Merge branch 'kvm-tdx-userspace-exit' into HEAD

Introduces support for VM exits that are forwarded the host VMM in
userspace.  These are initiated from the TDCALL exit code; although
these userspace exits have the same TDX exit code, they result in several
different types of exits to userspace.

When a guest TD issues a TDVMCALL, it
exits to VMM with a new exit reason.  The arguments from the guest TD and
return values from the VMM are passed through the guest registers.  The
ABI details for the guest TD hypercalls are specified in the TDX GHCI
specification.

There are two types of hypercalls defined in the GHCI specification:

- Standard TDVMCALLs: When input of R10 from guest TD is set to 0, it
  indicates that the TDVMCALL sub-function used in R11 is defined in GHCI
  specification.

- Vendor-Specific TDVMCALLs: When input of R10 from guest TD is non-zero,
  it indicates a vendor-specific TDVMCALL. KVM hypercalls from the guest
  follow this interface, using R10 as KVM hypercall number and R11-R14 as
  4 arguments.  The error code returned in R10.

This series includes basic standard TDVMCALLs that map to existing eixt
reasons:

- TDG.VP.VMCALL<MapGPA> reuses exit reason KVM_EXIT_HYPERCALL with the
  hypercall number KVM_HC_MAP_GPA_RANGE.

- TDG.VP.VMCALL<ReportFatalError> reuses exit reason KVM_EXIT_SYSTEM_EVENT
  with a new event type KVM_SYSTEM_EVENT_TDX_FATAL.

- TDG.VP.VMCALL<Instruction.IO> reuses exit reason KVM_EXIT_IO.

- TDG.VP.VMCALL<#VE.RequestMMIO> reuses exit reason KVM_EXIT_MMIO.

Notably, handling for TDG.VP.VMCALL<SetupEventNotifyInterrupt> and
TDG.VP.VMCALL<GetQuote> is not included yet.

14 files changed, 611 insertions, 35 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 2b52eb77e29c..8dd3151fb9e4 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6823,6 +6823,7 @@ should put the acknowledged interrupt vector into the 'epr' field.
   #define KVM_SYSTEM_EVENT_WAKEUP         4
   #define KVM_SYSTEM_EVENT_SUSPEND        5
   #define KVM_SYSTEM_EVENT_SEV_TERM       6
+  #define KVM_SYSTEM_EVENT_TDX_FATAL      7
 			__u32 type;
                         __u32 ndata;
                         __u64 data[16];
@@ -6849,6 +6850,11 @@ Valid values for 'type' are:
    reset/shutdown of the VM.
  - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV guest requested termination.
    The guest physical address of the guest's GHCB is stored in `data[0]`.
+ - KVM_SYSTEM_EVENT_TDX_FATAL -- a TDX guest reported a fatal error state.
+   KVM doesn't do any parsing or conversion, it just dumps 16 general-purpose
+   registers to userspace, in ascending order of the 4-bit indices for x86-64
+   general-purpose registers in instruction encoding, as defined in the Intel
+   SDM.
  - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and
    KVM has recognized a wakeup event. Userspace may honor this event by
    marking the exiting vCPU as runnable, or deny it and call KVM_RUN again.
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 4aedab1f2a1a..f23657350d28 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -77,6 +77,7 @@
 #define TDVMCALL_STATUS_SUCCESS		0x0000000000000000ULL
 #define TDVMCALL_STATUS_RETRY		0x0000000000000001ULL
 #define TDVMCALL_STATUS_INVALID_OPERAND	0x8000000000000000ULL
+#define TDVMCALL_STATUS_ALIGN_ERROR	0x8000000000000002ULL
 
 /*
  * Bitmasks of exposed registers (with VMM).
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index bb4a3bc26219..6d74f4d8c573 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -19,6 +19,7 @@
  * TDX module.
  */
 #define TDX_ERROR			_BITUL(63)
+#define TDX_NON_RECOVERABLE		_BITUL(62)
 #define TDX_SW_ERROR			(TDX_ERROR | GENMASK_ULL(47, 40))
 #define TDX_SEAMCALL_VMFAILINVALID	(TDX_SW_ERROR | _UL(0xFFFF0000))
 
