Merge tag 'kvm-x86-selftests-6.13' of https://github.com/kvm-x86/linux into HEAD

KVM selftests changes for 6.13

 - Enable XFAM-based features by default for all selftests VMs, which will
   allow removing the "no AVX" restriction.

Author: bonzini

tools/testing/selftests/kvm/hardware_disable_test.c

@@ -20,7 +20,6 @@
 #define SLEEPING_THREAD_NUM (1 << 4)
 #define FORK_NUM (1ULL << 9)
 #define DELAY_US_MAX 2000
-#define GUEST_CODE_PIO_PORT 4
 
 sem_t *sem;
 

tools/testing/selftests/kvm/include/x86_64/processor.h

@@ -1049,6 +1049,11 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu)
 	vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid);
 }
 
+static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu)
+{
+	vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid);
+}
+
 void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu,
 			     struct kvm_x86_cpu_property property,
 			     uint32_t value);

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -506,6 +506,8 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 
 	sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
 	sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
+	if (kvm_cpu_has(X86_FEATURE_XSAVE))
+		sregs.cr4 |= X86_CR4_OSXSAVE;
 	sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 	kvm_seg_set_unusable(&sregs.ldt);
@@ -519,6 +521,20 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 	vcpu_sregs_set(vcpu, &sregs);
 }
 
+static void vcpu_init_xcrs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+{
+	struct kvm_xcrs xcrs = {
+		.nr_xcrs = 1,
+		.xcrs[0].xcr = 0,
+		.xcrs[0].value = kvm_cpu_supported_xcr0(),
+	};
+
+	if (!kvm_cpu_has(X86_FEATURE_XSAVE))
+		return;
+
+	vcpu_xcrs_set(vcpu, &xcrs);
+}
+
 static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
 			  int dpl, unsigned short selector)
 {
@@ -675,6 +691,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
 	vcpu_init_sregs(vm, vcpu);
+	vcpu_init_xcrs(vm, vcpu);
 
 	/* Setup guest general purpose registers */
 	vcpu_regs_get(vcpu, &regs);
@@ -686,6 +703,13 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	mp_state.mp_state = 0;
 	vcpu_mp_state_set(vcpu, &mp_state);
 
+	/*
+	 * Refresh CPUID after setting SREGS and XCR0, so that KVM's "runtime"
+	 * updates to guest CPUID, e.g. for OSXSAVE and XSAVE state size, are
+	 * reflected into selftests' vCPU CPUID cache, i.e. so that the cache
+	 * is consistent with vCPU state.
+	 */
+	vcpu_get_cpuid(vcpu);
 	return vcpu;
 }
 

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

@@ -86,6 +86,8 @@ static inline void __xsavec(struct xstate *xstate, uint64_t rfbm)
 
 static void check_xtile_info(void)
 {
+	GUEST_ASSERT((xgetbv(0) & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE);
+
 	GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0));
 	GUEST_ASSERT(this_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0) <= XSAVE_SIZE);
 
@@ -122,29 +124,12 @@ static void set_tilecfg(struct tile_config *cfg)
 	}
 }
 
-static void init_regs(void)
-{
-	uint64_t cr4, xcr0;
-
-	GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE));
-
-	/* turn on CR4.OSXSAVE */
-	cr4 = get_cr4();
-	cr4 |= X86_CR4_OSXSAVE;
-	set_cr4(cr4);
-	GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE));
-
-	xcr0 = xgetbv(0);
-	xcr0 |= XFEATURE_MASK_XTILE;
-	xsetbv(0x0, xcr0);
-	GUEST_ASSERT((xgetbv(0) & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE);
-}
-
 static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
 						    struct tile_data *tiledata,
 						    struct xstate *xstate)
 {
-	init_regs();
+	GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE) &&
+		     this_cpu_has(X86_FEATURE_OSXSAVE));
 	check_xtile_info();
 	GUEST_SYNC(1);
 

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

@@ -12,17 +12,16 @@
 #include "kvm_util.h"
 #include "processor.h"
 
-/* CPUIDs known to differ */
-struct {
-	u32 function;
-	u32 index;
-} mangled_cpuids[] = {
-	/*
-	 * These entries depend on the vCPU's XCR0 register and IA32_XSS MSR,
-	 * which are not controlled for by this test.
-	 */
-	{.function = 0xd, .index = 0},
-	{.function = 0xd, .index = 1},
+struct cpuid_mask {
+	union {
+		struct {
+			u32 eax;
+			u32 ebx;
+			u32 ecx;
+			u32 edx;
+		};
+		u32 regs[4];
+	};
 };
 
 static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid)
@@ -56,17 +55,29 @@ static void guest_main(struct kvm_cpuid2 *guest_cpuid)
 	GUEST_DONE();
 }
 
