[PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[Ian Rogers]

It is intended that a "--null" run doesn't open any events.

Fixes: 2cc7aa995ce9 ("perf stat: Refactor retry/skip/fatal error handling")
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5c06e9b61821..6410115ed9c5 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -923,7 +923,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			goto err_out;
 		}
 	}
-	if (!has_supported_counters) {
+	if (!has_supported_counters && !stat_config.null_run) {
 		evsel__open_strerror(evlist__first(evsel_list), &target, open_err,
 				     msg, sizeof(msg));
 		ui__error("No supported events found.\n%s\n", msg);
-- 
2.52.0.158.g65b55ccf14-goog

[PATCH v1 2/4] libperf cpumap: Fix perf_cpu_map__max for an empty/NULL map

[Ian Rogers]

Passing an empty map to perf_cpu_map__max triggered a SEGV. Explicitly
test for the empty map.

Reported-by: Ingo Molnar <mingo@kernel.org>
Closes: https://lore.kernel.org/linux-perf-users/aSwt7yzFjVJCEmVp@gmail.com/
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/lib/perf/cpumap.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 7e88417ba84d..4160e7d2e120 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -368,10 +368,12 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 		.cpu = -1
 	};
 
-	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
-	return __perf_cpu_map__nr(map) > 0
-		? __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1)
-		: result;
+	if (!map)
+		return result;
+
+	// The CPUs are always sorted and nr is always > 0 as 0 length map is
+	// encoded as NULL.
+	return __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1);
 }
 
 /** Is 'b' a subset of 'a'. */
-- 
2.52.0.158.g65b55ccf14-goog

[PATCH v1 3/4] perf cpumap: Add "any" CPU handling to cpu_map__snprint_mask

[Ian Rogers]

If the perf_cpu_map is empty or is just the any CPU value, then early
return. Don't process the "any" CPU when creating the bitmap.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/cpumap.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 89570397a4b3..a80845038a5e 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -684,16 +684,21 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	struct perf_cpu c, last_cpu = perf_cpu_map__max(map);
 
-	if (buf == NULL)
+	if (buf == NULL || size == 0)
 		return 0;
 
+	if (last_cpu.cpu < 0) {
+		buf[0] = '\0';
+		return 0;
+	}
+
 	bitmap = zalloc(last_cpu.cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
 	}
 
-	perf_cpu_map__for_each_cpu(c, idx, map)
+	perf_cpu_map__for_each_cpu_skip_any(c, idx, map)
 		bitmap[c.cpu / 8] |= 1 << (c.cpu % 8);
 
 	for (int cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
-- 
2.52.0.158.g65b55ccf14-goog

[PATCH v1 4/4] perf tests stat: Add "--null" coverage

[Ian Rogers]

Ensure "--null" does a minimal run.

Reported-by: Ingo Molnar <mingo@kernel.org>
Closes: https://lore.kernel.org/linux-perf-users/aSwt7yzFjVJCEmVp@gmail.com/
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/shell/stat.sh | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 985adc02749e..7885e875caf4 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -16,6 +16,17 @@ test_default_stat() {
   echo "Basic stat command test [Success]"
 }
 
+test_null_stat() {
+  echo "Null stat command test"
+  if ! perf stat --null true 2>&1 | grep -E -q "Performance counter stats for 'true':"
+  then
+    echo "Null stat command test [Failed]"
+    err=1
+    return
+  fi
+  echo "Null stat command test [Success]"
+}
+
 test_stat_record_report() {
   echo "stat record and report test"
   if ! perf stat record -e task-clock -o - true | perf stat report -i - 2>&1 | \
@@ -212,6 +223,7 @@ test_hybrid() {
 }
 
 test_default_stat
+test_null_stat
 test_stat_record_report
 test_stat_record_script
 test_stat_repeat_weak_groups
-- 
2.52.0.158.g65b55ccf14-goog

Re: [PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[Ingo Molnar]

* Ian Rogers <irogers@google.com> wrote:

> It is intended that a "--null" run doesn't open any events.
> 
> Fixes: 2cc7aa995ce9 ("perf stat: Refactor retry/skip/fatal error handling")
> Signed-off-by: Ian Rogers <irogers@google.com>
> ---
>  tools/perf/builtin-stat.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 5c06e9b61821..6410115ed9c5 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -923,7 +923,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
>  			goto err_out;
>  		}
>  	}
> -	if (!has_supported_counters) {
> +	if (!has_supported_counters && !stat_config.null_run) {
>  		evsel__open_strerror(evlist__first(evsel_list), &target, open_err,
>  				     msg, sizeof(msg));
>  		ui__error("No supported events found.\n%s\n", msg);

Note that without the cpumask workaround patch I sent 
'perf stat --null' still segfaults on perf-tools-next 
even with the above patch applied - I suppose that's 
expected, right?

