diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 890461d3f5e5dddc4cd936fc3afc588563d0d751..2712d3c7371950de0a363a0aea5883d6654d7f65 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -104,6 +104,7 @@ config ARM64
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
+	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if !PREEMPT_RT
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index ae35939f395bb18e2e1c8862046edd8379113985..1c63256efd2503a1146a213e2e394ed4ca6e36b3 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -116,6 +116,10 @@
 #define ESR_ELx_FSC_SERROR	(0x11)
 #define ESR_ELx_FSC_ACCESS	(0x08)
 #define ESR_ELx_FSC_FAULT	(0x04)
+#define ESR_ELx_FSC_FAULT_L0    (0x04)
+#define ESR_ELx_FSC_FAULT_L1    (0x05)
+#define ESR_ELx_FSC_FAULT_L2    (0x06)
+#define ESR_ELx_FSC_FAULT_L3    (0x07)
 #define ESR_ELx_FSC_PERM	(0x0C)
 #define ESR_ELx_FSC_SEA_TTW0	(0x14)
 #define ESR_ELx_FSC_SEA_TTW1	(0x15)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 401087e8a43dc08621a0a60ca6d3fe431649bb4e..b72196ed5a76ffb7c3cb65251043495c3f4ac845 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1453,6 +1453,13 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 
 #endif /* CONFIG_ARM64_CONTPTE */
 
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+void vmemmap_update_pmd(unsigned long addr, pmd_t *pmdp, pte_t *ptep);
+#define vmemmap_update_pmd vmemmap_update_pmd
+void vmemmap_update_pte(unsigned long addr, pte_t *ptep, pte_t pte);
+#define vmemmap_update_pte vmemmap_update_pte
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 2e7a9b70ea6e1d2f495bc75e078c13a94572413a..046bc64be6d073f1bc80f9635263490d5a332c36 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -488,6 +488,22 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 	dsb(ish);
 	isb();
 }
+
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+static inline void vmemmap_flush_tlb_all(void)
+{
+	/* do nothing, already flushed tlb in every single BBM */
+}
+#define vmemmap_flush_tlb_all vmemmap_flush_tlb_all
+
+static inline void vmemmap_flush_tlb_range(unsigned long start,
+					   unsigned long end)
+{
+	/* do nothing, already flushed tlb in every single BBM */
+}
+#define vmemmap_flush_tlb_range vmemmap_flush_tlb_range
+#endif
+
 #endif
 
 #endif
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5d040bbfd247981a0d4c88f4076bb1381d4534d7..4ea07caba71cf26db93de00e22baf387186733b9 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -394,6 +394,85 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned long esr)
 	return false;
 }
 
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+static inline bool vmemmap_fault_may_fixup(unsigned long addr,
+					   unsigned long esr)
+{
+	if (!static_branch_likely(&hugetlb_optimize_vmemmap_key))
+		return false;
+
+	if (addr < VMEMMAP_START || addr >= VMEMMAP_END)
+		return false;
+
+	/*
+	 * Only try to handle translation fault level 2 or level 3,
+	 * because hugetlb vmemmap optimize only clear pmd or pte.
+	 */
+	switch (esr & ESR_ELx_FSC) {
+	case ESR_ELx_FSC_FAULT_L2:
+	case ESR_ELx_FSC_FAULT_L3:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/*
+ * PMD mapped vmemmap should has been split as PTE mapped
+ * by HVO now, here we only check this case, other cases
+ * should fail.
+ * Also should check the addr is healthy enough that will not cause
+ * a level2 or level3 translation fault again after page fault
+ * handled with success, so we need check both bits[1:0] of PMD and
+ * PTE as ARM Spec mentioned below:
+ * A Translation fault is generated if bits[1:0] of a translation
+ * table descriptor identify the descriptor as either a Fault
+ * encoding or a reserved encoding.
+ */
+static inline bool vmemmap_addr_healthy(unsigned long addr)
+{
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
+
+	pmdp = pmd_off_k(addr);
+	pmd = pmdp_get(pmdp);
+	if (!pmd_table(pmd))
+		return false;
+
+	ptep = pte_offset_kernel(pmdp, addr);
+	pte = ptep_get(ptep);
+	return (pte_val(pte) & PTE_TYPE_MASK) == PTE_TYPE_PAGE;
+}
+
+static bool vmemmap_handle_page_fault(unsigned long addr,
+				      unsigned long esr)
+{
+	bool ret;
+	unsigned long flags;
+
+	if (likely(!vmemmap_fault_may_fixup(addr, esr)))
+		return false;
+
+	spin_lock_irqsave(&init_mm.page_table_lock, flags);
+	ret = vmemmap_addr_healthy(addr);
+	spin_unlock_irqrestore(&init_mm.page_table_lock, flags);
+
+	return ret;
+}
+#else
+static inline bool vmemmap_fault_may_fixup(unsigned long addr,
+					   unsigned long esr)
+{
+	return false;
+}
+
+static inline bool vmemmap_handle_page_fault(unsigned long addr,
+					     unsigned long esr)
+{
+	return false;
+}
+#endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */
+
 static bool is_translation_fault(unsigned long esr)
 {
 	return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT;
@@ -411,9 +490,11 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
 		return;
 
