KVM: selftests: Test PMC virtualization with forced emulation

Extend the PMC counters test to use forced emulation to verify that KVM
emulates counter events for instructions retired and branches retired.
Force emulation for only a subset of the measured code to test that KVM
does the right thing when mixing perf events with emulated events.

Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://lore.kernel.org/r/20240109230250.424295-27-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

tools/testing/selftests/kvm/x86_64/pmu_counters_test.c

@@ -21,6 +21,7 @@
 
 static uint8_t kvm_pmu_version;
 static bool kvm_has_perf_caps;
+static bool is_forced_emulation_enabled;
 
 static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 						  void *guest_code,
@@ -34,6 +35,7 @@ static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 	vcpu_init_descriptor_tables(*vcpu);
 
 	sync_global_to_guest(vm, kvm_pmu_version);
+	sync_global_to_guest(vm, is_forced_emulation_enabled);
 
 	/*
 	 * Set PERF_CAPABILITIES before PMU version as KVM disallows enabling
@@ -138,37 +140,50 @@ static void guest_assert_event_count(uint8_t idx,
  * If CLFUSH{,OPT} is supported, flush the cacheline containing (at least) the
  * start of the loop to force LLC references and misses, i.e. to allow testing
  * that those events actually count.
+ *
+ * If forced emulation is enabled (and specified), force emulation on a subset
+ * of the measured code to verify that KVM correctly emulates instructions and
+ * branches retired events in conjunction with hardware also counting said
+ * events.
  */
-#define GUEST_MEASURE_EVENT(_msr, _value, clflush)				\
+#define GUEST_MEASURE_EVENT(_msr, _value, clflush, FEP)				\
 do {										\
 	__asm__ __volatile__("wrmsr\n\t"					\
 			     clflush "\n\t"					\
 			     "mfence\n\t"					\
 			     "1: mov $" __stringify(NUM_BRANCHES) ", %%ecx\n\t"	\
-			     "loop .\n\t"					\
-			     "mov %%edi, %%ecx\n\t"				\
-			     "xor %%eax, %%eax\n\t"				\
-			     "xor %%edx, %%edx\n\t"				\
+			     FEP "loop .\n\t"					\
+			     FEP "mov %%edi, %%ecx\n\t"				\
+			     FEP "xor %%eax, %%eax\n\t"				\
+			     FEP "xor %%edx, %%edx\n\t"				\
 			     "wrmsr\n\t"					\
 			     :: "a"((uint32_t)_value), "d"(_value >> 32),	\
 				"c"(_msr), "D"(_msr)				\
 	);									\
 } while (0)
 
+#define GUEST_TEST_EVENT(_idx, _event, _pmc, _pmc_msr, _ctrl_msr, _value, FEP)	\
+do {										\
+	wrmsr(pmc_msr, 0);							\
+										\
+	if (this_cpu_has(X86_FEATURE_CLFLUSHOPT))				\
+		GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt 1f", FEP);	\
+	else if (this_cpu_has(X86_FEATURE_CLFLUSH))				\
+		GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush 1f", FEP);	\
+	else									\
+		GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP);		\
+										\
+	guest_assert_event_count(_idx, _event, _pmc, _pmc_msr);			\
+} while (0)
+
 static void __guest_test_arch_event(uint8_t idx, struct kvm_x86_pmu_feature event,
 				    uint32_t pmc, uint32_t pmc_msr,
 				    uint32_t ctrl_msr, uint64_t ctrl_msr_value)
 {
-	wrmsr(pmc_msr, 0);
-
-	if (this_cpu_has(X86_FEATURE_CLFLUSHOPT))
-		GUEST_MEASURE_EVENT(ctrl_msr, ctrl_msr_value, "clflushopt 1f");
-	else if (this_cpu_has(X86_FEATURE_CLFLUSH))
-		GUEST_MEASURE_EVENT(ctrl_msr, ctrl_msr_value, "clflush 1f");
-	else
-		GUEST_MEASURE_EVENT(ctrl_msr, ctrl_msr_value, "nop");
+	GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, "");
 
-	guest_assert_event_count(idx, event, pmc, pmc_msr);
+	if (is_forced_emulation_enabled)
+		GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP);
 }
 
 #define X86_PMU_FEATURE_NULL						\
@@ -553,6 +568,7 @@ int main(int argc, char *argv[])
 
 	kvm_pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION);
 	kvm_has_perf_caps = kvm_cpu_has(X86_FEATURE_PDCM);
+	is_forced_emulation_enabled = kvm_is_forced_emulation_enabled();
 
 	test_intel_counters();