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

This series introduces callbacks to facilitate the entry of a TD VCPU
and the corresponding save/restore of host state.

A TD VCPU is entered via the SEAMCALL TDH.VP.ENTER. The TDX Module manages
the save/restore of guest state and, in conjunction with the SEAMCALL
interface, handles certain aspects of host state. However, there are
specific elements of the host state that require additional attention, as
detailed in the Intel TDX ABI documentation for TDH.VP.ENTER.

TDX is quite different from VMX in this regard.  For VMX, the host VMM is
heavily involved in restoring, managing and saving guest CPU state, whereas
for TDX this is handled by the TDX Module.  In that way, the TDX Module can
protect the confidentiality and integrity of TD CPU state.

The TDX Module does not save/restore all host CPU state because the host
VMM can do it more efficiently and selectively.  CPU state referred to
below is host CPU state.  Often values are already held in memory so no
explicit save is needed, and restoration may not be needed if the kernel
is not using a feature.

TDX does not support PAUSE-loop exiting.  According to the TDX Module
Base arch. spec., hypercalls are expected to be used instead.  Note that
the Linux TDX guest supports existing hypercalls via TDG.VP.VMCALL.

This series requires TDX module 1.5.06.00.0744, or later, due to removal
of the workarounds for the lack of the NO_RBP_MOD feature required by the
kernel. NO_RBP_MOD is now required.

15 files changed, 513 insertions, 149 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ddb08581c64d..3a6373fc58a1 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -606,8 +606,15 @@ struct kvm_pmu {
 struct kvm_pmu_ops;
 
 enum {
-	KVM_DEBUGREG_BP_ENABLED = 1,
-	KVM_DEBUGREG_WONT_EXIT = 2,
+	KVM_DEBUGREG_BP_ENABLED		= BIT(0),
+	KVM_DEBUGREG_WONT_EXIT		= BIT(1),
+	/*
+	 * Guest debug registers (DR0-3, DR6 and DR7) are saved/restored by
+	 * hardware on exit from or enter to guest. KVM needn't switch them.
+	 * DR0-3, DR6 and DR7 are set to their architectural INIT value on VM
+	 * exit, host values need to be restored.
+	 */
+	KVM_DEBUGREG_AUTO_SWITCH	= BIT(2),
 };
 
 struct kvm_mtrr {
@@ -2328,6 +2335,7 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 int kvm_add_user_return_msr(u32 msr);
 int kvm_find_user_return_msr(u32 msr);
 int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
+void kvm_user_return_msr_update_cache(unsigned int index, u64 val);
 
 static inline bool kvm_is_supported_user_return_msr(u32 msr)
 {
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index e38e7558c02f..bb4a3bc26219 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -165,6 +165,7 @@ static inline int pg_level_to_tdx_sept_level(enum pg_level level)
         return level - 1;
 }
 
+u64 tdh_vp_enter(struct tdx_vp *vp, struct tdx_module_args *args);
 u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page);
 u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, struct page *page, struct page *source, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2);
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index 7a592467a044..a298ac795c09 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -3,9 +3,78 @@
 #define __KVM_X86_VMX_COMMON_H
 
 #include <linux/kvm_host.h>
+#include <asm/posted_intr.h>
 
 #include "mmu.h"
 
+union vmx_exit_reason {
+	struct {
+		u32	basic			: 16;
+		u32	reserved16		: 1;
+		u32	reserved17		: 1;
+		u32	reserved18		: 1;
+		u32	reserved19		: 1;
+		u32	reserved20		: 1;
+		u32	reserved21		: 1;
+		u32	reserved22		: 1;
+		u32	reserved23		: 1;
+		u32	reserved24		: 1;
+		u32	reserved25		: 1;
+		u32	bus_lock_detected	: 1;
+		u32	enclave_mode		: 1;
+		u32	smi_pending_mtf		: 1;
+		u32	smi_from_vmx_root	: 1;
+		u32	reserved30		: 1;
+		u32	failed_vmentry		: 1;
+	};
+	u32 full;
+};
+
+struct vcpu_vt {
+	/* Posted interrupt descriptor */
+	struct pi_desc pi_desc;
+
+	/* Used if this vCPU is waiting for PI notification wakeup. */
+	struct list_head pi_wakeup_list;
+
+	union vmx_exit_reason exit_reason;
+
+	unsigned long	exit_qualification;
+	u32		exit_intr_info;
+
+	/*
+	 * If true, guest state has been loaded into hardware, and host state
+	 * saved into vcpu_{vt,vmx,tdx}.  If false, host state is loaded into
+	 * hardware.
+	 */
+	bool		guest_state_loaded;
+
+#ifdef CONFIG_X86_64
+	u64		msr_host_kernel_gs_base;
+#endif
+
+	unsigned long	host_debugctlmsr;
+};
+
+#ifdef CONFIG_KVM_INTEL_TDX
+
+static __always_inline bool is_td(struct kvm *kvm)
+{
+	return kvm->arch.vm_type == KVM_X86_TDX_VM;
+}
+
+static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu)
+{
+	return is_td(vcpu->kvm);
+}
+
+#else
+
+static inline bool is_td(struct kvm *kvm) { return false; }
+static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
+
+#endif
+
 static inline bool vt_is_tdx_private_gpa(struct kvm *kvm, gpa_t gpa)
 {
 	/* For TDX the direct mask is the shared mask. */
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index ec8223ee9d28..c0497ed0c9be 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -10,6 +10,10 @@
 #include "tdx.h"
 #include "tdx_arch.h"
 
