For a VCPU thread pinned to a single LPU, verify that interleaved host
and guest reads of IA32_[AM]PERF return strictly increasing values when
APERFMPERF exiting is disabled.
Signed-off-by: Jim Mattson <jmattson@xxxxxxxxxx>
---
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../selftests/kvm/x86/aperfmperf_test.c | 162 ++++++++++++++++++
2 files changed, 163 insertions(+)
create mode 100644 tools/testing/selftests/kvm/x86/aperfmperf_test.c
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 4277b983cace..bfee69b33310 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -116,6 +116,7 @@ TEST_GEN_PROGS_x86 += x86/amx_test
TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test
TEST_GEN_PROGS_x86 += x86/triple_fault_event_test
TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test
+TEST_GEN_PROGS_x86 += x86/aperfmperf_test
TEST_GEN_PROGS_x86 += access_tracking_perf_test
TEST_GEN_PROGS_x86 += coalesced_io_test
TEST_GEN_PROGS_x86 += demand_paging_test
diff --git a/tools/testing/selftests/kvm/x86/aperfmperf_test.c b/tools/testing/selftests/kvm/x86/aperfmperf_test.c
new file mode 100644
index 000000000000..7473afb7f6fa
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/aperfmperf_test.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test for KVM_X86_DISABLE_EXITS_APERFMPERF
+ *
+ * Copyright (C) 2025, Google LLC.
+ *
+ * Test the ability to disable VM-exits for rdmsr of IA32_APERF and
+ * IA32_MPERF. When these VM-exits are disabled, reads of these MSRs
+ * return the host's values.
+ *
+ * Note: Requires read access to /dev/cpu/<lpu>/msr to read host MSRs.
+ */
+
+#include <fcntl.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <asm/msr-index.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define NUM_ITERATIONS 100
+
+static void pin_thread(int cpu)
+{
+ cpu_set_t cpuset;
+ int rc;
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu, &cpuset);
+
+ rc = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+ TEST_ASSERT(rc == 0, "%s: Can't set thread affinity", __func__);
+}
+
+static int open_dev_msr(int cpu)
+{
+ char path[PATH_MAX];
+ int msr_fd;
+
+ snprintf(path, sizeof(path), "/dev/cpu/%d/msr", cpu);
+ msr_fd = open(path, O_RDONLY);
+ __TEST_REQUIRE(msr_fd >= 0, "Can't open %s for read", path);
+
+ return msr_fd;
+}
+
+static uint64_t read_dev_msr(int msr_fd, uint32_t msr)
+{
+ uint64_t data;
+ ssize_t rc;
+
+ rc = pread(msr_fd, &data, sizeof(data), msr);
+ TEST_ASSERT(rc == sizeof(data), "Read of MSR 0x%x failed", msr);
+
+ return data;
+}
+
+static void guest_code(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_ITERATIONS; i++) {
+ uint64_t aperf = rdmsr(MSR_IA32_APERF);
+ uint64_t mperf = rdmsr(MSR_IA32_MPERF);
+
+ GUEST_SYNC2(aperf, mperf);
+ }
+
+ GUEST_DONE();
+}
+
+static bool kvm_can_disable_aperfmperf_exits(struct kvm_vm *vm)
+{
+ int flags = vm_check_cap(vm, KVM_CAP_X86_DISABLE_EXITS);
+
+ return flags & KVM_X86_DISABLE_EXITS_APERFMPERF;
+}
+
+int main(int argc, char *argv[])
+{
+ uint64_t host_aperf_before, host_mperf_before;
+ int cpu = sched_getcpu();
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ int msr_fd;
+ int i;
+
+ pin_thread(cpu);
+
+ msr_fd = open_dev_msr(cpu);
+
+ /*
+ * This test requires a non-standard VM initialization, because
+ * KVM_ENABLE_CAP cannot be used on a VM file descriptor after
+ * a VCPU has been created.
+ */
+ vm = vm_create(1);
+
+ TEST_REQUIRE(kvm_can_disable_aperfmperf_exits(vm));
+
+ vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS,
+ KVM_X86_DISABLE_EXITS_APERFMPERF);
+
+ vcpu = vm_vcpu_add(vm, 0, guest_code);
+
+ host_aperf_before = read_dev_msr(msr_fd, MSR_IA32_APERF);
+ host_mperf_before = read_dev_msr(msr_fd, MSR_IA32_MPERF);
+
+ for (i = 0; i < NUM_ITERATIONS; i++) {
+ uint64_t host_aperf_after, host_mperf_after;
+ uint64_t guest_aperf, guest_mperf;
+ struct ucall uc;
+
+ vcpu_run(vcpu);
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ case UCALL_SYNC:
+ guest_aperf = uc.args[0];
+ guest_mperf = uc.args[1];
+
+ host_aperf_after = read_dev_msr(msr_fd, MSR_IA32_APERF);
+ host_mperf_after = read_dev_msr(msr_fd, MSR_IA32_MPERF);
+
+ TEST_ASSERT(host_aperf_before < guest_aperf,
+ "APERF: host_before (%lu) >= guest (%lu)",
+ host_aperf_before, guest_aperf);
+ TEST_ASSERT(guest_aperf < host_aperf_after,
+ "APERF: guest (%lu) >= host_after (%lu)",
+ guest_aperf, host_aperf_after);
+ TEST_ASSERT(host_mperf_before < guest_mperf,
+ "MPERF: host_before (%lu) >= guest (%lu)",
+ host_mperf_before, guest_mperf);
+ TEST_ASSERT(guest_mperf < host_mperf_after,
+ "MPERF: guest (%lu) >= host_after (%lu)",
+ guest_mperf, host_mperf_after);
+
+ host_aperf_before = host_aperf_after;
+ host_mperf_before = host_mperf_after;
+
+ break;
+ }
+ }
+
+ TEST_ASSERT_EQ(i, NUM_ITERATIONS);
+
+ kvm_vm_free(vm);
+ close(msr_fd);
+
+ return 0;
+}
--
2.49.0.395.g12beb8f557-goog