-static bool is_cpuid_mangled(const struct kvm_cpuid_entry2 *entrie)
+static struct cpuid_mask get_const_cpuid_mask(const struct kvm_cpuid_entry2 *entry)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mangled_cpuids); i++) {
-		if (mangled_cpuids[i].function == entrie->function &&
-		    mangled_cpuids[i].index == entrie->index)
-			return true;
+	struct cpuid_mask mask;
+
+	memset(&mask, 0xff, sizeof(mask));
+
+	switch (entry->function) {
+	case 0x1:
+		mask.regs[X86_FEATURE_OSXSAVE.reg] &= ~BIT(X86_FEATURE_OSXSAVE.bit);
+		break;
+	case 0x7:
+		mask.regs[X86_FEATURE_OSPKE.reg] &= ~BIT(X86_FEATURE_OSPKE.bit);
+		break;
+	case 0xd:
+		/*
+		 * CPUID.0xD.{0,1}.EBX enumerate XSAVE size based on the current
+		 * XCR0 and IA32_XSS MSR values.
+		 */
+		if (entry->index < 2)
+			mask.ebx = 0;
+		break;
 	}
-
-	return false;
+	return mask;
 }
 
 static void compare_cpuids(const struct kvm_cpuid2 *cpuid1,
@@ -79,6 +90,8 @@ static void compare_cpuids(const struct kvm_cpuid2 *cpuid1,
 		    "CPUID nent mismatch: %d vs. %d", cpuid1->nent, cpuid2->nent);
 
 	for (i = 0; i < cpuid1->nent; i++) {
+		struct cpuid_mask mask;
+
 		e1 = &cpuid1->entries[i];
 		e2 = &cpuid2->entries[i];
 
@@ -88,15 +101,19 @@ static void compare_cpuids(const struct kvm_cpuid2 *cpuid1,
 			    i, e1->function, e1->index, e1->flags,
 			    e2->function, e2->index, e2->flags);
 
-		if (is_cpuid_mangled(e1))
-			continue;
+		/* Mask off dynamic bits, e.g. OSXSAVE, when comparing entries. */
+		mask = get_const_cpuid_mask(e1);
 
-		TEST_ASSERT(e1->eax == e2->eax && e1->ebx == e2->ebx &&
-			    e1->ecx == e2->ecx && e1->edx == e2->edx,
+		TEST_ASSERT((e1->eax & mask.eax) == (e2->eax & mask.eax) &&
+			    (e1->ebx & mask.ebx) == (e2->ebx & mask.ebx) &&
+			    (e1->ecx & mask.ecx) == (e2->ecx & mask.ecx) &&
+			    (e1->edx & mask.edx) == (e2->edx & mask.edx),
 			    "CPUID 0x%x.%x differ: 0x%x:0x%x:0x%x:0x%x vs 0x%x:0x%x:0x%x:0x%x",
 			    e1->function, e1->index,
-			    e1->eax, e1->ebx, e1->ecx, e1->edx,
-			    e2->eax, e2->ebx, e2->ecx, e2->edx);
+			    e1->eax & mask.eax, e1->ebx & mask.ebx,
+			    e1->ecx & mask.ecx, e1->edx & mask.edx,
+			    e2->eax & mask.eax, e2->ebx & mask.ebx,
+			    e2->ecx & mask.ecx, e2->edx & mask.edx);
 	}
 }
 

tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c

@@ -19,30 +19,42 @@
 #include "kvm_util.h"
 #include "processor.h"
 
-static inline bool cr4_cpuid_is_sync(void)
-{
-	uint64_t cr4 = get_cr4();
-
-	return (this_cpu_has(X86_FEATURE_OSXSAVE) == !!(cr4 & X86_CR4_OSXSAVE));
-}
+#define MAGIC_HYPERCALL_PORT	0x80
 
 static void guest_code(void)
 {
-	uint64_t cr4;
+	u32 regs[4] = {
+		[KVM_CPUID_EAX] = X86_FEATURE_OSXSAVE.function,
+		[KVM_CPUID_ECX] = X86_FEATURE_OSXSAVE.index,
+	};
 
-	/* turn on CR4.OSXSAVE */
-	cr4 = get_cr4();
-	cr4 |= X86_CR4_OSXSAVE;
-	set_cr4(cr4);
+	/* CR4.OSXSAVE should be enabled by default (for selftests vCPUs). */
+	GUEST_ASSERT(get_cr4() & X86_CR4_OSXSAVE);
 
 	/* verify CR4.OSXSAVE == CPUID.OSXSAVE */
-	GUEST_ASSERT(cr4_cpuid_is_sync());
-
-	/* notify hypervisor to change CR4 */
-	GUEST_SYNC(0);
-
-	/* check again */
-	GUEST_ASSERT(cr4_cpuid_is_sync());
+	GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE));
+
+	/*
+	 * Notify hypervisor to clear CR4.0SXSAVE, do CPUID and save output,
+	 * and then restore CR4.  Do this all in  assembly to ensure no AVX
+	 * instructions are executed while OSXSAVE=0.
+	 */
+	asm volatile (
+		"out %%al, $" __stringify(MAGIC_HYPERCALL_PORT) "\n\t"
+		"cpuid\n\t"
+		"mov %%rdi, %%cr4\n\t"
+		: "+a" (regs[KVM_CPUID_EAX]),
+		  "=b" (regs[KVM_CPUID_EBX]),
+		  "+c" (regs[KVM_CPUID_ECX]),
+		  "=d" (regs[KVM_CPUID_EDX])
+		: "D" (get_cr4())
+	);
+
+	/* Verify KVM cleared OSXSAVE in CPUID when it was cleared in CR4. */
+	GUEST_ASSERT(!(regs[X86_FEATURE_OSXSAVE.reg] & BIT(X86_FEATURE_OSXSAVE.bit)));
+
+	/* Verify restoring CR4 also restored OSXSAVE in CPUID. */
+	GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE));
 
