1 files changed, 33 insertions, 23 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7236bd3a4c3d..9b7798c7b210 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -700,7 +700,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
 			return 1;
 	}
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -723,7 +722,7 @@ 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 +739,9 @@ 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 +767,7 @@ 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;
@@ -1559,7 +1561,7 @@ static cycle_t read_tsc(void)
 
 	/*
 	 * GCC likes to generate cmov here, but this branch is extremely
-	 * predictable (it's just a funciton of time and the likely is
+	 * predictable (it's just a function of time and the likely is
 	 * very likely) and there's a data dependence, so force GCC
 	 * to generate a branch instead.  I don't barrier() because
 	 * we don't actually need a barrier, and if this function
@@ -4326,9 +4328,14 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
 	u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0)
 		| (write ? PFERR_WRITE_MASK : 0);
 
+	/*
+	 * currently PKRU is only applied to ept enabled guest so
+	 * there is no pkey in EPT page table for L1 guest or EPT
+	 * shadow page table for L2 guest.
+	 */
 	if (vcpu_match_mmio_gva(vcpu, gva)
 	    && !permission_fault(vcpu, vcpu->arch.walk_mmu,
-				 vcpu->arch.access, access)) {
+				 vcpu->arch.access, 0, access)) {
 		*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
 					(gva & (PAGE_SIZE - 1));
 		trace_vcpu_match_mmio(gva, *gpa, write, false);
@@ -6087,12 +6094,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.nmi_pending) {
-		if (kvm_x86_ops->nmi_allowed(vcpu)) {
-			--vcpu->arch.nmi_pending;
-			vcpu->arch.nmi_injected = true;
-			kvm_x86_ops->set_nmi(vcpu);
-		}
+	if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+		--vcpu->arch.nmi_pending;
+		vcpu->arch.nmi_injected = true;
+		kvm_x86_ops->set_nmi(vcpu);
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
 		/*
 		 * Because interrupts can be injected asynchronously, we are
@@ -6561,10 +6566,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (inject_pending_event(vcpu, req_int_win) != 0)
 			req_immediate_exit = true;
 		/* enable NMI/IRQ window open exits if needed */
-		else if (vcpu->arch.nmi_pending)
-			kvm_x86_ops->enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
-			kvm_x86_ops->enable_irq_window(vcpu);
+		else {
+			if (vcpu->arch.nmi_pending)
+				kvm_x86_ops->enable_nmi_window(vcpu);
+			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
+				kvm_x86_ops->enable_irq_window(vcpu);
+		}
 
 		if (kvm_lapic_enabled(vcpu)) {
 			update_cr8_intercept(vcpu);
@@ -6582,14 +6589,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->prepare_guest_switch(vcpu);
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
-	kvm_load_guest_xcr0(vcpu);
-
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 
-	/* We should set ->mode before check ->requests,
-	 * see the comment in make_all_cpus_request.
+	/*
+	 * We should set ->mode before check ->requests,
+	 * Please see the comment in kvm_make_all_cpus_request.
+	 * This also orders the write to mode from any reads
+	 * to the page tables done while the VCPU is running.
+	 * Please see the comment in kvm_flush_remote_tlbs.
 	 */
 	smp_mb__after_srcu_read_unlock();
 
@@ -6606,6 +6615,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6655,6 +6666,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
+	kvm_put_guest_xcr0(vcpu);
+
 	/* Interrupt is enabled by handle_external_intr() */
 	kvm_x86_ops->handle_external_intr(vcpu);
 
@@ -7123,7 +7136,7 @@ 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);
@@ -7302,7 +7315,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 * and assume host would use all available bits.
 	 * Guest xcr0 would be loaded later.
 	 */
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7311,8 +7323,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	kvm_put_guest_xcr0(vcpu);
-
 	if (!vcpu->guest_fpu_loaded) {
 		vcpu->fpu_counter = 0;
 		return;