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index a5faf6d88f1b..6a9f268a2d2c 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -92,6 +92,7 @@
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
 #define EXIT_REASON_NOTIFY              75
+#define EXIT_REASON_TDCALL              77
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -155,7 +156,8 @@
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
 	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }, \
-	{ EXIT_REASON_NOTIFY,                "NOTIFY" }
+	{ EXIT_REASON_NOTIFY,                "NOTIFY" }, \
+	{ EXIT_REASON_TDCALL,                "TDCALL" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index c0497ed0c9be..a567865baf9b 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -181,6 +181,15 @@ static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	return vmx_vcpu_run(vcpu, force_immediate_exit);
 }
 
+static int vt_handle_exit(struct kvm_vcpu *vcpu,
+			  enum exit_fastpath_completion fastpath)
+{
+	if (is_td_vcpu(vcpu))
+		return tdx_handle_exit(vcpu, fastpath);
+
+	return vmx_handle_exit(vcpu, fastpath);
+}
+
 static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu)) {
@@ -228,6 +237,29 @@ static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 	vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
 }
 
+static void vt_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code)
+{
+	*intr_info = 0;
+	*error_code = 0;
+
+	if (is_td_vcpu(vcpu))
+		return;
+
+	vmx_get_entry_info(vcpu, intr_info, error_code);
+}
+
+static void vt_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+			u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_get_exit_info(vcpu, reason, info1, info2, intr_info,
+				  error_code);
+		return;
+	}
+
+	vmx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code);
+}
+
 static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	if (!is_td(kvm))
@@ -323,7 +355,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.vcpu_pre_run = vt_vcpu_pre_run,
 	.vcpu_run = vt_vcpu_run,
-	.handle_exit = vmx_handle_exit,
+	.handle_exit = vt_handle_exit,
 	.skip_emulated_instruction = vmx_skip_emulated_instruction,
 	.update_emulated_instruction = vmx_update_emulated_instruction,
 	.set_interrupt_shadow = vmx_set_interrupt_shadow,
@@ -357,8 +389,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.set_identity_map_addr = vmx_set_identity_map_addr,
 	.get_mt_mask = vmx_get_mt_mask,
 
-	.get_exit_info = vmx_get_exit_info,
-	.get_entry_info = vmx_get_entry_info,
+	.get_exit_info = vt_get_exit_info,
+	.get_entry_info = vt_get_entry_info,
 
 	.vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid,
 
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index a6388eb95988..35f28e165417 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -222,6 +222,28 @@ static bool tdx_operand_busy(u64 err)
  */
 static DEFINE_PER_CPU(struct list_head, associated_tdvcpus);
 
+static __always_inline unsigned long tdvmcall_exit_type(struct kvm_vcpu *vcpu)
+{
+	return to_tdx(vcpu)->vp_enter_args.r10;
+}
+
+static __always_inline unsigned long tdvmcall_leaf(struct kvm_vcpu *vcpu)
+{
+	return to_tdx(vcpu)->vp_enter_args.r11;
+}
+
+static __always_inline void tdvmcall_set_return_code(struct kvm_vcpu *vcpu,
+						     long val)
+{
+	to_tdx(vcpu)->vp_enter_args.r10 = val;
+}
+
+static __always_inline void tdvmcall_set_return_val(struct kvm_vcpu *vcpu,
+						    unsigned long val)
+{
+	to_tdx(vcpu)->vp_enter_args.r11 = val;
+}
+
 static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx)
 {
 	tdx_guest_keyid_free(kvm_tdx->hkid);
@@ -783,17 +805,97 @@ int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static __always_inline u32 tdcall_to_vmx_exit_reason(struct kvm_vcpu *vcpu)
+{
+	switch (tdvmcall_leaf(vcpu)) {
+	case EXIT_REASON_IO_INSTRUCTION:
+		return tdvmcall_leaf(vcpu);
+	case EXIT_REASON_EPT_VIOLATION:
+		return EXIT_REASON_EPT_MISCONFIG;
+	default:
+		break;
+	}
+
+	return EXIT_REASON_TDCALL;
+}
+
+static __always_inline u32 tdx_to_vmx_exit_reason(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u32 exit_reason;
+
+	switch (tdx->vp_enter_ret & TDX_SEAMCALL_STATUS_MASK) {
+	case TDX_SUCCESS:
+	case TDX_NON_RECOVERABLE_VCPU:
+	case TDX_NON_RECOVERABLE_TD:
+	case TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE:
+	case TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE:
+		break;
+	default:
+		return -1u;
+	}
+
+	exit_reason = tdx->vp_enter_ret;
+
+	switch (exit_reason) {
+	case EXIT_REASON_TDCALL:
+		if (tdvmcall_exit_type(vcpu))
+			return EXIT_REASON_VMCALL;
+
+		return tdcall_to_vmx_exit_reason(vcpu);
+	default:
+		break;
+	}
+
+	return exit_reason;
+}
+
 static noinstr void tdx_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 
 	guest_state_enter_irqoff();
 
