linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2 0/3] Test/uniquification related fixes
@ 2025-09-18 22:21 Ian Rogers
  2025-09-18 22:22 ` [PATCH v2 1/3] perf test: Don't leak workload gopipe in PERF_RECORD_* Ian Rogers
                   ` (3 more replies)
  0 siblings, 4 replies; 8+ messages in thread
From: Ian Rogers @ 2025-09-18 22:21 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Ian Rogers, Adrian Hunter, Kan Liang, Athira Rajeev,
	Chun-Tse Shao, James Clark, Howard Chu, linux-kernel,
	linux-perf-users

Failures discovered running as non-root and with v6.17-rc1 changes.

v2: Fix uniquification test when running as non-root. Rebase on
    tmp.perf-tools-next where the first patch was already merged.

Ian Rogers (3):
  perf test: Don't leak workload gopipe in PERF_RECORD_*
  perf evsel: Fix uniquification when PMU given without suffix
  perf test: Avoid uncore_imc/clockticks in uniquification test

 tools/perf/tests/perf-record.c                |   4 +
 .../tests/shell/stat+event_uniquifying.sh     | 109 ++++++++----------
 tools/perf/util/evsel.c                       |  28 +++--
 3 files changed, 71 insertions(+), 70 deletions(-)

-- 
2.51.0.470.ga7dc726c21-goog


^ permalink raw reply	[flat|nested] 8+ messages in thread

* [PATCH v2 1/3] perf test: Don't leak workload gopipe in PERF_RECORD_*
  2025-09-18 22:21 [PATCH v2 0/3] Test/uniquification related fixes Ian Rogers
@ 2025-09-18 22:22 ` Ian Rogers
  2025-09-18 22:22 ` [PATCH v2 2/3] perf evsel: Fix uniquification when PMU given without suffix Ian Rogers
                   ` (2 subsequent siblings)
  3 siblings, 0 replies; 8+ messages in thread
From: Ian Rogers @ 2025-09-18 22:22 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Ian Rogers, Adrian Hunter, Kan Liang, Athira Rajeev,
	Chun-Tse Shao, James Clark, Howard Chu, linux-kernel,
	linux-perf-users

The test starts a workload and then opens events. If the events fail
to open, for example because of perf_event_paranoid, the gopipe of the
workload is leaked and the file descriptor leak check fails when the
test exits. To avoid this cancel the workload when opening the events
fails.

Before:
```
$ perf test -vv 7
  7: PERF_RECORD_* events & perf_sample fields:
--- start ---
test child forked, pid 1189568
Using CPUID GenuineIntel-6-B7-1
------------------------------------------------------------
perf_event_attr:
  type                             0 (PERF_TYPE_HARDWARE)
  config                           0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/)
  disabled                         1
------------------------------------------------------------
sys_perf_event_open: pid 0  cpu -1  group_fd -1  flags 0x8
sys_perf_event_open failed, error -13
------------------------------------------------------------
perf_event_attr:
  type                             0 (PERF_TYPE_HARDWARE)
  config                           0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/)
  disabled                         1
  exclude_kernel                   1
------------------------------------------------------------
sys_perf_event_open: pid 0  cpu -1  group_fd -1  flags 0x8 = 3
------------------------------------------------------------
perf_event_attr:
  type                             0 (PERF_TYPE_HARDWARE)
  config                           0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/)
  disabled                         1
------------------------------------------------------------
sys_perf_event_open: pid 0  cpu -1  group_fd -1  flags 0x8
sys_perf_event_open failed, error -13
------------------------------------------------------------
perf_event_attr:
  type                             0 (PERF_TYPE_HARDWARE)
  config                           0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/)
  disabled                         1
  exclude_kernel                   1
------------------------------------------------------------
sys_perf_event_open: pid 0  cpu -1  group_fd -1  flags 0x8 = 3
Attempt to add: software/cpu-clock/
..after resolving event: software/config=0/
cpu-clock -> software/cpu-clock/
------------------------------------------------------------
perf_event_attr:
  type                             1 (PERF_TYPE_SOFTWARE)
  size                             136
  config                           0x9 (PERF_COUNT_SW_DUMMY)
  sample_type                      IP|TID|TIME|CPU
  read_format                      ID|LOST
  disabled                         1
  inherit                          1
  mmap                             1
  comm                             1
  enable_on_exec                   1
  task                             1
  sample_id_all                    1
  mmap2                            1
  comm_exec                        1
  ksymbol                          1
  bpf_event                        1
  { wakeup_events, wakeup_watermark } 1
------------------------------------------------------------
sys_perf_event_open: pid 1189569  cpu 0  group_fd -1  flags 0x8
sys_perf_event_open failed, error -13
perf_evlist__open: Permission denied
---- end(-2) ----
Leak of file descriptor 6 that opened: 'pipe:[14200347]'

---- unexpected signal (6) ----
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
Failed to read build ID for //anon
    #0 0x565358f6666e in child_test_sig_handler builtin-test.c:311
    #1 0x7f29ce849df0 in __restore_rt libc_sigaction.c:0
    #2 0x7f29ce89e95c in __pthread_kill_implementation pthread_kill.c:44
    #3 0x7f29ce849cc2 in raise raise.c:27
    #4 0x7f29ce8324ac in abort abort.c:81
    #5 0x565358f662d4 in check_leaks builtin-test.c:226
    #6 0x565358f6682e in run_test_child builtin-test.c:344
    #7 0x565358ef7121 in start_command run-command.c:128
    #8 0x565358f67273 in start_test builtin-test.c:545
    #9 0x565358f6771d in __cmd_test builtin-test.c:647
    #10 0x565358f682bd in cmd_test builtin-test.c:849
    #11 0x565358ee5ded in run_builtin perf.c:349
    #12 0x565358ee6085 in handle_internal_command perf.c:401
    #13 0x565358ee61de in run_argv perf.c:448
    #14 0x565358ee6527 in main perf.c:555
    #15 0x7f29ce833ca8 in __libc_start_call_main libc_start_call_main.h:74
    #16 0x7f29ce833d65 in __libc_start_main@@GLIBC_2.34 libc-start.c:128
    #17 0x565358e391c1 in _start perf[851c1]
  7: PERF_RECORD_* events & perf_sample fields                       : FAILED!
```

After:
```
$ perf test 7
  7: PERF_RECORD_* events & perf_sample fields                       : Skip (permissions)
```

Fixes: 16d00fee7038 ("perf tests: Move test__PERF_RECORD into separate object")
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/tests/perf-record.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index d895df037707..efbd9cd60c63 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -130,6 +130,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
+		evlist__cancel_workload(evlist);
 		goto out_delete_evlist;
 	}
 
@@ -141,6 +142,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
+		evlist__cancel_workload(evlist);
 		goto out_delete_evlist;
 	}
 
@@ -152,6 +154,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
+		evlist__cancel_workload(evlist);
 		goto out_delete_evlist;
 	}
 
@@ -164,6 +167,7 @@ static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest
 	if (err < 0) {
 		pr_debug("evlist__mmap: %s\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
+		evlist__cancel_workload(evlist);
 		goto out_delete_evlist;
 	}
 
