KVM: TDX: Add a place holder to handle TDX VM exit

Introduce the wiring for handling TDX VM exits by implementing the
callbacks .get_exit_info(), .get_entry_info(), and .handle_exit().
Additionally, add error handling during the TDX VM exit flow, and add a
place holder to handle various exit reasons.

Store VMX exit reason and exit qualification in struct vcpu_vt for TDX,
so that TDX/VMX can use the same helpers to get exit reason and exit
qualification. Store extended exit qualification and exit GPA info in
struct vcpu_tdx because they are used by TDX code only.

Contention Handling: The TDH.VP.ENTER operation may contend with TDH.MEM.*
operations due to secure EPT or TD EPOCH. If the contention occurs,
the return value will have TDX_OPERAND_BUSY set, prompting the vCPU to
attempt re-entry into the guest with EXIT_FASTPATH_EXIT_HANDLED,
not EXIT_FASTPATH_REENTER_GUEST, so that the interrupts pending during
IN_GUEST_MODE can be delivered for sure. Otherwise, the requester of
KVM_REQ_OUTSIDE_GUEST_MODE may be blocked endlessly.

Error Handling:
- TDX_SW_ERROR: This includes #UD caused by SEAMCALL instruction if the
  CPU isn't in VMX operation, #GP caused by SEAMCALL instruction when TDX
  isn't enabled by the BIOS, and TDX_SEAMCALL_VMFAILINVALID when SEAM
  firmware is not loaded or disabled.
- TDX_ERROR: This indicates some check failed in the TDX module, preventing
  the vCPU from running.
- Failed VM Entry: Exit to userspace with KVM_EXIT_FAIL_ENTRY. Handle it
  separately before handling TDX_NON_RECOVERABLE because when off-TD debug
  is not enabled, TDX_NON_RECOVERABLE is set.
- TDX_NON_RECOVERABLE: Set by the TDX module when the error is
  non-recoverable, indicating that the TDX guest is dead or the vCPU is
  disabled.
  A special case is triple fault, which also sets TDX_NON_RECOVERABLE but
  exits to userspace with KVM_EXIT_SHUTDOWN, aligning with the VMX case.
- Any unhandled VM exit reason will also return to userspace with
  KVM_EXIT_INTERNAL_ERROR.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Message-ID: <20250222014225.897298-4-binbin.wu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: yamahata

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))
 

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,
 

arch/x86/kvm/vmx/tdx.c

@@ -783,17 +783,70 @@ int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static __always_inline u32 tdx_to_vmx_exit_reason(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	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;
+	}
+
+	return tdx->vp_enter_ret;
+}
+
 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 +919,18 @@ 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);
 }
 
 void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
@@ -1184,6 +1246,83 @@ 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;
+	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;

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;

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

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; }