23 files changed, 1325 insertions, 85 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6800d3956ab1..ddb08581c64d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1562,6 +1562,13 @@ struct kvm_arch {
 	struct kvm_mmu_memory_cache split_desc_cache;
 
 	gfn_t gfn_direct_bits;
+
+	/*
+	 * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A Zero
+	 * value indicates CPU dirty logging is unsupported or disabled in
+	 * current VM.
+	 */
+	int cpu_dirty_log_size;
 };
 
 struct kvm_vm_stat {
@@ -1815,11 +1822,6 @@ struct kvm_x86_ops {
 			       struct x86_exception *exception);
 	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
 
-	/*
-	 * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer.  A zero
-	 * value indicates CPU dirty logging is unsupported or disabled.
-	 */
-	int cpu_dirty_log_size;
 	void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu);
 
 	const struct kvm_x86_nested_ops *nested_ops;
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 2879fc518a32..e38e7558c02f 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -148,7 +148,6 @@ struct tdx_vp {
 	struct page **tdcx_pages;
 };
 
-
 static inline u64 mk_keyed_paddr(u16 hkid, struct page *page)
 {
 	u64 ret;
@@ -158,15 +157,26 @@ static inline u64 mk_keyed_paddr(u16 hkid, struct page *page)
 	ret |= (u64)hkid << boot_cpu_data.x86_phys_bits;
 
 	return ret;
+}
 
+static inline int pg_level_to_tdx_sept_level(enum pg_level level)
+{
+        WARN_ON_ONCE(level == PG_LEVEL_NONE);
+        return level - 1;
 }
 
 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);
 u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page);
+u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mem_range_block(struct tdx_td *td, u64 gpa, int level, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_mng_key_config(struct tdx_td *td);
 u64 tdh_mng_create(struct tdx_td *td, u16 hkid);
 u64 tdh_vp_create(struct tdx_td *td, struct tdx_vp *vp);
 u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data);
+u64 tdh_mr_extend(struct tdx_td *td, u64 gpa, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mr_finalize(struct tdx_td *td);
 u64 tdh_vp_flush(struct tdx_vp *vp);
 u64 tdh_mng_vpflushdone(struct tdx_td *td);
 u64 tdh_mng_key_freeid(struct tdx_td *td);
@@ -175,8 +185,11 @@ u64 tdh_vp_init(struct tdx_vp *vp, u64 initial_rcx, u32 x2apicid);
 u64 tdh_vp_rd(struct tdx_vp *vp, u64 field, u64 *data);
 u64 tdh_vp_wr(struct tdx_vp *vp, u64 field, u64 data, u64 mask);
 u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64 *tdx_size);
+u64 tdh_mem_track(struct tdx_td *tdr);
+u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u64 *ext_err2);
 u64 tdh_phymem_cache_wb(bool resume);
 u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td);
+u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page);
 #else
 static inline void tdx_init(void) { }
 static inline int tdx_cpu_enable(void) { return -ENODEV; }
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f7fd4369b821..9298fb9d4bb3 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -256,6 +256,7 @@ enum vmcs_field {
 	TSC_MULTIPLIER_HIGH             = 0x00002033,
 	TERTIARY_VM_EXEC_CONTROL	= 0x00002034,
 	TERTIARY_VM_EXEC_CONTROL_HIGH	= 0x00002035,
+	SHARED_EPT_POINTER		= 0x0000203C,
 	PID_POINTER_TABLE		= 0x00002042,
 	PID_POINTER_TABLE_HIGH		= 0x00002043,
 	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index cd55484e3f0c..89cc7a18ef45 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -932,6 +932,8 @@ enum kvm_tdx_cmd_id {
 	KVM_TDX_CAPABILITIES = 0,
 	KVM_TDX_INIT_VM,
 	KVM_TDX_INIT_VCPU,
+	KVM_TDX_INIT_MEM_REGION,
+	KVM_TDX_FINALIZE_VM,
 	KVM_TDX_GET_CPUID,
 
 	KVM_TDX_CMD_NR_MAX,
@@ -987,4 +989,12 @@ struct kvm_tdx_init_vm {
 	struct kvm_cpuid2 cpuid;
 };
 
+#define KVM_TDX_MEASURE_MEMORY_REGION   _BITULL(0)
+
+struct kvm_tdx_init_mem_region {
+	__u64 source_addr;
+	__u64 gpa;
+	__u64 nr_pages;
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 050a0e229a4d..47e64a3c4ce3 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -79,6 +79,7 @@ static inline gfn_t kvm_mmu_max_gfn(void)
 u8 kvm_mmu_get_max_tdp_level(void);
 
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value);
 void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
 void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);
 
@@ -253,6 +254,9 @@ extern bool tdp_mmu_enabled;
 #define tdp_mmu_enabled false
 #endif
 
+bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa);
+int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level);
+
 static inline bool kvm_memslots_have_rmaps(struct kvm *kvm)
 {
 	return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a79bc15f31c6..0c6a4568af5b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -110,6 +110,7 @@ static bool __ro_after_init tdp_mmu_allowed;
 #ifdef CONFIG_X86_64
 bool __read_mostly tdp_mmu_enabled = true;
 module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444);
+EXPORT_SYMBOL_GPL(tdp_mmu_enabled);
 #endif
 
 static int max_huge_page_level __read_mostly;
@@ -1304,15 +1305,15 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	 * enabled but it chooses between clearing the Dirty bit and Writeable
 	 * bit based on the context.
 	 */
-	if (kvm_x86_ops.cpu_dirty_log_size)
+	if (kvm->arch.cpu_dirty_log_size)
 		kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask);
 	else
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
-int kvm_cpu_dirty_log_size(void)
+int kvm_cpu_dirty_log_size(struct kvm *kvm)
 {
-	return kvm_x86_ops.cpu_dirty_log_size;
+	return kvm->arch.cpu_dirty_log_size;
 }
 
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
@@ -4685,8 +4686,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	return direct_page_fault(vcpu, fault);
 }
 
-static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
-			    u8 *level)
+int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level)
 {
 	int r;
 
@@ -4700,6 +4700,10 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
 	do {
 		if (signal_pending(current))
 			return -EINTR;
+
+		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+			return -EIO;
+
 		cond_resched();
 		r = kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level);
 	} while (r == RET_PF_RETRY);
@@ -4724,6 +4728,7 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
 		return -EIO;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_tdp_map_page);
 
 long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 				    struct kvm_pre_fault_memory *range)
@@ -5747,6 +5752,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 out:
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_load);
 
 void kvm_mmu_unload(struct kvm_vcpu *vcpu)
 {
@@ -7072,6 +7078,7 @@ static void kvm_mmu_zap_memslot(struct kvm *kvm,
 		.start = slot->base_gfn,
 		.end = slot->base_gfn + slot->npages,
 		.may_block = true,
+		.attr_filter = KVM_FILTER_PRIVATE | KVM_FILTER_SHARED,
 	};
 	bool flush;
 
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 75f00598289d..db8f33e4de62 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -187,7 +187,8 @@ static inline gfn_t kvm_gfn_root_bits(const struct kvm *kvm, const struct kvm_mm
 	return kvm_gfn_direct_bits(kvm);
 }
 
-static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
+static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm *kvm,
+						      struct kvm_mmu_page *sp)
 {
 	/*
 	 * When using the EPT page-modification log, the GPAs in the CPU dirty
@@ -197,7 +198,7 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
 	 * being enabled is mandatory as the bits used to denote WP-only SPTEs
 	 * are reserved for PAE paging (32-bit KVM).
 	 */
-	return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode;
+	return kvm->arch.cpu_dirty_log_size && sp->role.guest_mode;
 }
 
 static inline gfn_t gfn_round_for_level(gfn_t gfn, int level)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 561c331fd6ec..1b17b12393a8 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -172,6 +172,9 @@ static int kvm_enable_external_write_tracking(struct kvm *kvm)
 	struct kvm_memory_slot *slot;
 	int r = 0, i, bkt;
 
+	if (kvm->arch.vm_type == KVM_X86_TDX_VM)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&kvm->slots_arch_lock);
 
 	/*
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 22551e2f1d00..a609d5b58b69 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -96,8 +96,6 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
 	u64 spte = generation_mmio_spte_mask(gen);
 	u64 gpa = gfn << PAGE_SHIFT;
 
-	WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);
-
 	access &= shadow_mmio_access_mask;
 	spte |= vcpu->kvm->arch.shadow_mmio_value | access;
 	spte |= gpa | shadow_nonpresent_or_rsvd_mask;
@@ -170,7 +168,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 
 	if (sp->role.ad_disabled)
 		spte |= SPTE_TDP_AD_DISABLED;
-	else if (kvm_mmu_page_ad_need_write_protect(sp))
+	else if (kvm_mmu_page_ad_need_write_protect(vcpu->kvm, sp))
 		spte |= SPTE_TDP_AD_WRPROT_ONLY;
 
 	spte |= shadow_present_mask;
@@ -433,6 +431,12 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value)
+{
+	kvm->arch.shadow_mmio_value = mmio_value;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_value);
+
 void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask)
 {
 	/* shadow_me_value must be a subset of shadow_me_mask */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 046b6ba31197..fd0a7792386b 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1613,21 +1613,21 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
 	}
 }
 
