KVM: arm64: Iterate arm_pmus list to probe for default PMU

To date KVM has relied on using a perf event to probe the core PMU at
the time of vPMU initialization. Behind the scenes perf_event_init()
would iteratively walk the PMUs of the system and return the PMU that
could handle the event. However, an upcoming change in perf core will
drop the iterative walk, thereby breaking the fragile dance we do on the
KVM side.

Avoid the problem altogether by iterating over the list of supported
PMUs maintained in KVM, returning the core PMU that matches the CPU
we were called on.

Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230525212723.3361524-2-oliver.upton@linux.dev

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 45727d50d18dd90c842285a2d621628c77c9b0e6..5deddc49e7454f9c3ca5d3a95e2681d547977fb3 100644 (file)
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -694,45 +694,23 @@ out_unlock:
 
 static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 {
-       struct perf_event_attr attr = { };
-       struct perf_event *event;
-       struct arm_pmu *pmu = NULL;
-
-       /*
-        * Create a dummy event that only counts user cycles. As we'll never
-        * leave this function with the event being live, it will never
-        * count anything. But it allows us to probe some of the PMU
-        * details. Yes, this is terrible.
-        */
-       attr.type = PERF_TYPE_RAW;
-       attr.size = sizeof(attr);
-       attr.pinned = 1;
-       attr.disabled = 0;
-       attr.exclude_user = 0;
-       attr.exclude_kernel = 1;
-       attr.exclude_hv = 1;
-       attr.exclude_host = 1;
-       attr.config = ARMV8_PMUV3_PERFCTR_CPU_CYCLES;
-       attr.sample_period = GENMASK(63, 0);
+       struct arm_pmu *tmp, *pmu = NULL;
+       struct arm_pmu_entry *entry;
+       int cpu;
 
-       event = perf_event_create_kernel_counter(&attr, -1, current,
-                                                kvm_pmu_perf_overflow, &attr);
+       mutex_lock(&arm_pmus_lock);
 
-       if (IS_ERR(event)) {
-               pr_err_once("kvm: pmu event creation failed %ld\n",
-                           PTR_ERR(event));
-               return NULL;
-       }
+       cpu = smp_processor_id();
+       list_for_each_entry(entry, &arm_pmus, entry) {
+               tmp = entry->arm_pmu;
 
-       if (event->pmu) {
-               pmu = to_arm_pmu(event->pmu);
-               if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI ||
-                   pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
-                       pmu = NULL;
+               if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) {
+                       pmu = tmp;
+                       break;
+               }
        }
 
-       perf_event_disable(event);
-       perf_event_release_kernel(event);
+       mutex_unlock(&arm_pmus_lock);
 
        return pmu;
 }