perf: arm_pmuv3: Don't use PMCCNTR_EL0 on SMT cores

CPU_CYCLES is expected to count the logical CPU (PE) clock. Currently it's
preferred to use PMCCNTR_EL0 for counting CPU_CYCLES, but it'll count
processor clock rather than the PE clock (ARM DDI0487 L.b D13.1.3) if
one of the SMT siblings is not idle on a multi-threaded implementation.
So don't use it on SMT cores.

Introduce topology_core_has_smt() for knowing the SMT implementation and
cached it in arm_pmu::has_smt during allocation.

When counting cycles on SMT CPU 2-3 and CPU 3 is idle, without this
patch we'll get:
[root@client1 tmp]# perf stat -e cycles -A -C 2-3 -- stress-ng -c 1
--taskset 2 --timeout 1
[...]
 Performance counter stats for 'CPU(s) 2-3':

CPU2           2880457316      cycles
CPU3           2880459810      cycles
       1.254688470 seconds time elapsed

With this patch the idle state of CPU3 is observed as expected:
[root@client1 ~]#  perf stat -e cycles -A -C 2-3 -- stress-ng -c 1
--taskset 2 --timeout 1
[...]
 Performance counter stats for 'CPU(s) 2-3':

CPU2           2558580492      cycles
CPU3               305749      cycles
       1.113626410 seconds time elapsed

Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Will Deacon <will@kernel.org>

4 files changed, 28 insertions, 0 deletions

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 5c310e803dd7..ae437791b5f8 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -925,6 +925,12 @@ int armpmu_register(struct arm_pmu *pmu)
 	if (ret)
 		return ret;
 
+	/*
+	 * By this stage we know our supported CPUs on either DT/ACPI platforms,
+	 * detect the SMT implementation.
+	 */
+	pmu->has_smt = topology_core_has_smt(cpumask_first(&pmu->supported_cpus));
+
 	if (!pmu->set_event_filter)
 		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
 
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 69c5cc8f5606..d1d6000517b2 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -981,6 +981,7 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
 static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc,
 				     struct perf_event *event)
 {
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
 
@@ -1001,6 +1002,15 @@ static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc,
 	if (has_branch_stack(event))
 		return false;
 
+	/*
+	 * The PMCCNTR_EL0 increments from the processor clock rather than
+	 * the PE clock (ARM DDI0487 L.b D13.1.3) which means it'll continue
+	 * counting on a WFI PE if one of its SMT sibling is not idle on a
+	 * multi-threaded implementation. So don't use it on SMT cores.
+	 */
+	if (cpu_pmu->has_smt)
+		return false;
+
 	return true;
 }
 
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index d72d6e5aa200..daa1af2e8204 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -89,6 +89,17 @@ void remove_cpu_topology(unsigned int cpuid);
 void reset_cpu_topology(void);
 int parse_acpi_topology(void);
 void freq_inv_set_max_ratio(int cpu, u64 max_rate);
+
+/*
+ * Architectures like ARM64 don't have reliable architectural way to get SMT
+ * information and depend on the firmware (ACPI/OF) report. Non-SMT core won't
+ * initialize thread_id so we can use this to detect the SMT implementation.
+ */
+static inline bool topology_core_has_smt(int cpu)
+{
+	return cpu_topology[cpu].thread_id != -1;
+}
+
 #endif
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 93c9a26492fc..2d39322c40c4 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -119,6 +119,7 @@ struct arm_pmu {
 
 	/* PMUv3 only */
 	int		pmuver;
+	bool		has_smt;
 	u64		reg_pmmir;
 	u64		reg_brbidr;
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40