Other than that:

  Tested-by: Ingo Molnar <mingo@kernel.org>

Thanks,

	Ingo

Re: [PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[Ingo Molnar]

* Ingo Molnar <mingo@kernel.org> wrote:

> Note that without the cpumask workaround patch I sent 
> 'perf stat --null' still segfaults on perf-tools-next 
> even with the above patch applied - I suppose that's 
> expected, right?

Ignore me, I just saw your fix series:

  git git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git perf-tools-next

Thanks,

	Ingo

Re: [PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[Ingo Molnar]

* Ingo Molnar <mingo@kernel.org> wrote:

> 
> * Ingo Molnar <mingo@kernel.org> wrote:
> 
> > Note that without the cpumask workaround patch I sent 
> > 'perf stat --null' still segfaults on perf-tools-next 
> > even with the above patch applied - I suppose that's 
> > expected, right?
> 
> Ignore me, I just saw your fix series:
> 
>   git git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git perf-tools-next

With all 4 patches applied to v6.18 'perf stat --null' 
works fine:

  Tested-by: Ingo Molnar <mingo@kernel.org>

Thanks,

	Ingo

Re: [PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[Ingo Molnar]

* Ingo Molnar <mingo@kernel.org> wrote:

> With all 4 patches applied to v6.18 'perf stat --null' 
> works fine:
> 
>   Tested-by: Ingo Molnar <mingo@kernel.org>

BTW., there's a long-standing perf-stat --repeat bug 
where signals don't seem to get properly propagated.

The following command takes 10 seconds to run, as 
expected:

  starship:~/tip> perf stat --null --repeat 10 sleep 1

   Performance counter stats for 'sleep 1' (10 runs):

           1.0026669 +- 0.0000503 seconds time elapsed  ( +-  0.01% )

But if I try to interrupt the test:

  starship:~/tip> perf stat --null --repeat 10 sleep 1
  ^Csleep: Interrupt
  ^Csleep: Interrupt

   Performance counter stats for 'sleep 1' (10 runs):

              0.9250 +- 0.0543 seconds time elapsed  ( +-  5.87% )


The Ctrl-C only propagates to the <command>, interrupts 
it (as can be seen from the shortened total runtime 
that is less than 10 seconds), and otherwise results in 
both an incorrect measurement and a misleading output 
of the partial results.

Furthermore, the test runs to full completion - which 
can be annoying if you happen to use high --repeat 
counts like I sometimes do. I have to Ctrl-Z and 
killall -9 perf to kill such instances.

Thanks,

	Ingo

Re: [PATCH v1 1/4] perf stat: Allow no events to open if this is a "--null" run

[Ian Rogers]

On Mon, Dec 1, 2025 at 8:52 PM Ingo Molnar <mingo@kernel.org> wrote:
>
>
> * Ingo Molnar <mingo@kernel.org> wrote:
>
> > With all 4 patches applied to v6.18 'perf stat --null'
> > works fine:
> >
> >   Tested-by: Ingo Molnar <mingo@kernel.org>
>
> BTW., there's a long-standing perf-stat --repeat bug
> where signals don't seem to get properly propagated.
>
> The following command takes 10 seconds to run, as
> expected:
>
>   starship:~/tip> perf stat --null --repeat 10 sleep 1
>
>    Performance counter stats for 'sleep 1' (10 runs):
>
>            1.0026669 +- 0.0000503 seconds time elapsed  ( +-  0.01% )
>
> But if I try to interrupt the test:
>
>   starship:~/tip> perf stat --null --repeat 10 sleep 1
>   ^Csleep: Interrupt
>   ^Csleep: Interrupt
>
>    Performance counter stats for 'sleep 1' (10 runs):
>
>               0.9250 +- 0.0543 seconds time elapsed  ( +-  5.87% )
>
>
> The Ctrl-C only propagates to the <command>, interrupts
> it (as can be seen from the shortened total runtime
> that is less than 10 seconds), and otherwise results in
> both an incorrect measurement and a misleading output
> of the partial results.
>
> Furthermore, the test runs to full completion - which
> can be annoying if you happen to use high --repeat
> counts like I sometimes do. I have to Ctrl-Z and
> killall -9 perf to kill such instances.

I've added a patch that hopefully fixes this in the v2 patch series:
https://lore.kernel.org/lkml/20251203214706.112174-8-irogers@google.com/

Thanks,
Ian

> Thanks,
>
>         Ingo