Merge tag 'kvm-x86-selftests-6.18' of https://github.com/kvm-x86/linux into HEAD

KVM selftests changes for 6.18

 - Add #DE coverage in the fastops test (the only exception that's guest-
   triggerable in fastop-emulated instructions).

 - Fix PMU selftests errors encountered on Granite Rapids (GNR), Sierra
   Forest (SRF) and Clearwater Forest (CWF).

 - Minor cleanups and improvements

Author: bonzini

tools/testing/selftests/kvm/include/kvm_util.h

@@ -263,13 +263,18 @@ int __open_path_or_exit(const char *path, int flags, const char *enoent_help);
 int open_path_or_exit(const char *path, int flags);
 int open_kvm_dev_path_or_exit(void);
 
-bool get_kvm_param_bool(const char *param);
-bool get_kvm_intel_param_bool(const char *param);
-bool get_kvm_amd_param_bool(const char *param);
+int kvm_get_module_param_integer(const char *module_name, const char *param);
+bool kvm_get_module_param_bool(const char *module_name, const char *param);
 
-int get_kvm_param_integer(const char *param);
-int get_kvm_intel_param_integer(const char *param);
-int get_kvm_amd_param_integer(const char *param);
+static inline bool get_kvm_param_bool(const char *param)
+{
+	return kvm_get_module_param_bool("kvm", param);
+}
+
+static inline int get_kvm_param_integer(const char *param)
+{
+	return kvm_get_module_param_integer("kvm", param);
+}
 
 unsigned int kvm_check_cap(long cap);
 

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

@@ -5,8 +5,11 @@
 #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
 
 /*
@@ -61,6 +64,11 @@
 #define	INTEL_ARCH_BRANCHES_RETIRED		RAW_EVENT(0xc4, 0x00)
 #define	INTEL_ARCH_BRANCHES_MISPREDICTED	RAW_EVENT(0xc5, 0x00)
 #define	INTEL_ARCH_TOPDOWN_SLOTS		RAW_EVENT(0xa4, 0x01)
+#define	INTEL_ARCH_TOPDOWN_BE_BOUND		RAW_EVENT(0xa4, 0x02)
+#define	INTEL_ARCH_TOPDOWN_BAD_SPEC		RAW_EVENT(0x73, 0x00)
+#define	INTEL_ARCH_TOPDOWN_FE_BOUND		RAW_EVENT(0x9c, 0x01)
+#define	INTEL_ARCH_TOPDOWN_RETIRING		RAW_EVENT(0xc2, 0x02)
+#define	INTEL_ARCH_LBR_INSERTS			RAW_EVENT(0xe4, 0x01)
 
 #define	AMD_ZEN_CORE_CYCLES			RAW_EVENT(0x76, 0x00)
 #define	AMD_ZEN_INSTRUCTIONS_RETIRED		RAW_EVENT(0xc0, 0x00)
@@ -80,6 +88,11 @@ enum intel_pmu_architectural_events {
 	INTEL_ARCH_BRANCHES_RETIRED_INDEX,
 	INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX,
 	INTEL_ARCH_TOPDOWN_SLOTS_INDEX,
+	INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX,
+	INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX,
+	INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX,
+	INTEL_ARCH_TOPDOWN_RETIRING_INDEX,
+	INTEL_ARCH_LBR_INSERTS_INDEX,
 	NR_INTEL_ARCH_EVENTS,
 };
 
@@ -94,4 +107,17 @@ enum amd_pmu_zen_events {
 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/include/x86/processor.h

@@ -34,6 +34,8 @@ extern uint64_t guest_tsc_khz;
 
 #define NMI_VECTOR		0x02
 
+const char *ex_str(int vector);
+
 #define X86_EFLAGS_FIXED	 (1u << 1)
 
