NVIDIA: VR: SAUCE: perf/arm_pmu: Skip PMCCNTR_EL0 on NVIDIA Olympus

The PMCCNTR_EL0 in NVIDIA Olympus CPU may increment while
in WFI/WFE, which does not align with counting CPU_CYCLES
on a programmable counter. Add a MIDR range entry and
refuse PMCCNTR_EL0 for cycle events on affected parts so
perf does not mix the two behaviors.

Signed-off-by: Besar Wicaksono <bwicaksono@nvidia.com>
(backported from https://lore.kernel.org/all/20260421203856.3539186-1-bwicaksono@nvidia.com/)
Signed-off-by: Matthew R. Ochs <mochs@nvidia.com>

Author: bwicaksononv

drivers/perf/arm_pmuv3.c

@@ -8,6 +8,7 @@
  * This code is based heavily on the ARMv7 perf event code.
  */
 
+#include <asm/cputype.h>
 #include <asm/irq_regs.h>
 #include <asm/perf_event.h>
 #include <asm/virt.h>
@@ -978,6 +979,41 @@ static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
 	return -EAGAIN;
 }
 
+#ifdef CONFIG_ARM64
+/*
+ * List of CPUs that should avoid using PMCCNTR_EL0.
+ */
+static struct midr_range armv8pmu_avoid_pmccntr_cpus[] = {
+	/*
+	 * The PMCCNTR_EL0 in Olympus CPU may still increment while in WFI/WFE state.
+	 * This is an implementation specific behavior and not an erratum.
+	 *
+	 * From ARM DDI0487 D14.4:
+	 *   It is IMPLEMENTATION SPECIFIC whether CPU_CYCLES and PMCCNTR count
+	 *   when the PE is in WFI or WFE state, even if the clocks are not stopped.
+	 *
+	 * From ARM DDI0487 D24.5.2:
+	 *   All counters are subject to any changes in clock frequency, including
+	 *   clock stopping caused by the WFI and WFE instructions.
+	 *   This means that it is CONSTRAINED UNPREDICTABLE whether or not
+	 *   PMCCNTR_EL0 continues to increment when clocks are stopped by WFI and
+	 *   WFE instructions.
+	 */
+	MIDR_ALL_VERSIONS(MIDR_NVIDIA_OLYMPUS),
+	{}
+};
+
+static bool armv8pmu_is_in_avoid_pmccntr_cpus(void)
+{
+	return is_midr_in_range_list(armv8pmu_avoid_pmccntr_cpus);
+}
+#else
+static bool armv8pmu_is_in_avoid_pmccntr_cpus(void)
+{
+	return false;
+}
+#endif
+
 static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc,
 				     struct perf_event *event)
 {
@@ -1011,6 +1047,14 @@ static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc,
 	if (cpu_pmu->has_smt)
 		return false;
 
+	/*
+	 * On some CPUs, PMCCNTR_EL0 does not match the behavior of CPU_CYCLES
+	 * programmable counter, so avoid routing cycles through PMCCNTR_EL0 to
+	 * prevent inconsistency in the results.
+	 */
+	if (armv8pmu_is_in_avoid_pmccntr_cpus())
+		return false;
+
 	return true;
 }