-- 
2.51.0.470.ga7dc726c21-goog


^ permalink raw reply related	[flat|nested] 8+ messages in thread

* [PATCH v2 2/3] perf evsel: Fix uniquification when PMU given without suffix
  2025-09-18 22:21 [PATCH v2 0/3] Test/uniquification related fixes Ian Rogers
  2025-09-18 22:22 ` [PATCH v2 1/3] perf test: Don't leak workload gopipe in PERF_RECORD_* Ian Rogers
@ 2025-09-18 22:22 ` Ian Rogers
  2025-09-18 22:22 ` [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test Ian Rogers
  2025-09-19 19:51 ` [PATCH v2 0/3] Test/uniquification related fixes Arnaldo Carvalho de Melo
  3 siblings, 0 replies; 8+ messages in thread
From: Ian Rogers @ 2025-09-18 22:22 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Ian Rogers, Adrian Hunter, Kan Liang, Athira Rajeev,
	Chun-Tse Shao, James Clark, Howard Chu, linux-kernel,
	linux-perf-users

The PMU name is appearing twice in:
```
$ perf stat -e uncore_imc_free_running/data_total/ -A true

 Performance counter stats for 'system wide':

CPU0                 1.57 MiB  uncore_imc_free_running_0/uncore_imc_free_running,data_total/
CPU0                 1.58 MiB  uncore_imc_free_running_1/uncore_imc_free_running,data_total/
       0.000892376 seconds time elapsed
```

Use the pmu_name_len_no_suffix to avoid this problem.

Fixes: 7d45f402d311 ("perf evlist: Make uniquifying counter names consistent")
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/evsel.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6a31f9699b49..6947072598b1 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -4053,9 +4053,9 @@ bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_con
 
 void evsel__uniquify_counter(struct evsel *counter)
 {
-	const char *name, *pmu_name;
-	char *new_name, *config;
-	int ret;
+	const char *name, *pmu_name, *config;
+	char *new_name;
+	int len, ret;
 
 	/* No uniquification necessary. */
 	if (!counter->needs_uniquify)
@@ -4069,15 +4069,23 @@ void evsel__uniquify_counter(struct evsel *counter)
 	counter->uniquified_name = true;
 
 	name = evsel__name(counter);
+	config = strchr(name, '/');
 	pmu_name = counter->pmu->name;
-	/* Already prefixed by the PMU name. */
-	if (!strncmp(name, pmu_name, strlen(pmu_name)))
-		return;
 
-	config = strchr(name, '/');
-	if (config) {
-		int len = config - name;
+	/* Already prefixed by the PMU name? */
+	len = pmu_name_len_no_suffix(pmu_name);
+
+	if (!strncmp(name, pmu_name, len)) {
+		/*
+		 * If the PMU name is there, then there is no sense in not
+		 * having a slash. Do this for robustness.
+		 */
+		if (config == NULL)
+			config = name - 1;
 
+		ret = asprintf(&new_name, "%s/%s", pmu_name, config + 1);
+	} else if (config) {
+		len = config - name;
 		if (config[1] == '/') {
 			/* case: event// */
 			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2);
@@ -4089,7 +4097,7 @@ void evsel__uniquify_counter(struct evsel *counter)
 		config = strchr(name, ':');
 		if (config) {
 			/* case: event:.. */
-			int len = config - name;
+			len = config - name;
 
 			ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1);
 		} else {
-- 
2.51.0.470.ga7dc726c21-goog


^ permalink raw reply related	[flat|nested] 8+ messages in thread

* [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test
  2025-09-18 22:21 [PATCH v2 0/3] Test/uniquification related fixes Ian Rogers
  2025-09-18 22:22 ` [PATCH v2 1/3] perf test: Don't leak workload gopipe in PERF_RECORD_* Ian Rogers
  2025-09-18 22:22 ` [PATCH v2 2/3] perf evsel: Fix uniquification when PMU given without suffix Ian Rogers
@ 2025-09-18 22:22 ` Ian Rogers
  2025-09-26  9:00   ` Qiao Zhao
  2025-09-19 19:51 ` [PATCH v2 0/3] Test/uniquification related fixes Arnaldo Carvalho de Melo
  3 siblings, 1 reply; 8+ messages in thread
From: Ian Rogers @ 2025-09-18 22:22 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Ian Rogers, Adrian Hunter, Kan Liang, Athira Rajeev,
	Chun-Tse Shao, James Clark, Howard Chu, linux-kernel,
	linux-perf-users

The detection of uncore_imc may happen for free running PMUs and the
clockticks event may be present on uncore_clock. Rewrite the test to
detect duplicated/deduplicated events from perf list, not hardcoded to
uncore_imc.

If perf stat fails then assume it is permissions and skip the test.

Fixes: 070b315333ee ("perf test: Restrict uniquifying test to machines with 'uncore_imc'")
Signed-off-by: Ian Rogers <irogers@google.com>
---
 .../tests/shell/stat+event_uniquifying.sh     | 109 ++++++++----------
 1 file changed, 49 insertions(+), 60 deletions(-)

diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
index bf54bd6c3e2e..b5dec6b6da36 100755
--- a/tools/perf/tests/shell/stat+event_uniquifying.sh
+++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
@@ -4,74 +4,63 @@
 
 set -e
 
-stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
-perf_tool=perf
 err=0
+stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
 
-test_event_uniquifying() {
-  # We use `clockticks` in `uncore_imc` to verify the uniquify behavior.
-  pmu="uncore_imc"
-  event="clockticks"
-
-  # If the `-A` option is added, the event should be uniquified.
-  #
-  # $perf list -v clockticks
-  #
-  # List of pre-defined events (to be used in -e or -M):
-  #
-  #   uncore_imc_0/clockticks/                           [Kernel PMU event]
-  #   uncore_imc_1/clockticks/                           [Kernel PMU event]
-  #   uncore_imc_2/clockticks/                           [Kernel PMU event]
-  #   uncore_imc_3/clockticks/                           [Kernel PMU event]
-  #   uncore_imc_4/clockticks/                           [Kernel PMU event]
-  #   uncore_imc_5/clockticks/                           [Kernel PMU event]
-  #
-  #   ...
-  #
-  # $perf stat -e clockticks -A -- true
-  #
-  #  Performance counter stats for 'system wide':
-  #
-  # CPU0            3,773,018      uncore_imc_0/clockticks/
-  # CPU0            3,609,025      uncore_imc_1/clockticks/
-  # CPU0                    0      uncore_imc_2/clockticks/
-  # CPU0            3,230,009      uncore_imc_3/clockticks/
-  # CPU0            3,049,897      uncore_imc_4/clockticks/
-  # CPU0                    0      uncore_imc_5/clockticks/
-  #
-  #        0.002029828 seconds time elapsed
-
-  echo "stat event uniquifying test"
-  uniquified_event_array=()
+cleanup() {
+  rm -f "${stat_output}"
 
-  # Skip if the machine does not have `uncore_imc` device.
-  if ! ${perf_tool} list pmu | grep -q ${pmu}; then
-    echo "Target does not support PMU ${pmu} [Skipped]"
-    err=2
-    return
-  fi
+  trap - EXIT TERM INT
+}
 
-  # Check how many uniquified events.
-  while IFS= read -r line; do
-    uniquified_event=$(echo "$line" | awk '{print $1}')
-    uniquified_event_array+=("${uniquified_event}")
-  done < <(${perf_tool} list -v ${event} | grep ${pmu})
+trap_cleanup() {
+  echo "Unexpected signal in ${FUNCNAME[1]}"
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
 
-  perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
-  $perf_command
+test_event_uniquifying() {
+  echo "Uniquification of PMU sysfs events test"
 
