kvm: selftests: Add support for KVM_CAP_XSAVE2

mainline inclusion
from mainline-v5.17-rc1
commit 415a3c33
category: feature
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I5RQLJ
CVE: NA

Intel-SIG: commit 415a3c33 kvm: selftests: Add support for KVM_CAP_XSAVE2.

--------------------------------

When KVM_CAP_XSAVE2 is supported, userspace is expected to allocate
buffer for KVM_GET_XSAVE2 and KVM_SET_XSAVE using the size returned
by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2).
Signed-off-by: NWei Wang <wei.w.wang@intel.com>
Signed-off-by: NGuang Zeng <guang.zeng@intel.com>
Signed-off-by: NJing Liu <jing2.liu@intel.com>
Signed-off-by: NYang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-20-yang.zhong@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NLin Wang <lin.x.wang@intel.com>

tools/arch/x86/include/uapi/asm/kvm.h

@@ -358,9 +358,23 @@ struct kvm_debugregs {
 	__u64 reserved[9];
 };
 
-/* for KVM_CAP_XSAVE */
+/* for KVM_CAP_XSAVE and KVM_CAP_XSAVE2 */
 struct kvm_xsave {
+	/*
+	 * KVM_GET_XSAVE2 and KVM_SET_XSAVE write and read as many bytes
+	 * as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
+	 * respectively, when invoked on the vm file descriptor.
+	 *
+	 * The size value returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
+	 * will always be at least 4096. Currently, it is only greater
+	 * than 4096 if a dynamic feature has been enabled with
+	 * ``arch_prctl()``, but this may change in the future.
+	 *
+	 * The offsets of the state save areas in struct kvm_xsave follow
+	 * the contents of CPUID leaf 0xD on the host.
+	 */
 	__u32 region[1024];
+	__u32 extra[0];
 };
 
 #define KVM_MAX_XCRS	16

tools/include/uapi/linux/kvm.h

@@ -1053,6 +1053,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_XSAVE2 207
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1462,6 +1463,8 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_XSAVE */
 #define KVM_GET_XSAVE		  _IOR(KVMIO,  0xa4, struct kvm_xsave)
 #define KVM_SET_XSAVE		  _IOW(KVMIO,  0xa5, struct kvm_xsave)
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 /* Available with KVM_CAP_XCRS */
 #define KVM_GET_XCRS		  _IOR(KVMIO,  0xa6, struct kvm_xcrs)
 #define KVM_SET_XCRS		  _IOW(KVMIO,  0xa7, struct kvm_xcrs)

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

@@ -256,6 +256,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
  *   guest_code - The vCPU's entry point
  */
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
+void vm_xsave_req_perm(void);
 
 bool vm_is_unrestricted_guest(struct kvm_vm *vm);
 

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

@@ -10,8 +10,10 @@
 
 #include <assert.h>
 #include <stdint.h>
+#include <syscall.h>
 
 #include <asm/msr-index.h>
+#include <asm/prctl.h>
 
 #define X86_EFLAGS_FIXED	 (1u << 1)
 
@@ -319,6 +321,7 @@ struct kvm_x86_state;
 struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_x86_state *state);
+void kvm_x86_state_cleanup(struct kvm_x86_state *state);
 
 struct kvm_msr_list *kvm_get_msr_index_list(void);
 
@@ -419,4 +422,11 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 /* VMX_EPT_VPID_CAP bits */
 #define VMX_EPT_VPID_CAP_AD_BITS       (1ULL << 21)
 
+#define XSTATE_XTILE_CFG_BIT		17
+#define XSTATE_XTILE_DATA_BIT		18
+
+#define XSTATE_XTILE_CFG_MASK		(1ULL << XSTATE_XTILE_CFG_BIT)
+#define XSTATE_XTILE_DATA_MASK		(1ULL << XSTATE_XTILE_DATA_BIT)
+#define XFEATURE_XTILE_MASK		(XSTATE_XTILE_CFG_MASK | \
+					XSTATE_XTILE_DATA_MASK)
 #endif /* SELFTEST_KVM_PROCESSOR_H */

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

@@ -580,6 +580,45 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
 	vcpu_sregs_set(vm, vcpuid, &sregs);
 }
 