 #define X86_CR4_VME		(1ul << 0)
@@ -265,7 +267,7 @@ struct kvm_x86_cpu_property {
 #define X86_PROPERTY_PMU_NR_GP_COUNTERS		KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15)
 #define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH	KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23)
 #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH	KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31)
-#define X86_PROPERTY_PMU_EVENTS_MASK		KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7)
+#define X86_PROPERTY_PMU_EVENTS_MASK		KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 12)
 #define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK	KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31)
 #define X86_PROPERTY_PMU_NR_FIXED_COUNTERS	KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4)
 #define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH	KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12)
@@ -332,6 +334,11 @@ struct kvm_x86_pmu_feature {
 #define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED		KVM_X86_PMU_FEATURE(EBX, 5)
 #define X86_PMU_FEATURE_BRANCHES_MISPREDICTED		KVM_X86_PMU_FEATURE(EBX, 6)
 #define X86_PMU_FEATURE_TOPDOWN_SLOTS			KVM_X86_PMU_FEATURE(EBX, 7)
+#define X86_PMU_FEATURE_TOPDOWN_BE_BOUND		KVM_X86_PMU_FEATURE(EBX, 8)
+#define X86_PMU_FEATURE_TOPDOWN_BAD_SPEC		KVM_X86_PMU_FEATURE(EBX, 9)
+#define X86_PMU_FEATURE_TOPDOWN_FE_BOUND		KVM_X86_PMU_FEATURE(EBX, 10)
+#define X86_PMU_FEATURE_TOPDOWN_RETIRING		KVM_X86_PMU_FEATURE(EBX, 11)
+#define X86_PMU_FEATURE_LBR_INSERTS			KVM_X86_PMU_FEATURE(EBX, 12)
 
 #define X86_PMU_FEATURE_INSNS_RETIRED_FIXED		KVM_X86_PMU_FEATURE(ECX, 0)
 #define X86_PMU_FEATURE_CPU_CYCLES_FIXED		KVM_X86_PMU_FEATURE(ECX, 1)
@@ -1179,6 +1186,12 @@ struct idt_entry {
 void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 			void (*handler)(struct ex_regs *));
 
+/*
+ * Exception fixup morphs #DE to an arbitrary magic vector so that '0' can be
+ * used to signal "no expcetion".
+ */
+#define KVM_MAGIC_DE_VECTOR 0xff
+
 /* If a toddler were to say "abracadabra". */
 #define KVM_EXCEPTION_MAGIC 0xabacadabaULL
 
@@ -1314,6 +1327,26 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value)
 
 bool kvm_is_tdp_enabled(void);
 
+static inline bool get_kvm_intel_param_bool(const char *param)
+{
+	return kvm_get_module_param_bool("kvm_intel", param);
+}
+
+static inline bool get_kvm_amd_param_bool(const char *param)
+{
+	return kvm_get_module_param_bool("kvm_amd", param);
+}
+
+static inline int get_kvm_intel_param_integer(const char *param)
+{
+	return kvm_get_module_param_integer("kvm_intel", param);
+}
+
+static inline int get_kvm_amd_param_integer(const char *param)
+{
+	return kvm_get_module_param_integer("kvm_amd", param);
+}
+
 static inline bool kvm_is_pmu_enabled(void)
 {
 	return get_kvm_param_bool("enable_pmu");

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -24,7 +24,7 @@ uint32_t guest_random_seed;
 struct guest_random_state guest_rng;
 static uint32_t last_guest_seed;
 
-static int vcpu_mmap_sz(void);
+static size_t vcpu_mmap_sz(void);
 
 int __open_path_or_exit(const char *path, int flags, const char *enoent_help)
 {
@@ -95,7 +95,7 @@ static ssize_t get_module_param(const char *module_name, const char *param,
 	return bytes_read;
 }
 
-static int get_module_param_integer(const char *module_name, const char *param)
+int kvm_get_module_param_integer(const char *module_name, const char *param)
 {
 	/*
 	 * 16 bytes to hold a 64-bit value (1 byte per char), 1 byte for the
@@ -119,7 +119,7 @@ static int get_module_param_integer(const char *module_name, const char *param)
 	return atoi_paranoid(value);
 }
 
-static bool get_module_param_bool(const char *module_name, const char *param)
+bool kvm_get_module_param_bool(const char *module_name, const char *param)
 {
 	char value;
 	ssize_t r;
@@ -135,36 +135,6 @@ static bool get_module_param_bool(const char *module_name, const char *param)
 	TEST_FAIL("Unrecognized value '%c' for boolean module param", value);
 }
 
-bool get_kvm_param_bool(const char *param)
-{
-	return get_module_param_bool("kvm", param);
-}
-
-bool get_kvm_intel_param_bool(const char *param)
-{
-	return get_module_param_bool("kvm_intel", param);
-}
-
-bool get_kvm_amd_param_bool(const char *param)
-{
-	return get_module_param_bool("kvm_amd", param);
-}
-
-int get_kvm_param_integer(const char *param)
-{
-	return get_module_param_integer("kvm", param);
-}
-
-int get_kvm_intel_param_integer(const char *param)
-{
-	return get_module_param_integer("kvm_intel", param);
-}
-
-int get_kvm_amd_param_integer(const char *param)
-{
-	return get_module_param_integer("kvm_amd", param);
-}
-
 /*
  * Capability
  *
@@ -1324,14 +1294,14 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
 }
 