+#ifdef CONFIG_KVM_INTEL_TDX
+static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt));
+#endif
+
 static void vt_disable_virtualization_cpu(void)
 {
 	/* Note, TDX *and* VMX need to be disabled if TDX is enabled. */
@@ -141,6 +145,42 @@ static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 	vmx_update_cpu_dirty_logging(vcpu);
 }
 
+static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_prepare_switch_to_guest(vcpu);
+		return;
+	}
+
+	vmx_prepare_switch_to_guest(vcpu);
+}
+
+static void vt_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_vcpu_put(vcpu);
+		return;
+	}
+
+	vmx_vcpu_put(vcpu);
+}
+
+static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return tdx_vcpu_pre_run(vcpu);
+
+	return vmx_vcpu_pre_run(vcpu);
+}
+
+static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+{
+	if (is_td_vcpu(vcpu))
+		return tdx_vcpu_run(vcpu, force_immediate_exit);
+
+	return vmx_vcpu_run(vcpu, force_immediate_exit);
+}
+
 static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu)) {
@@ -245,9 +285,9 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_free = vt_vcpu_free,
 	.vcpu_reset = vt_vcpu_reset,
 
-	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
+	.prepare_switch_to_guest = vt_prepare_switch_to_guest,
 	.vcpu_load = vt_vcpu_load,
-	.vcpu_put = vmx_vcpu_put,
+	.vcpu_put = vt_vcpu_put,
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_feature_msr = vmx_get_feature_msr,
@@ -281,8 +321,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.flush_tlb_gva = vt_flush_tlb_gva,
 	.flush_tlb_guest = vt_flush_tlb_guest,
 
-	.vcpu_pre_run = vmx_vcpu_pre_run,
-	.vcpu_run = vmx_vcpu_run,
+	.vcpu_pre_run = vt_vcpu_pre_run,
+	.vcpu_run = vt_vcpu_run,
 	.handle_exit = vmx_handle_exit,
 	.skip_emulated_instruction = vmx_skip_emulated_instruction,
 	.update_emulated_instruction = vmx_update_emulated_instruction,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index ed8a3cb53961..99f02972cd74 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -275,7 +275,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 {
 	struct vmcs_host_state *dest, *src;
 
-	if (unlikely(!vmx->guest_state_loaded))
+	if (unlikely(!vmx->vt.guest_state_loaded))
 		return;
 
 	src = &prev->host_state;
@@ -425,7 +425,7 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 		 * tables also changed, but KVM should not treat EPT Misconfig
 		 * VM-Exits as writes.
 		 */
-		WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
+		WARN_ON_ONCE(vmx->vt.exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
 
 		/*
 		 * PML Full and EPT Violation VM-Exits both use bit 12 to report
@@ -4622,7 +4622,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 {
 	/* update exit information fields: */
 	vmcs12->vm_exit_reason = vm_exit_reason;
-	if (to_vmx(vcpu)->exit_reason.enclave_mode)
+	if (vmx_get_exit_reason(vcpu).enclave_mode)
 		vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE;
 	vmcs12->exit_qualification = exit_qualification;
 
@@ -6126,7 +6126,7 @@ fail:
 	 * nested VM-Exit.  Pass the original exit reason, i.e. don't hardcode
 	 * EXIT_REASON_VMFUNC as the exit reason.
 	 */
-	nested_vmx_vmexit(vcpu, vmx->exit_reason.full,
+	nested_vmx_vmexit(vcpu, vmx->vt.exit_reason.full,
 			  vmx_get_intr_info(vcpu),
 			  vmx_get_exit_qual(vcpu));
 	return 1;
@@ -6571,7 +6571,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
 bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	union vmx_exit_reason exit_reason = vmx->exit_reason;
+	union vmx_exit_reason exit_reason = vmx->vt.exit_reason;
 	unsigned long exit_qual;
 	u32 exit_intr_info;
 
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index ec08fa3caf43..5696e0f9f924 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -33,7 +33,7 @@ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
 
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
-	return &(to_vmx(vcpu)->pi_desc);
+	return &(to_vt(vcpu)->pi_desc);
 }
 
 static int pi_try_set_control(struct pi_desc *pi_desc, u64 *pold, u64 new)
@@ -53,7 +53,7 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 *pold, u64 new)
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 	struct pi_desc old, new;
 	unsigned long flags;
 	unsigned int dest;
@@ -90,7 +90,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	 */
 	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
 		raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
-		list_del(&vmx->pi_wakeup_list);
+		list_del(&vt->pi_wakeup_list);
 		raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 	}
 
@@ -146,14 +146,14 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm)
 static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 	struct pi_desc old, new;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
 	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
-	list_add_tail(&vmx->pi_wakeup_list,
+	list_add_tail(&vt->pi_wakeup_list,
 		      &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
 	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 
@@ -220,13 +220,13 @@ void pi_wakeup_handler(void)
 	int cpu = smp_processor_id();
 	struct list_head *wakeup_list = &per_cpu(wakeup_vcpus_on_cpu, cpu);
 	raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, cpu);
-	struct vcpu_vmx *vmx;
+	struct vcpu_vt *vt;
 
 	raw_spin_lock(spinlock);
-	list_for_each_entry(vmx, wakeup_list, pi_wakeup_list) {
+	list_for_each_entry(vt, wakeup_list, pi_wakeup_list) {
 