-static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp)
+static bool tdp_mmu_need_write_protect(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	/*
 	 * All TDP MMU shadow pages share the same role as their root, aside
 	 * from level, so it is valid to key off any shadow page to determine if
 	 * write protection is needed for an entire tree.
 	 */
-	return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled;
+	return kvm_mmu_page_ad_need_write_protect(kvm, sp) || !kvm_ad_enabled;
 }
 
 static void clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 				  gfn_t start, gfn_t end)
 {
-	const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK :
-							    shadow_dirty_mask;
+	const u64 dbit = tdp_mmu_need_write_protect(kvm, root) ?
+			 PT_WRITABLE_MASK : shadow_dirty_mask;
 	struct tdp_iter iter;
 
 	rcu_read_lock();
@@ -1672,8 +1672,8 @@ void kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
 static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 				  gfn_t gfn, unsigned long mask, bool wrprot)
 {
-	const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK :
-									shadow_dirty_mask;
+	const u64 dbit = (wrprot || tdp_mmu_need_write_protect(kvm, root)) ?
+			  PT_WRITABLE_MASK : shadow_dirty_mask;
 	struct tdp_iter iter;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
@@ -1894,16 +1894,13 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
  *
  * Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}.
  */
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
-			 int *root_level)
+static int __kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+				  struct kvm_mmu_page *root)
 {
-	struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
 	struct tdp_iter iter;
 	gfn_t gfn = addr >> PAGE_SHIFT;
 	int leaf = -1;
 
-	*root_level = vcpu->arch.mmu->root_role.level;
-
 	tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
 		leaf = iter.level;
 		sptes[leaf] = iter.old_spte;
@@ -1912,6 +1909,36 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
 	return leaf;
 }
 
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level)
+{
+	struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
+	*root_level = vcpu->arch.mmu->root_role.level;
+
+	return __kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root);
+}
+
+bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool is_direct = kvm_is_addr_direct(kvm, gpa);
+	hpa_t root = is_direct ? vcpu->arch.mmu->root.hpa :
+				 vcpu->arch.mmu->mirror_root_hpa;
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1], spte;
+	int leaf;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	rcu_read_lock();
+	leaf = __kvm_tdp_mmu_get_walk(vcpu, gpa, sptes, root_to_sp(root));
+	rcu_read_unlock();
+	if (leaf < 0)
+		return false;
+
+	spte = sptes[leaf];
+	return is_shadow_present_pte(spte) && is_last_spte(spte, leaf);
+}
+EXPORT_SYMBOL_GPL(kvm_tdp_mmu_gpa_is_mapped);
+
 /*
  * Returns the last level spte pointer of the shadow page walk for the given
  * gpa, and sets *spte to the spte value. This spte may be non-preset. If no
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
new file mode 100644
index 000000000000..7a592467a044
--- /dev/null
+++ b/arch/x86/kvm/vmx/common.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __KVM_X86_VMX_COMMON_H
+#define __KVM_X86_VMX_COMMON_H
+
+#include <linux/kvm_host.h>
+
+#include "mmu.h"
+
+static inline bool vt_is_tdx_private_gpa(struct kvm *kvm, gpa_t gpa)
+{
+	/* For TDX the direct mask is the shared mask. */
+	return !kvm_is_addr_direct(kvm, gpa);
+}
+
+static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa,
+					     unsigned long exit_qualification)
+{
+	u64 error_code;
+
+	/* Is it a read fault? */
+	error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
+		     ? PFERR_USER_MASK : 0;
+	/* Is it a write fault? */
+	error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
+		      ? PFERR_WRITE_MASK : 0;
+	/* Is it a fetch fault? */
+	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
+		      ? PFERR_FETCH_MASK : 0;
+	/* ept page table entry is present? */
+	error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK)
+		      ? PFERR_PRESENT_MASK : 0;
+
+	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
+		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
+			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
+
+	if (vt_is_tdx_private_gpa(vcpu->kvm, gpa))
+		error_code |= PFERR_PRIVATE_ACCESS;
+
+	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
+}
+
+#endif /* __KVM_X86_VMX_COMMON_H */
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index e7d402b3a90d..ec8223ee9d28 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -3,12 +3,21 @@
 
 #include "x86_ops.h"
 #include "vmx.h"
+#include "mmu.h"
 #include "nested.h"
 #include "pmu.h"
 #include "posted_intr.h"
 #include "tdx.h"
 #include "tdx_arch.h"
 
+static void vt_disable_virtualization_cpu(void)
+{
+	/* Note, TDX *and* VMX need to be disabled if TDX is enabled. */
+	if (enable_tdx)
+		tdx_disable_virtualization_cpu();
+	vmx_disable_virtualization_cpu();
+}
+
 static __init int vt_hardware_setup(void)
 {
 	int ret;
@@ -35,9 +44,21 @@ static __init int vt_hardware_setup(void)
 	 * is KVM may allocate couple of more bytes than needed for
 	 * each VM.
 	 */
-	if (enable_tdx)
+	if (enable_tdx) {
 		vt_x86_ops.vm_size = max_t(unsigned int, vt_x86_ops.vm_size,
 				sizeof(struct kvm_tdx));
+		/*
+		 * Note, TDX may fail to initialize in a later time in
+		 * vt_init(), in which case it is not necessary to setup
+		 * those callbacks.  But making them valid here even
+		 * when TDX fails to init later is fine because those
+		 * callbacks won't be called if the VM isn't TDX guest.
+		 */
+		vt_x86_ops.link_external_spt = tdx_sept_link_private_spt;
+		vt_x86_ops.set_external_spte = tdx_sept_set_private_spte;
+		vt_x86_ops.free_external_spt = tdx_sept_free_private_spt;
+		vt_x86_ops.remove_external_spte = tdx_sept_remove_private_spte;
+	}
 
 	return 0;
 }
@@ -98,6 +119,75 @@ static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vmx_vcpu_reset(vcpu, init_event);
 }
 
+static void vt_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_vcpu_load(vcpu, cpu);
+		return;
+	}
+
+	vmx_vcpu_load(vcpu, cpu);
+}
+
+static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Basic TDX does not support feature PML. KVM does not enable PML in
+	 * TD's VMCS, nor does it allocate or flush PML buffer for TDX.
+	 */
+	if (WARN_ON_ONCE(is_td_vcpu(vcpu)))
+		return;
+
+	vmx_update_cpu_dirty_logging(vcpu);
+}
+
+static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_flush_tlb_all(vcpu);
+		return;
+	}
+
+	vmx_flush_tlb_all(vcpu);
+}
+
+static void vt_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_flush_tlb_current(vcpu);
+		return;
+	}
+
+	vmx_flush_tlb_current(vcpu);
+}
+
+static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
+{
+	if (is_td_vcpu(vcpu))
+		return;
+
+	vmx_flush_tlb_gva(vcpu, addr);
+}
+
+static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return;
+
+	vmx_flush_tlb_guest(vcpu);
+}
+
+static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
+			    int pgd_level)
+{
+	if (is_td_vcpu(vcpu)) {
+		tdx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
+		return;
+	}
+
+	vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
+}
+
 static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	if (!is_td(kvm))
@@ -114,6 +204,14 @@ static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 	return tdx_vcpu_ioctl(vcpu, argp);
 }
 
+static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+	if (is_td(kvm))
+		return tdx_gmem_private_max_mapping_level(kvm, pfn);
+
+	return 0;
+}
+
 #define VMX_REQUIRED_APICV_INHIBITS				\
 	(BIT(APICV_INHIBIT_REASON_DISABLED) |			\
 	 BIT(APICV_INHIBIT_REASON_ABSENT) |			\
@@ -131,7 +229,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.hardware_unsetup = vmx_hardware_unsetup,
 
 	.enable_virtualization_cpu = vmx_enable_virtualization_cpu,
-	.disable_virtualization_cpu = vmx_disable_virtualization_cpu,
+	.disable_virtualization_cpu = vt_disable_virtualization_cpu,
 	.emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu,
 
 	.has_emulated_msr = vmx_has_emulated_msr,
@@ -148,7 +246,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_reset = vt_vcpu_reset,
 
 	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
-	.vcpu_load = vmx_vcpu_load,
+	.vcpu_load = vt_vcpu_load,
 	.vcpu_put = vmx_vcpu_put,
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
@@ -178,10 +276,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.set_rflags = vmx_set_rflags,
 	.get_if_flag = vmx_get_if_flag,
 
