1 files changed, 239 insertions, 135 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c030c96fc81a..d4575ffb3cec 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -343,6 +343,48 @@ static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bit
 
 void vmx_vmexit(void);
 
+#define vmx_insn_failed(fmt...)		\
+do {					\
+	WARN_ONCE(1, fmt);		\
+	pr_warn_ratelimited(fmt);	\
+} while (0)
+
+asmlinkage void vmread_error(unsigned long field, bool fault)
+{
+	if (fault)
+		kvm_spurious_fault();
+	else
+		vmx_insn_failed("kvm: vmread failed: field=%lx\n", field);
+}
+
+noinline void vmwrite_error(unsigned long field, unsigned long value)
+{
+	vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n",
+			field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
+}
+
+noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr)
+{
+	vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr);
+}
+
+noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr)
+{
+	vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr);
+}
+
+noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva)
+{
+	vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n",
+			ext, vpid, gva);
+}
+
+noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa)
+{
+	vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n",
+			ext, eptp, gpa);
+}
+
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 DEFINE_PER_CPU(struct vmcs *, current_vmcs);
 /*
@@ -486,6 +528,31 @@ static int hv_remote_flush_tlb(struct kvm *kvm)
 	return hv_remote_flush_tlb_with_range(kvm, NULL);
 }
 
+static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu)
+{
+	struct hv_enlightened_vmcs *evmcs;
+	struct hv_partition_assist_pg **p_hv_pa_pg =
+			&vcpu->kvm->arch.hyperv.hv_pa_pg;
+	/*
+	 * Synthetic VM-Exit is not enabled in current code and so All
+	 * evmcs in singe VM shares same assist page.
+	 */
+	if (!*p_hv_pa_pg)
+		*p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL);
+
+	if (!*p_hv_pa_pg)
+		return -ENOMEM;
+
+	evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs;
+
+	evmcs->partition_assist_page =
+		__pa(*p_hv_pa_pg);
+	evmcs->hv_vm_id = (unsigned long)vcpu->kvm;
+	evmcs->hv_enlightenments_control.nested_flush_hypercall = 1;
+
+	return 0;
+}
+
 #endif /* IS_ENABLED(CONFIG_HYPERV) */
 
 /*
@@ -1472,17 +1539,32 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
 	return 0;
 }
 
-
-static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
+static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	unsigned long rip;
 
-	rip = kvm_rip_read(vcpu);
-	rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
-	kvm_rip_write(vcpu, rip);
+	/*
+	 * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on
+	 * undefined behavior: Intel's SDM doesn't mandate the VMCS field be
+	 * set when EPT misconfig occurs.  In practice, real hardware updates
+	 * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors
+	 * (namely Hyper-V) don't set it due to it being undefined behavior,
+	 * i.e. we end up advancing IP with some random value.
+	 */
+	if (!static_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) {
+		rip = kvm_rip_read(vcpu);
+		rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		kvm_rip_write(vcpu, rip);
+	} else {
+		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
+			return 0;
+	}
 
 	/* skipping an emulated instruction also counts */
 	vmx_set_interrupt_shadow(vcpu, 0);
+
+	return 1;
 }
 
 static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
@@ -1517,8 +1599,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 		int inc_eip = 0;
 		if (kvm_exception_is_soft(nr))
 			inc_eip = vcpu->arch.event_exit_inst_len;
-		if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE)
-			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		kvm_inject_realmode_interrupt(vcpu, nr, inc_eip);
 		return;
 	}
 
@@ -1690,6 +1771,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_UMWAIT_CONTROL:
+		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
+			return 1;
+
+		msr_info->data = vmx->msr_ia32_umwait_control;
+		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -1863,6 +1950,16 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
+	case MSR_IA32_UMWAIT_CONTROL:
+		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
+			return 1;
+
+		/* The reserved bit 1 and non-32 bit [63:32] should be zero */
+		if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32)))
+			return 1;
+
+		vmx->msr_ia32_umwait_control = data;
+		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -2280,6 +2377,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			SECONDARY_EXEC_RDRAND_EXITING |
 			SECONDARY_EXEC_ENABLE_PML |
 			SECONDARY_EXEC_TSC_SCALING |
+			SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
 			SECONDARY_EXEC_PT_USE_GPA |
 			SECONDARY_EXEC_PT_CONCEAL_VMX |
 			SECONDARY_EXEC_ENABLE_VMFUNC |
@@ -4016,6 +4114,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 		}
 	}
 
+	if (vmx_waitpkg_supported()) {
+		bool waitpkg_enabled =
+			guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG);
+
+		if (!waitpkg_enabled)
+			exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+
+		if (nested) {
+			if (waitpkg_enabled)
+				vmx->nested.msrs.secondary_ctls_high |=
+					SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+			else
+				vmx->nested.msrs.secondary_ctls_high &=
+					~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
+		}
+	}
+
 	vmx->secondary_exec_control = exec_control;
 }
 
