1 files changed, 52 insertions, 58 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4fc43859e59a..624671aaa60d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -88,7 +88,7 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	/*
 	 * If the hardware/firmware marked hugepage support disabled.
 	 */
-	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX))
+	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED))
 		return false;
 
 	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
@@ -460,18 +460,14 @@ static int __init hugepage_init(void)
 	struct kobject *hugepage_kobj;
 
 	if (!has_transparent_hugepage()) {
-		/*
-		 * Hardware doesn't support hugepages, hence disable
-		 * DAX PMD support.
-		 */
-		transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX;
+		transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED;
 		return -EINVAL;
 	}
 
 	/*
 	 * hugepages can't be allocated by the buddy allocator
 	 */
-	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER);
+	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_ORDER);
 	/*
 	 * we use page->mapping and page->index in second tail page
 	 * as list_head: assuming THP order >= 2
@@ -656,19 +652,20 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 			struct page *page, gfp_t gfp)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct folio *folio = page_folio(page);
 	pgtable_t pgtable;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	vm_fault_t ret = 0;
 
-	VM_BUG_ON_PAGE(!PageCompound(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
-	if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) {
-		put_page(page);
+	if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
+		folio_put(folio);
 		count_vm_event(THP_FAULT_FALLBACK);
 		count_vm_event(THP_FAULT_FALLBACK_CHARGE);
 		return VM_FAULT_FALLBACK;
 	}
-	cgroup_throttle_swaprate(page, gfp);
+	folio_throttle_swaprate(folio, gfp);
 
 	pgtable = pte_alloc_one(vma->vm_mm);
 	if (unlikely(!pgtable)) {
@@ -678,11 +675,11 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 
 	clear_huge_page(page, vmf->address, HPAGE_PMD_NR);
 	/*
-	 * The memory barrier inside __SetPageUptodate makes sure that
+	 * The memory barrier inside __folio_mark_uptodate makes sure that
 	 * clear_huge_page writes become visible before the set_pmd_at()
 	 * write.
 	 */
-	__SetPageUptodate(page);
+	__folio_mark_uptodate(folio);
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 	if (unlikely(!pmd_none(*vmf->pmd))) {
@@ -697,7 +694,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		/* Deliver the page fault to userland */
 		if (userfaultfd_missing(vma)) {
 			spin_unlock(vmf->ptl);
-			put_page(page);
+			folio_put(folio);
 			pte_free(vma->vm_mm, pgtable);
 			ret = handle_userfault(vmf, VM_UFFD_MISSING);
 			VM_BUG_ON(ret & VM_FAULT_FALLBACK);
@@ -706,8 +703,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 
 		entry = mk_huge_pmd(page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		page_add_new_anon_rmap(page, vma, haddr);
-		lru_cache_add_inactive_or_unevictable(page, vma);
+		folio_add_new_anon_rmap(folio, vma, haddr);
+		folio_add_lru_vma(folio, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
 		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
@@ -724,7 +721,7 @@ unlock_release:
 release:
 	if (pgtable)
 		pte_free(vma->vm_mm, pgtable);
-	put_page(page);
+	folio_put(folio);
 	return ret;
 
 }
@@ -888,23 +885,20 @@ out_unlock:
 }
 
 /**
- * vmf_insert_pfn_pmd_prot - insert a pmd size pfn
+ * vmf_insert_pfn_pmd - insert a pmd size pfn
  * @vmf: Structure describing the fault
  * @pfn: pfn to insert
- * @pgprot: page protection to use
  * @write: whether it's a write fault
  *
- * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and
- * also consult the vmf_insert_mixed_prot() documentation when
- * @pgprot != @vmf->vma->vm_page_prot.
+ * Insert a pmd size pfn. See vmf_insert_pfn() for additional info.
  *
  * Return: vm_fault_t value.
  */
-vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
-				   pgprot_t pgprot, bool write)
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 {
 	unsigned long addr = vmf->address & PMD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
+	pgprot_t pgprot = vma->vm_page_prot;
 	pgtable_t pgtable = NULL;
 
 	/*
@@ -932,7 +926,7 @@ vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
 	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
 	return VM_FAULT_NOPAGE;
 }
-EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot);
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
@@ -943,9 +937,10 @@ static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
 }
 
 static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
-		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+		pud_t *pud, pfn_t pfn, bool write)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	pgprot_t prot = vma->vm_page_prot;
 	pud_t entry;
 	spinlock_t *ptl;
 
