1 files changed, 396 insertions, 117 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e545a8a613b1..3f7c1fc7a3ce 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -197,7 +197,8 @@ EXPORT_SYMBOL_GPL(host_efer);
 bool __read_mostly allow_smaller_maxphyaddr = 0;
 EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 
-static u64 __read_mostly host_xss;
+u64 __read_mostly host_xss;
+EXPORT_SYMBOL_GPL(host_xss);
 u64 __read_mostly supported_xss;
 EXPORT_SYMBOL_GPL(supported_xss);
 
@@ -804,11 +805,29 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(pdptrs_changed);
 
+void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0)
+{
+	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
+
+	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
+		kvm_clear_async_pf_completion_queue(vcpu);
+		kvm_async_pf_hash_reset(vcpu);
+	}
+
+	if ((cr0 ^ old_cr0) & update_bits)
+		kvm_mmu_reset_context(vcpu);
+
+	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
+	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
+	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
+}
+EXPORT_SYMBOL_GPL(kvm_post_set_cr0);
+
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	unsigned long old_cr0 = kvm_read_cr0(vcpu);
 	unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG;
-	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
 
 	cr0 |= X86_CR0_ET;
 
@@ -847,18 +866,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	kvm_x86_ops.set_cr0(vcpu, cr0);
 
-	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
-		kvm_clear_async_pf_completion_queue(vcpu);
-		kvm_async_pf_hash_reset(vcpu);
-	}
-
-	if ((cr0 ^ old_cr0) & update_bits)
-		kvm_mmu_reset_context(vcpu);
-
-	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
-	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
-	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
-		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
+	kvm_post_set_cr0(vcpu, old_cr0, cr0);
 
 	return 0;
 }
@@ -872,6 +880,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw);
 
 void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.guest_state_protected)
+		return;
+
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
 
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -892,6 +903,9 @@ EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.guest_state_protected)
+		return;
+
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
 	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
@@ -964,26 +978,36 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
-		return -EINVAL;
+		return false;
 
 	if (cr4 & vcpu->arch.cr4_guest_rsvd_bits)
-		return -EINVAL;
+		return false;
 
-	return 0;
+	return kvm_x86_ops.is_valid_cr4(vcpu, cr4);
+}
+EXPORT_SYMBOL_GPL(kvm_is_valid_cr4);
+
+void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4)
+{
+	unsigned long mmu_role_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				      X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
+	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
+		kvm_mmu_reset_context(vcpu);
 }
-EXPORT_SYMBOL_GPL(kvm_valid_cr4);
+EXPORT_SYMBOL_GPL(kvm_post_set_cr4);
 
 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;
-	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
-	if (kvm_valid_cr4(vcpu, cr4))
+	if (!kvm_is_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -1006,15 +1030,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			return 1;
 	}
 
-	if (kvm_x86_ops.set_cr4(vcpu, cr4))
-		return 1;
+	kvm_x86_ops.set_cr4(vcpu, cr4);
 
-	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
-	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
-		kvm_mmu_reset_context(vcpu);
-
-	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
-		kvm_update_cpuid_runtime(vcpu);
+	kvm_post_set_cr4(vcpu, old_cr4, cr4);
 
 	return 0;
 }
@@ -1638,27 +1656,20 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
-static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
+static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->run->msr.error) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	} else if (is_read) {
+	int err = vcpu->run->msr.error;
+	if (!err) {
 		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
 		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
 	}
 
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
-{
-	return complete_emulated_msr(vcpu, true);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, err);
 }
 
 static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
 {
-	return complete_emulated_msr(vcpu, false);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, vcpu->run->msr.error);
 }
 
 static u64 kvm_msr_reason(int r)
@@ -1721,18 +1732,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	/* MSR read failed? Inject a #GP */
-	if (r) {
+	if (!r) {
+		trace_kvm_msr_read(ecx, data);
+
+		kvm_rax_write(vcpu, data & -1u);
+		kvm_rdx_write(vcpu, (data >> 32) & -1u);
+	} else {
 		trace_kvm_msr_read_ex(ecx);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
 	}
 