 	GUEST_DONE();
 }
@@ -62,13 +74,16 @@ int main(int argc, char *argv[])
 		vcpu_run(vcpu);
 		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
-		switch (get_ucall(vcpu, &uc)) {
-		case UCALL_SYNC:
+		if (vcpu->run->io.port == MAGIC_HYPERCALL_PORT &&
+		    vcpu->run->io.direction == KVM_EXIT_IO_OUT) {
 			/* emulate hypervisor clearing CR4.OSXSAVE */
 			vcpu_sregs_get(vcpu, &sregs);
 			sregs.cr4 &= ~X86_CR4_OSXSAVE;
 			vcpu_sregs_set(vcpu, &sregs);
-			break;
+			continue;
+		}
+
+		switch (get_ucall(vcpu, &uc)) {
 		case UCALL_ABORT:
 			REPORT_GUEST_ASSERT(uc);
 			break;

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

@@ -166,7 +166,7 @@ int main(void)
 	/* Test single step */
 	target_rip = CAST_TO_RIP(ss_start);
 	target_dr6 = 0xffff4ff0ULL;
-	for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) {
+	for (i = 0; i < ARRAY_SIZE(ss_size); i++) {
 		target_rip += ss_size[i];
 		memset(&debug, 0, sizeof(debug));
 		debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP |

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

@@ -41,8 +41,8 @@ static void guest_sev_code(void)
 /* Stash state passed via VMSA before any compiled code runs.  */
 extern void guest_code_xsave(void);
 asm("guest_code_xsave:\n"
-    "mov $-1, %eax\n"
-    "mov $-1, %edx\n"
+    "mov $" __stringify(XFEATURE_MASK_X87_AVX) ", %eax\n"
+    "xor %edx, %edx\n"
     "xsave (%rdi)\n"
     "jmp guest_sev_es_code");
 
@@ -70,12 +70,6 @@ static void test_sync_vmsa(uint32_t policy)
 
 	double x87val = M_PI;
 	struct kvm_xsave __attribute__((aligned(64))) xsave = { 0 };
-	struct kvm_sregs sregs;
-	struct kvm_xcrs xcrs = {
-		.nr_xcrs = 1,
-		.xcrs[0].xcr = 0,
-		.xcrs[0].value = XFEATURE_MASK_X87_AVX,
-	};
 
 	vm = vm_sev_create_with_one_vcpu(KVM_X86_SEV_ES_VM, guest_code_xsave, &vcpu);
 	gva = vm_vaddr_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR,
@@ -84,11 +78,6 @@ static void test_sync_vmsa(uint32_t policy)
 
 	vcpu_args_set(vcpu, 1, gva);
 
-	vcpu_sregs_get(vcpu, &sregs);
-	sregs.cr4 |= X86_CR4_OSFXSR | X86_CR4_OSXSAVE;
-	vcpu_sregs_set(vcpu, &sregs);
-
-	vcpu_xcrs_set(vcpu, &xcrs);
 	asm("fninit\n"
 	    "vpcmpeqb %%ymm4, %%ymm4, %%ymm4\n"
 	    "fldl %3\n"
@@ -192,6 +181,8 @@ static void test_sev_es_shutdown(void)
 
 int main(int argc, char *argv[])
 {
+	const u64 xf_mask = XFEATURE_MASK_X87_AVX;
+
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
 
 	test_sev(guest_sev_code, SEV_POLICY_NO_DBG);
@@ -204,7 +195,7 @@ int main(int argc, char *argv[])
 		test_sev_es_shutdown();
 
 		if (kvm_has_cap(KVM_CAP_XCRS) &&
-		    (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) {
+		    (xgetbv(0) & kvm_cpu_supported_xcr0() & xf_mask) == xf_mask) {
 			test_sync_vmsa(0);
 			test_sync_vmsa(SEV_POLICY_NO_DBG);
 		}

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

@@ -145,11 +145,6 @@ static void __attribute__((__flatten__)) guest_code(void *arg)
 
 		memset(buffer, 0xcc, sizeof(buffer));
 
-		set_cr4(get_cr4() | X86_CR4_OSXSAVE);
-		GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE));
-
-		xsetbv(0, xgetbv(0) | supported_xcr0);
-
 		/*
 		 * Modify state for all supported xfeatures to take them out of
 		 * their "init" state, i.e. to make them show up in XSTATE_BV.