 	tdx->vp_enter_ret = tdh_vp_enter(&tdx->vp, &tdx->vp_enter_args);
 
+	vt->exit_reason.full = tdx_to_vmx_exit_reason(vcpu);
+
+	vt->exit_qualification = tdx->vp_enter_args.rcx;
+	tdx->ext_exit_qualification = tdx->vp_enter_args.rdx;
+	tdx->exit_gpa = tdx->vp_enter_args.r8;
+	vt->exit_intr_info = tdx->vp_enter_args.r9;
+
 	guest_state_exit_irqoff();
 }
 
+static bool tdx_failed_vmentry(struct kvm_vcpu *vcpu)
+{
+	return vmx_get_exit_reason(vcpu).failed_vmentry &&
+	       vmx_get_exit_reason(vcpu).full != -1u;
+}
+
+static fastpath_t tdx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
+{
+	u64 vp_enter_ret = to_tdx(vcpu)->vp_enter_ret;
+
+	/*
+	 * TDX_OPERAND_BUSY could be returned for SEPT due to 0-step mitigation
+	 * or for TD EPOCH due to contention with TDH.MEM.TRACK on TDH.VP.ENTER.
+	 *
+	 * When KVM requests KVM_REQ_OUTSIDE_GUEST_MODE, which has both
+	 * KVM_REQUEST_WAIT and KVM_REQUEST_NO_ACTION set, it requires target
+	 * vCPUs leaving fastpath so that interrupt can be enabled to ensure the
+	 * IPIs can be delivered. Return EXIT_FASTPATH_EXIT_HANDLED instead of
+	 * EXIT_FASTPATH_REENTER_GUEST to exit fastpath, otherwise, the
+	 * requester may be blocked endlessly.
+	 */
+	if (unlikely(tdx_operand_busy(vp_enter_ret)))
+		return EXIT_FASTPATH_EXIT_HANDLED;
+
+	return EXIT_FASTPATH_NONE;
+}
+
 #define TDX_REGS_AVAIL_SET	(BIT_ULL(VCPU_EXREG_EXIT_INFO_1) | \
 				 BIT_ULL(VCPU_EXREG_EXIT_INFO_2) | \
 				 BIT_ULL(VCPU_REGS_RAX) | \
@@ -866,9 +968,344 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 
 	vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET;
 
+	if (unlikely((tdx->vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR))
+		return EXIT_FASTPATH_NONE;
+
+	if (unlikely(vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY))
+		kvm_machine_check();
+
 	trace_kvm_exit(vcpu, KVM_ISA_VMX);
 
