,7 +366,7 @@ __add_event(struct list_head *list, int *idx,
 	}
 
 	(*idx)++;
-	evsel->core.cpus   = perf_cpu_map__get(cpus);
+	evsel->core.cpus = cpus;
 	evsel->core.own_cpus = perf_cpu_map__get(cpus);
 	evsel->core.system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
Signature · 1 line
2.28.0.618.gf4bc123cb7-goog
Signature · 1 line
- Arnaldo
#3 lore raw
In reply to Namhyung Kim
Quoted 10 lines · Namhyung Kim
---
 tools/perf/util/parse-events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/parse-events.c +0 -0
index 667cbca1547a..176a51698a64 100644

tools/perf/util/parse-events.c __add_event(struct list_head *list, int *idx, · line 364

Quoted 6 lines
tools/perf/util/parse-events.c +2 -1
@@ -360,8 +360,10 @@ __add_event(struct list_head *list, int *idx,
 		event_attr_init(attr);
 
 	evsel = evsel__new_idx(attr, *idx);
-	if (!evsel)
+	if (!evsel) {
+		perf_cpu_map__put(cpus);

if there's pmu defined, we don't we get on perf_cpu_map:

        struct perf_cpu_map *cpus = pmu ? pmu->cpus :
                               cpu_list ? perf_cpu_map__new(cpu_list) : NULL;

jirka

Quoted 8 lines
tools/perf/util/parse-events.c +1 -0
 		return NULL;
+	}
 
 	(*idx)++;
 	evsel->core.cpus   = perf_cpu_map__get(cpus);
Signature · 1 line
2.28.0.618.gf4bc123cb7-goog
author maintainer
#4 lore raw
Quoted 21 lines · Jiri Olsa
Quoted 10 lines · Namhyung Kim
---
 tools/perf/util/parse-events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/parse-events.c +0 -0
index 667cbca1547a..176a51698a64 100644

tools/perf/util/parse-events.c __add_event(struct list_head *list, int *idx, · line 364

Quoted 6 lines
tools/perf/util/parse-events.c +2 -1
@@ -360,8 +360,10 @@ __add_event(struct list_head *list, int *idx,
              event_attr_init(attr);
 
      evsel = evsel__new_idx(attr, *idx);
-     if (!evsel)
+     if (!evsel) {
+             perf_cpu_map__put(cpus);

if there's pmu defined, we don't we get on perf_cpu_map:

Quoted 2 lines
        struct perf_cpu_map *cpus = pmu ? pmu->cpus :
                               cpu_list ? perf_cpu_map__new(cpu_list) : NULL;

Right, but it's changed in the next patch. Maybe I need to exchange them.

Thanks
Namhyung

Quoted 10 lines
Quoted 9 lines
tools/perf/util/parse-events.c +1 -1
              return NULL;
+     }
 
      (*idx)++;
      evsel->core.cpus   = perf_cpu_map__get(cpus);
--

2.28.0.618.gf4bc123cb7-goog

#5 lore raw
In reply to Jiri Olsa

Em Thu, Sep 17, 2020 at 03:10:58PM +0200, Jiri Olsa escreveu:

Quoted 20 lines · Namhyung Kim
Quoted 10 lines
---
 tools/perf/util/parse-events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/parse-events.c +0 -0
index 667cbca1547a..176a51698a64 100644

tools/perf/util/parse-events.c __add_event(struct list_head *list, int *idx, · line 364

Quoted 6 lines
tools/perf/util/parse-events.c +2 -1
@@ -360,8 +360,10 @@ __add_event(struct list_head *list, int *idx,
 		event_attr_init(attr);
 
 	evsel = evsel__new_idx(attr, *idx);
-	if (!evsel)
+	if (!evsel) {
+		perf_cpu_map__put(cpus);

if there's pmu defined, we don't we get on perf_cpu_map:

Quoted 2 lines
        struct perf_cpu_map *cpus = pmu ? pmu->cpus :
                               cpu_list ? perf_cpu_map__new(cpu_list) : NULL;

Yeah, I fixed this up by applying first the patch that grabs the pmu->cpus refcount and makes the first attribution of evsel->core.cpus be directly to 'cpus', as it will either have the refcount for pmu->cpus or the newly created, refcount set at 1 cpu map.o

Then the error path fix goes in, just dropping the reference to whatever cpu map we have a refcount for.

- Arnaldo

Quoted 11 lines

jirka

Quoted 8 lines
tools/perf/util/parse-events.c +1 -0
 		return NULL;
+	}
 
 	(*idx)++;
 	evsel->core.cpus   = perf_cpu_map__get(cpus);
Signature · 1 line
2.28.0.618.gf4bc123cb7-goog
Signature · 1 line
- Arnaldo
author maintainer
#6 lore raw
Quoted 25 lines · Arnaldo Carvalho de Melo

Em Thu, Sep 17, 2020 at 03:10:58PM +0200, Jiri Olsa escreveu:

Quoted 20 lines · Namhyung Kim
Quoted 10 lines
---
 tools/perf/util/parse-events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/parse-events.c +0 -0
index 667cbca1547a..176a51698a64 100644

tools/perf/util/parse-events.c __add_event(struct list_head *list, int *idx, · line 364

Quoted 6 lines
tools/perf/util/parse-events.c +2 -1
@@ -360,8 +360,10 @@ __add_event(struct list_head *list, int *idx,
            event_attr_init(attr);
 
    evsel = evsel__new_idx(attr, *idx);
-   if (!evsel)
+   if (!evsel) {
+           perf_cpu_map__put(cpus);

if there's pmu defined, we don't we get on perf_cpu_map:

Quoted 2 lines
        struct perf_cpu_map *cpus = pmu ? pmu->cpus :
                               cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
Quoted 7 lines

Yeah, I fixed this up by applying first the patch that grabs the pmu->cpus refcount and makes the first attribution of evsel->core.cpus be directly to 'cpus', as it will either have the refcount for pmu->cpus or the newly created, refcount set at 1 cpu map.o

Then the error path fix goes in, just dropping the reference to whatever cpu map we have a refcount for.

Sorry for messing this up and thanks for fixing it. I'll take more care later..

Thanks
Namhyung

Quoted 14 lines
Quoted 10 lines
Quoted 9 lines
tools/perf/util/parse-events.c +1 -1
            return NULL;
+   }
 
    (*idx)++;
    evsel->core.cpus   = perf_cpu_map__get(cpus);
--

2.28.0.618.gf4bc123cb7-goog

--

- Arnaldo