-	.flush_tlb_all = vmx_flush_tlb_all,
-	.flush_tlb_current = vmx_flush_tlb_current,
-	.flush_tlb_gva = vmx_flush_tlb_gva,
-	.flush_tlb_guest = vmx_flush_tlb_guest,
+	.flush_tlb_all = vt_flush_tlb_all,
+	.flush_tlb_current = vt_flush_tlb_current,
+	.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,
@@ -231,13 +329,12 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.write_tsc_offset = vmx_write_tsc_offset,
 	.write_tsc_multiplier = vmx_write_tsc_multiplier,
 
-	.load_mmu_pgd = vmx_load_mmu_pgd,
+	.load_mmu_pgd = vt_load_mmu_pgd,
 
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
 
-	.cpu_dirty_log_size = PML_LOG_NR_ENTRIES,
-	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
+	.update_cpu_dirty_logging = vt_update_cpu_dirty_logging,
 
 	.nested_ops = &vmx_nested_ops,
 
@@ -271,6 +368,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.mem_enc_ioctl = vt_mem_enc_ioctl,
 	.vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl,
+
+	.private_max_mapping_level = vt_gmem_private_max_mapping_level
 };
 
 struct kvm_x86_init_ops vt_init_ops __initdata = {
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 01166cb8f2e6..277f5decde9c 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <asm/cpufeature.h>
 #include <linux/misc_cgroup.h>
@@ -8,6 +9,9 @@
 #include "x86_ops.h"
 #include "lapic.h"
 #include "tdx.h"
+#include "vmx.h"
+#include "mmu/spte.h"
+#include "common.h"
 
 #pragma GCC poison to_vmx
 
@@ -32,10 +36,26 @@
 bool enable_tdx __ro_after_init;
 module_param_named(tdx, enable_tdx, bool, 0444);
 
+#define TDX_SHARED_BIT_PWL_5 gpa_to_gfn(BIT_ULL(51))
+#define TDX_SHARED_BIT_PWL_4 gpa_to_gfn(BIT_ULL(47))
+
 static enum cpuhp_state tdx_cpuhp_state;
 
 static const struct tdx_sys_info *tdx_sysinfo;
 
+void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err)
+{
+	KVM_BUG_ON(1, tdx->vcpu.kvm);
+	pr_err("TDH_VP_RD[%s.0x%x] failed 0x%llx\n", uclass, field, err);
+}
+
+void tdh_vp_wr_failed(struct vcpu_tdx *tdx, char *uclass, char *op, u32 field,
+		      u64 val, u64 err)
+{
+	KVM_BUG_ON(1, tdx->vcpu.kvm);
+	pr_err("TDH_VP_WR[%s.0x%x]%s0x%llx failed: 0x%llx\n", uclass, field, op, val, err);
+}
+
 #define KVM_SUPPORTED_TD_ATTRS (TDX_TD_ATTR_SEPT_VE_DISABLE)
 
 static __always_inline struct kvm_tdx *to_kvm_tdx(struct kvm *kvm)
@@ -136,6 +156,27 @@ static DEFINE_MUTEX(tdx_lock);
 
 static atomic_t nr_configured_hkid;
 
+static bool tdx_operand_busy(u64 err)
+{
+	return (err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_BUSY;
+}
+
+
+/*
+ * A per-CPU list of TD vCPUs associated with a given CPU.
+ * Protected by interrupt mask. Only manipulated by the CPU owning this per-CPU
+ * list.
+ * - When a vCPU is loaded onto a CPU, it is removed from the per-CPU list of
+ *   the old CPU during the IPI callback running on the old CPU, and then added
+ *   to the per-CPU list of the new CPU.
+ * - When a TD is tearing down, all vCPUs are disassociated from their current
+ *   running CPUs and removed from the per-CPU list during the IPI callback
+ *   running on those CPUs.
+ * - When a CPU is brought down, traverse the per-CPU list to disassociate all
+ *   associated TD vCPUs and remove them from the per-CPU list.
+ */
+static DEFINE_PER_CPU(struct list_head, associated_tdvcpus);
+
 static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx)
 {
 	tdx_guest_keyid_free(kvm_tdx->hkid);
@@ -151,6 +192,22 @@ static inline bool is_hkid_assigned(struct kvm_tdx *kvm_tdx)
 	return kvm_tdx->hkid > 0;
 }
 
+static inline void tdx_disassociate_vp(struct kvm_vcpu *vcpu)
+{
+	lockdep_assert_irqs_disabled();
+
+	list_del(&to_tdx(vcpu)->cpu_list);
+
+	/*
+	 * Ensure tdx->cpu_list is updated before setting vcpu->cpu to -1,
+	 * otherwise, a different CPU can see vcpu->cpu = -1 and add the vCPU
+	 * to its list before it's deleted from this CPU's list.
+	 */
+	smp_wmb();
+
+	vcpu->cpu = -1;
+}
+
 static void tdx_clear_page(struct page *page)
 {
 	const void *zero_page = (const void *) page_to_virt(ZERO_PAGE(0));
@@ -217,6 +274,83 @@ static void tdx_reclaim_control_page(struct page *ctrl_page)
 	__free_page(ctrl_page);
 }
 
+struct tdx_flush_vp_arg {
+	struct kvm_vcpu *vcpu;
+	u64 err;
+};
+
+static void tdx_flush_vp(void *_arg)
+{
+	struct tdx_flush_vp_arg *arg = _arg;
+	struct kvm_vcpu *vcpu = arg->vcpu;
+	u64 err;
+
+	arg->err = 0;
+	lockdep_assert_irqs_disabled();
+
+	/* Task migration can race with CPU offlining. */
+	if (unlikely(vcpu->cpu != raw_smp_processor_id()))
+		return;
+
+	/*
+	 * No need to do TDH_VP_FLUSH if the vCPU hasn't been initialized.  The
+	 * list tracking still needs to be updated so that it's correct if/when
+	 * the vCPU does get initialized.
+	 */
+	if (to_tdx(vcpu)->state != VCPU_TD_STATE_UNINITIALIZED) {
+		/*
+		 * No need to retry.  TDX Resources needed for TDH.VP.FLUSH are:
+		 * TDVPR as exclusive, TDR as shared, and TDCS as shared.  This
+		 * vp flush function is called when destructing vCPU/TD or vCPU
+		 * migration.  No other thread uses TDVPR in those cases.
+		 */
+		err = tdh_vp_flush(&to_tdx(vcpu)->vp);
+		if (unlikely(err && err != TDX_VCPU_NOT_ASSOCIATED)) {
+			/*
+			 * This function is called in IPI context. Do not use
+			 * printk to avoid console semaphore.
+			 * The caller prints out the error message, instead.
+			 */
+			if (err)
+				arg->err = err;
+		}
+	}
+
+	tdx_disassociate_vp(vcpu);
+}
+
+static void tdx_flush_vp_on_cpu(struct kvm_vcpu *vcpu)
+{
+	struct tdx_flush_vp_arg arg = {
+		.vcpu = vcpu,
+	};
+	int cpu = vcpu->cpu;
+
+	if (unlikely(cpu == -1))
+		return;
+
+	smp_call_function_single(cpu, tdx_flush_vp, &arg, 1);
+	if (KVM_BUG_ON(arg.err, vcpu->kvm))
+		pr_tdx_error(TDH_VP_FLUSH, arg.err);
+}
+
+void tdx_disable_virtualization_cpu(void)
+{
+	int cpu = raw_smp_processor_id();
+	struct list_head *tdvcpus = &per_cpu(associated_tdvcpus, cpu);
+	struct tdx_flush_vp_arg arg;
+	struct vcpu_tdx *tdx, *tmp;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	/* Safe variant needed as tdx_disassociate_vp() deletes the entry. */
+	list_for_each_entry_safe(tdx, tmp, tdvcpus, cpu_list) {
+		arg.vcpu = &tdx->vcpu;
+		tdx_flush_vp(&arg);
+	}
+	local_irq_restore(flags);
+}
+
 #define TDX_SEAMCALL_RETRIES 10000
 
 static void smp_func_do_phymem_cache_wb(void *unused)
@@ -255,22 +389,21 @@ void tdx_mmu_release_hkid(struct kvm *kvm)
 	bool packages_allocated, targets_allocated;
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
 	cpumask_var_t packages, targets;
-	u64 err;
+	struct kvm_vcpu *vcpu;
+	unsigned long j;
 	int i;
+	u64 err;
 
 	if (!is_hkid_assigned(kvm_tdx))
 		return;
 
-	/* KeyID has been allocated but guest is not yet configured */
-	if (!kvm_tdx->td.tdr_page) {
-		tdx_hkid_free(kvm_tdx);
-		return;
-	}
-
 	packages_allocated = zalloc_cpumask_var(&packages, GFP_KERNEL);
 	targets_allocated = zalloc_cpumask_var(&targets, GFP_KERNEL);
 	cpus_read_lock();
 