-		if (pi_test_on(&vmx->pi_desc))
-			kvm_vcpu_wake_up(&vmx->vcpu);
+		if (pi_test_on(&vt->pi_desc))
+			kvm_vcpu_wake_up(vt_to_vcpu(vt));
 	}
 	raw_spin_unlock(spinlock);
 }
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 277f5decde9c..a6388eb95988 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -2,7 +2,9 @@
 #include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <asm/cpufeature.h>
+#include <asm/fpu/xcr.h>
 #include <linux/misc_cgroup.h>
+#include <linux/mmu_context.h>
 #include <asm/tdx.h>
 #include "capabilities.h"
 #include "mmu.h"
@@ -12,6 +14,9 @@
 #include "vmx.h"
 #include "mmu/spte.h"
 #include "common.h"
+#include "posted_intr.h"
+#include <trace/events/kvm.h>
+#include "trace.h"
 
 #pragma GCC poison to_vmx
 
@@ -102,6 +107,44 @@ static u32 tdx_set_guest_phys_addr_bits(const u32 eax, int addr_bits)
 	return (eax & ~GENMASK(23, 16)) | (addr_bits & 0xff) << 16;
 }
 
+#define TDX_FEATURE_TSX (__feature_bit(X86_FEATURE_HLE) | __feature_bit(X86_FEATURE_RTM))
+
+static bool has_tsx(const struct kvm_cpuid_entry2 *entry)
+{
+	return entry->function == 7 && entry->index == 0 &&
+	       (entry->ebx & TDX_FEATURE_TSX);
+}
+
+static void clear_tsx(struct kvm_cpuid_entry2 *entry)
+{
+	entry->ebx &= ~TDX_FEATURE_TSX;
+}
+
+static bool has_waitpkg(const struct kvm_cpuid_entry2 *entry)
+{
+	return entry->function == 7 && entry->index == 0 &&
+	       (entry->ecx & __feature_bit(X86_FEATURE_WAITPKG));
+}
+
+static void clear_waitpkg(struct kvm_cpuid_entry2 *entry)
+{
+	entry->ecx &= ~__feature_bit(X86_FEATURE_WAITPKG);
+}
+
+static void tdx_clear_unsupported_cpuid(struct kvm_cpuid_entry2 *entry)
+{
+	if (has_tsx(entry))
+		clear_tsx(entry);
+
+	if (has_waitpkg(entry))
+		clear_waitpkg(entry);
+}
+
+static bool tdx_unsupported_cpuid(const struct kvm_cpuid_entry2 *entry)
+{
+	return has_tsx(entry) || has_waitpkg(entry);
+}
+
 #define KVM_TDX_CPUID_NO_SUBLEAF	((__u32)-1)
 
 static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char idx)
@@ -125,6 +168,8 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
 	 */
 	if (entry->function == 0x80000008)
 		entry->eax = tdx_set_guest_phys_addr_bits(entry->eax, 0xff);
+
+	tdx_clear_unsupported_cpuid(entry);
 }
 
 static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
@@ -585,6 +630,7 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.efer = EFER_SCE | EFER_LME | EFER_LMA | EFER_NX;
 
+	vcpu->arch.switch_db_regs = KVM_DEBUGREG_AUTO_SWITCH;
 	vcpu->arch.cr0_guest_owned_bits = -1ul;
 	vcpu->arch.cr4_guest_owned_bits = -1ul;
 
@@ -627,6 +673,74 @@ void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	local_irq_enable();
 }
 
+/*
+ * Compared to vmx_prepare_switch_to_guest(), there is not much to do
+ * as SEAMCALL/SEAMRET calls take care of most of save and restore.
+ */
+void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vt *vt = to_vt(vcpu);
+
+	if (vt->guest_state_loaded)
+		return;
+
+	if (likely(is_64bit_mm(current->mm)))
+		vt->msr_host_kernel_gs_base = current->thread.gsbase;
+	else
+		vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+
+	vt->host_debugctlmsr = get_debugctlmsr();
+
+	vt->guest_state_loaded = true;
+}
+
+struct tdx_uret_msr {
+	u32 msr;
+	unsigned int slot;
+	u64 defval;
+};
+
+static struct tdx_uret_msr tdx_uret_msrs[] = {
+	{.msr = MSR_SYSCALL_MASK, .defval = 0x20200 },
+	{.msr = MSR_STAR,},
+	{.msr = MSR_LSTAR,},
+	{.msr = MSR_TSC_AUX,},
+};
+
+static void tdx_user_return_msr_update_cache(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++)
+		kvm_user_return_msr_update_cache(tdx_uret_msrs[i].slot,
+						 tdx_uret_msrs[i].defval);
+}
+
+static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vt *vt = to_vt(vcpu);
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	if (!vt->guest_state_loaded)
+		return;
+
+	++vcpu->stat.host_state_reload;
+	wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base);
+
+	if (tdx->guest_entered) {
+		tdx_user_return_msr_update_cache();
+		tdx->guest_entered = false;
+	}
+
+	vt->guest_state_loaded = false;
+}
+
+void tdx_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vmx_vcpu_pi_put(vcpu);
+	tdx_prepare_switch_to_host(vcpu);
+}
+
 void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
@@ -660,6 +774,102 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 	tdx->state = VCPU_TD_STATE_UNINITIALIZED;
 }
 
