KVM, pkeys: expose CPUID/CR4 to guest

X86_FEATURE_PKU is referred to as "PKU" in the hardware documentation:
CPUID.7.0.ECX[3]:PKU. X86_FEATURE_OSPKE is software support for pkeys,
enumerated with CPUID.7.0.ECX[4]:OSPKE, and it reflects the setting of
CR4.PKE(bit 22).

This patch disables CPUID:PKU without ept, because pkeys is not yet
implemented for shadow paging.

Signed-off-by: Huaitong Han <huaitong.han@intel.com>
Reviewed-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 37 insertions, 6 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0d75ecdfa077..f62a9f37f79f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -84,7 +84,8 @@
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
-			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE | X86_CR4_SMAP))
+			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE | X86_CR4_SMAP \
+			  | X86_CR4_PKE))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 00a69ecdd401..8efb839948e5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -88,6 +88,16 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			apic->lapic_timer.timer_mode_mask = 1 << 17;
 	}
 
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if (best) {
+		/* Update OSPKE bit */
+		if (boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) {
+			best->ecx &= ~F(OSPKE);
+			if (kvm_read_cr4_bits(vcpu, X86_CR4_PKE))
+				best->ecx |= F(OSPKE);
+		}
+	}
+
 	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
 	if (!best) {
 		vcpu->arch.guest_supported_xcr0 = 0;
@@ -360,6 +370,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_cpuid_D_1_eax_x86_features =
 		F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
 
+	/* cpuid 7.0.ecx*/
+	const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/;
+
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 
@@ -437,10 +450,16 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			cpuid_mask(&entry->ebx, CPUID_7_0_EBX);
 			// TSC_ADJUST is emulated
 			entry->ebx |= F(TSC_ADJUST);
-		} else
+			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
+			cpuid_mask(&entry->ecx, CPUID_7_ECX);
+			/* PKU is not yet implemented for shadow paging. */
+			if (!tdp_enabled)
+				entry->ecx &= ~F(PKU);
+		} else {
 			entry->ebx = 0;
+			entry->ecx = 0;
+		}
 		entry->eax = 0;
-		entry->ecx = 0;
 		entry->edx = 0;
 		break;
 	}
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 66a6581724ad..e17a74b1d852 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -80,6 +80,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
 }
 
+static inline bool guest_cpuid_has_pku(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ecx & bit(X86_FEATURE_PKU));
+}
+
 static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d0a5918da654..98ae1fb9fd66 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -723,7 +723,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP;
+				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
 
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
@@ -740,6 +740,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
 		return 1;
 
+	if (!guest_cpuid_has_pku(vcpu) && (cr4 & X86_CR4_PKE))
+		return 1;
+
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
@@ -765,7 +768,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
-	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
+	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
 		kvm_update_cpuid(vcpu);
 
 	return 0;
@@ -7128,7 +7131,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
-	if (sregs->cr4 & X86_CR4_OSXSAVE)
+	if (sregs->cr4 & (X86_CR4_OSXSAVE | X86_CR4_PKE))
 		kvm_update_cpuid(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);