+	kvm_for_each_vcpu(j, vcpu, kvm)
+		tdx_flush_vp_on_cpu(vcpu);
+
 	/*
 	 * TDH.PHYMEM.CACHE.WB tries to acquire the TDX module global lock
 	 * and can fail with TDX_OPERAND_BUSY when it fails to get the lock.
@@ -284,6 +417,16 @@ void tdx_mmu_release_hkid(struct kvm *kvm)
 	 * After the above flushing vps, there should be no more vCPU
 	 * associations, as all vCPU fds have been released at this stage.
 	 */
+	err = tdh_mng_vpflushdone(&kvm_tdx->td);
+	if (err == TDX_FLUSHVP_NOT_DONE)
+		goto out;
+	if (KVM_BUG_ON(err, kvm)) {
+		pr_tdx_error(TDH_MNG_VPFLUSHDONE, err);
+		pr_err("tdh_mng_vpflushdone() failed. HKID %d is leaked.\n",
+		       kvm_tdx->hkid);
+		goto out;
+	}
+
 	for_each_online_cpu(i) {
 		if (packages_allocated &&
 		    cpumask_test_and_set_cpu(topology_physical_package_id(i),
@@ -309,6 +452,7 @@ void tdx_mmu_release_hkid(struct kvm *kvm)
 		tdx_hkid_free(kvm_tdx);
 	}
 
+out:
 	mutex_unlock(&tdx_lock);
 	cpus_read_unlock();
 	free_cpumask_var(targets);
@@ -395,6 +539,19 @@ int tdx_vm_init(struct kvm *kvm)
 	kvm->arch.has_private_mem = true;
 
 	/*
+	 * Because guest TD is protected, VMM can't parse the instruction in TD.
+	 * Instead, guest uses MMIO hypercall.  For unmodified device driver,
+	 * #VE needs to be injected for MMIO and #VE handler in TD converts MMIO
+	 * instruction into MMIO hypercall.
+	 *
+	 * SPTE value for MMIO needs to be setup so that #VE is injected into
+	 * TD instead of triggering EPT MISCONFIG.
+	 * - RWX=0 so that EPT violation is triggered.
+	 * - suppress #VE bit is cleared to inject #VE.
+	 */
+	kvm_mmu_set_mmio_spte_value(kvm, 0);
+
+	/*
 	 * TDX has its own limit of maximum vCPUs it can support for all
 	 * TDX guests in addition to KVM_MAX_VCPUS.  TDX module reports
 	 * such limit via the MAX_VCPU_PER_TD global metadata.  In
@@ -449,6 +606,27 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	if (vcpu->cpu == cpu || !is_hkid_assigned(to_kvm_tdx(vcpu->kvm)))
+		return;
+
+	tdx_flush_vp_on_cpu(vcpu);
+
+	KVM_BUG_ON(cpu != raw_smp_processor_id(), vcpu->kvm);
+	local_irq_disable();
+	/*
+	 * Pairs with the smp_wmb() in tdx_disassociate_vp() to ensure
+	 * vcpu->cpu is read before tdx->cpu_list.
+	 */
+	smp_rmb();
+
+	list_add(&tdx->cpu_list, &per_cpu(associated_tdvcpus, cpu));
+	local_irq_enable();
+}
+
 void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
@@ -482,6 +660,320 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 	tdx->state = VCPU_TD_STATE_UNINITIALIZED;
 }
 