+int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(to_tdx(vcpu)->state != VCPU_TD_STATE_INITIALIZED ||
+		     to_kvm_tdx(vcpu->kvm)->state != TD_STATE_RUNNABLE))
+		return -EINVAL;
+
+	return 1;
+}
+
+static noinstr void tdx_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	guest_state_enter_irqoff();
+
+	tdx->vp_enter_ret = tdh_vp_enter(&tdx->vp, &tdx->vp_enter_args);
+
+	guest_state_exit_irqoff();
+}
+
+#define TDX_REGS_AVAIL_SET	(BIT_ULL(VCPU_EXREG_EXIT_INFO_1) | \
+				 BIT_ULL(VCPU_EXREG_EXIT_INFO_2) | \
+				 BIT_ULL(VCPU_REGS_RAX) | \
+				 BIT_ULL(VCPU_REGS_RBX) | \
+				 BIT_ULL(VCPU_REGS_RCX) | \
+				 BIT_ULL(VCPU_REGS_RDX) | \
+				 BIT_ULL(VCPU_REGS_RBP) | \
+				 BIT_ULL(VCPU_REGS_RSI) | \
+				 BIT_ULL(VCPU_REGS_RDI) | \
+				 BIT_ULL(VCPU_REGS_R8) | \
+				 BIT_ULL(VCPU_REGS_R9) | \
+				 BIT_ULL(VCPU_REGS_R10) | \
+				 BIT_ULL(VCPU_REGS_R11) | \
+				 BIT_ULL(VCPU_REGS_R12) | \
+				 BIT_ULL(VCPU_REGS_R13) | \
+				 BIT_ULL(VCPU_REGS_R14) | \
+				 BIT_ULL(VCPU_REGS_R15))
+
+static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+
+	/*
+	 * All TDX hosts support PKRU; but even if they didn't,
+	 * vcpu->arch.host_pkru would be 0 and the wrpkru would be
+	 * skipped.
+	 */
+	if (vcpu->arch.host_pkru != 0)
+		wrpkru(vcpu->arch.host_pkru);
+
+	if (kvm_host.xcr0 != (kvm_tdx->xfam & kvm_caps.supported_xcr0))
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0);
+
+	/*
+	 * Likewise, even if a TDX hosts didn't support XSS both arms of
+	 * the comparison would be 0 and the wrmsrl would be skipped.
+	 */
+	if (kvm_host.xss != (kvm_tdx->xfam & kvm_caps.supported_xss))
+		wrmsrl(MSR_IA32_XSS, kvm_host.xss);
+}
+
+#define TDX_DEBUGCTL_PRESERVED (DEBUGCTLMSR_BTF | \
+				DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \
+				DEBUGCTLMSR_FREEZE_IN_SMM)
+
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
+
+	/*
+	 * force_immediate_exit requires vCPU entering for events injection with
+	 * an immediately exit followed. But The TDX module doesn't guarantee
+	 * entry, it's already possible for KVM to _think_ it completely entry
+	 * to the guest without actually having done so.
+	 * Since KVM never needs to force an immediate exit for TDX, and can't
+	 * do direct injection, just warn on force_immediate_exit.
+	 */
+	WARN_ON_ONCE(force_immediate_exit);
+
+	trace_kvm_entry(vcpu, force_immediate_exit);
+
+	tdx_vcpu_enter_exit(vcpu);
+
+	if (vt->host_debugctlmsr & ~TDX_DEBUGCTL_PRESERVED)
+		update_debugctlmsr(vt->host_debugctlmsr);
+
+	tdx_load_host_xsave_state(vcpu);
+	tdx->guest_entered = true;
+
+	vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET;
+
+	trace_kvm_exit(vcpu, KVM_ISA_VMX);
+
+	return EXIT_FASTPATH_NONE;
+}
 
 void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
 {
@@ -1084,6 +1294,9 @@ static int setup_tdparams_cpuids(struct kvm_cpuid2 *cpuid,
 		if (!entry)
 			continue;
 
+		if (tdx_unsupported_cpuid(entry))
+			return -EINVAL;
+
 		copy_cnt++;
 
 		value = &td_params->cpuid_values[i];
@@ -2113,7 +2326,25 @@ static int __init __do_tdx_bringup(void)
 static int __init __tdx_bringup(void)
 {
 	const struct tdx_sys_info_td_conf *td_conf;
-	int r;
+	int r, i;
+
+	for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) {
+		/*
+		 * Check if MSRs (tdx_uret_msrs) can be saved/restored
+		 * before returning to user space.
+		 *
+		 * this_cpu_ptr(user_return_msrs)->registered isn't checked
+		 * because the registration is done at vcpu runtime by
+		 * tdx_user_return_msr_update_cache().
+		 */
+		tdx_uret_msrs[i].slot = kvm_find_user_return_msr(tdx_uret_msrs[i].msr);
+		if (tdx_uret_msrs[i].slot == -1) {
+			/* If any MSR isn't supported, it is a KVM bug */
+			pr_err("MSR %x isn't included by kvm_find_user_return_msr\n",
+				tdx_uret_msrs[i].msr);
+			return -EIO;
+		}
+	}
 