@@ -4026,7 +4141,7 @@ static void ept_set_mmio_spte_mask(void)
 	 * of an EPT paging-structure entry is 110b (write/execute).
 	 */
 	kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK,
-				   VMX_EPT_MISCONFIG_WX_VALUE);
+				   VMX_EPT_MISCONFIG_WX_VALUE, 0);
 }
 
 #define VMX_XSS_EXIT_BITMAP 0
@@ -4150,8 +4265,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx->rmode.vm86_active = 0;
 	vmx->spec_ctrl = 0;
 
+	vmx->msr_ia32_umwait_control = 0;
+
 	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
+	vmx->hv_deadline_tsc = -1;
 	kvm_set_cr8(vcpu, 0);
 
 	if (!init_event) {
@@ -4266,8 +4384,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu)
 		int inc_eip = 0;
 		if (vcpu->arch.interrupt.soft)
 			inc_eip = vcpu->arch.event_exit_inst_len;
-		if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE)
-			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		kvm_inject_realmode_interrupt(vcpu, irq, inc_eip);
 		return;
 	}
 	intr = irq | INTR_INFO_VALID_MASK;
@@ -4303,8 +4420,7 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
 	vmx->loaded_vmcs->nmi_known_unmasked = false;
 
 	if (vmx->rmode.vm86_active) {
-		if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE)
-			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+		kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0);
 		return;
 	}
 
@@ -4431,7 +4547,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	 * Cause the #SS fault with 0 error code in VM86 mode.
 	 */
 	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
-		if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) {
+		if (kvm_emulate_instruction(vcpu, 0)) {
 			if (vcpu->arch.halt_request) {
 				vcpu->arch.halt_request = 0;
 				return kvm_vcpu_halt(vcpu);
@@ -4482,7 +4598,6 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	u32 intr_info, ex_no, error_code;
 	unsigned long cr2, rip, dr6;
 	u32 vect_info;
-	enum emulation_result er;
 
 	vect_info = vmx->idt_vectoring_info;
 	intr_info = vmx->exit_intr_info;
@@ -4499,13 +4614,17 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 
 	if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) {
 		WARN_ON_ONCE(!enable_vmware_backdoor);
-		er = kvm_emulate_instruction(vcpu,
-			EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
-		if (er == EMULATE_USER_EXIT)
-			return 0;
-		else if (er != EMULATE_DONE)
+
+		/*
+		 * VMware backdoor emulation on #GP interception only handles
+		 * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero
+		 * error code on #GP.
+		 */
+		if (error_code) {
 			kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
-		return 1;
+			return 1;
+		}
+		return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP);
 	}
 
 	/*
@@ -4547,7 +4666,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
 			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			if (is_icebp(intr_info))
-				skip_emulated_instruction(vcpu);
+				WARN_ON(!skip_emulated_instruction(vcpu));
 
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			return 1;
@@ -4602,7 +4721,7 @@ static int handle_io(struct kvm_vcpu *vcpu)
 	++vcpu->stat.io_exits;
 
 	if (string)
-		return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
+		return kvm_emulate_instruction(vcpu, 0);
 
 	port = exit_qualification >> 16;
 	size = (exit_qualification & 7) + 1;
@@ -4676,7 +4795,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
 static int handle_desc(struct kvm_vcpu *vcpu)
 {
 	WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
-	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(vcpu, 0);
 }
 
 static int handle_cr(struct kvm_vcpu *vcpu)
@@ -4856,41 +4975,12 @@ static int handle_cpuid(struct kvm_vcpu *vcpu)
 
 static int handle_rdmsr(struct kvm_vcpu *vcpu)
 {
-	u32 ecx = kvm_rcx_read(vcpu);
-	struct msr_data msr_info;
-
-	msr_info.index = ecx;
-	msr_info.host_initiated = false;
-	if (vmx_get_msr(vcpu, &msr_info)) {
-		trace_kvm_msr_read_ex(ecx);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	trace_kvm_msr_read(ecx, msr_info.data);
-
-	kvm_rax_write(vcpu, msr_info.data & -1u);
-	kvm_rdx_write(vcpu, (msr_info.data >> 32) & -1u);
-	return kvm_skip_emulated_instruction(vcpu);
+	return kvm_emulate_rdmsr(vcpu);
 }
 
 static int handle_wrmsr(struct kvm_vcpu *vcpu)
 {
-	struct msr_data msr;
-	u32 ecx = kvm_rcx_read(vcpu);
-	u64 data = kvm_read_edx_eax(vcpu);
-
-	msr.data = data;
-	msr.index = ecx;
-	msr.host_initiated = false;
-	if (kvm_set_msr(vcpu, &msr) != 0) {
-		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_emulate_wrmsr(vcpu);
 }
 