+
+void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
+{
+	u64 shared_bit = (pgd_level == 5) ? TDX_SHARED_BIT_PWL_5 :
+			  TDX_SHARED_BIT_PWL_4;
+
+	if (KVM_BUG_ON(shared_bit != kvm_gfn_direct_bits(vcpu->kvm), vcpu->kvm))
+		return;
+
+	td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa);
+}
+
+static void tdx_unpin(struct kvm *kvm, struct page *page)
+{
+	put_page(page);
+}
+
+static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
+			    enum pg_level level, struct page *page)
+{
+	int tdx_level = pg_level_to_tdx_sept_level(level);
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	gpa_t gpa = gfn_to_gpa(gfn);
+	u64 entry, level_state;
+	u64 err;
+
+	err = tdh_mem_page_aug(&kvm_tdx->td, gpa, tdx_level, page, &entry, &level_state);
+	if (unlikely(tdx_operand_busy(err))) {
+		tdx_unpin(kvm, page);
+		return -EBUSY;
+	}
+
+	if (KVM_BUG_ON(err, kvm)) {
+		pr_tdx_error_2(TDH_MEM_PAGE_AUG, err, entry, level_state);
+		tdx_unpin(kvm, page);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * KVM_TDX_INIT_MEM_REGION calls kvm_gmem_populate() to map guest pages; the
+ * callback tdx_gmem_post_populate() then maps pages into private memory.
+ * through the a seamcall TDH.MEM.PAGE.ADD().  The SEAMCALL also requires the
+ * private EPT structures for the page to have been built before, which is
+ * done via kvm_tdp_map_page(). nr_premapped counts the number of pages that
+ * were added to the EPT structures but not added with TDH.MEM.PAGE.ADD().
+ * The counter has to be zero on KVM_TDX_FINALIZE_VM, to ensure that there
+ * are no half-initialized shared EPT pages.
+ */
+static int tdx_mem_page_record_premap_cnt(struct kvm *kvm, gfn_t gfn,
+					  enum pg_level level, kvm_pfn_t pfn)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+	if (KVM_BUG_ON(kvm->arch.pre_fault_allowed, kvm))
+		return -EINVAL;
+
+	/* nr_premapped will be decreased when tdh_mem_page_add() is called. */
+	atomic64_inc(&kvm_tdx->nr_premapped);
+	return 0;
+}
+
+int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
+			      enum pg_level level, kvm_pfn_t pfn)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	struct page *page = pfn_to_page(pfn);
+
+	/* TODO: handle large pages. */
+	if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
+		return -EINVAL;
+
+	/*
+	 * Because guest_memfd doesn't support page migration with
+	 * a_ops->migrate_folio (yet), no callback is triggered for KVM on page
+	 * migration.  Until guest_memfd supports page migration, prevent page
+	 * migration.
+	 * TODO: Once guest_memfd introduces callback on page migration,
+	 * implement it and remove get_page/put_page().
+	 */
+	get_page(page);
+
+	/*
+	 * Read 'pre_fault_allowed' before 'kvm_tdx->state'; see matching
+	 * barrier in tdx_td_finalize().
+	 */
+	smp_rmb();
+	if (likely(kvm_tdx->state == TD_STATE_RUNNABLE))
+		return tdx_mem_page_aug(kvm, gfn, level, page);
+
+	return tdx_mem_page_record_premap_cnt(kvm, gfn, level, pfn);
+}
+
+static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
+				      enum pg_level level, struct page *page)
+{
+	int tdx_level = pg_level_to_tdx_sept_level(level);
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	gpa_t gpa = gfn_to_gpa(gfn);
+	u64 err, entry, level_state;
+
+	/* TODO: handle large pages. */
+	if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
+		return -EINVAL;
+
+	if (KVM_BUG_ON(!is_hkid_assigned(kvm_tdx), kvm))
+		return -EINVAL;
+
+	do {
+		/*
+		 * When zapping private page, write lock is held. So no race
+		 * condition with other vcpu sept operation.  Race only with
+		 * TDH.VP.ENTER.
+		 */
+		err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
+					  &level_state);
+	} while (unlikely(tdx_operand_busy(err)));
+
+	if (KVM_BUG_ON(err, kvm)) {
+		pr_tdx_error_2(TDH_MEM_PAGE_REMOVE, err, entry, level_state);
+		return -EIO;
+	}
+
+	err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page);
+
+	if (KVM_BUG_ON(err, kvm)) {
+		pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
+		return -EIO;
+	}
+	tdx_clear_page(page);
+	tdx_unpin(kvm, page);
+	return 0;
+}
+
+int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
+			      enum pg_level level, void *private_spt)
+{
+	int tdx_level = pg_level_to_tdx_sept_level(level);
+	gpa_t gpa = gfn_to_gpa(gfn);
+	struct page *page = virt_to_page(private_spt);
+	u64 err, entry, level_state;
+
+	err = tdh_mem_sept_add(&to_kvm_tdx(kvm)->td, gpa, tdx_level, page, &entry,
+			       &level_state);
+	if (unlikely(tdx_operand_busy(err)))
+		return -EBUSY;
+
+	if (KVM_BUG_ON(err, kvm)) {
+		pr_tdx_error_2(TDH_MEM_SEPT_ADD, err, entry, level_state);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * Check if the error returned from a SEPT zap SEAMCALL is due to that a page is
+ * mapped by KVM_TDX_INIT_MEM_REGION without tdh_mem_page_add() being called
+ * successfully.
+ *
+ * Since tdh_mem_sept_add() must have been invoked successfully before a
+ * non-leaf entry present in the mirrored page table, the SEPT ZAP related
+ * SEAMCALLs should not encounter err TDX_EPT_WALK_FAILED. They should instead
+ * find TDX_EPT_ENTRY_STATE_INCORRECT due to an empty leaf entry found in the
+ * SEPT.
+ *
+ * Further check if the returned entry from SEPT walking is with RWX permissions
+ * to filter out anything unexpected.
+ *
+ * Note: @level is pg_level, not the tdx_level. The tdx_level extracted from
+ * level_state returned from a SEAMCALL error is the same as that passed into
+ * the SEAMCALL.
+ */
+static int tdx_is_sept_zap_err_due_to_premap(struct kvm_tdx *kvm_tdx, u64 err,
+					     u64 entry, int level)
+{
+	if (!err || kvm_tdx->state == TD_STATE_RUNNABLE)
+		return false;
+
+	if (err != (TDX_EPT_ENTRY_STATE_INCORRECT | TDX_OPERAND_ID_RCX))
+		return false;
+
+	if ((is_last_spte(entry, level) && (entry & VMX_EPT_RWX_MASK)))
+		return false;
+
+	return true;
+}
+
+static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn,
+				     enum pg_level level, struct page *page)
+{
+	int tdx_level = pg_level_to_tdx_sept_level(level);
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	gpa_t gpa = gfn_to_gpa(gfn) & KVM_HPAGE_MASK(level);
+	u64 err, entry, level_state;
+
+	/* For now large page isn't supported yet. */
+	WARN_ON_ONCE(level != PG_LEVEL_4K);
+
+	err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state);
+	if (unlikely(tdx_operand_busy(err)))
+		return -EBUSY;
+
+	if (tdx_is_sept_zap_err_due_to_premap(kvm_tdx, err, entry, level) &&
+	    !KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) {
+		atomic64_dec(&kvm_tdx->nr_premapped);
+		tdx_unpin(kvm, page);
+		return 0;
+	}
+
+	if (KVM_BUG_ON(err, kvm)) {
+		pr_tdx_error_2(TDH_MEM_RANGE_BLOCK, err, entry, level_state);
+		return -EIO;
+	}
+	return 1;
+}
+
+/*
+ * Ensure shared and private EPTs to be flushed on all vCPUs.
+ * tdh_mem_track() is the only caller that increases TD epoch. An increase in
+ * the TD epoch (e.g., to value "N + 1") is successful only if no vCPUs are
+ * running in guest mode with the value "N - 1".
+ *
+ * A successful execution of tdh_mem_track() ensures that vCPUs can only run in
+ * guest mode with TD epoch value "N" if no TD exit occurs after the TD epoch
+ * being increased to "N + 1".
+ *
+ * Kicking off all vCPUs after that further results in no vCPUs can run in guest
+ * mode with TD epoch value "N", which unblocks the next tdh_mem_track() (e.g.
+ * to increase TD epoch to "N + 2").
+ *
+ * TDX module will flush EPT on the next TD enter and make vCPUs to run in
+ * guest mode with TD epoch value "N + 1".
+ *
+ * kvm_make_all_cpus_request() guarantees all vCPUs are out of guest mode by
+ * waiting empty IPI handler ack_kick().
+ *
+ * No action is required to the vCPUs being kicked off since the kicking off
+ * occurs certainly after TD epoch increment and before the next
+ * tdh_mem_track().
+ */
+static void tdx_track(struct kvm *kvm)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	u64 err;
+
+	/* If TD isn't finalized, it's before any vcpu running. */
+	if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE))
+		return;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	do {
+		err = tdh_mem_track(&kvm_tdx->td);
+	} while (unlikely(tdx_operand_busy(err)));
+
+	if (KVM_BUG_ON(err, kvm))
+		pr_tdx_error(TDH_MEM_TRACK, err);
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
+}
+
+int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
+			      enum pg_level level, void *private_spt)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+	/*
+	 * free_external_spt() is only called after hkid is freed when TD is
+	 * tearing down.
+	 * KVM doesn't (yet) zap page table pages in mirror page table while
+	 * TD is active, though guest pages mapped in mirror page table could be
+	 * zapped during TD is active, e.g. for shared <-> private conversion
+	 * and slot move/deletion.
+	 */
+	if (KVM_BUG_ON(is_hkid_assigned(kvm_tdx), kvm))
+		return -EINVAL;
+
+	/*
+	 * The HKID assigned to this TD was already freed and cache was
+	 * already flushed. We don't have to flush again.
+	 */
+	return tdx_reclaim_page(virt_to_page(private_spt));
+}
+
+int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
+				 enum pg_level level, kvm_pfn_t pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	int ret;
+
+	/*
+	 * HKID is released after all private pages have been removed, and set
+	 * before any might be populated. Warn if zapping is attempted when
+	 * there can't be anything populated in the private EPT.
+	 */
+	if (KVM_BUG_ON(!is_hkid_assigned(to_kvm_tdx(kvm)), kvm))
+		return -EINVAL;
+
+	ret = tdx_sept_zap_private_spte(kvm, gfn, level, page);
+	if (ret <= 0)
+		return ret;
+
+	/*
+	 * TDX requires TLB tracking before dropping private page.  Do
+	 * it here, although it is also done later.
+	 */
+	tdx_track(kvm);
+
+	return tdx_sept_drop_private_spte(kvm, gfn, level, page);
+}
+
 static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
 {
 	const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
@@ -1023,6 +1515,11 @@ static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
 	kvm_tdx->attributes = td_params->attributes;
 	kvm_tdx->xfam = td_params->xfam;
 
+	if (td_params->config_flags & TDX_CONFIG_FLAGS_MAX_GPAW)
+		kvm->arch.gfn_direct_bits = TDX_SHARED_BIT_PWL_5;
+	else
+		kvm->arch.gfn_direct_bits = TDX_SHARED_BIT_PWL_4;
+
 	kvm_tdx->state = TD_STATE_INITIALIZED;
 out:
 	/* kfree() accepts NULL. */
@@ -1032,6 +1529,71 @@ out:
 	return ret;
 }
 
+void tdx_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * flush_tlb_current() is invoked when the first time for the vcpu to
+	 * run or when root of shared EPT is invalidated.
+	 * KVM only needs to flush shared EPT because the TDX module handles TLB
+	 * invalidation for private EPT in tdh_vp_enter();
+	 *
+	 * A single context invalidation for shared EPT can be performed here.
+	 * However, this single context invalidation requires the private EPTP
+	 * rather than the shared EPTP to flush shared EPT, as shared EPT uses
+	 * private EPTP as its ASID for TLB invalidation.
+	 *
+	 * To avoid reading back private EPTP, perform a global invalidation for
+	 * shared EPT instead to keep this function simple.
+	 */
+	ept_sync_global();
+}
+
+void tdx_flush_tlb_all(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * TDX has called tdx_track() in tdx_sept_remove_private_spte() to
+	 * ensure that private EPT will be flushed on the next TD enter. No need
+	 * to call tdx_track() here again even when this callback is a result of
+	 * zapping private EPT.
+	 *
+	 * Due to the lack of the context to determine which EPT has been
+	 * affected by zapping, invoke invept() directly here for both shared
+	 * EPT and private EPT for simplicity, though it's not necessary for
+	 * private EPT.
+	 */
+	ept_sync_global();
+}
+
+static int tdx_td_finalize(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+	guard(mutex)(&kvm->slots_lock);
+
+	if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE)
+		return -EINVAL;
+	/*
+	 * Pages are pending for KVM_TDX_INIT_MEM_REGION to issue
+	 * TDH.MEM.PAGE.ADD().
+	 */
+	if (atomic64_read(&kvm_tdx->nr_premapped))
+		return -EINVAL;
+
+	cmd->hw_error = tdh_mr_finalize(&kvm_tdx->td);
+	if (tdx_operand_busy(cmd->hw_error))
+		return -EBUSY;
+	if (KVM_BUG_ON(cmd->hw_error, kvm)) {
+		pr_tdx_error(TDH_MR_FINALIZE, cmd->hw_error);
+		return -EIO;
+	}
+
+	kvm_tdx->state = TD_STATE_RUNNABLE;
+	/* TD_STATE_RUNNABLE must be set before 'pre_fault_allowed' */
+	smp_wmb();
+	kvm->arch.pre_fault_allowed = true;
+	return 0;
+}
+
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_tdx_cmd tdx_cmd;
@@ -1056,6 +1618,9 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_TDX_INIT_VM:
 		r = tdx_td_init(kvm, &tdx_cmd);
 		break;
+	case KVM_TDX_FINALIZE_VM:
+		r = tdx_td_finalize(kvm, &tdx_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
@@ -1269,6 +1834,148 @@ static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
 	return 0;
 }
 