-	trace_kvm_msr_read(ecx, data);
-
-	kvm_rax_write(vcpu, data & -1u);
-	kvm_rdx_write(vcpu, (data >> 32) & -1u);
-	return kvm_skip_emulated_instruction(vcpu);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, r);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);
 
@@ -1753,15 +1762,12 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		return r;
 
-	/* MSR write failed? Inject a #GP */
-	if (r > 0) {
+	if (!r)
+		trace_kvm_msr_write(ecx, data);
+	else
 		trace_kvm_msr_write_ex(ecx, data);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
 
-	trace_kvm_msr_write(ecx, data);
-	return kvm_skip_emulated_instruction(vcpu);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, r);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
 
@@ -3678,6 +3684,27 @@ static inline bool kvm_can_mwait_in_guest(void)
 		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
+static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
+					    struct kvm_cpuid2 __user *cpuid_arg)
+{
+	struct kvm_cpuid2 cpuid;
+	int r;
+
+	r = -EFAULT;
+	if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
+		return r;
+
+	r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries);
+	if (r)
+		return r;
+
+	r = -EFAULT;
+	if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
+		return r;
+
+	return 0;
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -3714,6 +3741,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_TLBFLUSH:
 	case KVM_CAP_HYPERV_SEND_IPI:
 	case KVM_CAP_HYPERV_CPUID:
+	case KVM_CAP_SYS_HYPERV_CPUID:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -3762,7 +3790,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops.has_emulated_msr(MSR_IA32_SMBASE);
+		r = kvm_x86_ops.has_emulated_msr(kvm, MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_VAPIC:
 		r = !kvm_x86_ops.cpu_has_accelerated_tpr();
@@ -3899,6 +3927,9 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	case KVM_GET_MSRS:
 		r = msr_io(NULL, argp, do_get_msr_feature, 1);
 		break;
+	case KVM_GET_SUPPORTED_HV_CPUID:
+		r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -3997,7 +4028,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
-	if (vcpu->preempted)
+	if (vcpu->preempted && !vcpu->arch.guest_state_protected)
 		vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu);
 
 	/*
@@ -4481,6 +4512,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
+	if (!vcpu->arch.guest_fpu)
+		return;
+
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
@@ -4498,9 +4532,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
-	u64 xstate_bv =
-		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
-	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
+	u64 xstate_bv;
+	u32 mxcsr;
+
+	if (!vcpu->arch.guest_fpu)
+		return 0;
+
+	xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
@@ -4977,25 +5016,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
-	case KVM_GET_SUPPORTED_HV_CPUID: {
-		struct kvm_cpuid2 __user *cpuid_arg = argp;
-		struct kvm_cpuid2 cpuid;
-
-		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
-			goto out;
-
-		r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid,
-						cpuid_arg->entries);
-		if (r)
-			goto out;
-
-		r = -EFAULT;
-		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
-			goto out;
-		r = 0;
+	case KVM_GET_SUPPORTED_HV_CPUID:
+		r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp);
 		break;
-	}
 	default:
 		r = -EINVAL;
 	}
@@ -5776,7 +5799,7 @@ static void kvm_init_msr_list(void)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
-		if (!kvm_x86_ops.has_emulated_msr(emulated_msrs_all[i]))
+		if (!kvm_x86_ops.has_emulated_msr(NULL, emulated_msrs_all[i]))
 			continue;
 
 		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
@@ -8158,7 +8181,14 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+	/*
+	 * if_flag is obsolete and useless, so do not bother
+	 * setting it for SEV-ES guests.  Userspace can just
+	 * use kvm_run->ready_for_interrupt_injection.
+	 */
+	kvm_run->if_flag = !vcpu->arch.guest_state_protected
+		&& (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+
 	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
@@ -8748,6 +8778,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
+	/* Forbid vmenter if vcpu dirty ring is soft-full */
+	if (unlikely(vcpu->kvm->dirty_ring_size &&
+		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
+		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+		trace_kvm_dirty_ring_exit(vcpu);
+		r = 0;
+		goto out;
+	}
+
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
@@ -9223,9 +9262,14 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 	kvm_save_current_fpu(vcpu->arch.user_fpu);
 
