arm_pmu: fix event CPU filtering

Janne reports that perf has been broken on Apple M1 as of commit:

  bd27568 ("perf: Rewrite core context handling")

That commit replaced the pmu::filter_match() callback with
pmu::filter(), whose return value has the opposite polarity, with true
implying events should be ignored rather than scheduled. While an
attempt was made to update the logic in armv8pmu_filter() and
armpmu_filter() accordingly, the return value remains inverted in a
couple of cases:

* If the arm_pmu does not have an arm_pmu::filter() callback,
  armpmu_filter() will always return whether the CPU is supported rather
  than whether the CPU is not supported.

  As a result, the perf core will not schedule events on supported CPUs,
  resulting in a loss of events. Additionally, the perf core will
  attempt to schedule events on unsupported CPUs, but this will be
  rejected by armpmu_add(), which may result in a loss of events from
  other PMUs on those unsupported CPUs.

* If the arm_pmu does have an arm_pmu::filter() callback, and
  armpmu_filter() is called on a CPU which is not supported by the
  arm_pmu, armpmu_filter() will return false rather than true.

  As a result, the perf core will attempt to schedule events on
  unsupported CPUs, but this will be rejected by armpmu_add(), which may
  result in a loss of events from other PMUs on those unsupported CPUs.

This means a loss of events can be seen with any arm_pmu driver, but
with the ARMv8 PMUv3 driver (which is the only arm_pmu driver with an
arm_pmu::filter() callback) the event loss will be more limited and may
go unnoticed, which is how this issue evaded testing so far.

Fix the CPU filtering by performing this consistently in
armpmu_filter(), and remove the redundant arm_pmu::filter() callback and
armv8pmu_filter() implementation.

Commit bd27568 also silently removed the CHAIN event filtering from
armv8pmu_filter(), which will be addressed by a separate patch without
using the filter callback.

Fixes: bd27568 ("perf: Rewrite core context handling")
Reported-by: Janne Grunau <[email protected]>
Link: https://lore.kernel.org/asahi/[email protected]/
Signed-off-by: Mark Rutland <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Asahi Lina <[email protected]>
Cc: Eric Curtin <[email protected]>
Tested-by: Janne Grunau <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: mrutland-arm

arch/arm64/kernel/perf_event.c

@@ -1023,12 +1023,6 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	return 0;
 }
 
-static bool armv8pmu_filter(struct pmu *pmu, int cpu)
-{
-	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	return !cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus);
-}
-
 static void armv8pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
@@ -1258,7 +1252,6 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->stop			= armv8pmu_stop;
 	cpu_pmu->reset			= armv8pmu_reset;
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
-	cpu_pmu->filter			= armv8pmu_filter;
 
 	cpu_pmu->pmu.event_idx		= armv8pmu_user_event_idx;
 

drivers/perf/arm_pmu.c

@@ -550,13 +550,7 @@ static void armpmu_disable(struct pmu *pmu)
 static bool armpmu_filter(struct pmu *pmu, int cpu)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	bool ret;
-
-	ret = cpumask_test_cpu(cpu, &armpmu->supported_cpus);
-	if (ret && armpmu->filter)
-		return armpmu->filter(pmu, cpu);
-
-	return ret;
+	return !cpumask_test_cpu(cpu, &armpmu->supported_cpus);
 }
 
 static ssize_t cpus_show(struct device *dev,

include/linux/perf/arm_pmu.h

@@ -100,7 +100,6 @@ struct arm_pmu {
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
-	bool		(*filter)(struct pmu *pmu, int cpu);
 	int		num_events;
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40