-	return EXIT_FASTPATH_NONE;
+	if (unlikely(tdx_failed_vmentry(vcpu)))
+		return EXIT_FASTPATH_NONE;
+
+	return tdx_exit_handlers_fastpath(vcpu);
+}
+
+static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
+{
+	tdvmcall_set_return_code(vcpu, vcpu->run->hypercall.ret);
+	return 1;
+}
+
+static int tdx_emulate_vmcall(struct kvm_vcpu *vcpu)
+{
+	kvm_rax_write(vcpu, to_tdx(vcpu)->vp_enter_args.r10);
+	kvm_rbx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r11);
+	kvm_rcx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r12);
+	kvm_rdx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r13);
+	kvm_rsi_write(vcpu, to_tdx(vcpu)->vp_enter_args.r14);
+
+	return __kvm_emulate_hypercall(vcpu, 0, complete_hypercall_exit);
+}
+
+/*
+ * Split into chunks and check interrupt pending between chunks.  This allows
+ * for timely injection of interrupts to prevent issues with guest lockup
+ * detection.
+ */
+#define TDX_MAP_GPA_MAX_LEN (2 * 1024 * 1024)
+static void __tdx_map_gpa(struct vcpu_tdx *tdx);
+
+static int tdx_complete_vmcall_map_gpa(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	if (vcpu->run->hypercall.ret) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		tdx->vp_enter_args.r11 = tdx->map_gpa_next;
+		return 1;
+	}
+
+	tdx->map_gpa_next += TDX_MAP_GPA_MAX_LEN;
+	if (tdx->map_gpa_next >= tdx->map_gpa_end)
+		return 1;
+
+	/*
+	 * Stop processing the remaining part if there is a pending interrupt,
+	 * which could be qualified to deliver.  Skip checking pending RVI for
+	 * TDVMCALL_MAP_GPA.
+	 * TODO: Add a comment to link the reason when the target function is
+	 * implemented.
+	 */
+	if (kvm_vcpu_has_events(vcpu)) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_RETRY);
+		tdx->vp_enter_args.r11 = tdx->map_gpa_next;
+		return 1;
+	}
+
+	__tdx_map_gpa(tdx);
+	return 0;
+}
+
+static void __tdx_map_gpa(struct vcpu_tdx *tdx)
+{
+	u64 gpa = tdx->map_gpa_next;
+	u64 size = tdx->map_gpa_end - tdx->map_gpa_next;
+
+	if (size > TDX_MAP_GPA_MAX_LEN)
+		size = TDX_MAP_GPA_MAX_LEN;
+
+	tdx->vcpu.run->exit_reason       = KVM_EXIT_HYPERCALL;
+	tdx->vcpu.run->hypercall.nr      = KVM_HC_MAP_GPA_RANGE;
+	/*
+	 * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2)
+	 * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that
+	 * it was always zero on KVM_EXIT_HYPERCALL.  Since KVM is now overwriting
+	 * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU.
+	 */
+	tdx->vcpu.run->hypercall.ret = 0;
+	tdx->vcpu.run->hypercall.args[0] = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
+	tdx->vcpu.run->hypercall.args[1] = size / PAGE_SIZE;
+	tdx->vcpu.run->hypercall.args[2] = vt_is_tdx_private_gpa(tdx->vcpu.kvm, gpa) ?
+					   KVM_MAP_GPA_RANGE_ENCRYPTED :
+					   KVM_MAP_GPA_RANGE_DECRYPTED;
+	tdx->vcpu.run->hypercall.flags   = KVM_EXIT_HYPERCALL_LONG_MODE;
+
+	tdx->vcpu.arch.complete_userspace_io = tdx_complete_vmcall_map_gpa;
+}
+
+static int tdx_map_gpa(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 gpa = tdx->vp_enter_args.r12;
+	u64 size = tdx->vp_enter_args.r13;
+	u64 ret;
+
+	/*
+	 * Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires
+	 * userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE
+	 * bit set.  If not, the error code is not defined in GHCI for TDX, use
+	 * TDVMCALL_STATUS_INVALID_OPERAND for this case.
+	 */
+	if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
+		ret = TDVMCALL_STATUS_INVALID_OPERAND;
+		goto error;
+	}
+
+	if (gpa + size <= gpa || !kvm_vcpu_is_legal_gpa(vcpu, gpa) ||
+	    !kvm_vcpu_is_legal_gpa(vcpu, gpa + size - 1) ||
+	    (vt_is_tdx_private_gpa(vcpu->kvm, gpa) !=
+	     vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1))) {
+		ret = TDVMCALL_STATUS_INVALID_OPERAND;
+		goto error;
+	}
+
+	if (!PAGE_ALIGNED(gpa) || !PAGE_ALIGNED(size)) {
+		ret = TDVMCALL_STATUS_ALIGN_ERROR;
+		goto error;
+	}
+
+	tdx->map_gpa_end = gpa + size;
+	tdx->map_gpa_next = gpa;
+
+	__tdx_map_gpa(tdx);
+	return 0;
+
+error:
+	tdvmcall_set_return_code(vcpu, ret);
+	tdx->vp_enter_args.r11 = gpa;
+	return 1;
+}
+
+static int tdx_report_fatal_error(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 *regs = vcpu->run->system_event.data;
+	u64 *module_regs = &tdx->vp_enter_args.r8;
+	int index = VCPU_REGS_RAX;
+
+	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+	vcpu->run->system_event.type = KVM_SYSTEM_EVENT_TDX_FATAL;
+	vcpu->run->system_event.ndata = 16;
+
+	/* Dump 16 general-purpose registers to userspace in ascending order. */
+	regs[index++] = tdx->vp_enter_ret;