-  # Check the output contains all uniquified events.
-  for uniquified_event in "${uniquified_event_array[@]}"; do
-    if ! cat "${stat_output}" | grep -q "${uniquified_event}"; then
-      echo "Event is not uniquified [Failed]"
-      echo "${perf_command}"
-      cat "${stat_output}"
-      err=1
-      break
-    fi
+  # Read events from perf list with and without -v. With -v the duplicate PMUs
+  # aren't deduplicated. Note, json events are listed by perf list without a
+  # PMU.
+  read -ra pmu_events <<< "$(perf list --raw pmu)"
+  read -ra pmu_v_events <<< "$(perf list -v --raw pmu)"
+  # For all non-deduplicated events.
+  for pmu_v_event in "${pmu_v_events[@]}"; do
+    # If the event matches an event in the deduplicated events then it musn't
+    # be an event with duplicate PMUs, continue the outer loop.
+    for pmu_event in "${pmu_events[@]}"; do
+      if [[ "$pmu_v_event" == "$pmu_event" ]]; then
+        continue 2
+      fi
+    done
+    # Strip the suffix from the non-deduplicated event's PMU.
+    event=$(echo "$pmu_v_event" | sed -E 's/_[0-9]+//')
+    for pmu_event in "${pmu_events[@]}"; do
+      if [[ "$event" == "$pmu_event" ]]; then
+        echo "Testing event ${event} is uniquified to ${pmu_v_event}"
+        if ! perf stat -e "$event" -A -o ${stat_output} -- true; then
+          echo "Error running perf stat for event '$event'  [Skip]"
+          if [ $err = 0 ]; then
+            err=2
+          fi
+          continue
+        fi
+        # Ensure the non-deduplicated event appears in the output.
+        if ! grep -q "${pmu_v_event}" "${stat_output}"; then
+          echo "Uniquification of PMU sysfs events test [Failed]"
+          cat "${stat_output}"
+          err=1
+        fi
+        break
+      fi
+    done
   done
 }
 
 test_event_uniquifying
-rm -f "${stat_output}"
+cleanup
 exit $err
-- 
2.51.0.470.ga7dc726c21-goog


^ permalink raw reply related	[flat|nested] 8+ messages in thread

* Re: [PATCH v2 0/3] Test/uniquification related fixes
  2025-09-18 22:21 [PATCH v2 0/3] Test/uniquification related fixes Ian Rogers
                   ` (2 preceding siblings ...)
  2025-09-18 22:22 ` [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test Ian Rogers
@ 2025-09-19 19:51 ` Arnaldo Carvalho de Melo
  3 siblings, 0 replies; 8+ messages in thread
From: Arnaldo Carvalho de Melo @ 2025-09-19 19:51 UTC (permalink / raw)
  To: Ian Rogers
  Cc: Peter Zijlstra, Ingo Molnar, Namhyung Kim, Mark Rutland,
	Alexander Shishkin, Jiri Olsa, Adrian Hunter, Kan Liang,
	Athira Rajeev, Chun-Tse Shao, James Clark, Howard Chu,
	linux-kernel, linux-perf-users

On Thu, Sep 18, 2025 at 03:21:59PM -0700, Ian Rogers wrote:
> Failures discovered running as non-root and with v6.17-rc1 changes.
> 
> v2: Fix uniquification test when running as non-root. Rebase on
>     tmp.perf-tools-next where the first patch was already merged.

Thanks, all reproduced before/after and applied.

- Arnaldo
 
> Ian Rogers (3):
>   perf test: Don't leak workload gopipe in PERF_RECORD_*
>   perf evsel: Fix uniquification when PMU given without suffix
>   perf test: Avoid uncore_imc/clockticks in uniquification test
> 
>  tools/perf/tests/perf-record.c                |   4 +
>  .../tests/shell/stat+event_uniquifying.sh     | 109 ++++++++----------
>  tools/perf/util/evsel.c                       |  28 +++--
>  3 files changed, 71 insertions(+), 70 deletions(-)
> 
> -- 
> 2.51.0.470.ga7dc726c21-goog

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test
  2025-09-18 22:22 ` [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test Ian Rogers
@ 2025-09-26  9:00   ` Qiao Zhao
  2025-09-26 16:21     ` Ian Rogers
  0 siblings, 1 reply; 8+ messages in thread
From: Qiao Zhao @ 2025-09-26  9:00 UTC (permalink / raw)
  To: Ian Rogers
  Cc: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Adrian Hunter, Kan Liang, Athira Rajeev, Chun-Tse Shao,
	James Clark, Howard Chu, linux-kernel, linux-perf-users

Hi Ian,

I tested your patch (latest linux-next code + your patch) on hybrid
CPU machine {CPU Model name: 12th Gen Intel(R) Core(TM) i7-12800HE}
and failed,
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
# perf test -vv "perf stat events uniquifying"
 95: perf stat events uniquifying:
--- start ---
test child forked, pid 21799
Uniquification of PMU sysfs events test
Testing event uncore_imc_free_running/data_read/ is uniquified to
uncore_imc_free_running_0/data_read/
Uniquification of PMU sysfs events test [Failed]
# started on Fri Sep 26 04:49:54 2025


 Performance counter stats for 'system wide':

CPU0                 1.47 MiB
uncore_imc_free_running_0/uncore_imc_free_running,data_read/
CPU0                 1.47 MiB
uncore_imc_free_running_1/uncore_imc_free_running,data_read/

       0.000925108 seconds time elapsed

Testing event uncore_imc_free_running/data_total/ is uniquified to
uncore_imc_free_running_0/data_total/
Uniquification of PMU sysfs events test [Failed]
# started on Fri Sep 26 04:49:54 2025


 Performance counter stats for 'system wide':

CPU0                 0.59 MiB
uncore_imc_free_running_0/uncore_imc_free_running,data_total/
CPU0                 0.58 MiB
uncore_imc_free_running_1/uncore_imc_free_running,data_total/

       0.000969877 seconds time elapsed

Testing event uncore_imc_free_running/data_write/ is uniquified to
uncore_imc_free_running_0/data_write/
Uniquification of PMU sysfs events test [Failed]
# started on Fri Sep 26 04:49:54 2025


 Performance counter stats for 'system wide':

CPU0                 0.00 MiB
uncore_imc_free_running_0/uncore_imc_free_running,data_write/
CPU0                 0.00 MiB
uncore_imc_free_running_1/uncore_imc_free_running,data_write/

       0.001183888 seconds time elapsed

Testing event uncore_imc_free_running/data_read/ is uniquified to
uncore_imc_free_running_1/data_read/
Uniquification of PMU sysfs events test [Failed]
# started on Fri Sep 26 04:49:54 2025


 Performance counter stats for 'system wide':

CPU0                 0.29 MiB
uncore_imc_free_running_0/uncore_imc_free_running,data_read/
CPU0                 0.29 MiB
uncore_imc_free_running_1/uncore_imc_free_running,data_read/

       0.000710088 seconds time elapsed

Testing event uncore_imc_free_running/data_total/ is uniquified to
uncore_imc_free_running_1/data_total/
Uniquification of PMU sysfs events test [Failed]
# started on Fri Sep 26 04:49:54 2025


 Performance counter stats for 'system wide':

CPU0                 0.62 MiB
uncore_imc_free_running_0/uncore_imc_free_running,data_total/
CPU0                 0.67 MiB
uncore_imc_free_running_1/uncore_imc_free_running,data_total/

       0.000959074 seconds time elapsed

Testing event uncore_imc_free_running/data_write/ is uniquified to
uncore_imc_free_running_1/data_write/
Uniquification of PMU sysfs events test [Failed]
# started on Fri Sep 26 04:49:54 2025


