KVM: selftests: Handle Intel Atom errata that leads to PMU event overcount

Add a PMU errata framework and use it to relax precise event counts on
Atom platforms that overcount "Instruction Retired" and "Branch Instruction
Retired" events, as the overcount issues on VM-Exit/VM-Entry are impossible
to prevent from userspace, e.g. the test can't prevent host IRQs.

Setup errata during early initialization and automatically sync the mask
to VMs so that tests can check for errata without having to manually
manage host=>guest variables.

For Intel Atom CPUs, the PMU events "Instruction Retired" or
"Branch Instruction Retired" may be overcounted for some certain
instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD
and complex SGX/SMX/CSTATE instructions/flows.

The detailed information can be found in the errata (section SRF7):
https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/

For the Atom platforms before Sierra Forest (including Sierra Forest),
Both 2 events "Instruction Retired" and "Branch Instruction Retired" would
be overcounted on these certain instructions, but for Clearwater Forest
only "Instruction Retired" event is overcounted on these instructions.

Signed-off-by: dongsheng <[e-mail]>
Co-developed-by: Dapeng Mi <[e-mail]>
Signed-off-by: Dapeng Mi <[e-mail]>
Tested-by: Yi Lai <[e-mail]>
Co-developed-by: Sean Christopherson <[e-mail]>
Reviewed-by: Dapeng Mi <[e-mail]>
Tested-by: Dapeng Mi <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Sean Christopherson <[e-mail]>

tools/testing/selftests/kvm/include/x86/pmu.h

···
 #ifndef SELFTEST_KVM_PMU_H
 #define SELFTEST_KVM_PMU_H
 
+#include <stdbool.h>
 #include <stdint.h>
+
+#include <linux/bits.h>
 
 #define KVM_PMU_EVENT_FILTER_MAX_EVENTS			300
 
···
 
 extern const uint64_t intel_pmu_arch_events[];
 extern const uint64_t amd_pmu_zen_events[];
+
+enum pmu_errata {
+	INSTRUCTIONS_RETIRED_OVERCOUNT,
+	BRANCHES_RETIRED_OVERCOUNT,
+};
+extern uint64_t pmu_errata_mask;
+
+void kvm_init_pmu_errata(void);
+
+static inline bool this_pmu_has_errata(enum pmu_errata errata)
+{
+	return pmu_errata_mask & BIT_ULL(errata);
+}
 
 #endif /* SELFTEST_KVM_PMU_H */

tools/testing/selftests/kvm/lib/x86/pmu.c

···
 #include <linux/kernel.h>
 
 #include "kvm_util.h"
+#include "processor.h"
 #include "pmu.h"
 
 const uint64_t intel_pmu_arch_events[] = {
···
 	AMD_ZEN_BRANCHES_MISPREDICTED,
 };
 kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS);
+
+/*
+ * For Intel Atom CPUs, the PMU events "Instruction Retired" or
+ * "Branch Instruction Retired" may be overcounted for some certain
+ * instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD
+ * and complex SGX/SMX/CSTATE instructions/flows.
+ *
+ * The detailed information can be found in the errata (section SRF7):
+ * https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/
+ *
+ * For the Atom platforms before Sierra Forest (including Sierra Forest),
+ * Both 2 events "Instruction Retired" and "Branch Instruction Retired" would
+ * be overcounted on these certain instructions, but for Clearwater Forest
+ * only "Instruction Retired" event is overcounted on these instructions.
+ */
+static uint64_t get_pmu_errata(void)
+{
+	if (!this_cpu_is_intel())
+		return 0;
+
+	if (this_cpu_family() != 0x6)
+		return 0;
+
+	switch (this_cpu_model()) {
+	case 0xDD: /* Clearwater Forest */
+		return BIT_ULL(INSTRUCTIONS_RETIRED_OVERCOUNT);
+	case 0xAF: /* Sierra Forest */
+	case 0x4D: /* Avaton, Rangely */
+	case 0x5F: /* Denverton */
+	case 0x86: /* Jacobsville */
+		return BIT_ULL(INSTRUCTIONS_RETIRED_OVERCOUNT) |
+		       BIT_ULL(BRANCHES_RETIRED_OVERCOUNT);
+	default:
+		return 0;
+	}
+}
+
+uint64_t pmu_errata_mask;
+
+void kvm_init_pmu_errata(void)
+{
+	pmu_errata_mask = get_pmu_errata();
+}

tools/testing/selftests/kvm/lib/x86/processor.c

···
 #include "linux/bitmap.h"
 #include "test_util.h"
 #include "kvm_util.h"
+#include "pmu.h"
 #include "processor.h"
 #include "sev.h"
 
···
 	sync_global_to_guest(vm, host_cpu_is_intel);
 	sync_global_to_guest(vm, host_cpu_is_amd);
 	sync_global_to_guest(vm, is_forced_emulation_enabled);
+	sync_global_to_guest(vm, pmu_errata_mask);
 
 	if (is_sev_vm(vm)) {
 		struct kvm_sev_init init = { 0 };
···
 	host_cpu_is_intel = this_cpu_is_intel();
 	host_cpu_is_amd = this_cpu_is_amd();
 	is_forced_emulation_enabled = kvm_is_forced_emulation_enabled();
+
+	kvm_init_pmu_errata();
 }
 
 bool sys_clocksource_is_based_on_tsc(void)

tools/testing/selftests/kvm/x86/pmu_counters_test.c

···
 
 	switch (idx) {
 	case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX:
-		GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED);
+		/* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */
+		if (this_pmu_has_errata(INSTRUCTIONS_RETIRED_OVERCOUNT))
+			GUEST_ASSERT(count >= NUM_INSNS_RETIRED);
+		else
+			GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED);
 		break;
 	case INTEL_ARCH_BRANCHES_RETIRED_INDEX:
-		GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED);
+		/* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */
+		if (this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT))
+			GUEST_ASSERT(count >= NUM_BRANCH_INSNS_RETIRED);
+		else
+			GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED);
 		break;
 	case INTEL_ARCH_LLC_REFERENCES_INDEX:
 	case INTEL_ARCH_LLC_MISSES_INDEX:

tools/testing/selftests/kvm/x86/pmu_event_filter_test.c

···
 do {											\
 	uint64_t br = pmc_results.branches_retired;					\
 	uint64_t ir = pmc_results.instructions_retired;					\
+	bool br_matched = this_pmu_has_errata(BRANCHES_RETIRED_OVERCOUNT) ?		\
+			  br >= NUM_BRANCHES : br == NUM_BRANCHES;			\
 											\
-	if (br && br != NUM_BRANCHES)							\
+	if (br && !br_matched)								\
 		pr_info("%s: Branch instructions retired = %lu (expected %u)\n",	\
 			__func__, br, NUM_BRANCHES);					\
 	TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)",		\