+	regs[index++] = tdx->vp_enter_args.rcx;
+	regs[index++] = tdx->vp_enter_args.rdx;
+	regs[index++] = tdx->vp_enter_args.rbx;
+	regs[index++] = 0;
+	regs[index++] = 0;
+	regs[index++] = tdx->vp_enter_args.rsi;
+	regs[index] = tdx->vp_enter_args.rdi;
+	for (index = 0; index < 8; index++)
+		regs[VCPU_REGS_R8 + index] = module_regs[index];
+
+	return 0;
+}
+
+static int tdx_complete_pio_out(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+	return 1;
+}
+
+static int tdx_complete_pio_in(struct kvm_vcpu *vcpu)
+{
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+	unsigned long val = 0;
+	int ret;
+
+	ret = ctxt->ops->pio_in_emulated(ctxt, vcpu->arch.pio.size,
+					 vcpu->arch.pio.port, &val, 1);
+
+	WARN_ON_ONCE(!ret);
+
+	tdvmcall_set_return_val(vcpu, val);
+
+	return 1;
+}
+
+static int tdx_emulate_io(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+	unsigned long val = 0;
+	unsigned int port;
+	u64 size, write;
+	int ret;
+
+	++vcpu->stat.io_exits;
+
+	size = tdx->vp_enter_args.r12;
+	write = tdx->vp_enter_args.r13;
+	port = tdx->vp_enter_args.r14;
+
+	if ((write != 0 && write != 1) || (size != 1 && size != 2 && size != 4)) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
+	}
+
+	if (write) {
+		val = tdx->vp_enter_args.r15;
+		ret = ctxt->ops->pio_out_emulated(ctxt, size, port, &val, 1);
+	} else {
+		ret = ctxt->ops->pio_in_emulated(ctxt, size, port, &val, 1);
+	}
+
+	if (!ret)
+		vcpu->arch.complete_userspace_io = write ? tdx_complete_pio_out :
+							   tdx_complete_pio_in;
+	else if (!write)
+		tdvmcall_set_return_val(vcpu, val);
+
+	return ret;
+}
+
+static int tdx_complete_mmio_read(struct kvm_vcpu *vcpu)
+{
+	unsigned long val = 0;
+	gpa_t gpa;
+	int size;
+
+	gpa = vcpu->mmio_fragments[0].gpa;
+	size = vcpu->mmio_fragments[0].len;
+
+	memcpy(&val, vcpu->run->mmio.data, size);
+	tdvmcall_set_return_val(vcpu, val);
+	trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val);
+	return 1;
+}
+
+static inline int tdx_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, int size,
+				 unsigned long val)
+{
+	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+		trace_kvm_fast_mmio(gpa);
+		return 0;
+	}
+
+	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, size, gpa, &val);
+	if (kvm_io_bus_write(vcpu, KVM_MMIO_BUS, gpa, size, &val))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static inline int tdx_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, int size)
+{
+	unsigned long val;
+
+	if (kvm_io_bus_read(vcpu, KVM_MMIO_BUS, gpa, size, &val))
+		return -EOPNOTSUPP;
+
+	tdvmcall_set_return_val(vcpu, val);
+	trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val);
+	return 0;
+}
+
+static int tdx_emulate_mmio(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	int size, write, r;
+	unsigned long val;
+	gpa_t gpa;
+
+	size = tdx->vp_enter_args.r12;
+	write = tdx->vp_enter_args.r13;
+	gpa = tdx->vp_enter_args.r14;
+	val = write ? tdx->vp_enter_args.r15 : 0;
+
+	if (size != 1 && size != 2 && size != 4 && size != 8)
+		goto error;
+	if (write != 0 && write != 1)
+		goto error;
+
+	/*
+	 * TDG.VP.VMCALL<MMIO> allows only shared GPA, it makes no sense to
+	 * do MMIO emulation for private GPA.
+	 */
+	if (vt_is_tdx_private_gpa(vcpu->kvm, gpa) ||
+	    vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1))
+		goto error;
+
+	gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
+
+	if (write)
+		r = tdx_mmio_write(vcpu, gpa, size, val);
+	else
+		r = tdx_mmio_read(vcpu, gpa, size);
+	if (!r)
+		/* Kernel completed device emulation. */
+		return 1;
+
+	/* Request the device emulation to userspace device model. */
+	vcpu->mmio_is_write = write;
+	if (!write)
+		vcpu->arch.complete_userspace_io = tdx_complete_mmio_read;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = size;
+	vcpu->run->mmio.is_write = write;
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	if (write) {
+		memcpy(vcpu->run->mmio.data, &val, size);
+	} else {
+		vcpu->mmio_fragments[0].gpa = gpa;
+		vcpu->mmio_fragments[0].len = size;
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, size, gpa, NULL);
+	}
+	return 0;
+
+error:
+	tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+	return 1;
+}
+
+static int handle_tdvmcall(struct kvm_vcpu *vcpu)
+{
+	switch (tdvmcall_leaf(vcpu)) {
+	case TDVMCALL_MAP_GPA:
+		return tdx_map_gpa(vcpu);
+	case TDVMCALL_REPORT_FATAL_ERROR:
+		return tdx_report_fatal_error(vcpu);
+	default:
+		break;
+	}
+
+	tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+	return 1;
 }
 
