Merge tag 'perf-urgent-2024-09-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fix from Thomas Gleixner:
 "A single fix for x86 performance monitoring.

  Haswell PMUs suffer from several errata and require a limit the
  minimal period for counter events, otherwise they suffer from endless
  loops in the PMU interrupt"

* tag 'perf-urgent-2024-09-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Limit the period on Haswell

1 files changed, 21 insertions, 2 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 0c9c2706d4ec..9e519d8a810a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4589,6 +4589,25 @@ static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
 	return HYBRID_INTEL_CORE;
 }
 
+static inline bool erratum_hsw11(struct perf_event *event)
+{
+	return (event->hw.config & INTEL_ARCH_EVENT_MASK) ==
+		X86_CONFIG(.event=0xc0, .umask=0x01);
+}
+
+/*
+ * The HSW11 requires a period larger than 100 which is the same as the BDM11.
+ * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL.
+ *
+ * The message 'interrupt took too long' can be observed on any counter which
+ * was armed with a period < 32 and two events expired in the same NMI.
+ * A minimum period of 32 is enforced for the rest of the events.
+ */
+static void hsw_limit_period(struct perf_event *event, s64 *left)
+{
+	*left = max(*left, erratum_hsw11(event) ? 128 : 32);
+}
+
 /*
  * Broadwell:
  *
@@ -4606,8 +4625,7 @@ static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
  */
 static void bdw_limit_period(struct perf_event *event, s64 *left)
 {
-	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
-			X86_CONFIG(.event=0xc0, .umask=0x01)) {
+	if (erratum_hsw11(event)) {
 		if (*left < 128)
 			*left = 128;
 		*left &= ~0x3fULL;
@@ -6766,6 +6784,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.limit_period = hsw_limit_period;
 		x86_pmu.lbr_double_abort = true;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;