-	if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs),
-	    "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr))
+	if (is_spurious_el1_translation_fault(addr, esr, regs)) {
+		WARN_RATELIMIT(!vmemmap_fault_may_fixup(addr, esr),
+		"Ignoring spurious kernel translation fault at virtual address %016lx\n", addr);
 		return;
+	}
 
 	if (is_el1_mte_sync_tag_check_fault(esr)) {
 		do_tag_recovery(addr, esr, regs);
@@ -431,9 +512,12 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
 	} else if (addr < PAGE_SIZE) {
 		msg = "NULL pointer dereference";
 	} else {
-		if (is_translation_fault(esr) &&
-		    kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs))
-			return;
+		if (is_translation_fault(esr)) {
+			if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs))
+				return;
+			if (vmemmap_handle_page_fault(addr, esr))
+				return;
+		}
 
 		msg = "paging request";
 	}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 84fb680f69cea9cc015d1965f6292d859d497f01..4142a75a414ec510f9bcb4304c95daed7bafaaca 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1151,6 +1151,34 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
 	return 1;
 }
 
+#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
+/*
+ * In the window between the page table entry is cleared and filled
+ * with a new value, other threads have the opportunity to concurrently
+ * access the vmemmap area then page translation fault occur.
+ * Therefore, we need to ensure that the init_mm.page_table_lock is held
+ * to synchronize the vmemmap page fault handling which will wait for
+ * this lock to be released to ensure that the page table entry has been
+ * refreshed with a new valid value.
+ */
+void vmemmap_update_pmd(unsigned long addr, pmd_t *pmdp, pte_t *ptep)
+{
+	lockdep_assert_held(&init_mm.page_table_lock);
+	pmd_clear(pmdp);
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	pmd_populate_kernel(&init_mm, pmdp, ptep);
+}
+
+void vmemmap_update_pte(unsigned long addr, pte_t *ptep, pte_t pte)
+{
+	spin_lock_irq(&init_mm.page_table_lock);
+	pte_clear(&init_mm, addr, ptep);
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	set_pte_at(&init_mm, addr, ptep, pte);
+	spin_unlock_irq(&init_mm.page_table_lock);
+}
+#endif
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index beaae51033db3b08246a25f7f855b09a14504a0b..fb0b05d4659ab68b4d5d0f2692302c7a0e7eb0f1 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -37,6 +37,37 @@ struct vmemmap_remap_walk {
 	struct list_head	*vmemmap_pages;
 };
 
+#ifndef vmemmap_update_pmd
+static inline void vmemmap_update_pmd(unsigned long addr,
+				      pmd_t *pmdp, pte_t *ptep)
+{
+	pmd_populate_kernel(&init_mm, pmdp, ptep);
+}
+#endif
+
+#ifndef vmemmap_update_pte
+static inline void vmemmap_update_pte(unsigned long addr,
+				      pte_t *ptep, pte_t pte)
+{
+	set_pte_at(&init_mm, addr, ptep, pte);
+}
+#endif
+
+#ifndef vmemmap_flush_tlb_all
+static inline void vmemmap_flush_tlb_all(void)
+{
+	flush_tlb_all();
+}
+#endif
+
+#ifndef vmemmap_flush_tlb_range
+static inline void vmemmap_flush_tlb_range(unsigned long start,
+					   unsigned long end)
+{
+	flush_tlb_kernel_range(start, end);
+}
+#endif
+
 static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 {
 	pmd_t __pmd;
@@ -67,7 +98,7 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
 
-	spin_lock(&init_mm.page_table_lock);
+	spin_lock_irq(&init_mm.page_table_lock);
 	if (likely(pmd_leaf(*pmd))) {
 		/*
 		 * Higher order allocations from buddy allocator must be able to
@@ -79,12 +110,12 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
 
 		/* Make pte visible before pmd. See comment in pmd_install(). */
 		smp_wmb();
-		pmd_populate_kernel(&init_mm, pmd, pgtable);
-		flush_tlb_kernel_range(start, start + PMD_SIZE);
+		vmemmap_update_pmd(start, pmd, pgtable);
+		vmemmap_flush_tlb_range(start, start + PMD_SIZE);
 	} else {
 		pte_free_kernel(&init_mm, pgtable);
 	}
-	spin_unlock(&init_mm.page_table_lock);
+	spin_unlock_irq(&init_mm.page_table_lock);
 
 	return 0;
 }
@@ -198,7 +229,7 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
 			return ret;
 	} while (pgd++, addr = next, addr != end);
 
-	flush_tlb_kernel_range(start, end);
+	vmemmap_flush_tlb_range(start, end);
 
 	return 0;
 }
@@ -244,15 +275,15 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
 
 		/*
 		 * Makes sure that preceding stores to the page contents from
-		 * vmemmap_remap_free() become visible before the set_pte_at()
-		 * write.
+		 * vmemmap_remap_free() become visible before the
+		 * vmemmap_update_pte() write.
 		 */
 		smp_wmb();
 	}
 
 	entry = mk_pte(walk->reuse_page, pgprot);
 	list_add_tail(&page->lru, walk->vmemmap_pages);
-	set_pte_at(&init_mm, addr, pte, entry);
+	vmemmap_update_pte(addr, pte, entry);
 }
 
 /*
@@ -291,10 +322,10 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
 
 	/*
 	 * Makes sure that preceding stores to the page contents become visible
-	 * before the set_pte_at() write.
+	 * before the vmemmap_update_pte() write.
 	 */
 	smp_wmb();
-	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
+	vmemmap_update_pte(addr, pte, mk_pte(page, pgprot));
 }
 
 /**