 void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
@@ -1184,6 +1621,91 @@ int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
 	return tdx_sept_drop_private_spte(kvm, gfn, level, page);
 }
 
+int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 vp_enter_ret = tdx->vp_enter_ret;
+	union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu);
+
+	if (fastpath != EXIT_FASTPATH_NONE)
+		return 1;
+
+	/*
+	 * Handle TDX SW errors, including TDX_SEAMCALL_UD, TDX_SEAMCALL_GP and
+	 * TDX_SEAMCALL_VMFAILINVALID.
+	 */
+	if (unlikely((vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR)) {
+		KVM_BUG_ON(!kvm_rebooting, vcpu->kvm);
+		goto unhandled_exit;
+	}
+
+	if (unlikely(tdx_failed_vmentry(vcpu))) {
+		/*
+		 * If the guest state is protected, that means off-TD debug is
+		 * not enabled, TDX_NON_RECOVERABLE must be set.
+		 */
+		WARN_ON_ONCE(vcpu->arch.guest_state_protected &&
+				!(vp_enter_ret & TDX_NON_RECOVERABLE));
+		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason.full;
+		vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu;
+		return 0;
+	}
+
+	if (unlikely(vp_enter_ret & (TDX_ERROR | TDX_NON_RECOVERABLE)) &&
+		exit_reason.basic != EXIT_REASON_TRIPLE_FAULT) {
+		kvm_pr_unimpl("TD vp_enter_ret 0x%llx\n", vp_enter_ret);
+		goto unhandled_exit;
+	}
+
+	WARN_ON_ONCE(exit_reason.basic != EXIT_REASON_TRIPLE_FAULT &&
+		     (vp_enter_ret & TDX_SEAMCALL_STATUS_MASK) != TDX_SUCCESS);
+
+	switch (exit_reason.basic) {
+	case EXIT_REASON_TRIPLE_FAULT:
+		vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+		vcpu->mmio_needed = 0;
+		return 0;
+	case EXIT_REASON_TDCALL:
+		return handle_tdvmcall(vcpu);
+	case EXIT_REASON_VMCALL:
+		return tdx_emulate_vmcall(vcpu);
+	case EXIT_REASON_IO_INSTRUCTION:
+		return tdx_emulate_io(vcpu);
+	case EXIT_REASON_EPT_MISCONFIG:
+		return tdx_emulate_mmio(vcpu);
+	default:
+		break;
+	}
+
+unhandled_exit:
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+	vcpu->run->internal.ndata = 2;
+	vcpu->run->internal.data[0] = vp_enter_ret;
+	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+	return 0;
+}
+
+void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+		u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	*reason = tdx->vt.exit_reason.full;
+	if (*reason != -1u) {
+		*info1 = vmx_get_exit_qual(vcpu);
+		*info2 = tdx->ext_exit_qualification;
+		*intr_info = vmx_get_intr_info(vcpu);
+	} else {
+		*info1 = 0;
+		*info2 = 0;
+		*intr_info = 0;
+	}
+
+	*error_code = 0;
+}
+
 static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
 {
 	const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 0a54d286e380..3aa36ddcd472 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -48,6 +48,8 @@ enum vcpu_tdx_state {
 struct vcpu_tdx {
 	struct kvm_vcpu	vcpu;
 	struct vcpu_vt vt;
+	u64 ext_exit_qualification;
+	gpa_t exit_gpa;
 	struct tdx_module_args vp_enter_args;
 
