Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 regression fix from Will Deacon:
 "Apologies for the _extremely_ late pull request here, but we had a
  'perf' (i.e. CPU PMU) regression on the Apple M1 reported on Wednesday
  [1] which was introduced by bd2756811766 ("perf: Rewrite core context
  handling") during the merge window.

  Mark and I looked into this and noticed an additional problem caused
  by the same patch, where the 'CHAIN' event (used to combine two
  adjacent 32-bit counters into a single 64-bit counter) was not being
  filtered correctly. Mark posted a series on Thursday [2] which
  addresses both of these regressions and I queued it the same day.

  The changes are small, self-contained and have been confirmed to fix
  the original regression.

  Summary:

   - Fix 'perf' regression for non-standard CPU PMU hardware (i.e. Apple
     M1)"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: perf: reject CHAIN events at creation time
  arm_pmu: fix event CPU filtering

1 files changed, 1 insertions, 7 deletions

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 9b593f985805..40f70f83daba 100644
--- a/drivers/perf/arm_pmu.c
+++ b/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,