Skip to contentSkip to conversation

perf/x86/intel: Correct wrong 'or' operation for pmu capabilities

PATCH Applied Dapeng Mi 3 participants 3 messages Nov 21, 2023

Subsystems (3)
lore
Share & tools
lore

Dapeng Mi

author
#0 lore raw

PATCH 1/1 perf/x86/intel: Correct wrong 'or' operation for pmu capabilities

When running perf-stat command on Intel hybrid platform, perf-stat reports the following errors.

sudo taskset -c 7 ./perf stat -vvvv -e cpu_atom/instructions/ sleep 1

Opening: cpu/cycles/:HG
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  config                           0xa00000000
  disabled                         1

------------------------------------------------------------
sys_perf_event_open: pid 0 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -16

Performance counter stats for 'sleep 1':

<not counted> cpu_atom/instructions/

It looks the cpu_atom/instructions/ event can't be enabled on atom pmu even the process is pinned on atom core. The investigation shows that exclusive_event_init() helper always returns -EBUSY error in the perf event creation. That's strange since the atom pmu should not be a exclusive PMU.

Further investigation shows the issue is introduced by commit 97588df87b56 ("perf/x86/intel: Add common intel_pmu_init_hybrid()"). The commit originally intents to clear the bit PERF_PMU_CAP_AUX_OUTPUT from pmu capabilities if intel_cap.pebs_output_pt_available is not set, but it incorrectly uses 'or' operation and leads to all pmu capabilities bits are set to 1 except bit PERF_PMU_CAP_AUX_OUTPUT.

Testing this fix on Intel hybrid platforms, the observed issues disappear.

Fixes 97588df87b56 ("perf/x86/intel: Add common intel_pmu_init_hybrid()")
---
 arch/x86/events/intel/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/events/intel/core.c +1 -1
index a08f794a0e79..ce1c777227b4 100644
@@ -4660,7 +4660,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	if (pmu->intel_cap.pebs_output_pt_available)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 	else
-		pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->num_counters,

base-commit: b85ea95d086471afb4ad062012a4d73cd328fa86

Signature · 1 line
2.34.1
merge bot Applied
#1 lore raw

[tip: perf/urgent] perf/x86/intel: Correct incorrect 'or' operation for PMU capabilities

The following commit has been merged into the perf/urgent branch of tip:

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     e8df9d9f4209c04161321d8c12640ae560f65939
Gitweb:        https://git.kernel.org/tip/e8df9d9f4209c04161321d8c12640ae560f65939
Author:        Dapeng Mi <[email protected]>
AuthorDate:    Tue, 21 Nov 2023 09:46:28 +08:00
Committer:     Ingo Molnar <[email protected]>
CommitterDate: Tue, 21 Nov 2023 13:44:36 +01:00

perf/x86/intel: Correct incorrect 'or' operation for PMU capabilities

When running perf-stat command on Intel hybrid platform, perf-stat reports the following errors:

sudo taskset -c 7 ./perf stat -vvvv -e cpu_atom/instructions/ sleep 1

Opening: cpu/cycles/:HG
------------------------------------------------------------
perf_event_attr:

    type                             0 (PERF_TYPE_HARDWARE)
    config                           0xa00000000
    disabled                         1

------------------------------------------------------------
sys_perf_event_open: pid 0 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -16

Performance counter stats for 'sleep 1':

<not counted> cpu_atom/instructions/

It looks the cpu_atom/instructions/ event can't be enabled on atom PMU even when the process is pinned on atom core. Investigation shows that exclusive_event_init() helper always returns -EBUSY error in the perf event creation. That's strange since the atom PMU should not be an exclusive PMU.

Further investigation shows the issue was introduced by commit:

97588df87b56 ("perf/x86/intel: Add common intel_pmu_init_hybrid()")

The commit originally intents to clear the bit PERF_PMU_CAP_AUX_OUTPUT from PMU capabilities if intel_cap.pebs_output_pt_available is not set, but it incorrectly uses 'or' operation and leads to all PMU capabilities bits are set to 1 except bit PERF_PMU_CAP_AUX_OUTPUT.

Testing this fix on Intel hybrid platforms, the observed issues disappear.

Fixes 97588df87b56 ("perf/x86/intel: Add common intel_pmu_init_hybrid()")
---
 arch/x86/events/intel/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/events/intel/core.c +1 -1
index a08f794..ce1c777 100644
@@ -4660,7 +4660,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	if (pmu->intel_cap.pebs_output_pt_available)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 	else
-		pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->num_counters,
Reviewed-by on v1 1/1
#2 lore raw
In reply to Dapeng Mi
Quoted 32 lines · Dapeng Mi

When running perf-stat command on Intel hybrid platform, perf-stat reports the following errors.

sudo taskset -c 7 ./perf stat -vvvv -e cpu_atom/instructions/ sleep 1

Opening: cpu/cycles/:HG
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  config                           0xa00000000
  disabled                         1

------------------------------------------------------------
sys_perf_event_open: pid 0 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -16

Performance counter stats for 'sleep 1':

<not counted> cpu_atom/instructions/

It looks the cpu_atom/instructions/ event can't be enabled on atom pmu even the process is pinned on atom core. The investigation shows that exclusive_event_init() helper always returns -EBUSY error in the perf event creation. That's strange since the atom pmu should not be a exclusive PMU.

Further investigation shows the issue is introduced by commit 97588df87b56 ("perf/x86/intel: Add common intel_pmu_init_hybrid()"). The commit originally intents to clear the bit PERF_PMU_CAP_AUX_OUTPUT from pmu capabilities if intel_cap.pebs_output_pt_available is not set, but it incorrectly uses 'or' operation and leads to all pmu capabilities bits are set to 1 except bit PERF_PMU_CAP_AUX_OUTPUT.

Quoted 6 lines

Testing this fix on Intel hybrid platforms, the observed issues disappear.

Fixes 97588df87b56 ("perf/x86/intel: Add common intel_pmu_init_hybrid()")

Thanks,
Kan

Quoted 19 lines
---
 arch/x86/events/intel/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/events/intel/core.c +1 -1
index a08f794a0e79..ce1c777227b4 100644
@@ -4660,7 +4660,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	if (pmu->intel_cap.pebs_output_pt_available)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 	else
-		pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->num_counters,

base-commit: b85ea95d086471afb4ad062012a4d73cd328fa86