+#define CPUID_XFD_BIT (1 << 4)
+static bool is_xfd_supported(void)
+{
+	int eax, ebx, ecx, edx;
+	const int leaf = 0xd, subleaf = 0x1;
+
+	__asm__ __volatile__(
+		"cpuid"
+		: /* output */ "=a"(eax), "=b"(ebx),
+		  "=c"(ecx), "=d"(edx)
+		: /* input */ "0"(leaf), "2"(subleaf));
+
+	return !!(eax & CPUID_XFD_BIT);
+}
+
+void vm_xsave_req_perm(void)
+{
+	unsigned long bitmask;
+	long rc;
+
+	if (!is_xfd_supported())
+		return;
+
+	rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM,
+		     XSTATE_XTILE_DATA_BIT);
+	/*
+	 * The older kernel version(<5.15) can't support
+	 * ARCH_REQ_XCOMP_GUEST_PERM and directly return.
+	 */
+	if (rc)
+		return;
+
+	rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask);
+	TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc);
+	TEST_ASSERT(bitmask & XFEATURE_XTILE_MASK,
+		    "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx",
+		    bitmask);
+}
+
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 {
 	struct kvm_mp_state mp_state;
@@ -588,6 +627,11 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
 				     DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
 
+	/*
+	 * Permission needs to be requested before KVM_SET_CPUID2.
+	 */
+	vm_xsave_req_perm();
+
 	/* Create VCPU */
 	vm_vcpu_add(vm, vcpuid);
 	vcpu_setup(vm, vcpuid, 0, 0);
@@ -904,10 +948,10 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 }
 
 struct kvm_x86_state {
+	struct kvm_xsave *xsave;
 	struct kvm_vcpu_events events;
 	struct kvm_mp_state mp_state;
 	struct kvm_regs regs;
-	struct kvm_xsave xsave;
 	struct kvm_xcrs xcrs;
 	struct kvm_sregs sregs;
 	struct kvm_debugregs debugregs;
@@ -957,6 +1001,22 @@ struct kvm_msr_list *kvm_get_msr_index_list(void)
 	return list;
 }
 
+static int vcpu_save_xsave_state(struct kvm_vm *vm, struct vcpu *vcpu,
+				 struct kvm_x86_state *state)
+{
+	int size;
+
+	size = vm_check_cap(vm, KVM_CAP_XSAVE2);
+	if (!size)
+		size = sizeof(struct kvm_xsave);
+
+	state->xsave = malloc(size);
+	if (size == sizeof(struct kvm_xsave))
+		return ioctl(vcpu->fd, KVM_GET_XSAVE, state->xsave);
+	else
+		return ioctl(vcpu->fd, KVM_GET_XSAVE2, state->xsave);
+}
+
 struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1000,7 +1060,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
         TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
                 r);
 
-	r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
+	r = vcpu_save_xsave_state(vm, vcpu, state);
         TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
                 r);
 
@@ -1045,7 +1105,7 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int r;
 
-	r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
+	r = ioctl(vcpu->fd, KVM_SET_XSAVE, state->xsave);
         TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
                 r);
 
@@ -1086,6 +1146,12 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
 	}
 }
 
+void kvm_x86_state_cleanup(struct kvm_x86_state *state)
+{
+	free(state->xsave);
+	free(state);
+}
+
 bool is_intel_cpu(void)
 {
 	int eax, ebx, ecx, edx;

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

@@ -148,7 +148,7 @@ int main(int argc, char *argv[])
 		vcpu_enable_evmcs(vm, VCPU_ID);
 		vcpu_load_state(vm, VCPU_ID, state);
 		run = vcpu_state(vm, VCPU_ID);
-		free(state);
+		kvm_x86_state_cleanup(state);
 
 		memset(&regs2, 0, sizeof(regs2));
 		vcpu_regs_get(vm, VCPU_ID, &regs2);

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

@@ -156,7 +156,7 @@ int main(int argc, char *argv[])
 		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 		vcpu_load_state(vm, VCPU_ID, state);
 		run = vcpu_state(vm, VCPU_ID);
-		free(state);
+		kvm_x86_state_cleanup(state);
 	}
 
 done:

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

@@ -219,7 +219,7 @@ int main(int argc, char *argv[])
 		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 		vcpu_load_state(vm, VCPU_ID, state);
 		run = vcpu_state(vm, VCPU_ID);
-		free(state);
+		kvm_x86_state_cleanup(state);
 
 		memset(&regs2, 0, sizeof(regs2));
 		vcpu_regs_get(vm, VCPU_ID, &regs2);

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

@@ -245,7 +245,7 @@ int main(int argc, char *argv[])
 		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 		vcpu_load_state(vm, VCPU_ID, state);
 		run = vcpu_state(vm, VCPU_ID);
-		free(state);
+		kvm_x86_state_cleanup(state);
 
 		memset(&regs2, 0, sizeof(regs2));
 		vcpu_regs_get(vm, VCPU_ID, &regs2);