 	/*
 	 * Enabling TDX requires enabling hardware virtualization first,
@@ -2230,6 +2461,11 @@ int __init tdx_bringup(void)
 		goto success_disable_tdx;
 	}
 
+	if (!cpu_feature_enabled(X86_FEATURE_OSXSAVE)) {
+		pr_err("tdx: OSXSAVE is required for TDX\n");
+		goto success_disable_tdx;
+	}
+
 	if (!cpu_feature_enabled(X86_FEATURE_MOVDIR64B)) {
 		pr_err("tdx: MOVDIR64B is required for TDX\n");
 		goto success_disable_tdx;
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 5f34b79d16dd..0a54d286e380 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -6,6 +6,8 @@
 #include "tdx_errno.h"
 
 #ifdef CONFIG_KVM_INTEL_TDX
+#include "common.h"
+
 int tdx_bringup(void);
 void tdx_cleanup(void);
 
@@ -45,28 +47,23 @@ enum vcpu_tdx_state {
 
 struct vcpu_tdx {
 	struct kvm_vcpu	vcpu;
+	struct vcpu_vt vt;
+	struct tdx_module_args vp_enter_args;
 
 	struct tdx_vp vp;
 
 	struct list_head cpu_list;
 
+	u64 vp_enter_ret;
+
 	enum vcpu_tdx_state state;
+	bool guest_entered;
 };
 
 void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err);
 void tdh_vp_wr_failed(struct vcpu_tdx *tdx, char *uclass, char *op, u32 field,
 		      u64 val, u64 err);
 
-static inline bool is_td(struct kvm *kvm)
-{
-	return kvm->arch.vm_type == KVM_X86_TDX_VM;
-}
-
-static inline bool is_td_vcpu(struct kvm_vcpu *vcpu)
-{
-	return is_td(vcpu->kvm);
-}
-
 static __always_inline u64 td_tdcs_exec_read64(struct kvm_tdx *kvm_tdx, u32 field)
 {
 	u64 err, data;
@@ -176,9 +173,6 @@ struct vcpu_tdx {
 	struct kvm_vcpu	vcpu;
 };
 
-static inline bool is_td(struct kvm *kvm) { return false; }
-static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
-
 #endif
 
 #endif
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 39d55d638899..e7e451209306 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1282,6 +1282,7 @@ void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
 void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 	struct vmcs_host_state *host_state;
 #ifdef CONFIG_X86_64
 	int cpu = raw_smp_processor_id();
@@ -1310,7 +1311,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	if (vmx->nested.need_vmcs12_to_shadow_sync)
 		nested_sync_vmcs12_to_shadow(vcpu);
 
-	if (vmx->guest_state_loaded)
+	if (vt->guest_state_loaded)
 		return;
 
 	host_state = &vmx->loaded_vmcs->host_state;
@@ -1331,12 +1332,12 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		fs_sel = current->thread.fsindex;
 		gs_sel = current->thread.gsindex;
 		fs_base = current->thread.fsbase;
-		vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+		vt->msr_host_kernel_gs_base = current->thread.gsbase;
 	} else {
 		savesegment(fs, fs_sel);
 		savesegment(gs, gs_sel);
 		fs_base = read_msr(MSR_FS_BASE);
-		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+		vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
 	}
 
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
@@ -1348,14 +1349,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 #endif
 
 	vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
-	vmx->guest_state_loaded = true;
+	vt->guest_state_loaded = true;
 }
 
 static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 {
 	struct vmcs_host_state *host_state;
 
-	if (!vmx->guest_state_loaded)
+	if (!vmx->vt.guest_state_loaded)
 		return;
 
 	host_state = &vmx->loaded_vmcs->host_state;
@@ -1383,10 +1384,10 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 #endif
 	invalidate_tss_limit();
 #ifdef CONFIG_X86_64
-	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, vmx->vt.msr_host_kernel_gs_base);
 #endif
 	load_fixmap_gdt(raw_smp_processor_id());
-	vmx->guest_state_loaded = false;
+	vmx->vt.guest_state_loaded = false;
 	vmx->guest_uret_msrs_loaded = false;
 }
 
@@ -1394,7 +1395,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
 {
 	preempt_disable();
-	if (vmx->guest_state_loaded)
+	if (vmx->vt.guest_state_loaded)
 		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 	preempt_enable();
 	return vmx->msr_guest_kernel_gs_base;
@@ -1403,7 +1404,7 @@ static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
 static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
 {
 	preempt_disable();
-	if (vmx->guest_state_loaded)
+	if (vmx->vt.guest_state_loaded)
 		wrmsrl(MSR_KERNEL_GS_BASE, data);
 	preempt_enable();
 	vmx->msr_guest_kernel_gs_base = data;
@@ -1699,7 +1700,7 @@ int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 	 * so that guest userspace can't DoS the guest simply by triggering
 	 * emulation (enclaves are CPL3 only).
 	 */
-	if (to_vmx(vcpu)->exit_reason.enclave_mode) {
+	if (vmx_get_exit_reason(vcpu).enclave_mode) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return X86EMUL_PROPAGATE_FAULT;
 	}
@@ -1714,7 +1715,7 @@ int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
 
 static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
-	union vmx_exit_reason exit_reason = to_vmx(vcpu)->exit_reason;
+	union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu);
 	unsigned long rip, orig_rip;
 	u32 instr_len;
 