 static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
@@ -4921,7 +5011,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu)
 
 static int handle_invd(struct kvm_vcpu *vcpu)
 {
-	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(vcpu, 0);
 }
 
 static int handle_invlpg(struct kvm_vcpu *vcpu)
@@ -4955,20 +5045,6 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_xsaves(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN(1, "this should never happen\n");
-	return 1;
-}
-
-static int handle_xrstors(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN(1, "this should never happen\n");
-	return 1;
-}
-
 static int handle_apic_access(struct kvm_vcpu *vcpu)
 {
 	if (likely(fasteoi)) {
@@ -4988,7 +5064,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
 			return kvm_skip_emulated_instruction(vcpu);
 		}
 	}
-	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(vcpu, 0);
 }
 
 static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
@@ -5057,23 +5133,15 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 	if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION &&
 		       type != INTR_TYPE_EXT_INTR &&
 		       type != INTR_TYPE_NMI_INTR))
-		skip_emulated_instruction(vcpu);
-
-	if (kvm_task_switch(vcpu, tss_selector,
-			    type == INTR_TYPE_SOFT_INTR ? idt_index : -1, reason,
-			    has_error_code, error_code) == EMULATE_FAIL) {
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
-		return 0;
-	}
+		WARN_ON(!skip_emulated_instruction(vcpu));
 
 	/*
 	 * TODO: What about debug traps on tss switch?
 	 *       Are we supposed to inject them and update dr6?
 	 */
-
-	return 1;
+	return kvm_task_switch(vcpu, tss_selector,
+			       type == INTR_TYPE_SOFT_INTR ? idt_index : -1,
+			       reason, has_error_code, error_code);
 }
 
 static int handle_ept_violation(struct kvm_vcpu *vcpu)
@@ -5132,21 +5200,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 	if (!is_guest_mode(vcpu) &&
 	    !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
 		trace_kvm_fast_mmio(gpa);
-		/*
-		 * Doing kvm_skip_emulated_instruction() depends on undefined
-		 * behavior: Intel's manual doesn't mandate
-		 * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
-		 * occurs and while on real hardware it was observed to be set,
-		 * other hypervisors (namely Hyper-V) don't set it, we end up
-		 * advancing IP with some random value. Disable fast mmio when
-		 * running nested and keep it for real hardware in hope that
-		 * VM_EXIT_INSTRUCTION_LEN will always be set correctly.
-		 */
-		if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
-			return kvm_skip_emulated_instruction(vcpu);
-		else
-			return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) ==
-								EMULATE_DONE;
+		return kvm_skip_emulated_instruction(vcpu);
 	}
 
 	return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
@@ -5165,8 +5219,6 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu)
 static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	enum emulation_result err = EMULATE_DONE;
-	int ret = 1;
 	bool intr_window_requested;
 	unsigned count = 130;
 
@@ -5187,71 +5239,67 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
 			return 1;
 
-		err = kvm_emulate_instruction(vcpu, 0);
-
-		if (err == EMULATE_USER_EXIT) {
-			++vcpu->stat.mmio_exits;
-			ret = 0;
-			goto out;
-		}
-
-		if (err != EMULATE_DONE)
-			goto emulation_error;
+		if (!kvm_emulate_instruction(vcpu, 0))
+			return 0;
 
 		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
-		    vcpu->arch.exception.pending)
-			goto emulation_error;
+		    vcpu->arch.exception.pending) {
+			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			vcpu->run->internal.suberror =
+						KVM_INTERNAL_ERROR_EMULATION;
+			vcpu->run->internal.ndata = 0;
+			return 0;
+		}
 
 		if (vcpu->arch.halt_request) {
 			vcpu->arch.halt_request = 0;
-			ret = kvm_vcpu_halt(vcpu);
-			goto out;
+			return kvm_vcpu_halt(vcpu);
 		}
 
+		/*
+		 * Note, return 1 and not 0, vcpu_run() is responsible for
+		 * morphing the pending signal into the proper return code.
+		 */
 		if (signal_pending(current))
-			goto out;
+			return 1;
+
 		if (need_resched())
 			schedule();
 	}
 
-out:
-	return ret;
-
-emulation_error:
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-	vcpu->run->internal.ndata = 0;
-	return 0;
+	return 1;
 }
 
 static void grow_ple_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int old = vmx->ple_window;
+	unsigned int old = vmx->ple_window;
 
 	vmx->ple_window = __grow_ple_window(old, ple_window,
 					    ple_window_grow,
 					    ple_window_max);
 
-	if (vmx->ple_window != old)
+	if (vmx->ple_window != old) {
 		vmx->ple_window_dirty = true;
-
-	trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old);
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    vmx->ple_window, old);
+	}
 }
 
 static void shrink_ple_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int old = vmx->ple_window;
+	unsigned int old = vmx->ple_window;
 
 	vmx->ple_window = __shrink_ple_window(old, ple_window,
 					      ple_window_shrink,
 					      ple_window);
 