-	/* PKRU is separately restored in kvm_x86_ops.run.  */
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
-				~XFEATURE_MASK_PKRU);
+	/*
+	 * Guests with protected state can't have it set by the hypervisor,
+	 * so skip trying to set it.
+	 */
+	if (vcpu->arch.guest_fpu)
+		/* PKRU is separately restored in kvm_x86_ops.run. */
+		__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
+					~XFEATURE_MASK_PKRU);
 
 	fpregs_mark_activate();
 	fpregs_unlock();
@@ -9238,7 +9282,12 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+	/*
+	 * Guests with protected state can't have it read by the hypervisor,
+	 * so skip trying to save it.
+	 */
+	if (vcpu->arch.guest_fpu)
+		kvm_save_current_fpu(vcpu->arch.guest_fpu);
 
 	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
@@ -9417,6 +9466,9 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct desc_ptr dt;
 
+	if (vcpu->arch.guest_state_protected)
+		goto skip_protected_regs;
+
 	kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
 	kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
@@ -9434,9 +9486,11 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->gdt.limit = dt.size;
 	sregs->gdt.base = dt.address;
 
-	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = kvm_read_cr3(vcpu);
+
+skip_protected_regs:
+	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
 	sregs->efer = vcpu->arch.efer;
@@ -9535,7 +9589,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
-static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
@@ -9543,31 +9597,29 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		 * 64-bit mode (though maybe in a 32-bit code segment).
 		 * CR4.PAE and EFER.LMA must be set.
 		 */
-		if (!(sregs->cr4 & X86_CR4_PAE)
-		    || !(sregs->efer & EFER_LMA))
-			return -EINVAL;
+		if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
+			return false;
 	} else {
 		/*
 		 * Not in 64-bit mode: EFER.LMA is clear and the code
 		 * segment cannot be 64-bit.
 		 */
 		if (sregs->efer & EFER_LMA || sregs->cs.l)
-			return -EINVAL;
+			return false;
 	}
 
-	return kvm_valid_cr4(vcpu, sregs->cr4);
+	return kvm_is_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct msr_data apic_base_msr;
 	int mmu_reset_needed = 0;
-	int cpuid_update_needed = 0;
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 	int ret = -EINVAL;
 
-	if (kvm_valid_sregs(vcpu, sregs))
+	if (!kvm_is_valid_sregs(vcpu, sregs))
 		goto out;
 
 	apic_base_msr.data = sregs->apic_base;
@@ -9575,6 +9627,9 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	if (kvm_set_apic_base(vcpu, &apic_base_msr))
 		goto out;
 
+	if (vcpu->arch.guest_state_protected)
+		goto skip_protected_regs;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops.set_idt(vcpu, &dt);
@@ -9597,11 +9652,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr0 = sregs->cr0;
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
-	cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
-				(X86_CR4_OSXSAVE | X86_CR4_PKE));
 	kvm_x86_ops.set_cr4(vcpu, sregs->cr4);
-	if (cpuid_update_needed)
-		kvm_update_cpuid_runtime(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	if (is_pae_paging(vcpu)) {
@@ -9613,14 +9664,6 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
 
-	max_bits = KVM_NR_INTERRUPTS;
-	pending_vec = find_first_bit(
-		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
-	if (pending_vec < max_bits) {
-		kvm_queue_interrupt(vcpu, pending_vec, false);
-		pr_debug("Set back pending irq %d\n", pending_vec);
-	}
-
 	kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
 	kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES);
@@ -9639,6 +9682,15 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	    !is_protmode(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
+skip_protected_regs:
+	max_bits = KVM_NR_INTERRUPTS;
+	pending_vec = find_first_bit(
+		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
+	if (pending_vec < max_bits) {
+		kvm_queue_interrupt(vcpu, pending_vec, false);
+		pr_debug("Set back pending irq %d\n", pending_vec);
+	}
+
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	ret = 0;
@@ -9663,6 +9715,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	unsigned long rflags;
 	int i, r;
 