@@ -4273,7 +4274,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
  */
 static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 	int r;
 
 	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
@@ -4284,11 +4285,11 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (!vcpu->arch.apic->apicv_active)
 		return -1;
 
-	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
+	if (pi_test_and_set_pir(vector, &vt->pi_desc))
 		return 0;
 
 	/* If a previous notification has sent the IPI, nothing to do.  */
-	if (pi_test_and_set_on(&vmx->pi_desc))
+	if (pi_test_and_set_on(&vt->pi_desc))
 		return 0;
 
 	/*
@@ -4764,7 +4765,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 		vmcs_write16(GUEST_INTR_STATUS, 0);
 
 		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
-		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
+		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->vt.pi_desc)));
 	}
 
 	if (vmx_can_use_ipiv(&vmx->vcpu)) {
@@ -4877,8 +4878,8 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
 	 * or POSTED_INTR_WAKEUP_VECTOR.
 	 */
-	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
-	__pi_set_sn(&vmx->pi_desc);
+	vmx->vt.pi_desc.nv = POSTED_INTR_VECTOR;
+	__pi_set_sn(&vmx->vt.pi_desc);
 }
 
 void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -6064,7 +6065,7 @@ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
 	 * VM-Exits. Unconditionally set the flag here and leave the handling to
 	 * vmx_handle_exit().
 	 */
-	to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+	to_vt(vcpu)->exit_reason.bus_lock_detected = true;
 	return 1;
 }
 
@@ -6162,9 +6163,9 @@ void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	*reason = vmx->exit_reason.full;
+	*reason = vmx->vt.exit_reason.full;
 	*info1 = vmx_get_exit_qual(vcpu);
-	if (!(vmx->exit_reason.failed_vmentry)) {
+	if (!(vmx->vt.exit_reason.failed_vmentry)) {
 		*info2 = vmx->idt_vectoring_info;
 		*intr_info = vmx_get_intr_info(vcpu);
 		if (is_exception_with_error_code(*intr_info))
@@ -6460,7 +6461,7 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
 static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	union vmx_exit_reason exit_reason = vmx->exit_reason;
+	union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu);
 	u32 vectoring_info = vmx->idt_vectoring_info;
 	u16 exit_handler_index;
 
@@ -6626,7 +6627,7 @@ int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	 * Exit to user space when bus lock detected to inform that there is
 	 * a bus lock in guest.
 	 */
-	if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
+	if (vmx_get_exit_reason(vcpu).bus_lock_detected) {
 		if (ret > 0)
 			vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
 
@@ -6905,22 +6906,22 @@ static void vmx_set_rvi(int vector)
 
 int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 	int max_irr;
 	bool got_posted_interrupt;
 
 	if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
 		return -EIO;
 
-	if (pi_test_on(&vmx->pi_desc)) {
-		pi_clear_on(&vmx->pi_desc);
+	if (pi_test_on(&vt->pi_desc)) {
+		pi_clear_on(&vt->pi_desc);
 		/*
 		 * IOMMU can write to PID.ON, so the barrier matters even on UP.
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
 		got_posted_interrupt =
-			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
+			kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
 		got_posted_interrupt = false;
@@ -6962,10 +6963,10 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 
 void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vcpu_vt *vt = to_vt(vcpu);
 
-	pi_clear_on(&vmx->pi_desc);
-	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
+	pi_clear_on(&vt->pi_desc);
+	memset(vt->pi_desc.pir, 0, sizeof(vt->pi_desc.pir));
 }
 
 void vmx_do_interrupt_irqoff(unsigned long entry);
@@ -7030,9 +7031,9 @@ void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return;
 
-	if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT)
+	if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXTERNAL_INTERRUPT)
 		handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu));
-	else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI)
+	else if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXCEPTION_NMI)
 		handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu));
 }
 
@@ -7263,10 +7264,10 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu,
 	 * the fastpath even, all other exits must use the slow path.
 	 */
 	if (is_guest_mode(vcpu) &&
-	    to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER)
+	    vmx_get_exit_reason(vcpu).basic != EXIT_REASON_PREEMPTION_TIMER)
 		return EXIT_FASTPATH_NONE;
 
-	switch (to_vmx(vcpu)->exit_reason.basic) {
+	switch (vmx_get_exit_reason(vcpu).basic) {
 	case EXIT_REASON_MSR_WRITE:
 		return handle_fastpath_set_msr_irqoff(vcpu);
 	case EXIT_REASON_PREEMPTION_TIMER:
@@ -7313,15 +7314,15 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	vmx_enable_fb_clear(vmx);
 
 	if (unlikely(vmx->fail)) {
-		vmx->exit_reason.full = 0xdead;
+		vmx->vt.exit_reason.full = 0xdead;
 		goto out;
 	}
 