 	struct tdx_vp vp;
@@ -58,6 +60,9 @@ struct vcpu_tdx {
 
 	enum vcpu_tdx_state state;
 	bool guest_entered;
+
+	u64 map_gpa_next;
+	u64 map_gpa_end;
 };
 
 void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err);
diff --git a/arch/x86/kvm/vmx/tdx_errno.h b/arch/x86/kvm/vmx/tdx_errno.h
index f9dbb3a065cc..6ff4672c4181 100644
--- a/arch/x86/kvm/vmx/tdx_errno.h
+++ b/arch/x86/kvm/vmx/tdx_errno.h
@@ -10,6 +10,9 @@
  * TDX SEAMCALL Status Codes (returned in RAX)
  */
 #define TDX_NON_RECOVERABLE_VCPU		0x4000000100000000ULL
+#define TDX_NON_RECOVERABLE_TD			0x4000000200000000ULL
+#define TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE	0x6000000500000000ULL
+#define TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE	0x6000000700000000ULL
 #define TDX_INTERRUPTED_RESUMABLE		0x8000000300000000ULL
 #define TDX_OPERAND_INVALID			0xC000010000000000ULL
 #define TDX_OPERAND_BUSY			0x8000020000000000ULL
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index cd18e9b1e124..2960d95c2c78 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -135,6 +135,10 @@ int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu);
 fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
 void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void tdx_vcpu_put(struct kvm_vcpu *vcpu);
+int tdx_handle_exit(struct kvm_vcpu *vcpu,
+		enum exit_fastpath_completion fastpath);
+void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+		u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
 
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
 
@@ -168,6 +172,10 @@ static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediat
 }
 static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
 static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {}
+static inline int tdx_handle_exit(struct kvm_vcpu *vcpu,
+		enum exit_fastpath_completion fastpath) { return 0; }
+static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1,
+				     u64 *info2, u32 *intr_info, u32 *error_code) {}
 
 static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ef83f24449d..5c37bc4fb80e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10030,13 +10030,16 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
-int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
-			      unsigned long a0, unsigned long a1,
-			      unsigned long a2, unsigned long a3,
-			      int op_64_bit, int cpl,
+int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl,
 			      int (*complete_hypercall)(struct kvm_vcpu *))
 {
 	unsigned long ret;
+	unsigned long nr = kvm_rax_read(vcpu);
+	unsigned long a0 = kvm_rbx_read(vcpu);
+	unsigned long a1 = kvm_rcx_read(vcpu);
+	unsigned long a2 = kvm_rdx_read(vcpu);
+	unsigned long a3 = kvm_rsi_read(vcpu);
+	int op_64_bit = is_64_bit_hypercall(vcpu);
 
 	++vcpu->stat.hypercalls;
 