 Performance counter stats for 'system wide':

CPU0                 0.23 MiB
uncore_imc_free_running_0/uncore_imc_free_running,data_write/
CPU0                 0.23 MiB
uncore_imc_free_running_1/uncore_imc_free_running,data_write/

       0.000775028 seconds time elapsed

---- end(-1) ----
 95: perf stat events uniquifying                                    : FAILED!
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
# ls -la /sys/bus/event_source/devices/uncore_imc_free_running_*/events/
/sys/bus/event_source/devices/uncore_imc_free_running_0/events/:
total 0
drwxr-xr-x. 2 root root    0 Sep 26 04:57 .
drwxr-xr-x. 5 root root    0 Sep 26 01:49 ..
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_read
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.scale
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.unit
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_total
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.scale
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.unit
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_write
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.scale
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.unit

/sys/bus/event_source/devices/uncore_imc_free_running_1/events/:
total 0
drwxr-xr-x. 2 root root    0 Sep 26 04:57 .
drwxr-xr-x. 5 root root    0 Sep 26 01:49 ..
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_read
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.scale
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.unit
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_total
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.scale
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.unit
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_write
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.scale
-r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.unit

- Qiao

>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>


On Fri, Sep 19, 2025 at 6:22 AM Ian Rogers <irogers@google.com> wrote:
>
> The detection of uncore_imc may happen for free running PMUs and the
> clockticks event may be present on uncore_clock. Rewrite the test to
> detect duplicated/deduplicated events from perf list, not hardcoded to
> uncore_imc.
>
> If perf stat fails then assume it is permissions and skip the test.
>
> Fixes: 070b315333ee ("perf test: Restrict uniquifying test to machines with 'uncore_imc'")
> Signed-off-by: Ian Rogers <irogers@google.com>
> ---
>  .../tests/shell/stat+event_uniquifying.sh     | 109 ++++++++----------
>  1 file changed, 49 insertions(+), 60 deletions(-)
>
> diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
> index bf54bd6c3e2e..b5dec6b6da36 100755
> --- a/tools/perf/tests/shell/stat+event_uniquifying.sh
> +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
> @@ -4,74 +4,63 @@
>
>  set -e
>
> -stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
> -perf_tool=perf
>  err=0
> +stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
>
> -test_event_uniquifying() {
> -  # We use `clockticks` in `uncore_imc` to verify the uniquify behavior.
> -  pmu="uncore_imc"
> -  event="clockticks"
> -
> -  # If the `-A` option is added, the event should be uniquified.
> -  #
> -  # $perf list -v clockticks
> -  #
> -  # List of pre-defined events (to be used in -e or -M):
> -  #
> -  #   uncore_imc_0/clockticks/                           [Kernel PMU event]
> -  #   uncore_imc_1/clockticks/                           [Kernel PMU event]
> -  #   uncore_imc_2/clockticks/                           [Kernel PMU event]
> -  #   uncore_imc_3/clockticks/                           [Kernel PMU event]
> -  #   uncore_imc_4/clockticks/                           [Kernel PMU event]
> -  #   uncore_imc_5/clockticks/                           [Kernel PMU event]
> -  #
> -  #   ...
> -  #
> -  # $perf stat -e clockticks -A -- true
> -  #
> -  #  Performance counter stats for 'system wide':
> -  #
> -  # CPU0            3,773,018      uncore_imc_0/clockticks/
> -  # CPU0            3,609,025      uncore_imc_1/clockticks/
> -  # CPU0                    0      uncore_imc_2/clockticks/
> -  # CPU0            3,230,009      uncore_imc_3/clockticks/
> -  # CPU0            3,049,897      uncore_imc_4/clockticks/
> -  # CPU0                    0      uncore_imc_5/clockticks/
> -  #
> -  #        0.002029828 seconds time elapsed
> -
> -  echo "stat event uniquifying test"
> -  uniquified_event_array=()
> +cleanup() {
> +  rm -f "${stat_output}"
>
> -  # Skip if the machine does not have `uncore_imc` device.
> -  if ! ${perf_tool} list pmu | grep -q ${pmu}; then
> -    echo "Target does not support PMU ${pmu} [Skipped]"
> -    err=2
> -    return
> -  fi
> +  trap - EXIT TERM INT
> +}
>
> -  # Check how many uniquified events.
> -  while IFS= read -r line; do
> -    uniquified_event=$(echo "$line" | awk '{print $1}')
> -    uniquified_event_array+=("${uniquified_event}")
> -  done < <(${perf_tool} list -v ${event} | grep ${pmu})
> +trap_cleanup() {
> +  echo "Unexpected signal in ${FUNCNAME[1]}"
> +  cleanup
> +  exit 1
> +}
> +trap trap_cleanup EXIT TERM INT
>
> -  perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
> -  $perf_command
> +test_event_uniquifying() {
> +  echo "Uniquification of PMU sysfs events test"
>
> -  # Check the output contains all uniquified events.
> -  for uniquified_event in "${uniquified_event_array[@]}"; do
> -    if ! cat "${stat_output}" | grep -q "${uniquified_event}"; then
> -      echo "Event is not uniquified [Failed]"
> -      echo "${perf_command}"
> -      cat "${stat_output}"
> -      err=1
> -      break
> -    fi
> +  # Read events from perf list with and without -v. With -v the duplicate PMUs
> +  # aren't deduplicated. Note, json events are listed by perf list without a
> +  # PMU.
> +  read -ra pmu_events <<< "$(perf list --raw pmu)"
> +  read -ra pmu_v_events <<< "$(perf list -v --raw pmu)"
> +  # For all non-deduplicated events.
> +  for pmu_v_event in "${pmu_v_events[@]}"; do
> +    # If the event matches an event in the deduplicated events then it musn't
> +    # be an event with duplicate PMUs, continue the outer loop.
> +    for pmu_event in "${pmu_events[@]}"; do
> +      if [[ "$pmu_v_event" == "$pmu_event" ]]; then
> +        continue 2
> +      fi
> +    done
> +    # Strip the suffix from the non-deduplicated event's PMU.
> +    event=$(echo "$pmu_v_event" | sed -E 's/_[0-9]+//')
> +    for pmu_event in "${pmu_events[@]}"; do
> +      if [[ "$event" == "$pmu_event" ]]; then
> +        echo "Testing event ${event} is uniquified to ${pmu_v_event}"
> +        if ! perf stat -e "$event" -A -o ${stat_output} -- true; then
> +          echo "Error running perf stat for event '$event'  [Skip]"
> +          if [ $err = 0 ]; then
> +            err=2
> +          fi
> +          continue
> +        fi
> +        # Ensure the non-deduplicated event appears in the output.
> +        if ! grep -q "${pmu_v_event}" "${stat_output}"; then
> +          echo "Uniquification of PMU sysfs events test [Failed]"
> +          cat "${stat_output}"
> +          err=1
> +        fi
> +        break
> +      fi
> +    done
>    done
>  }
>
>  test_event_uniquifying
> -rm -f "${stat_output}"
> +cleanup
>  exit $err
> --
> 2.51.0.470.ga7dc726c21-goog
>
>


^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test
  2025-09-26  9:00   ` Qiao Zhao
@ 2025-09-26 16:21     ` Ian Rogers
  2025-09-29  2:39       ` Qiao Zhao
  0 siblings, 1 reply; 8+ messages in thread
From: Ian Rogers @ 2025-09-26 16:21 UTC (permalink / raw)
  To: Qiao Zhao
  Cc: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Adrian Hunter, Kan Liang, Athira Rajeev, Chun-Tse Shao,
	James Clark, Howard Chu, linux-kernel, linux-perf-users