-	vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
-	if (likely(!vmx->exit_reason.failed_vmentry))
+	vmx->vt.exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+	if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry))
 		vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 
-	if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
+	if ((u16)vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXCEPTION_NMI &&
 	    is_nmi(vmx_get_intr_info(vcpu))) {
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 		if (cpu_feature_enabled(X86_FEATURE_FRED))
@@ -7353,12 +7354,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	if (unlikely(vmx->emulation_required)) {
 		vmx->fail = 0;
 
-		vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
-		vmx->exit_reason.failed_vmentry = 1;
+		vmx->vt.exit_reason.full = EXIT_REASON_INVALID_STATE;
+		vmx->vt.exit_reason.failed_vmentry = 1;
 		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
-		vmx->exit_qualification = ENTRY_FAIL_DEFAULT;
+		vmx->vt.exit_qualification = ENTRY_FAIL_DEFAULT;
 		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
-		vmx->exit_intr_info = 0;
+		vmx->vt.exit_intr_info = 0;
 		return EXIT_FASTPATH_NONE;
 	}
 
@@ -7461,7 +7462,7 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 		 * checking.
 		 */
 		if (vmx->nested.nested_run_pending &&
-		    !vmx->exit_reason.failed_vmentry)
+		    !vmx_get_exit_reason(vcpu).failed_vmentry)
 			++vcpu->stat.nested_run;
 
 		vmx->nested.nested_run_pending = 0;
@@ -7470,12 +7471,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	if (unlikely(vmx->fail))
 		return EXIT_FASTPATH_NONE;
 
-	if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY))
+	if (unlikely((u16)vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY))
 		kvm_machine_check();
 
 	trace_kvm_exit(vcpu, KVM_ISA_VMX);
 
-	if (unlikely(vmx->exit_reason.failed_vmentry))
+	if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry))
 		return EXIT_FASTPATH_NONE;
 
 	vmx->loaded_vmcs->launched = 1;
@@ -7507,7 +7508,7 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
 	vmx = to_vmx(vcpu);
 
-	INIT_LIST_HEAD(&vmx->pi_wakeup_list);
+	INIT_LIST_HEAD(&vmx->vt.pi_wakeup_list);
 
 	err = -ENOMEM;
 
@@ -7605,7 +7606,7 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 
 	if (vmx_can_use_ipiv(vcpu))
 		WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id],
-			   __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID);
+			   __pa(&vmx->vt.pi_desc) | PID_TABLE_ENTRY_VALID);
 
 	return 0;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a4ee44ffaede..e635199901e2 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -17,6 +17,7 @@
 #include "../cpuid.h"
 #include "run_flags.h"
 #include "../mmu.h"
+#include "common.h"
 
 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
 
@@ -68,29 +69,6 @@ struct pt_desc {
 	struct pt_ctx guest;
 };
 
-union vmx_exit_reason {
-	struct {
-		u32	basic			: 16;
-		u32	reserved16		: 1;
-		u32	reserved17		: 1;
-		u32	reserved18		: 1;
-		u32	reserved19		: 1;
-		u32	reserved20		: 1;
-		u32	reserved21		: 1;
-		u32	reserved22		: 1;
-		u32	reserved23		: 1;
-		u32	reserved24		: 1;
-		u32	reserved25		: 1;
-		u32	bus_lock_detected	: 1;
-		u32	enclave_mode		: 1;
-		u32	smi_pending_mtf		: 1;
-		u32	smi_from_vmx_root	: 1;
-		u32	reserved30		: 1;
-		u32	failed_vmentry		: 1;
-	};
-	u32 full;
-};
-
 /*
  * The nested_vmx structure is part of vcpu_vmx, and holds information we need
  * for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -231,20 +209,10 @@ struct nested_vmx {
 
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
+	struct vcpu_vt	      vt;
 	u8                    fail;
 	u8		      x2apic_msr_bitmap_mode;
 
-	/*
-	 * If true, host state has been stored in vmx->loaded_vmcs for
-	 * the CPU registers that only need to be switched when transitioning
-	 * to/from the kernel, and the registers have been loaded with guest
-	 * values.  If false, host state is loaded in the CPU registers
-	 * and vmx->loaded_vmcs->host_state is invalid.
-	 */
-	bool		      guest_state_loaded;
-
-	unsigned long         exit_qualification;
-	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
 	ulong                 rflags;
 
@@ -257,7 +225,6 @@ struct vcpu_vmx {
 	struct vmx_uret_msr   guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
 	bool                  guest_uret_msrs_loaded;
 #ifdef CONFIG_X86_64
-	u64		      msr_host_kernel_gs_base;
 	u64		      msr_guest_kernel_gs_base;
 #endif
 
@@ -298,14 +265,6 @@ struct vcpu_vmx {
 	int vpid;
 	bool emulation_required;
 
-	union vmx_exit_reason exit_reason;
-
-	/* Posted interrupt descriptor */
-	struct pi_desc pi_desc;
-
-	/* Used if this vCPU is waiting for PI notification wakeup. */
-	struct list_head pi_wakeup_list;
-
 	/* Support for a guest hypervisor (nested VMX) */
 	struct nested_vmx nested;
 
@@ -359,6 +318,43 @@ struct kvm_vmx {
 	u64 *pid_table;
 };
 
