diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 5063b482e34f..113d35d993ce 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -313,6 +313,13 @@ static inline bool arch_has_hw_pte_young(void)
 }
 #endif
 
+#ifndef arch_wants_pte_order
+static inline int arch_wants_pte_order(void)
+{
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
diff --git a/mm/memory.c b/mm/memory.c
index cf4ae87b1563..238f1a2ffbff 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4059,6 +4059,81 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	return ret;
 }
 
+static bool vmf_pte_range_changed(struct vm_fault *vmf, int nr_pages)
+{
+	int i;
+
+	if (nr_pages == 1)
+		return vmf_pte_changed(vmf);
+
+	for (i = 0; i < nr_pages; i++) {
+		if (!pte_none(ptep_get_lockless(vmf->pte + i)))
+			return true;
+	}
+
+	return false;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static struct folio *alloc_anon_folio(struct vm_fault *vmf)
+{
+	int i;
+	gfp_t gfp;
+	pte_t *pte;
+	unsigned long addr;
+	struct vm_area_struct *vma = vmf->vma;
+	int preferred = arch_wants_pte_order() ? : PAGE_ALLOC_COSTLY_ORDER;
+	int orders[] = {
+		preferred,
+		preferred > PAGE_ALLOC_COSTLY_ORDER ? PAGE_ALLOC_COSTLY_ORDER : 0,
+		0,
+	};
+
+	if (vmf_orig_pte_uffd_wp(vmf))
+		goto fallback;
+
+	for (i = 0; orders[i]; i++) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << orders[i]);
+		if (addr >= vma->vm_start && addr + (PAGE_SIZE << orders[i]) <= vma->vm_end)
+			break;
+	}
+
+	if (!orders[i])
+		goto fallback;
+
+	pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK);
+	VM_WARN_ON_ONCE(vmf->pte);
+
+	for (; orders[i]; i++) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << orders[i]);
+		vmf->pte = pte + pte_index(addr);
+		if (!vmf_pte_range_changed(vmf, 1 << orders[i]))
+			break;
+	}
+
+	vmf->pte = NULL;
+	pte_unmap(pte);
+
+	gfp = vma_thp_gfp_mask(vma);
+
+	for (; orders[i]; i++) {
+		struct folio *folio;
+
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << orders[i]);
+		folio = vma_alloc_folio(gfp, orders[i], vma, addr, true);
+		if (folio) {
+			clear_huge_page(&folio->page, addr, 1 << orders[i]);
+			vmf->address = addr;
+			return folio;
+		}
+	}
+fallback:
+	return vma_alloc_zeroed_movable_folio(vma, vmf->address);
+}
+#else
+#define alloc_anon_folio(vmf) vma_alloc_zeroed_movable_folio((vmf)->vma, (vmf)->address)
+#endif
+
 /*
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -4066,6 +4141,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
  */
 static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
+	int i = 0;
+	int nr_pages = 1;
 	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	struct vm_area_struct *vma = vmf->vma;
 	struct folio *folio;
@@ -4110,10 +4187,12 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	/* Allocate our own private page. */
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
-	folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
+	folio = alloc_anon_folio(vmf);
 	if (!folio)
 		goto oom;
 
+	nr_pages = folio_nr_pages(folio);
+
 	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
 		goto oom_free_page;
 	folio_throttle_swaprate(folio, GFP_KERNEL);
@@ -4125,17 +4204,13 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	 */
 	__folio_mark_uptodate(folio);
 
-	entry = mk_pte(&folio->page, vma->vm_page_prot);
-	entry = pte_sw_mkyoung(entry);
-	if (vma->vm_flags & VM_WRITE)
-		entry = pte_mkwrite(pte_mkdirty(entry));
-
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
 	if (!vmf->pte)
 		goto release;
-	if (vmf_pte_changed(vmf)) {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
+	if (vmf_pte_range_changed(vmf, nr_pages)) {
+		for (i = 0; i < nr_pages; i++)
+			update_mmu_tlb(vma, vmf->address + PAGE_SIZE * i, vmf->pte + i);
 		goto release;
 	}
 
@@ -4150,16 +4225,24 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
-	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
+	folio_ref_add(folio, nr_pages - 1);
+	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
 	folio_add_new_anon_rmap(folio, vma, vmf->address);
 	folio_add_lru_vma(folio, vma);
+
+	for (i = 0; i < nr_pages; i++) {
+		entry = mk_pte(folio_page(folio, i), vma->vm_page_prot);
+		entry = pte_sw_mkyoung(entry);
+		if (vma->vm_flags & VM_WRITE)
+			entry = pte_mkwrite(pte_mkdirty(entry));
 setpte:
-	if (uffd_wp)
-		entry = pte_mkuffd_wp(entry);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
+		if (uffd_wp)
+			entry = pte_mkuffd_wp(entry);
+		set_pte_at(vma->vm_mm, vmf->address + PAGE_SIZE * i, vmf->pte + i, entry);
 
-	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(vma, vmf->address, vmf->pte);
+		/* No need to invalidate - it was non-present before */
+		update_mmu_cache(vma, vmf->address + PAGE_SIZE * i, vmf->pte + i);
+	}
 unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
diff --git a/mm/rmap.c b/mm/rmap.c
index 0c0d8857dfce..fb120c8717ec 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1284,25 +1284,36 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 		unsigned long address)
 {
-	int nr;
+	int nr = folio_nr_pages(folio);
 
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+	VM_BUG_ON_VMA(address < vma->vm_start || address + PAGE_SIZE * nr > vma->vm_end, vma);
 	__folio_set_swapbacked(folio);
 
-	if (likely(!folio_test_pmd_mappable(folio))) {
+	if (!folio_test_large(folio)) {
 		/* increment count (starts at -1) */
 		atomic_set(&folio->_mapcount, 0);
-		nr = 1;
+		__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
+	} else if (!folio_test_pmd_mappable(folio)) {
+		int i;
+
+		for (i = 0; i < nr; i++) {
+			struct page *page = folio_page(folio, i);
+
+			/* increment count (starts at -1) */
+			atomic_set(&page->_mapcount, 0);
+			__page_set_anon_rmap(folio, page, vma, address + PAGE_SIZE * i, 1);
+		}
+		/* increment count (starts at 0) */
+		atomic_set(&folio->_nr_pages_mapped, nr);
 	} else {
 		/* increment count (starts at -1) */
 		atomic_set(&folio->_entire_mapcount, 0);
 		atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
-		nr = folio_nr_pages(folio);
+		__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
 		__lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
 	}
 
 	__lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
-	__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
 }
 
 /**
@@ -1430,7 +1441,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 		 * page of the folio is unmapped and at least one page
 		 * is still mapped.
 		 */
-		if (folio_test_pmd_mappable(folio) && folio_test_anon(folio))
+		if (folio_test_large(folio) && folio_test_anon(folio))
 			if (!compound || nr < nr_pmdmapped)
 				deferred_split_folio(folio);
 	}