diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 8310875133ff..401087e8a43d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1185,6 +1185,8 @@ extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
  * where it is possible and makes sense to do so. The PTE_CONT bit is considered
  * a private implementation detail of the public ptep API (see below).
  */
+extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte);
 extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, pte_t pte);
 extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte);
@@ -1206,6 +1208,29 @@ extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep,
 				pte_t entry, int dirty);
 
+static __always_inline void contpte_try_fold(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep, pte_t pte)
+{
+	/*
+	 * Only bother trying if both the virtual and physical addresses are
+	 * aligned and correspond to the last entry in a contig range. The core
+	 * code mostly modifies ranges from low to high, so this is the likely
+	 * the last modification in the contig range, so a good time to fold.
+	 * We can't fold special mappings, because there is no associated folio.
+	 */
+
+	const unsigned long contmask = CONT_PTES - 1;
+	bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask;
+
+	if (unlikely(valign)) {
+		bool palign = (pte_pfn(pte) & contmask) == contmask;
+
+		if (unlikely(palign &&
+		    pte_valid(pte) && !pte_cont(pte) && !pte_special(pte)))
+			__contpte_try_fold(mm, addr, ptep, pte);
+	}
+}
+
 static __always_inline void contpte_try_unfold(struct mm_struct *mm,
 				unsigned long addr, pte_t *ptep, pte_t pte)
 {
@@ -1286,6 +1311,7 @@ static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr,
 	if (likely(nr == 1)) {
 		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
 		__set_ptes(mm, addr, ptep, pte, 1);
+		contpte_try_fold(mm, addr, ptep, pte);
 	} else {
 		contpte_set_ptes(mm, addr, ptep, pte, nr);
 	}
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index 50e0173dc5ee..16788f07716d 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -73,6 +73,70 @@ static void contpte_convert(struct mm_struct *mm, unsigned long addr,
 	__set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES);
 }
 
+void __contpte_try_fold(struct mm_struct *mm, unsigned long addr,
+			pte_t *ptep, pte_t pte)
+{
+	/*
+	 * We have already checked that the virtual and pysical addresses are
+	 * correctly aligned for a contpte mapping in contpte_try_fold() so the
+	 * remaining checks are to ensure that the contpte range is fully
+	 * covered by a single folio, and ensure that all the ptes are valid
+	 * with contiguous PFNs and matching prots. We ignore the state of the
+	 * access and dirty bits for the purpose of deciding if its a contiguous
+	 * range; the folding process will generate a single contpte entry which
+	 * has a single access and dirty bit. Those 2 bits are the logical OR of
+	 * their respective bits in the constituent pte entries. In order to
+	 * ensure the contpte range is covered by a single folio, we must
+	 * recover the folio from the pfn, but special mappings don't have a
+	 * folio backing them. Fortunately contpte_try_fold() already checked
+	 * that the pte is not special - we never try to fold special mappings.
+	 * Note we can't use vm_normal_page() for this since we don't have the
+	 * vma.
+	 */
+
+	unsigned long folio_start, folio_end;
+	unsigned long cont_start, cont_end;
+	pte_t expected_pte, subpte;
+	struct folio *folio;
+	struct page *page;
+	unsigned long pfn;
+	pte_t *orig_ptep;
+	pgprot_t prot;
+
+	int i;
+
+	if (!mm_is_user(mm))
+		return;
+
+	page = pte_page(pte);
+	folio = page_folio(page);
+	folio_start = addr - (page - &folio->page) * PAGE_SIZE;
+	folio_end = folio_start + folio_nr_pages(folio) * PAGE_SIZE;
+	cont_start = ALIGN_DOWN(addr, CONT_PTE_SIZE);
+	cont_end = cont_start + CONT_PTE_SIZE;
+
+	if (folio_start > cont_start || folio_end < cont_end)
+		return;
+
+	pfn = ALIGN_DOWN(pte_pfn(pte), CONT_PTES);
+	prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
+	expected_pte = pfn_pte(pfn, prot);
+	orig_ptep = ptep;
+	ptep = contpte_align_down(ptep);
+
+	for (i = 0; i < CONT_PTES; i++) {
+		subpte = pte_mkold(pte_mkclean(__ptep_get(ptep)));
+		if (!pte_same(subpte, expected_pte))
+			return;
+		expected_pte = pte_advance_pfn(expected_pte, 1);
+		ptep++;
+	}
+
+	pte = pte_mkcont(pte);
+	contpte_convert(mm, addr, orig_ptep, pte);
+}
+EXPORT_SYMBOL(__contpte_try_fold);
+
 void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr,
 			pte_t *ptep, pte_t pte)
 {