On Fri, Sep 26, 2025 at 2:00 AM Qiao Zhao <qzhao@redhat.com> wrote:
>
> Hi Ian,
>
> I tested your patch (latest linux-next code + your patch) on hybrid
> CPU machine {CPU Model name: 12th Gen Intel(R) Core(TM) i7-12800HE}
> and failed,

Hi Qiao,

in your output is:
uncore_imc_free_running_0/uncore_imc_free_running,data_total/
ie the uncore PMU is reported twice. This is fixed in the immediately
prior patch in this series:
https://lore.kernel.org/lkml/20250918222202.1353854-3-irogers@google.com/

Thanks,
Ian

> >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
> # perf test -vv "perf stat events uniquifying"
>  95: perf stat events uniquifying:
> --- start ---
> test child forked, pid 21799
> Uniquification of PMU sysfs events test
> Testing event uncore_imc_free_running/data_read/ is uniquified to
> uncore_imc_free_running_0/data_read/
> Uniquification of PMU sysfs events test [Failed]
> # started on Fri Sep 26 04:49:54 2025
>
>
>  Performance counter stats for 'system wide':
>
> CPU0                 1.47 MiB
> uncore_imc_free_running_0/uncore_imc_free_running,data_read/
> CPU0                 1.47 MiB
> uncore_imc_free_running_1/uncore_imc_free_running,data_read/
>
>        0.000925108 seconds time elapsed
>
> Testing event uncore_imc_free_running/data_total/ is uniquified to
> uncore_imc_free_running_0/data_total/
> Uniquification of PMU sysfs events test [Failed]
> # started on Fri Sep 26 04:49:54 2025
>
>
>  Performance counter stats for 'system wide':
>
> CPU0                 0.59 MiB
> uncore_imc_free_running_0/uncore_imc_free_running,data_total/
> CPU0                 0.58 MiB
> uncore_imc_free_running_1/uncore_imc_free_running,data_total/
>
>        0.000969877 seconds time elapsed
>
> Testing event uncore_imc_free_running/data_write/ is uniquified to
> uncore_imc_free_running_0/data_write/
> Uniquification of PMU sysfs events test [Failed]
> # started on Fri Sep 26 04:49:54 2025
>
>
>  Performance counter stats for 'system wide':
>
> CPU0                 0.00 MiB
> uncore_imc_free_running_0/uncore_imc_free_running,data_write/
> CPU0                 0.00 MiB
> uncore_imc_free_running_1/uncore_imc_free_running,data_write/
>
>        0.001183888 seconds time elapsed
>
> Testing event uncore_imc_free_running/data_read/ is uniquified to
> uncore_imc_free_running_1/data_read/
> Uniquification of PMU sysfs events test [Failed]
> # started on Fri Sep 26 04:49:54 2025
>
>
>  Performance counter stats for 'system wide':
>
> CPU0                 0.29 MiB
> uncore_imc_free_running_0/uncore_imc_free_running,data_read/
> CPU0                 0.29 MiB
> uncore_imc_free_running_1/uncore_imc_free_running,data_read/
>
>        0.000710088 seconds time elapsed
>
> Testing event uncore_imc_free_running/data_total/ is uniquified to
> uncore_imc_free_running_1/data_total/
> Uniquification of PMU sysfs events test [Failed]
> # started on Fri Sep 26 04:49:54 2025
>
>
>  Performance counter stats for 'system wide':
>
> CPU0                 0.62 MiB
> uncore_imc_free_running_0/uncore_imc_free_running,data_total/
> CPU0                 0.67 MiB
> uncore_imc_free_running_1/uncore_imc_free_running,data_total/
>
>        0.000959074 seconds time elapsed
>
> Testing event uncore_imc_free_running/data_write/ is uniquified to
> uncore_imc_free_running_1/data_write/
> Uniquification of PMU sysfs events test [Failed]
> # started on Fri Sep 26 04:49:54 2025
>
>
>  Performance counter stats for 'system wide':
>
> CPU0                 0.23 MiB
> uncore_imc_free_running_0/uncore_imc_free_running,data_write/
> CPU0                 0.23 MiB
> uncore_imc_free_running_1/uncore_imc_free_running,data_write/
>
>        0.000775028 seconds time elapsed
>
> ---- end(-1) ----
>  95: perf stat events uniquifying                                    : FAILED!
> >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
> # ls -la /sys/bus/event_source/devices/uncore_imc_free_running_*/events/
> /sys/bus/event_source/devices/uncore_imc_free_running_0/events/:
> total 0
> drwxr-xr-x. 2 root root    0 Sep 26 04:57 .
> drwxr-xr-x. 5 root root    0 Sep 26 01:49 ..
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.scale
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.unit
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.scale
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.unit
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.scale
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.unit
>
> /sys/bus/event_source/devices/uncore_imc_free_running_1/events/:
> total 0
> drwxr-xr-x. 2 root root    0 Sep 26 04:57 .
> drwxr-xr-x. 5 root root    0 Sep 26 01:49 ..
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.scale
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.unit
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.scale
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.unit
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.scale
> -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.unit
>
> - Qiao
>
> >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
>
>
> On Fri, Sep 19, 2025 at 6:22 AM Ian Rogers <irogers@google.com> wrote:
> >
> > The detection of uncore_imc may happen for free running PMUs and the
> > clockticks event may be present on uncore_clock. Rewrite the test to
> > detect duplicated/deduplicated events from perf list, not hardcoded to
> > uncore_imc.
> >
> > If perf stat fails then assume it is permissions and skip the test.
> >
> > Fixes: 070b315333ee ("perf test: Restrict uniquifying test to machines with 'uncore_imc'")
> > Signed-off-by: Ian Rogers <irogers@google.com>
> > ---
> >  .../tests/shell/stat+event_uniquifying.sh     | 109 ++++++++----------
> >  1 file changed, 49 insertions(+), 60 deletions(-)
> >
> > diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
> > index bf54bd6c3e2e..b5dec6b6da36 100755
> > --- a/tools/perf/tests/shell/stat+event_uniquifying.sh
> > +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
> > @@ -4,74 +4,63 @@
> >
> >  set -e
> >
> > -stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
> > -perf_tool=perf
> >  err=0
> > +stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
> >
> > -test_event_uniquifying() {
> > -  # We use `clockticks` in `uncore_imc` to verify the uniquify behavior.
> > -  pmu="uncore_imc"
> > -  event="clockticks"
> > -
> > -  # If the `-A` option is added, the event should be uniquified.
> > -  #
> > -  # $perf list -v clockticks
> > -  #
> > -  # List of pre-defined events (to be used in -e or -M):
> > -  #
> > -  #   uncore_imc_0/clockticks/                           [Kernel PMU event]
> > -  #   uncore_imc_1/clockticks/                           [Kernel PMU event]
> > -  #   uncore_imc_2/clockticks/                           [Kernel PMU event]
> > -  #   uncore_imc_3/clockticks/                           [Kernel PMU event]
> > -  #   uncore_imc_4/clockticks/                           [Kernel PMU event]
> > -  #   uncore_imc_5/clockticks/                           [Kernel PMU event]
> > -  #
> > -  #   ...
> > -  #
> > -  # $perf stat -e clockticks -A -- true
> > -  #
> > -  #  Performance counter stats for 'system wide':
> > -  #
> > -  # CPU0            3,773,018      uncore_imc_0/clockticks/
> > -  # CPU0            3,609,025      uncore_imc_1/clockticks/
> > -  # CPU0                    0      uncore_imc_2/clockticks/
> > -  # CPU0            3,230,009      uncore_imc_3/clockticks/
> > -  # CPU0            3,049,897      uncore_imc_4/clockticks/
> > -  # CPU0                    0      uncore_imc_5/clockticks/
> > -  #
> > -  #        0.002029828 seconds time elapsed
> > -
> > -  echo "stat event uniquifying test"
> > -  uniquified_event_array=()
> > +cleanup() {
> > +  rm -f "${stat_output}"
> >
> > -  # Skip if the machine does not have `uncore_imc` device.
> > -  if ! ${perf_tool} list pmu | grep -q ${pmu}; then
> > -    echo "Target does not support PMU ${pmu} [Skipped]"
> > -    err=2
> > -    return
> > -  fi
> > +  trap - EXIT TERM INT
> > +}
> >
> > -  # Check how many uniquified events.
> > -  while IFS= read -r line; do
> > -    uniquified_event=$(echo "$line" | awk '{print $1}')
> > -    uniquified_event_array+=("${uniquified_event}")
> > -  done < <(${perf_tool} list -v ${event} | grep ${pmu})
> > +trap_cleanup() {
> > +  echo "Unexpected signal in ${FUNCNAME[1]}"
> > +  cleanup
> > +  exit 1
> > +}
> > +trap trap_cleanup EXIT TERM INT
> >
> > -  perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
> > -  $perf_command
> > +test_event_uniquifying() {
> > +  echo "Uniquification of PMU sysfs events test"
> >
> > -  # Check the output contains all uniquified events.
> > -  for uniquified_event in "${uniquified_event_array[@]}"; do
> > -    if ! cat "${stat_output}" | grep -q "${uniquified_event}"; then
> > -      echo "Event is not uniquified [Failed]"
> > -      echo "${perf_command}"
> > -      cat "${stat_output}"
> > -      err=1
> > -      break
> > -    fi
> > +  # Read events from perf list with and without -v. With -v the duplicate PMUs
> > +  # aren't deduplicated. Note, json events are listed by perf list without a
> > +  # PMU.
> > +  read -ra pmu_events <<< "$(perf list --raw pmu)"
> > +  read -ra pmu_v_events <<< "$(perf list -v --raw pmu)"
> > +  # For all non-deduplicated events.
> > +  for pmu_v_event in "${pmu_v_events[@]}"; do
> > +    # If the event matches an event in the deduplicated events then it musn't
> > +    # be an event with duplicate PMUs, continue the outer loop.
> > +    for pmu_event in "${pmu_events[@]}"; do
> > +      if [[ "$pmu_v_event" == "$pmu_event" ]]; then
> > +        continue 2
> > +      fi
> > +    done
> > +    # Strip the suffix from the non-deduplicated event's PMU.
> > +    event=$(echo "$pmu_v_event" | sed -E 's/_[0-9]+//')
> > +    for pmu_event in "${pmu_events[@]}"; do
> > +      if [[ "$event" == "$pmu_event" ]]; then
> > +        echo "Testing event ${event} is uniquified to ${pmu_v_event}"
> > +        if ! perf stat -e "$event" -A -o ${stat_output} -- true; then
> > +          echo "Error running perf stat for event '$event'  [Skip]"
> > +          if [ $err = 0 ]; then
> > +            err=2
> > +          fi
> > +          continue
> > +        fi
> > +        # Ensure the non-deduplicated event appears in the output.
> > +        if ! grep -q "${pmu_v_event}" "${stat_output}"; then
> > +          echo "Uniquification of PMU sysfs events test [Failed]"
> > +          cat "${stat_output}"
> > +          err=1
> > +        fi
> > +        break
> > +      fi
> > +    done
> >    done
> >  }
> >
> >  test_event_uniquifying
> > -rm -f "${stat_output}"
> > +cleanup
> >  exit $err
> > --
> > 2.51.0.470.ga7dc726c21-goog
> >
> >
>