+struct tdx_gmem_post_populate_arg {
+	struct kvm_vcpu *vcpu;
+	__u32 flags;
+};
+
+static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+				  void __user *src, int order, void *_arg)
+{
+	u64 error_code = PFERR_GUEST_FINAL_MASK | PFERR_PRIVATE_ACCESS;
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	struct tdx_gmem_post_populate_arg *arg = _arg;
+	struct kvm_vcpu *vcpu = arg->vcpu;
+	gpa_t gpa = gfn_to_gpa(gfn);
+	u8 level = PG_LEVEL_4K;
+	struct page *src_page;
+	int ret, i;
+	u64 err, entry, level_state;
+
+	/*
+	 * Get the source page if it has been faulted in. Return failure if the
+	 * source page has been swapped out or unmapped in primary memory.
+	 */
+	ret = get_user_pages_fast((unsigned long)src, 1, 0, &src_page);
+	if (ret < 0)
+		return ret;
+	if (ret != 1)
+		return -ENOMEM;
+
+	ret = kvm_tdp_map_page(vcpu, gpa, error_code, &level);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * The private mem cannot be zapped after kvm_tdp_map_page()
+	 * because all paths are covered by slots_lock and the
+	 * filemap invalidate lock.  Check that they are indeed enough.
+	 */
+	if (IS_ENABLED(CONFIG_KVM_PROVE_MMU)) {
+		scoped_guard(read_lock, &kvm->mmu_lock) {
+			if (KVM_BUG_ON(!kvm_tdp_mmu_gpa_is_mapped(vcpu, gpa), kvm)) {
+				ret = -EIO;
+				goto out;
+			}
+		}
+	}
+
+	ret = 0;
+	err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn_to_page(pfn),
+			       src_page, &entry, &level_state);
+	if (err) {
+		ret = unlikely(tdx_operand_busy(err)) ? -EBUSY : -EIO;
+		goto out;
+	}
+
+	if (!KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm))
+		atomic64_dec(&kvm_tdx->nr_premapped);
+
+	if (arg->flags & KVM_TDX_MEASURE_MEMORY_REGION) {
+		for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) {
+			err = tdh_mr_extend(&kvm_tdx->td, gpa + i, &entry,
+					    &level_state);
+			if (err) {
+				ret = -EIO;
+				break;
+			}
+		}
+	}
+
+out:
+	put_page(src_page);
+	return ret;
+}
+
+static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+	struct kvm_tdx_init_mem_region region;
+	struct tdx_gmem_post_populate_arg arg;
+	long gmem_ret;
+	int ret;
+
+	if (tdx->state != VCPU_TD_STATE_INITIALIZED)
+		return -EINVAL;
+
+	guard(mutex)(&kvm->slots_lock);
+
+	/* Once TD is finalized, the initial guest memory is fixed. */
+	if (kvm_tdx->state == TD_STATE_RUNNABLE)
+		return -EINVAL;
+
+	if (cmd->flags & ~KVM_TDX_MEASURE_MEMORY_REGION)
+		return -EINVAL;
+
+	if (copy_from_user(&region, u64_to_user_ptr(cmd->data), sizeof(region)))
+		return -EFAULT;
+
+	if (!PAGE_ALIGNED(region.source_addr) || !PAGE_ALIGNED(region.gpa) ||
+	    !region.nr_pages ||
+	    region.gpa + (region.nr_pages << PAGE_SHIFT) <= region.gpa ||
+	    !vt_is_tdx_private_gpa(kvm, region.gpa) ||
+	    !vt_is_tdx_private_gpa(kvm, region.gpa + (region.nr_pages << PAGE_SHIFT) - 1))
+		return -EINVAL;
+
+	kvm_mmu_reload(vcpu);
+	ret = 0;
+	while (region.nr_pages) {
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		arg = (struct tdx_gmem_post_populate_arg) {
+			.vcpu = vcpu,
+			.flags = cmd->flags,
+		};
+		gmem_ret = kvm_gmem_populate(kvm, gpa_to_gfn(region.gpa),
+					     u64_to_user_ptr(region.source_addr),
+					     1, tdx_gmem_post_populate, &arg);
+		if (gmem_ret < 0) {
+			ret = gmem_ret;
+			break;
+		}
+
+		if (gmem_ret != 1) {
+			ret = -EIO;
+			break;
+		}
+
+		region.source_addr += PAGE_SIZE;
+		region.gpa += PAGE_SIZE;
+		region.nr_pages--;
+
+		cond_resched();
+	}
+
+	if (copy_to_user(u64_to_user_ptr(cmd->data), &region, sizeof(region)))
+		ret = -EFAULT;
+	return ret;
+}
+
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 {
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
@@ -1288,6 +1995,9 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 	case KVM_TDX_INIT_VCPU:
 		ret = tdx_vcpu_init(vcpu, &cmd);
 		break;
+	case KVM_TDX_INIT_MEM_REGION:
+		ret = tdx_vcpu_init_mem_region(vcpu, &cmd);
+		break;
 	case KVM_TDX_GET_CPUID:
 		ret = tdx_vcpu_get_cpuid(vcpu, &cmd);
 		break;
@@ -1299,6 +2009,11 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 	return ret;
 }
 
+int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+	return PG_LEVEL_4K;
+}
+
 static int tdx_online_cpu(unsigned int cpu)
 {
 	unsigned long flags;
@@ -1496,11 +2211,25 @@ void tdx_cleanup(void)
 
 int __init tdx_bringup(void)
 {
-	int r;
+	int r, i;
+
+	/* tdx_disable_virtualization_cpu() uses associated_tdvcpus. */
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(associated_tdvcpus, i));
 
 	if (!enable_tdx)
 		return 0;
 
+	if (!enable_ept) {
+		pr_err("EPT is required for TDX\n");
+		goto success_disable_tdx;
+	}
+
+	if (!tdp_mmu_enabled || !enable_mmio_caching || !enable_ept_ad_bits) {
+		pr_err("TDP MMU and MMIO caching and EPT A/D bit 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 0559126c8f9d..5f34b79d16dd 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -32,6 +32,9 @@ struct kvm_tdx {
 	u64 tsc_multiplier;
 
 	struct tdx_td td;
+
+	/* For KVM_TDX_INIT_MEM_REGION. */
+	atomic64_t nr_premapped;
 };
 
 /* TDX module vCPU states */
@@ -45,9 +48,15 @@ struct vcpu_tdx {
 
 	struct tdx_vp vp;
 
+	struct list_head cpu_list;
+
 	enum vcpu_tdx_state state;
 };
 