+static __always_inline struct vcpu_vt *to_vt(struct kvm_vcpu *vcpu)
+{
+	return &(container_of(vcpu, struct vcpu_vmx, vcpu)->vt);
+}
+
+static __always_inline struct kvm_vcpu *vt_to_vcpu(struct vcpu_vt *vt)
+{
+	return &(container_of(vt, struct vcpu_vmx, vt)->vcpu);
+}
+
+static __always_inline union vmx_exit_reason vmx_get_exit_reason(struct kvm_vcpu *vcpu)
+{
+	return to_vt(vcpu)->exit_reason;
+}
+
+static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vt *vt = to_vt(vcpu);
+
+	if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1) &&
+	    !WARN_ON_ONCE(is_td_vcpu(vcpu)))
+		vt->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	return vt->exit_qualification;
+}
+
+static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vt *vt = to_vt(vcpu);
+
+	if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2) &&
+	    !WARN_ON_ONCE(is_td_vcpu(vcpu)))
+		vt->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	return vt->exit_intr_info;
+}
+
 void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 			struct loaded_vmcs *buddy);
 int allocate_vpid(void);
@@ -649,26 +645,6 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu);
 int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu);
 void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu);
 
-static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1))
-		vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	return vmx->exit_qualification;
-}
-
-static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2))
-		vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-
-	return vmx->exit_intr_info;
-}
-
 struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags);
 void free_vmcs(struct vmcs *vmcs);
 int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index f47d739051cf..cd18e9b1e124 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -131,6 +131,10 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
 int tdx_vcpu_create(struct kvm_vcpu *vcpu);
 void tdx_vcpu_free(struct kvm_vcpu *vcpu);
 void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+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_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
 
@@ -157,6 +161,13 @@ static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOP
 static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
 static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {}
 static inline void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) {}
+static inline int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
+static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+{
+	return EXIT_FASTPATH_NONE;
+}
+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_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 8f3292ccdca4..1ef83f24449d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -636,6 +636,15 @@ static void kvm_user_return_msr_cpu_online(void)
 	}
 }
 
+static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs)
+{
+	if (!msrs->registered) {
+		msrs->urn.on_user_return = kvm_on_user_return;
+		user_return_notifier_register(&msrs->urn);
+		msrs->registered = true;
+	}
+}
+
 int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 {
 	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
@@ -649,15 +658,20 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 		return 1;
 
 	msrs->values[slot].curr = value;
-	if (!msrs->registered) {
-		msrs->urn.on_user_return = kvm_on_user_return;
-		user_return_notifier_register(&msrs->urn);
-		msrs->registered = true;
-	}
+	kvm_user_return_register_notifier(msrs);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
 
+void kvm_user_return_msr_update_cache(unsigned int slot, u64 value)
+{
+	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
+
+	msrs->values[slot].curr = value;
+	kvm_user_return_register_notifier(msrs);
+}
+EXPORT_SYMBOL_GPL(kvm_user_return_msr_update_cache);
+
 static void drop_user_return_notifiers(void)
 {
 	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
@@ -10971,7 +10985,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_fpu.xfd_err)
 		wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
 
-	if (unlikely(vcpu->arch.switch_db_regs)) {
+	if (unlikely(vcpu->arch.switch_db_regs &&
+		     !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
 		set_debugreg(vcpu->arch.eff_db[1], 1);
@@ -11023,6 +11038,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 */
 	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
 		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
+		WARN_ON(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH);
 		kvm_x86_call(sync_dirty_debug_regs)(vcpu);
 		kvm_update_dr0123(vcpu);
 		kvm_update_dr7(vcpu);
diff --git a/arch/x86/virt/vmx/tdx/seamcall.S b/arch/x86/virt/vmx/tdx/seamcall.S
index 5b1f2286aea9..6854c52c374b 100644
--- a/arch/x86/virt/vmx/tdx/seamcall.S
+++ b/arch/x86/virt/vmx/tdx/seamcall.S
@@ -41,6 +41,9 @@ SYM_FUNC_START(__seamcall_ret)
 	TDX_MODULE_CALL host=1 ret=1
 SYM_FUNC_END(__seamcall_ret)
 
+/* KVM requires non-instrumentable __seamcall_saved_ret() for TDH.VP.ENTER */
+.section .noinstr.text, "ax"
+
 /*
  * __seamcall_saved_ret() - Host-side interface functions to SEAM software
  * (the P-SEAMLDR or the TDX module), with saving output registers to the
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 8eaaf31a4187..f5e2a937c1e7 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1517,6 +1517,14 @@ static void tdx_clflush_page(struct page *page)
 	clflush_cache_range(page_to_virt(page), PAGE_SIZE);
 }
 
+noinstr u64 tdh_vp_enter(struct tdx_vp *td, struct tdx_module_args *args)
+{
+	args->rcx = tdx_tdvpr_pa(td);
+
+	return __seamcall_saved_ret(TDH_VP_ENTER, args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_enter);
+
 u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page)
 {
 	struct tdx_module_args args = {
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index ed7152f81a6d..82bb82be8567 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -14,6 +14,7 @@
 /*
  * TDX module SEAMCALL leaf functions
  */
+#define TDH_VP_ENTER			0
 #define TDH_MNG_ADDCX			1
 #define TDH_MEM_PAGE_ADD		2
 #define TDH_MEM_SEPT_ADD		3