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test
  2025-09-26 16:21     ` Ian Rogers
@ 2025-09-29  2:39       ` Qiao Zhao
  0 siblings, 0 replies; 8+ messages in thread
From: Qiao Zhao @ 2025-09-29  2:39 UTC (permalink / raw)
  To: Ian Rogers
  Cc: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Mark Rutland, Alexander Shishkin, Jiri Olsa,
	Adrian Hunter, Kan Liang, Athira Rajeev, Chun-Tse Shao,
	James Clark, Howard Chu, linux-kernel, linux-perf-users

Hi Ian,

Cool! After applied your patch "[PATCH v2 2/3] perf evsel: Fix
uniquification when PMU given without suffix" and  "[PATCH v2 3/3]
perf test: Avoid uncore_imc/clockticks in uniquification test",
the uniquifying testing passed on both Intel hybrid and non-hybrid machine:

hybrid CPU machine:
>>>>>>>>>>>>>>>>>>
# ./perf test -vv 96
 96: perf stat events uniquifying:
--- start ---
test child forked, pid 40541
Uniquification of PMU sysfs events test
Testing event uncore_imc_free_running/data_read/ is uniquified to
uncore_imc_free_running_0/data_read/
Testing event uncore_imc_free_running/data_total/ is uniquified to
uncore_imc_free_running_0/data_total/
Testing event uncore_imc_free_running/data_write/ is uniquified to
uncore_imc_free_running_0/data_write/
Testing event uncore_imc_free_running/data_read/ is uniquified to
uncore_imc_free_running_1/data_read/
Testing event uncore_imc_free_running/data_total/ is uniquified to
uncore_imc_free_running_1/data_total/
Testing event uncore_imc_free_running/data_write/ is uniquified to
uncore_imc_free_running_1/data_write/
---- end(0) ----
 96: perf stat events uniquifying                                    : Ok
>>>>>>>>>>>>>>>>>>

