KVM: selftests: Touch relevant XSAVE state in guest for state test

Modify support XSAVE state in the "state test's" guest code so that saving
and loading state via KVM_{G,S}ET_XSAVE actually does something useful,
i.e. so that xstate_bv in XSAVE state isn't empty.

Punt on BNDCSR for now, it's easier to just stuff that xfeature from the
host side.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230928001956.924301-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 91 insertions, 0 deletions

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 4fd042112526..6f66861175ad 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -68,6 +68,12 @@ struct xstate {
 #define XFEATURE_MASK_OPMASK		BIT_ULL(5)
 #define XFEATURE_MASK_ZMM_Hi256		BIT_ULL(6)
 #define XFEATURE_MASK_Hi16_ZMM		BIT_ULL(7)
+#define XFEATURE_MASK_PT		BIT_ULL(8)
+#define XFEATURE_MASK_PKRU		BIT_ULL(9)
+#define XFEATURE_MASK_PASID		BIT_ULL(10)
+#define XFEATURE_MASK_CET_USER		BIT_ULL(11)
+#define XFEATURE_MASK_CET_KERNEL	BIT_ULL(12)
+#define XFEATURE_MASK_LBR		BIT_ULL(15)
 #define XFEATURE_MASK_XTILE_CFG		BIT_ULL(17)
 #define XFEATURE_MASK_XTILE_DATA	BIT_ULL(18)
 
@@ -147,6 +153,7 @@ struct kvm_x86_cpu_feature {
 #define	X86_FEATURE_CLWB		KVM_X86_CPU_FEATURE(0x7, 0, EBX, 24)
 #define	X86_FEATURE_UMIP		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 2)
 #define	X86_FEATURE_PKU			KVM_X86_CPU_FEATURE(0x7, 0, ECX, 3)
+#define	X86_FEATURE_OSPKE		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 4)
 #define	X86_FEATURE_LA57		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 16)
 #define	X86_FEATURE_RDPID		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 22)
 #define	X86_FEATURE_SGX_LC		KVM_X86_CPU_FEATURE(0x7, 0, ECX, 30)
@@ -553,6 +560,13 @@ static inline void xsetbv(u32 index, u64 value)
 	__asm__ __volatile__("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
 }
 
+static inline void wrpkru(u32 pkru)
+{
+	/* Note, ECX and EDX are architecturally required to be '0'. */
+	asm volatile(".byte 0x0f,0x01,0xef\n\t"
+		     : : "a" (pkru), "c"(0), "d"(0));
+}
+
 static inline struct desc_ptr get_gdt(void)
 {
 	struct desc_ptr gdt;
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 4c4925a8ab45..df3e93df4343 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -139,6 +139,83 @@ static void vmx_l1_guest_code(struct vmx_pages *vmx_pages)
 static void __attribute__((__flatten__)) guest_code(void *arg)
 {
 	GUEST_SYNC(1);
+
+	if (this_cpu_has(X86_FEATURE_XSAVE)) {
+		uint64_t supported_xcr0 = this_cpu_supported_xcr0();
+		uint8_t buffer[4096];
+
+		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.
+		 *
+		 * Note off-by-default features, e.g. AMX, are out of scope for
+		 * this particular testcase as they have a different ABI.
+		 */
+		GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_FP);
+		asm volatile ("fincstp");
+
+		GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_SSE);
+		asm volatile ("vmovdqu %0, %%xmm0" :: "m" (buffer));
+
+		if (supported_xcr0 & XFEATURE_MASK_YMM)
+			asm volatile ("vmovdqu %0, %%ymm0" :: "m" (buffer));
+
+		if (supported_xcr0 & XFEATURE_MASK_AVX512) {
+			asm volatile ("kmovq %0, %%k1" :: "r" (-1ull));
+			asm volatile ("vmovupd %0, %%zmm0" :: "m" (buffer));
+			asm volatile ("vmovupd %0, %%zmm16" :: "m" (buffer));
+		}
+
+		if (this_cpu_has(X86_FEATURE_MPX)) {
+			uint64_t bounds[2] = { 10, 0xffffffffull };
+			uint64_t output[2] = { };
+
+			GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDREGS);
+			GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDCSR);
+
+			/*
+			 * Don't bother trying to get BNDCSR into the INUSE
+			 * state.  MSR_IA32_BNDCFGS doesn't count as it isn't
+			 * managed via XSAVE/XRSTOR, and BNDCFGU can only be
+			 * modified by XRSTOR.  Stuffing XSTATE_BV in the host
+			 * is simpler than doing XRSTOR here in the guest.
+			 *
+			 * However, temporarily enable MPX in BNDCFGS so that
+			 * BNDMOV actually loads BND1.  If MPX isn't *fully*
+			 * enabled, all MPX instructions are treated as NOPs.
+			 *
+			 * Hand encode "bndmov (%rax),%bnd1" as support for MPX
+			 * mnemonics/registers has been removed from gcc and
+			 * clang (and was never fully supported by clang).
+			 */
+			wrmsr(MSR_IA32_BNDCFGS, BIT_ULL(0));
+			asm volatile (".byte 0x66,0x0f,0x1a,0x08" :: "a" (bounds));
+			/*
+			 * Hand encode "bndmov %bnd1, (%rax)" to sanity check
+			 * that BND1 actually got loaded.
+			 */
+			asm volatile (".byte 0x66,0x0f,0x1b,0x08" :: "a" (output));
+			wrmsr(MSR_IA32_BNDCFGS, 0);
+
+			GUEST_ASSERT_EQ(bounds[0], output[0]);
+			GUEST_ASSERT_EQ(bounds[1], output[1]);
+		}
+		if (this_cpu_has(X86_FEATURE_PKU)) {
+			GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_PKRU);
+			set_cr4(get_cr4() | X86_CR4_PKE);
+			GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSPKE));
+
+			wrpkru(-1u);
+		}
+	}
+
 	GUEST_SYNC(2);
 
 	if (arg) {