+	if (vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 
 	if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
@@ -9742,6 +9797,9 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	struct fxregs_state *fxsave;
 
+	if (!vcpu->arch.guest_fpu)
+		return 0;
+
 	vcpu_load(vcpu);
 
 	fxsave = &vcpu->arch.guest_fpu->state.fxsave;
@@ -9762,6 +9820,9 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	struct fxregs_state *fxsave;
 
+	if (!vcpu->arch.guest_fpu)
+		return 0;
+
 	vcpu_load(vcpu);
 
 	fxsave = &vcpu->arch.guest_fpu->state.fxsave;
@@ -9820,6 +9881,9 @@ static int sync_regs(struct kvm_vcpu *vcpu)
 
 static void fx_init(struct kvm_vcpu *vcpu)
 {
+	if (!vcpu->arch.guest_fpu)
+		return;
+
 	fpstate_init(&vcpu->arch.guest_fpu->state);
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
@@ -9833,6 +9897,15 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
+void kvm_free_guest_fpu(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.guest_fpu) {
+		kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+		vcpu->arch.guest_fpu = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_free_guest_fpu);
+
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 {
 	if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
@@ -9869,7 +9942,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	r = -ENOMEM;
 
-	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!page)
 		goto fail_free_lapic;
 	vcpu->arch.pio_data = page_address(page);
@@ -9928,7 +10001,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	return 0;
 
 free_guest_fpu:
-	kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+	kvm_free_guest_fpu(vcpu);
 free_user_fpu:
 	kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
 free_emulate_ctxt:
@@ -9982,7 +10055,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
-	kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+	kvm_free_guest_fpu(vcpu);
 
 	kvm_hv_vcpu_uninit(vcpu);
 	kvm_pmu_destroy(vcpu);
@@ -10030,7 +10103,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_async_pf_hash_reset(vcpu);
 	vcpu->arch.apf.halted = false;
 
-	if (kvm_mpx_supported()) {
+	if (vcpu->arch.guest_fpu && kvm_mpx_supported()) {
 		void *mpx_state_buffer;
 
 		/*
@@ -10349,7 +10422,32 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
+#define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))
+
+/**
+ * __x86_set_memory_region: Setup KVM internal memory slot
+ *
+ * @kvm: the kvm pointer to the VM.
+ * @id: the slot ID to setup.
+ * @gpa: the GPA to install the slot (unused when @size == 0).
+ * @size: the size of the slot. Set to zero to uninstall a slot.
+ *
+ * This function helps to setup a KVM internal memory slot.  Specify
+ * @size > 0 to install a new slot, while @size == 0 to uninstall a
+ * slot.  The return code can be one of the following:
+ *
+ *   HVA:           on success (uninstall will return a bogus HVA)
+ *   -errno:        on error
+ *
+ * The caller should always use IS_ERR() to check the return value
+ * before use.  Note, the KVM internal memory slots are guaranteed to
+ * remain valid and unchanged until the VM is destroyed, i.e., the
+ * GPA->HVA translation will not change.  However, the HVA is a user
+ * address, i.e. its accessibility is not guaranteed, and must be
+ * accessed via __copy_{to,from}_user().
+ */
+void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+				      u32 size)
 {
 	int i, r;
 	unsigned long hva, old_npages;
@@ -10358,12 +10456,12 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 
 	/* Called with kvm->slots_lock held.  */
 	if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
-		return -EINVAL;
+		return ERR_PTR_USR(-EINVAL);
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
 		if (slot && slot->npages)
-			return -EEXIST;
+			return ERR_PTR_USR(-EEXIST);
 