non-hybrid CPU machine:
>>>>>>>>>>>>>>>>>>
# ./perf test -vv 96
 96: perf stat events uniquifying:
--- start ---
test child forked, pid 114458
Uniquification of PMU sysfs events test
Testing event uncore_iio_free_running/bw_in_port0/ is uniquified to
uncore_iio_free_running_0/bw_in_port0/
Testing event uncore_iio_free_running/bw_in_port1/ is uniquified to
uncore_iio_free_running_0/bw_in_port1/
Testing event uncore_iio_free_running/bw_in_port2/ is uniquified to
uncore_iio_free_running_0/bw_in_port2/
Testing event uncore_iio_free_running/bw_in_port3/ is uniquified to
uncore_iio_free_running_0/bw_in_port3/
Testing event uncore_iio_free_running/bw_in_port4/ is uniquified to
uncore_iio_free_running_0/bw_in_port4/
Testing event uncore_iio_free_running/bw_in_port5/ is uniquified to
uncore_iio_free_running_0/bw_in_port5/
Testing event uncore_iio_free_running/bw_in_port6/ is uniquified to
uncore_iio_free_running_0/bw_in_port6/
Testing event uncore_iio_free_running/bw_in_port7/ is uniquified to
uncore_iio_free_running_0/bw_in_port7/
Testing event uncore_iio_free_running/ioclk/ is uniquified to
uncore_iio_free_running_0/ioclk/
... ...
Testing event uncore_imc_free_running/dclk/ is uniquified to
uncore_imc_free_running_0/dclk/
Testing event uncore_imc_free_running/rpq_cycles/ is uniquified to
uncore_imc_free_running_0/rpq_cycles/
Testing event uncore_imc_free_running/wpq_cycles/ is uniquified to
uncore_imc_free_running_0/wpq_cycles/
Testing event uncore_imc_free_running/dclk/ is uniquified to
uncore_imc_free_running_1/dclk/
Testing event uncore_imc_free_running/rpq_cycles/ is uniquified to
uncore_imc_free_running_1/rpq_cycles/
Testing event uncore_imc_free_running/wpq_cycles/ is uniquified to
uncore_imc_free_running_1/wpq_cycles/
Testing event uncore_imc_free_running/dclk/ is uniquified to
uncore_imc_free_running_2/dclk/
Testing event uncore_imc_free_running/rpq_cycles/ is uniquified to
uncore_imc_free_running_2/rpq_cycles/
Testing event uncore_imc_free_running/wpq_cycles/ is uniquified to
uncore_imc_free_running_2/wpq_cycles/
Testing event uncore_imc_free_running/dclk/ is uniquified to
uncore_imc_free_running_3/dclk/
Testing event uncore_imc_free_running/rpq_cycles/ is uniquified to
uncore_imc_free_running_3/rpq_cycles/
Testing event uncore_imc_free_running/wpq_cycles/ is uniquified to
uncore_imc_free_running_3/wpq_cycles/
---- end(0) ----
 96: perf stat events uniquifying                                    : Ok
>>>>>>>>>>>>>>>>>>