 /* Returns the size of a vCPU's kvm_run structure. */
-static int vcpu_mmap_sz(void)
+static size_t vcpu_mmap_sz(void)
 {
 	int dev_fd, ret;
 
 	dev_fd = open_kvm_dev_path_or_exit();
 
 	ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
-	TEST_ASSERT(ret >= sizeof(struct kvm_run),
+	TEST_ASSERT(ret >= 0 && ret >= sizeof(struct kvm_run),
 		    KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, ret));
 
 	close(dev_fd);
@@ -1372,7 +1342,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm);
 
 	TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size "
-		"smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
+		"smaller than expected, vcpu_mmap_sz: %zi expected_min: %zi",
 		vcpu_mmap_sz(), sizeof(*vcpu->run));
 	vcpu->run = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(),
 		PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0);

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

@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 
 #include "kvm_util.h"
+#include "processor.h"
 #include "pmu.h"
 
 const uint64_t intel_pmu_arch_events[] = {
@@ -19,6 +20,11 @@ const uint64_t intel_pmu_arch_events[] = {
 	INTEL_ARCH_BRANCHES_RETIRED,
 	INTEL_ARCH_BRANCHES_MISPREDICTED,
 	INTEL_ARCH_TOPDOWN_SLOTS,
+	INTEL_ARCH_TOPDOWN_BE_BOUND,
+	INTEL_ARCH_TOPDOWN_BAD_SPEC,
+	INTEL_ARCH_TOPDOWN_FE_BOUND,
+	INTEL_ARCH_TOPDOWN_RETIRING,
+	INTEL_ARCH_LBR_INSERTS,
 };
 kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS);
 
@@ -29,3 +35,46 @@ const uint64_t amd_pmu_zen_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

@@ -6,6 +6,7 @@
 #include "linux/bitmap.h"
 #include "test_util.h"
 #include "kvm_util.h"
+#include "pmu.h"
 #include "processor.h"
 #include "sev.h"
 
@@ -23,6 +24,39 @@ bool host_cpu_is_intel;
 bool is_forced_emulation_enabled;
 uint64_t guest_tsc_khz;
 
+const char *ex_str(int vector)
+{
+	switch (vector) {
+#define VEC_STR(v) case v##_VECTOR: return "#" #v
+	case DE_VECTOR: return "no exception";
+	case KVM_MAGIC_DE_VECTOR: return "#DE";
+	VEC_STR(DB);
+	VEC_STR(NMI);
+	VEC_STR(BP);
+	VEC_STR(OF);
+	VEC_STR(BR);
+	VEC_STR(UD);
+	VEC_STR(NM);
+	VEC_STR(DF);
+	VEC_STR(TS);
+	VEC_STR(NP);
+	VEC_STR(SS);
+	VEC_STR(GP);
+	VEC_STR(PF);
+	VEC_STR(MF);
+	VEC_STR(AC);
+	VEC_STR(MC);
+	VEC_STR(XM);
+	VEC_STR(VE);
+	VEC_STR(CP);
+	VEC_STR(HV);
+	VEC_STR(VC);
+	VEC_STR(SX);
+	default: return "#??";
+#undef VEC_STR
+	}
+}
+
 static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent)
 {
 	fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
@@ -557,7 +591,7 @@ static bool kvm_fixup_exception(struct ex_regs *regs)
 		return false;
 
 	if (regs->vector == DE_VECTOR)
-		return false;
+		regs->vector = KVM_MAGIC_DE_VECTOR;
 
 	regs->rip = regs->r11;
 	regs->r9 = regs->vector;
@@ -638,6 +672,7 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus)
 	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 };
@@ -1269,6 +1304,8 @@ void kvm_selftest_arch_init(void)
 	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/s390/cpumodel_subfuncs_test.c

@@ -291,7 +291,7 @@ int main(int argc, char *argv[])
 			ksft_test_result_pass("%s\n", testlist[idx].subfunc_name);
 			free(array);
 		} else {
-			ksft_test_result_skip("%s feature is not avaialable\n",
+			ksft_test_result_skip("%s feature is not available\n",
 					      testlist[idx].subfunc_name);
 		}
 	}