@@ -10139,9 +10142,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	if (kvm_hv_hypercall_enabled(vcpu))
 		return kvm_hv_hypercall(vcpu);
 
-	return __kvm_emulate_hypercall(vcpu, rax, rbx, rcx, rdx, rsi,
-				       is_64_bit_hypercall(vcpu),
-				       kvm_x86_call(get_cpl)(vcpu),
+	return __kvm_emulate_hypercall(vcpu, kvm_x86_call(get_cpl)(vcpu),
 				       complete_hypercall_exit);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -11142,7 +11143,7 @@ static bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted);
 }
 
-static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 {
 	if (!list_empty_careful(&vcpu->async_pf.done))
 		return true;
@@ -11151,9 +11152,6 @@ static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	    kvm_apic_init_sipi_allowed(vcpu))
 		return true;
 
-	if (vcpu->arch.pv.pv_unhalted)
-		return true;
-
 	if (kvm_is_exception_pending(vcpu))
 		return true;
 
@@ -11191,10 +11189,12 @@ static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_has_events);
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
+	return kvm_vcpu_running(vcpu) || vcpu->arch.pv.pv_unhalted ||
+	       kvm_vcpu_has_events(vcpu);
 }
 
 /* Called within kvm->srcu read side.  */
@@ -11330,7 +11330,7 @@ static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
 	 */
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
-		if (kvm_vcpu_has_events(vcpu))
+		if (kvm_vcpu_has_events(vcpu) || vcpu->arch.pv.pv_unhalted)
 			vcpu->arch.pv.pv_unhalted = false;
 		else
 			vcpu->arch.mp_state = state;
@@ -14024,6 +14024,7 @@ EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 91e50a513100..8b27f70c6321 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -621,25 +621,17 @@ static inline bool user_exit_on_hypercall(struct kvm *kvm, unsigned long hc_nr)
 	return kvm->arch.hypercall_exit_enabled & BIT(hc_nr);
 }
 
-int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
-			      unsigned long a0, unsigned long a1,
-			      unsigned long a2, unsigned long a3,
-			      int op_64_bit, int cpl,
+int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl,
 			      int (*complete_hypercall)(struct kvm_vcpu *));
 
-#define __kvm_emulate_hypercall(_vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl, complete_hypercall)	\
-({												\
-	int __ret;										\
-												\
-	__ret = ____kvm_emulate_hypercall(_vcpu,						\
-					  kvm_##nr##_read(_vcpu), kvm_##a0##_read(_vcpu),	\
-					  kvm_##a1##_read(_vcpu), kvm_##a2##_read(_vcpu),	\
-					  kvm_##a3##_read(_vcpu), op_64_bit, cpl,		\
-					  complete_hypercall);					\
-												\
-	if (__ret > 0)										\
-		__ret = complete_hypercall(_vcpu);						\
-	__ret;											\
+#define __kvm_emulate_hypercall(_vcpu, cpl, complete_hypercall)			\
+({										\
+	int __ret;								\
+	__ret = ____kvm_emulate_hypercall(_vcpu, cpl, complete_hypercall);	\
+										\
+	if (__ret > 0)								\
+		__ret = complete_hypercall(_vcpu);				\
+	__ret;									\
 })
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3bfe3140f444..ed1968f6f841 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1609,6 +1609,7 @@ void kvm_arch_disable_virtualization(void);
 int kvm_arch_enable_virtualization_cpu(void);
 void kvm_arch_disable_virtualization_cpu(void);
 #endif
+bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 45e6d8fca9b9..937400350317 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -375,6 +375,7 @@ struct kvm_run {
 #define KVM_SYSTEM_EVENT_WAKEUP         4
 #define KVM_SYSTEM_EVENT_SUSPEND        5
 #define KVM_SYSTEM_EVENT_SEV_TERM       6
+#define KVM_SYSTEM_EVENT_TDX_FATAL      7
 			__u32 type;
 			__u32 ndata;
 			union {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 549537da3062..08f237bf4107 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5842,6 +5842,7 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
 	r = __kvm_io_bus_read(vcpu, bus, &range, val);
 	return r < 0 ? r : 0;
 }
+EXPORT_SYMBOL_GPL(kvm_io_bus_read);
 
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)