Tested-by: Qiao Zhao <qzhao@redhat.com>

On Fri, Sep 26, 2025 at 9:22 AM Ian Rogers <irogers@google.com> wrote:
>
> On Fri, Sep 26, 2025 at 2:00 AM Qiao Zhao <qzhao@redhat.com> wrote:
> >
> > Hi Ian,
> >
> > I tested your patch (latest linux-next code + your patch) on hybrid
> > CPU machine {CPU Model name: 12th Gen Intel(R) Core(TM) i7-12800HE}
> > and failed,
>
> Hi Qiao,
>
> in your output is:
> uncore_imc_free_running_0/uncore_imc_free_running,data_total/
> ie the uncore PMU is reported twice. This is fixed in the immediately
> prior patch in this series:
> https://lore.kernel.org/lkml/20250918222202.1353854-3-irogers@google.com/
>
> Thanks,
> Ian
>
> > >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
> > # perf test -vv "perf stat events uniquifying"
> >  95: perf stat events uniquifying:
> > --- start ---
> > test child forked, pid 21799
> > Uniquification of PMU sysfs events test
> > Testing event uncore_imc_free_running/data_read/ is uniquified to
> > uncore_imc_free_running_0/data_read/
> > Uniquification of PMU sysfs events test [Failed]
> > # started on Fri Sep 26 04:49:54 2025
> >
> >
> >  Performance counter stats for 'system wide':
> >
> > CPU0                 1.47 MiB
> > uncore_imc_free_running_0/uncore_imc_free_running,data_read/
> > CPU0                 1.47 MiB
> > uncore_imc_free_running_1/uncore_imc_free_running,data_read/
> >
> >        0.000925108 seconds time elapsed
> >
> > Testing event uncore_imc_free_running/data_total/ is uniquified to
> > uncore_imc_free_running_0/data_total/
> > Uniquification of PMU sysfs events test [Failed]
> > # started on Fri Sep 26 04:49:54 2025
> >
> >
> >  Performance counter stats for 'system wide':
> >
> > CPU0                 0.59 MiB
> > uncore_imc_free_running_0/uncore_imc_free_running,data_total/
> > CPU0                 0.58 MiB
> > uncore_imc_free_running_1/uncore_imc_free_running,data_total/
> >
> >        0.000969877 seconds time elapsed
> >
> > Testing event uncore_imc_free_running/data_write/ is uniquified to
> > uncore_imc_free_running_0/data_write/
> > Uniquification of PMU sysfs events test [Failed]
> > # started on Fri Sep 26 04:49:54 2025
> >
> >
> >  Performance counter stats for 'system wide':
> >
> > CPU0                 0.00 MiB
> > uncore_imc_free_running_0/uncore_imc_free_running,data_write/
> > CPU0                 0.00 MiB
> > uncore_imc_free_running_1/uncore_imc_free_running,data_write/
> >
> >        0.001183888 seconds time elapsed
> >
> > Testing event uncore_imc_free_running/data_read/ is uniquified to
> > uncore_imc_free_running_1/data_read/
> > Uniquification of PMU sysfs events test [Failed]
> > # started on Fri Sep 26 04:49:54 2025
> >
> >
> >  Performance counter stats for 'system wide':
> >
> > CPU0                 0.29 MiB
> > uncore_imc_free_running_0/uncore_imc_free_running,data_read/
> > CPU0                 0.29 MiB
> > uncore_imc_free_running_1/uncore_imc_free_running,data_read/
> >
> >        0.000710088 seconds time elapsed
> >
> > Testing event uncore_imc_free_running/data_total/ is uniquified to
> > uncore_imc_free_running_1/data_total/
> > Uniquification of PMU sysfs events test [Failed]
> > # started on Fri Sep 26 04:49:54 2025
> >
> >
> >  Performance counter stats for 'system wide':
> >
> > CPU0                 0.62 MiB
> > uncore_imc_free_running_0/uncore_imc_free_running,data_total/
> > CPU0                 0.67 MiB
> > uncore_imc_free_running_1/uncore_imc_free_running,data_total/
> >
> >        0.000959074 seconds time elapsed
> >
> > Testing event uncore_imc_free_running/data_write/ is uniquified to
> > uncore_imc_free_running_1/data_write/
> > Uniquification of PMU sysfs events test [Failed]
> > # started on Fri Sep 26 04:49:54 2025
> >
> >
> >  Performance counter stats for 'system wide':
> >
> > CPU0                 0.23 MiB
> > uncore_imc_free_running_0/uncore_imc_free_running,data_write/
> > CPU0                 0.23 MiB
> > uncore_imc_free_running_1/uncore_imc_free_running,data_write/
> >
> >        0.000775028 seconds time elapsed
> >
> > ---- end(-1) ----
> >  95: perf stat events uniquifying                                    : FAILED!
> > >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
> > # ls -la /sys/bus/event_source/devices/uncore_imc_free_running_*/events/
> > /sys/bus/event_source/devices/uncore_imc_free_running_0/events/:
> > total 0
> > drwxr-xr-x. 2 root root    0 Sep 26 04:57 .
> > drwxr-xr-x. 5 root root    0 Sep 26 01:49 ..
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.scale
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.unit
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.scale
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.unit
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.scale
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.unit
> >
> > /sys/bus/event_source/devices/uncore_imc_free_running_1/events/:
> > total 0
> > drwxr-xr-x. 2 root root    0 Sep 26 04:57 .
> > drwxr-xr-x. 5 root root    0 Sep 26 01:49 ..
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.scale
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_read.unit
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.scale
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_total.unit
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.scale
> > -r--r--r--. 1 root root 4096 Sep 26 01:49 data_write.unit
> >
> > - Qiao
> >
> > >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
> >
> >
> > On Fri, Sep 19, 2025 at 6:22 AM Ian Rogers <irogers@google.com> wrote:
> > >
> > > The detection of uncore_imc may happen for free running PMUs and the
> > > clockticks event may be present on uncore_clock. Rewrite the test to
> > > detect duplicated/deduplicated events from perf list, not hardcoded to
> > > uncore_imc.
> > >
> > > If perf stat fails then assume it is permissions and skip the test.
> > >
> > > Fixes: 070b315333ee ("perf test: Restrict uniquifying test to machines with 'uncore_imc'")
> > > Signed-off-by: Ian Rogers <irogers@google.com>
> > > ---
> > >  .../tests/shell/stat+event_uniquifying.sh     | 109 ++++++++----------
> > >  1 file changed, 49 insertions(+), 60 deletions(-)
> > >
> > > diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
> > > index bf54bd6c3e2e..b5dec6b6da36 100755
> > > --- a/tools/perf/tests/shell/stat+event_uniquifying.sh
> > > +++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
> > > @@ -4,74 +4,63 @@
> > >
> > >  set -e
> > >
> > > -stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
> > > -perf_tool=perf
> > >  err=0
> > > +stat_output=$(mktemp /tmp/__perf_test.stat_output.XXXXX)
> > >
> > > -test_event_uniquifying() {
> > > -  # We use `clockticks` in `uncore_imc` to verify the uniquify behavior.
> > > -  pmu="uncore_imc"
> > > -  event="clockticks"
> > > -
> > > -  # If the `-A` option is added, the event should be uniquified.
> > > -  #
> > > -  # $perf list -v clockticks
> > > -  #
> > > -  # List of pre-defined events (to be used in -e or -M):
> > > -  #
> > > -  #   uncore_imc_0/clockticks/                           [Kernel PMU event]
> > > -  #   uncore_imc_1/clockticks/                           [Kernel PMU event]
> > > -  #   uncore_imc_2/clockticks/                           [Kernel PMU event]
> > > -  #   uncore_imc_3/clockticks/                           [Kernel PMU event]
> > > -  #   uncore_imc_4/clockticks/                           [Kernel PMU event]
> > > -  #   uncore_imc_5/clockticks/                           [Kernel PMU event]
> > > -  #
> > > -  #   ...
> > > -  #
> > > -  # $perf stat -e clockticks -A -- true
> > > -  #
> > > -  #  Performance counter stats for 'system wide':
> > > -  #
> > > -  # CPU0            3,773,018      uncore_imc_0/clockticks/
> > > -  # CPU0            3,609,025      uncore_imc_1/clockticks/
> > > -  # CPU0                    0      uncore_imc_2/clockticks/
> > > -  # CPU0            3,230,009      uncore_imc_3/clockticks/
> > > -  # CPU0            3,049,897      uncore_imc_4/clockticks/
> > > -  # CPU0                    0      uncore_imc_5/clockticks/
> > > -  #
> > > -  #        0.002029828 seconds time elapsed
> > > -
> > > -  echo "stat event uniquifying test"
> > > -  uniquified_event_array=()
> > > +cleanup() {
> > > +  rm -f "${stat_output}"
> > >
> > > -  # Skip if the machine does not have `uncore_imc` device.
> > > -  if ! ${perf_tool} list pmu | grep -q ${pmu}; then
> > > -    echo "Target does not support PMU ${pmu} [Skipped]"
> > > -    err=2
> > > -    return
> > > -  fi
> > > +  trap - EXIT TERM INT
> > > +}
> > >
> > > -  # Check how many uniquified events.
> > > -  while IFS= read -r line; do
> > > -    uniquified_event=$(echo "$line" | awk '{print $1}')
> > > -    uniquified_event_array+=("${uniquified_event}")
> > > -  done < <(${perf_tool} list -v ${event} | grep ${pmu})
> > > +trap_cleanup() {
> > > +  echo "Unexpected signal in ${FUNCNAME[1]}"
> > > +  cleanup
> > > +  exit 1
> > > +}
> > > +trap trap_cleanup EXIT TERM INT
> > >
> > > -  perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
> > > -  $perf_command
> > > +test_event_uniquifying() {
> > > +  echo "Uniquification of PMU sysfs events test"
> > >
> > > -  # Check the output contains all uniquified events.
> > > -  for uniquified_event in "${uniquified_event_array[@]}"; do
> > > -    if ! cat "${stat_output}" | grep -q "${uniquified_event}"; then
> > > -      echo "Event is not uniquified [Failed]"
> > > -      echo "${perf_command}"
> > > -      cat "${stat_output}"
> > > -      err=1
> > > -      break
> > > -    fi
> > > +  # Read events from perf list with and without -v. With -v the duplicate PMUs
> > > +  # aren't deduplicated. Note, json events are listed by perf list without a
> > > +  # PMU.
> > > +  read -ra pmu_events <<< "$(perf list --raw pmu)"
> > > +  read -ra pmu_v_events <<< "$(perf list -v --raw pmu)"
> > > +  # For all non-deduplicated events.
> > > +  for pmu_v_event in "${pmu_v_events[@]}"; do
> > > +    # If the event matches an event in the deduplicated events then it musn't
> > > +    # be an event with duplicate PMUs, continue the outer loop.
> > > +    for pmu_event in "${pmu_events[@]}"; do
> > > +      if [[ "$pmu_v_event" == "$pmu_event" ]]; then
> > > +        continue 2
> > > +      fi
> > > +    done
> > > +    # Strip the suffix from the non-deduplicated event's PMU.
> > > +    event=$(echo "$pmu_v_event" | sed -E 's/_[0-9]+//')
> > > +    for pmu_event in "${pmu_events[@]}"; do
> > > +      if [[ "$event" == "$pmu_event" ]]; then
> > > +        echo "Testing event ${event} is uniquified to ${pmu_v_event}"
> > > +        if ! perf stat -e "$event" -A -o ${stat_output} -- true; then
> > > +          echo "Error running perf stat for event '$event'  [Skip]"
> > > +          if [ $err = 0 ]; then
> > > +            err=2
> > > +          fi
> > > +          continue
> > > +        fi
> > > +        # Ensure the non-deduplicated event appears in the output.
> > > +        if ! grep -q "${pmu_v_event}" "${stat_output}"; then
> > > +          echo "Uniquification of PMU sysfs events test [Failed]"
> > > +          cat "${stat_output}"
> > > +          err=1
> > > +        fi
> > > +        break
> > > +      fi
> > > +    done
> > >    done
> > >  }
> > >
> > >  test_event_uniquifying
> > > -rm -f "${stat_output}"
> > > +cleanup
> > >  exit $err
> > > --
> > > 2.51.0.470.ga7dc726c21-goog
> > >
> > >
> >
>


^ permalink raw reply	[flat|nested] 8+ messages in thread

end of thread, other threads:[~2025-09-29  2:39 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-09-18 22:21 [PATCH v2 0/3] Test/uniquification related fixes Ian Rogers
2025-09-18 22:22 ` [PATCH v2 1/3] perf test: Don't leak workload gopipe in PERF_RECORD_* Ian Rogers
2025-09-18 22:22 ` [PATCH v2 2/3] perf evsel: Fix uniquification when PMU given without suffix Ian Rogers
2025-09-18 22:22 ` [PATCH v2 3/3] perf test: Avoid uncore_imc/clockticks in uniquification test Ian Rogers
2025-09-26  9:00   ` Qiao Zhao
2025-09-26 16:21     ` Ian Rogers
2025-09-29  2:39       ` Qiao Zhao
2025-09-19 19:51 ` [PATCH v2 0/3] Test/uniquification related fixes Arnaldo Carvalho de Melo

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).