+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;
@@ -69,6 +78,90 @@ static __always_inline u64 td_tdcs_exec_read64(struct kvm_tdx *kvm_tdx, u32 fiel
 	}
 	return data;
 }
+
+static __always_inline void tdvps_vmcs_check(u32 field, u8 bits)
+{
+#define VMCS_ENC_ACCESS_TYPE_MASK	0x1UL
+#define VMCS_ENC_ACCESS_TYPE_FULL	0x0UL
+#define VMCS_ENC_ACCESS_TYPE_HIGH	0x1UL
+#define VMCS_ENC_ACCESS_TYPE(field)	((field) & VMCS_ENC_ACCESS_TYPE_MASK)
+
+	/* TDX is 64bit only.  HIGH field isn't supported. */
+	BUILD_BUG_ON_MSG(__builtin_constant_p(field) &&
+			 VMCS_ENC_ACCESS_TYPE(field) == VMCS_ENC_ACCESS_TYPE_HIGH,
+			 "Read/Write to TD VMCS *_HIGH fields not supported");
+
+	BUILD_BUG_ON(bits != 16 && bits != 32 && bits != 64);
+
+#define VMCS_ENC_WIDTH_MASK	GENMASK(14, 13)
+#define VMCS_ENC_WIDTH_16BIT	(0UL << 13)
+#define VMCS_ENC_WIDTH_64BIT	(1UL << 13)
+#define VMCS_ENC_WIDTH_32BIT	(2UL << 13)
+#define VMCS_ENC_WIDTH_NATURAL	(3UL << 13)
+#define VMCS_ENC_WIDTH(field)	((field) & VMCS_ENC_WIDTH_MASK)
+
+	/* TDX is 64bit only.  i.e. natural width = 64bit. */
+	BUILD_BUG_ON_MSG(bits != 64 && __builtin_constant_p(field) &&
+			 (VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_64BIT ||
+			  VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_NATURAL),
+			 "Invalid TD VMCS access for 64-bit field");
+	BUILD_BUG_ON_MSG(bits != 32 && __builtin_constant_p(field) &&
+			 VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_32BIT,
+			 "Invalid TD VMCS access for 32-bit field");
+	BUILD_BUG_ON_MSG(bits != 16 && __builtin_constant_p(field) &&
+			 VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_16BIT,
+			 "Invalid TD VMCS access for 16-bit field");
+}
+
+#define TDX_BUILD_TDVPS_ACCESSORS(bits, uclass, lclass)				\
+static __always_inline u##bits td_##lclass##_read##bits(struct vcpu_tdx *tdx,	\
+							u32 field)		\
+{										\
+	u64 err, data;								\
+										\
+	tdvps_##lclass##_check(field, bits);					\
+	err = tdh_vp_rd(&tdx->vp, TDVPS_##uclass(field), &data);		\
+	if (unlikely(err)) {							\
+		tdh_vp_rd_failed(tdx, #uclass, field, err);			\
+		return 0;							\
+	}									\
+	return (u##bits)data;							\
+}										\
+static __always_inline void td_##lclass##_write##bits(struct vcpu_tdx *tdx,	\
+						      u32 field, u##bits val)	\
+{										\
+	u64 err;								\
+										\
+	tdvps_##lclass##_check(field, bits);					\
+	err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), val,			\
+		      GENMASK_ULL(bits - 1, 0));				\
+	if (unlikely(err))							\
+		tdh_vp_wr_failed(tdx, #uclass, " = ", field, (u64)val, err);	\
+}										\
+static __always_inline void td_##lclass##_setbit##bits(struct vcpu_tdx *tdx,	\
+						       u32 field, u64 bit)	\
+{										\
+	u64 err;								\
+										\
+	tdvps_##lclass##_check(field, bits);					\
+	err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), bit, bit);		\
+	if (unlikely(err))							\
+		tdh_vp_wr_failed(tdx, #uclass, " |= ", field, bit, err);	\
+}										\
+static __always_inline void td_##lclass##_clearbit##bits(struct vcpu_tdx *tdx,	\
+							 u32 field, u64 bit)	\
+{										\
+	u64 err;								\
+										\
+	tdvps_##lclass##_check(field, bits);					\
+	err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), 0, bit);		\
+	if (unlikely(err))							\
+		tdh_vp_wr_failed(tdx, #uclass, " &= ~", field, bit, err);\
+}
+
+TDX_BUILD_TDVPS_ACCESSORS(16, VMCS, vmcs);
+TDX_BUILD_TDVPS_ACCESSORS(32, VMCS, vmcs);
+TDX_BUILD_TDVPS_ACCESSORS(64, VMCS, vmcs);
 #else
 static inline int tdx_bringup(void) { return 0; }
 static inline void tdx_cleanup(void) {}
diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h
index 55a740f90e67..58bda8a5ce9a 100644
--- a/arch/x86/kvm/vmx/tdx_arch.h
+++ b/arch/x86/kvm/vmx/tdx_arch.h
@@ -121,6 +121,29 @@ struct td_params {
 #define TDX_MIN_TSC_FREQUENCY_KHZ		(100 * 1000)
 #define TDX_MAX_TSC_FREQUENCY_KHZ		(10 * 1000 * 1000)
 
+/* Additional Secure EPT entry information */
+#define TDX_SEPT_LEVEL_MASK		GENMASK_ULL(2, 0)
+#define TDX_SEPT_STATE_MASK		GENMASK_ULL(15, 8)
+#define TDX_SEPT_STATE_SHIFT		8
+
+enum tdx_sept_entry_state {
+	TDX_SEPT_FREE = 0,
+	TDX_SEPT_BLOCKED = 1,
+	TDX_SEPT_PENDING = 2,
+	TDX_SEPT_PENDING_BLOCKED = 3,
+	TDX_SEPT_PRESENT = 4,
+};
+
+static inline u8 tdx_get_sept_level(u64 sept_entry_info)
+{
+	return sept_entry_info & TDX_SEPT_LEVEL_MASK;
+}
+
+static inline u8 tdx_get_sept_state(u64 sept_entry_info)
+{
+	return (sept_entry_info & TDX_SEPT_STATE_MASK) >> TDX_SEPT_STATE_SHIFT;
+}
+
 #define MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM	BIT_ULL(20)
 
 /*
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 03d9e5069791..39d55d638899 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -53,6 +53,7 @@
 #include <trace/events/ipi.h>
 
 #include "capabilities.h"
+#include "common.h"
 #include "cpuid.h"
 #include "hyperv.h"
 #include "kvm_onhyperv.h"
@@ -5787,11 +5788,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 
 static int handle_ept_violation(struct kvm_vcpu *vcpu)
 {
-	unsigned long exit_qualification;
+	unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
 	gpa_t gpa;
-	u64 error_code;
-
-	exit_qualification = vmx_get_exit_qual(vcpu);
 
 	/*
 	 * EPT violation happened while executing iret from NMI,
@@ -5807,23 +5805,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
 	trace_kvm_page_fault(vcpu, gpa, exit_qualification);
 
-	/* Is it a read fault? */
-	error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
-		     ? PFERR_USER_MASK : 0;
-	/* Is it a write fault? */
-	error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
-		      ? PFERR_WRITE_MASK : 0;
-	/* Is it a fetch fault? */
-	error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
-		      ? PFERR_FETCH_MASK : 0;
-	/* ept page table entry is present? */
-	error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK)
-		      ? PFERR_PRESENT_MASK : 0;
-
-	if (error_code & EPT_VIOLATION_GVA_IS_VALID)
-		error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
-			      PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
-
 	/*
 	 * Check that the GPA doesn't exceed physical memory limits, as that is
 	 * a guest page fault.  We have to emulate the instruction here, because
@@ -5835,7 +5816,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa)))
 		return kvm_emulate_instruction(vcpu, 0);
 
-	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
+	return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification);
 }
 
 static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
@@ -7668,6 +7649,9 @@ int vmx_vm_init(struct kvm *kvm)
 			break;
 		}
 	}
+
+	if (enable_pml)
+		kvm->arch.cpu_dirty_log_size = PML_LOG_NR_ENTRIES;
 	return 0;
 }
 
@@ -8521,9 +8505,6 @@ __init int vmx_hardware_setup(void)
 	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
 		enable_pml = 0;
 
-	if (!enable_pml)
-		vt_x86_ops.cpu_dirty_log_size = 0;
-
 	if (!cpu_has_vmx_preemption_timer())
 		enable_preemption_timer = false;
 
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 89bb7785bd09..f47d739051cf 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -122,6 +122,7 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu);
 void vmx_setup_mce(struct kvm_vcpu *vcpu);
 
 #ifdef CONFIG_KVM_INTEL_TDX
+void tdx_disable_virtualization_cpu(void);
 int tdx_vm_init(struct kvm *kvm);
 void tdx_mmu_release_hkid(struct kvm *kvm);
 void tdx_vm_destroy(struct kvm *kvm);
@@ -129,9 +130,25 @@ 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_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
+
+int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
+			      enum pg_level level, void *private_spt);
+int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
+			      enum pg_level level, void *private_spt);
+int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
+			      enum pg_level level, kvm_pfn_t pfn);
+int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
+				 enum pg_level level, kvm_pfn_t pfn);
+
+void tdx_flush_tlb_current(struct kvm_vcpu *vcpu);
+void tdx_flush_tlb_all(struct kvm_vcpu *vcpu);
+void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
+int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
 #else
+static inline void tdx_disable_virtualization_cpu(void) {}
 static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; }
 static inline void tdx_mmu_release_hkid(struct kvm *kvm) {}
 static inline void tdx_vm_destroy(struct kvm *kvm) {}
@@ -139,8 +156,42 @@ 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_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
+
+static inline int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
+					    enum pg_level level,
+					    void *private_spt)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
+					    enum pg_level level,
+					    void *private_spt)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
+					    enum pg_level level,
+					    kvm_pfn_t pfn)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
+					       enum pg_level level,
+					       kvm_pfn_t pfn)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void tdx_flush_tlb_current(struct kvm_vcpu *vcpu) {}
+static inline void tdx_flush_tlb_all(struct kvm_vcpu *vcpu) {}
+static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {}
+static inline int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) { return 0; }
 #endif
 
 #endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9f92170226e5..8f3292ccdca4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6480,7 +6480,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
-	if (!kvm_x86_ops.cpu_dirty_log_size)
+	if (!kvm->arch.cpu_dirty_log_size)
 		return;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -13078,7 +13078,7 @@ static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable)
 {
 	int nr_slots;
 
-	if (!kvm_x86_ops.cpu_dirty_log_size)
+	if (!kvm->arch.cpu_dirty_log_size)
 		return;
 
 	nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging);
@@ -13150,7 +13150,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 		if (READ_ONCE(eager_page_split))
 			kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K);
 
-		if (kvm_x86_ops.cpu_dirty_log_size) {
+		if (kvm->arch.cpu_dirty_log_size) {
 			kvm_mmu_slot_leaf_clear_dirty(kvm, new);
 			kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M);
 		} else {
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 3a272e9ff2ca..8eaaf31a4187 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -1529,6 +1529,45 @@ u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page)
 }
 EXPORT_SYMBOL_GPL(tdh_mng_addcx);
 