-	if (vmx->ple_window != old)
+	if (vmx->ple_window != old) {
 		vmx->ple_window_dirty = true;
-
-	trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old);
+		trace_kvm_ple_window_update(vcpu->vcpu_id,
+					    vmx->ple_window, old);
+	}
 }
 
 /*
@@ -5490,6 +5538,14 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu)
+{
+	kvm_skip_emulated_instruction(vcpu);
+	WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x",
+		vmcs_read32(VM_EXIT_REASON));
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -5541,13 +5597,15 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_INVVPID]                 = handle_vmx_instruction,
 	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
 	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
-	[EXIT_REASON_XSAVES]                  = handle_xsaves,
-	[EXIT_REASON_XRSTORS]                 = handle_xrstors,
+	[EXIT_REASON_XSAVES]                  = handle_unexpected_vmexit,
+	[EXIT_REASON_XRSTORS]                 = handle_unexpected_vmexit,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
 	[EXIT_REASON_INVPCID]                 = handle_invpcid,
 	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
 	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
 	[EXIT_REASON_ENCLS]		      = handle_encls,
+	[EXIT_REASON_UMWAIT]                  = handle_unexpected_vmexit,
+	[EXIT_REASON_TPAUSE]                  = handle_unexpected_vmexit,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -5887,8 +5945,13 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	else {
 		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
 				exit_reason);
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 1;
+		dump_vmcs();
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror =
+			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+		vcpu->run->internal.ndata = 1;
+		vcpu->run->internal.data[0] = exit_reason;
+		return 0;
 	}
 }
 
@@ -6373,6 +6436,23 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
+static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
+{
+	u32 host_umwait_control;
+
+	if (!vmx_has_waitpkg(vmx))
+		return;
+
+	host_umwait_control = get_umwait_control_msr();
+
+	if (vmx->msr_ia32_umwait_control != host_umwait_control)
+		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
+			vmx->msr_ia32_umwait_control,
+			host_umwait_control, false);
+	else
+		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
+}
+
 static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6467,6 +6547,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	pt_guest_enter(vmx);
 
 	atomic_switch_perf_msrs(vmx);
+	atomic_switch_umwait_control_msr(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
@@ -6522,6 +6603,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		current_evmcs->hv_clean_fields |=
 			HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
+	if (static_branch_unlikely(&enable_evmcs))
+		current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index;
+
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
 	if (vmx->host_debugctlmsr)
 		update_debugctlmsr(vmx->host_debugctlmsr);
@@ -6589,6 +6673,7 @@ static struct kvm *vmx_vm_alloc(void)
 
 static void vmx_vm_free(struct kvm *kvm)
 {
+	kfree(kvm->arch.hyperv.hv_pa_pg);
 	vfree(to_kvm_vmx(kvm));
 }
 
@@ -6615,6 +6700,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	unsigned long *msr_bitmap;
 	int cpu;
 
+	BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0,
+		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+
 	vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!vmx)
 		return ERR_PTR(-ENOMEM);
@@ -7369,10 +7457,14 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		 * irqbalance to make the interrupts single-CPU.
 		 *
 		 * We will support full lowest-priority interrupt later.
+		 *
+		 * In addition, we can only inject generic interrupts using
+		 * the PI mechanism, refuse to route others through it.
 		 */
 
 		kvm_set_msi_irq(kvm, e, &irq);
-		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
+		    !kvm_irq_is_postable(&irq)) {
 			/*
 			 * Make sure the IRTE is in remapped mode if
 			 * we don't handle it in posted mode.
@@ -7474,6 +7566,11 @@ static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
 	return false;
 }
 
+static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.vmxon;
+}
+
 static __init int hardware_setup(void)
 {
 	unsigned long host_bndcfgs;
@@ -7799,6 +7896,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.nested_enable_evmcs = NULL,
 	.nested_get_evmcs_version = NULL,
 	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
+	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
 };
 
 static void vmx_cleanup_l1d_flush(void)
@@ -7835,6 +7933,7 @@ static void vmx_exit(void)
 			if (!vp_ap)
 				continue;
 
+			vp_ap->nested_control.features.directhypercall = 0;
 			vp_ap->current_nested_vmcs = 0;
 			vp_ap->enlighten_vmentry = 0;
 		}
@@ -7874,6 +7973,11 @@ static int __init vmx_init(void)
 			pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n");
 			static_branch_enable(&enable_evmcs);
 		}
+
+		if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH)
+			vmx_x86_ops.enable_direct_tlbflush
+				= hv_enable_direct_tlbflush;
+
 	} else {
 		enlightened_vmcs = false;
 	}