 		/*
 		 * MAP_SHARED to prevent internal slot pages from being moved
@@ -10372,7 +10470,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 		hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
 			      MAP_SHARED | MAP_ANONYMOUS, 0);
 		if (IS_ERR((void *)hva))
-			return PTR_ERR((void *)hva);
+			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
 			return 0;
@@ -10391,13 +10489,13 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 		m.memory_size = size;
 		r = __kvm_set_memory_region(kvm, &m);
 		if (r < 0)
-			return r;
+			return ERR_PTR_USR(r);
 	}
 
 	if (!size)
 		vm_munmap(hva, old_npages * PAGE_SIZE);
 
-	return 0;
+	return (void __user *)hva;
 }
 EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
@@ -10754,6 +10852,10 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
 
 unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu)
 {
+	/* Can't read the RIP when guest state is protected, just return 0 */
+	if (vcpu->arch.guest_state_protected)
+		return 0;
+
 	if (is_64_bit_mode(vcpu))
 		return kvm_rip_read(vcpu);
 	return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) +
@@ -11263,6 +11365,179 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 }
 EXPORT_SYMBOL_GPL(kvm_handle_invpcid);
 
+static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_mmio_fragment *frag;
+	unsigned int len;
+
+	BUG_ON(!vcpu->mmio_needed);
+
+	/* Complete previous fragment */
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
+	if (!vcpu->mmio_is_write)
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
+		vcpu->mmio_needed = 0;
+
+		// VMG change, at this point, we're always done
+		// RIP has already been advanced
+		return 1;
+	}
+
+	// More MMIO is needed
+	run->mmio.phys_addr = frag->gpa;
+	run->mmio.len = min(8u, frag->len);
+	run->mmio.is_write = vcpu->mmio_is_write;
+	if (run->mmio.is_write)
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+
+int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
+			  void *data)
+{
+	int handled;
+	struct kvm_mmio_fragment *frag;
+
+	if (!data)
+		return -EINVAL;
+
+	handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data);
+	if (handled == bytes)
+		return 1;
+
+	bytes -= handled;
+	gpa += handled;
+	data += handled;
+
+	/*TODO: Check if need to increment number of frags */
+	frag = vcpu->mmio_fragments;
+	vcpu->mmio_nr_fragments = 1;
+	frag->len = bytes;
+	frag->gpa = gpa;
+	frag->data = data;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = min(8u, frag->len);
+	vcpu->run->mmio.is_write = 1;
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write);
+
+int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
+			 void *data)
+{
+	int handled;
+	struct kvm_mmio_fragment *frag;
+
+	if (!data)
+		return -EINVAL;
+
+	handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data);
+	if (handled == bytes)
+		return 1;
+
+	bytes -= handled;
+	gpa += handled;
+	data += handled;
+
+	/*TODO: Check if need to increment number of frags */
+	frag = vcpu->mmio_fragments;
+	vcpu->mmio_nr_fragments = 1;
+	frag->len = bytes;
+	frag->gpa = gpa;
+	frag->data = data;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = min(8u, frag->len);
+	vcpu->run->mmio.is_write = 0;
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
+
+static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+	memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data,
+	       vcpu->arch.pio.count * vcpu->arch.pio.size);
+	vcpu->arch.pio.count = 0;
+
+	return 1;
+}
+
+static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
+			   unsigned int port, void *data,  unsigned int count)
+{
+	int ret;
+
+	ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port,
+					data, count);
+	if (ret)
+		return ret;
+
+	vcpu->arch.pio.count = 0;
+
+	return 0;
+}
+
+static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
+			  unsigned int port, void *data, unsigned int count)
+{
+	int ret;
+
+	ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port,
+				       data, count);
+	if (ret) {
+		vcpu->arch.pio.count = 0;
+	} else {
+		vcpu->arch.guest_ins_data = data;
+		vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
+	}
+
+	return 0;
+}
+
+int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
+			 unsigned int port, void *data,  unsigned int count,
+			 int in)
+{
+	return in ? kvm_sev_es_ins(vcpu, size, port, data, count)
+		  : kvm_sev_es_outs(vcpu, size, port, data, count);
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
@@ -11285,3 +11560,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);