+u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, struct page *page, struct page *source, u64 *ext_err1, u64 *ext_err2)
+{
+	struct tdx_module_args args = {
+		.rcx = gpa,
+		.rdx = tdx_tdr_pa(td),
+		.r8 = page_to_phys(page),
+		.r9 = page_to_phys(source),
+	};
+	u64 ret;
+
+	tdx_clflush_page(page);
+	ret = seamcall_ret(TDH_MEM_PAGE_ADD, &args);
+
+	*ext_err1 = args.rcx;
+	*ext_err2 = args.rdx;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_page_add);
+
+u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2)
+{
+	struct tdx_module_args args = {
+		.rcx = gpa | level,
+		.rdx = tdx_tdr_pa(td),
+		.r8 = page_to_phys(page),
+	};
+	u64 ret;
+
+	tdx_clflush_page(page);
+	ret = seamcall_ret(TDH_MEM_SEPT_ADD, &args);
+
+	*ext_err1 = args.rcx;
+	*ext_err2 = args.rdx;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_sept_add);
+
 u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page)
 {
 	struct tdx_module_args args = {
@@ -1541,6 +1580,42 @@ u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page)
 }
 EXPORT_SYMBOL_GPL(tdh_vp_addcx);
 
+u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2)
+{
+	struct tdx_module_args args = {
+		.rcx = gpa | level,
+		.rdx = tdx_tdr_pa(td),
+		.r8 = page_to_phys(page),
+	};
+	u64 ret;
+
+	tdx_clflush_page(page);
+	ret = seamcall_ret(TDH_MEM_PAGE_AUG, &args);
+
+	*ext_err1 = args.rcx;
+	*ext_err2 = args.rdx;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_page_aug);
+
+u64 tdh_mem_range_block(struct tdx_td *td, u64 gpa, int level, u64 *ext_err1, u64 *ext_err2)
+{
+	struct tdx_module_args args = {
+		.rcx = gpa | level,
+		.rdx = tdx_tdr_pa(td),
+	};
+	u64 ret;
+
+	ret = seamcall_ret(TDH_MEM_RANGE_BLOCK, &args);
+
+	*ext_err1 = args.rcx;
+	*ext_err2 = args.rdx;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_range_block);
+
 u64 tdh_mng_key_config(struct tdx_td *td)
 {
 	struct tdx_module_args args = {
@@ -1592,6 +1667,33 @@ u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data)
 }
 EXPORT_SYMBOL_GPL(tdh_mng_rd);
 
+u64 tdh_mr_extend(struct tdx_td *td, u64 gpa, u64 *ext_err1, u64 *ext_err2)
+{
+	struct tdx_module_args args = {
+		.rcx = gpa,
+		.rdx = tdx_tdr_pa(td),
+	};
+	u64 ret;
+
+	ret = seamcall_ret(TDH_MR_EXTEND, &args);
+
+	*ext_err1 = args.rcx;
+	*ext_err2 = args.rdx;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mr_extend);
+
+u64 tdh_mr_finalize(struct tdx_td *td)
+{
+	struct tdx_module_args args = {
+		.rcx = tdx_tdr_pa(td),
+	};
+
+	return seamcall(TDH_MR_FINALIZE, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mr_finalize);
+
 u64 tdh_vp_flush(struct tdx_vp *vp)
 {
 	struct tdx_module_args args = {
@@ -1703,6 +1805,33 @@ u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64
 }
 EXPORT_SYMBOL_GPL(tdh_phymem_page_reclaim);
 
+u64 tdh_mem_track(struct tdx_td *td)
+{
+	struct tdx_module_args args = {
+		.rcx = tdx_tdr_pa(td),
+	};
+
+	return seamcall(TDH_MEM_TRACK, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mem_track);
+
+u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u64 *ext_err2)
+{
+	struct tdx_module_args args = {
+		.rcx = gpa | level,
+		.rdx = tdx_tdr_pa(td),
+	};
+	u64 ret;
+
+	ret = seamcall_ret(TDH_MEM_PAGE_REMOVE, &args);
+
+	*ext_err1 = args.rcx;
+	*ext_err2 = args.rdx;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_page_remove);
+
 u64 tdh_phymem_cache_wb(bool resume)
 {
 	struct tdx_module_args args = {
@@ -1722,3 +1851,13 @@ u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td)
 	return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
 }
 EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_tdr);
+
+u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)
+{
+	struct tdx_module_args args = {};
+
+	args.rcx = mk_keyed_paddr(hkid, page);
+
+	return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_hkid);
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index da384387d4eb..ed7152f81a6d 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -15,10 +15,16 @@
  * TDX module SEAMCALL leaf functions
  */
 #define TDH_MNG_ADDCX			1
+#define TDH_MEM_PAGE_ADD		2
+#define TDH_MEM_SEPT_ADD		3
 #define TDH_VP_ADDCX			4
+#define TDH_MEM_PAGE_AUG		6
+#define TDH_MEM_RANGE_BLOCK		7
 #define TDH_MNG_KEY_CONFIG		8
 #define TDH_MNG_CREATE			9
 #define TDH_MNG_RD			11
+#define TDH_MR_EXTEND			16
+#define TDH_MR_FINALIZE			17
 #define TDH_VP_FLUSH			18
 #define TDH_MNG_VPFLUSHDONE		19
 #define TDH_VP_CREATE			10
@@ -28,11 +34,13 @@
 #define TDH_PHYMEM_PAGE_RDMD		24
 #define TDH_VP_RD			26
 #define TDH_PHYMEM_PAGE_RECLAIM		28
+#define TDH_MEM_PAGE_REMOVE		29
 #define TDH_SYS_KEY_CONFIG		31
 #define TDH_SYS_INIT			33
 #define TDH_SYS_RD			34
 #define TDH_SYS_LP_INIT			35
 #define TDH_SYS_TDMR_INIT		36
+#define TDH_MEM_TRACK			38
 #define TDH_PHYMEM_CACHE_WB		40
 #define TDH_PHYMEM_PAGE_WBINVD		41
 #define TDH_VP_WR			43
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index 4862c98d80d3..da4d9b5f58f1 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -32,7 +32,7 @@ struct kvm_dirty_ring {
  * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should
  * not be included as well, so define these nop functions for the arch.
  */
-static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+static inline u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm)
 {
 	return 0;
 }
@@ -42,7 +42,7 @@ static inline bool kvm_use_dirty_bitmap(struct kvm *kvm)
 	return true;
 }
 
-static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+static inline int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
 				       int index, u32 size)
 {
 	return 0;
@@ -71,11 +71,12 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
-int kvm_cpu_dirty_log_size(void);
+int kvm_cpu_dirty_log_size(struct kvm *kvm);
 bool kvm_use_dirty_bitmap(struct kvm *kvm);
 bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm);
-u32 kvm_dirty_ring_get_rsvd_entries(void);
-int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
+u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm);
+int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int index, u32 size);
 
 /*
  * called with kvm->slots_lock held, returns the number of
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index 7bc74969a819..d14ffc7513ee 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -11,14 +11,14 @@
 #include <trace/events/kvm.h>
 #include "kvm_mm.h"
 
-int __weak kvm_cpu_dirty_log_size(void)
+int __weak kvm_cpu_dirty_log_size(struct kvm *kvm)
 {
 	return 0;
 }
 
-u32 kvm_dirty_ring_get_rsvd_entries(void)
+u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm)
 {
-	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
+	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(kvm);
 }
 
 bool kvm_use_dirty_bitmap(struct kvm *kvm)
@@ -74,14 +74,15 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
 	KVM_MMU_UNLOCK(kvm);
 }
 
-int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
+int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int index, u32 size)
 {
 	ring->dirty_gfns = vzalloc(size);
 	if (!ring->dirty_gfns)
 		return -ENOMEM;
 
 	ring->size = size / sizeof(struct kvm_dirty_gfn);
-	ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
+	ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries(kvm);
 	ring->dirty_index = 0;
 	ring->reset_index = 0;
 	ring->index = index;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 622b5a99078a..549537da3062 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4108,7 +4108,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id)
 		goto vcpu_free_run_page;
 
 	if (kvm->dirty_ring_size) {
-		r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
+		r = kvm_dirty_ring_alloc(kvm, &vcpu->dirty_ring,
 					 id, kvm->dirty_ring_size);
 		if (r)
 			goto arch_vcpu_destroy;
@@ -4847,7 +4847,7 @@ static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
 		return -EINVAL;
 
 	/* Should be bigger to keep the reserved entries, or a page */
-	if (size < kvm_dirty_ring_get_rsvd_entries() *
+	if (size < kvm_dirty_ring_get_rsvd_entries(kvm) *
 	    sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
 		return -EINVAL;