diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index b3be87489108..b4d1cf2e4628 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8082,6 +8082,14 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
                                     guest CPUID on writes to MISC_ENABLE if
                                     KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
                                     disabled.
+
+KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, KVM invalidates all SPTEs in
+                                    fast way for memslot deletion when VM type
+                                    is KVM_X86_DEFAULT_VM.
+                                    When this quirk is disabled or when VM type
+                                    is other than KVM_X86_DEFAULT_VM, KVM zaps
+                                    only leaf SPTEs that are within the range of
+                                    the memslot being deleted.
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4a68cb3eba78..e4fc362ba3da 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2345,7 +2345,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_OUT_7E_INC_RIP |		\
 	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT |	\
 	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN |	\
-	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS)
+	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS |	\
+	 KVM_X86_QUIRK_SLOT_ZAP_ALL)
 
 /*
  * KVM previously used a u32 field in kvm_run to indicate the hypercall was
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index bf57a824f722..a8debbf2f702 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -439,6 +439,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT	(1 << 4)
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
 #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
+#define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 928cf84778b0..f107ec2557c1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6997,10 +6997,50 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 	kvm_mmu_zap_all(kvm);
 }
 
+/*
+ * Zapping leaf SPTEs with memslot range when a memslot is moved/deleted.
+ *
+ * Zapping non-leaf SPTEs, a.k.a. not-last SPTEs, isn't required, worst
+ * case scenario we'll have unused shadow pages lying around until they
+ * are recycled due to age or when the VM is destroyed.
+ */
+static void kvm_mmu_zap_memslot_leafs(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_gfn_range range = {
+		.slot = slot,
+		.start = slot->base_gfn,
+		.end = slot->base_gfn + slot->npages,
+		.may_block = true,
+	};
+	bool flush = false;
+
+	write_lock(&kvm->mmu_lock);
+
+	if (kvm_memslots_have_rmaps(kvm))
+		flush = kvm_handle_gfn_range(kvm, &range, kvm_zap_rmap);
+
+	if (tdp_mmu_enabled)
+		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, &range, flush);
+
+	if (flush)
+		kvm_flush_remote_tlbs_memslot(kvm, slot);
+
+	write_unlock(&kvm->mmu_lock);
+}
+
+static inline bool kvm_memslot_flush_zap_all(struct kvm *kvm)
+{
+	return kvm->arch.vm_type == KVM_X86_DEFAULT_VM &&
+	       kvm_check_has_quirk(kvm, KVM_X86_QUIRK_SLOT_ZAP_ALL);
+}
+
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
-	kvm_mmu_zap_all_fast(kvm);
+	if (kvm_memslot_flush_zap_all(kvm))
+		kvm_mmu_zap_all_fast(kvm);
+	else
+		kvm_mmu_zap_memslot_leafs(kvm, slot);
 }
 
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)