@@ -979,23 +974,20 @@ out_unlock:
 }
 
 /**
- * vmf_insert_pfn_pud_prot - insert a pud size pfn
+ * vmf_insert_pfn_pud - insert a pud size pfn
  * @vmf: Structure describing the fault
  * @pfn: pfn to insert
- * @pgprot: page protection to use
  * @write: whether it's a write fault
  *
- * Insert a pud size pfn. See vmf_insert_pfn() for additional info and
- * also consult the vmf_insert_mixed_prot() documentation when
- * @pgprot != @vmf->vma->vm_page_prot.
+ * Insert a pud size pfn. See vmf_insert_pfn() for additional info.
  *
  * Return: vm_fault_t value.
  */
-vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn,
-				   pgprot_t pgprot, bool write)
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 {
 	unsigned long addr = vmf->address & PUD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
+	pgprot_t pgprot = vma->vm_page_prot;
 
 	/*
 	 * If we had pud_special, we could avoid all these restrictions,
@@ -1013,10 +1005,10 @@ vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
-	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
+	insert_pfn_pud(vma, addr, vmf->pud, pfn, write);
 	return VM_FAULT_NOPAGE;
 }
-EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot);
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -1838,10 +1830,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (is_swap_pmd(*pmd)) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 		struct page *page = pfn_swap_entry_to_page(entry);
+		pmd_t newpmd;
 
 		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
 		if (is_writable_migration_entry(entry)) {
-			pmd_t newpmd;
 			/*
 			 * A protection check is difficult so
 			 * just be safe and disable write
@@ -1853,10 +1845,16 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			newpmd = swp_entry_to_pmd(entry);
 			if (pmd_swp_soft_dirty(*pmd))
 				newpmd = pmd_swp_mksoft_dirty(newpmd);
-			if (pmd_swp_uffd_wp(*pmd))
-				newpmd = pmd_swp_mkuffd_wp(newpmd);
-			set_pmd_at(mm, addr, pmd, newpmd);
+		} else {
+			newpmd = *pmd;
 		}
+
+		if (uffd_wp)
+			newpmd = pmd_swp_mkuffd_wp(newpmd);
+		else if (uffd_wp_resolve)
+			newpmd = pmd_swp_clear_uffd_wp(newpmd);
+		if (!pmd_same(*pmd, newpmd))
+			set_pmd_at(mm, addr, pmd, newpmd);
 		goto unlock;
 	}
 #endif
@@ -2037,7 +2035,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgtable_t pgtable;
-	pmd_t _pmd;
+	pmd_t _pmd, old_pmd;
 	int i;
 
 	/*
@@ -2048,7 +2046,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	 *
 	 * See Documentation/mm/mmu_notifier.rst
 	 */
-	pmdp_huge_clear_flush(vma, haddr, pmd);
+	old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd);
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
@@ -2057,6 +2055,8 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 		pte_t *pte, entry;
 		entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
 		entry = pte_mkspecial(entry);
+		if (pmd_uffd_wp(old_pmd))
+			entry = pte_mkuffd_wp(entry);
 		pte = pte_offset_map(&_pmd, haddr);
 		VM_BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, haddr, pte, entry);
@@ -2233,7 +2233,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_swp_mkuffd_wp(entry);
 		} else {
 			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
-			entry = maybe_mkwrite(entry, vma);
+			if (write)
+				entry = pte_mkwrite(entry);
 			if (anon_exclusive)
 				SetPageAnonExclusive(page + i);
 			if (!young)
@@ -2241,13 +2242,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			/* NOTE: this may set soft-dirty too on some archs */
 			if (dirty)
 				entry = pte_mkdirty(entry);
-			/*
-			 * NOTE: this needs to happen after pte_mkdirty,
-			 * because some archs (sparc64, loongarch) could
-			 * set hw write bit when mkdirty.
-			 */
-			if (!write)
-				entry = pte_wrprotect(entry);
 			if (soft_dirty)
 				entry = pte_mksoft_dirty(entry);
 			if (uffd_wp)
@@ -2655,9 +2649,10 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
 	is_hzp = is_huge_zero_page(&folio->page);
-	VM_WARN_ON_ONCE_FOLIO(is_hzp, folio);
-	if (is_hzp)
+	if (is_hzp) {
+		pr_warn_ratelimited("Called split_huge_page for huge zero page\n");
 		return -EBUSY;
+	}
 
 	if (folio_test_writeback(folio))
 		return -EBUSY;
@@ -3090,11 +3085,10 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 	mapping = candidate->f_mapping;
 
 	for (index = off_start; index < off_end; index += nr_pages) {
-		struct folio *folio = __filemap_get_folio(mapping, index,
-						FGP_ENTRY, 0);
+		struct folio *folio = filemap_get_folio(mapping, index);
 
 		nr_pages = 1;
-		if (xa_is_value(folio) || !folio)
+		if (IS_ERR(folio))
 			continue;
 
 		if (!folio_test_large(folio))
@@ -3249,6 +3243,8 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	pmdswp = swp_entry_to_pmd(entry);
 	if (pmd_soft_dirty(pmdval))
 		pmdswp = pmd_swp_mksoft_dirty(pmdswp);
+	if (pmd_uffd_wp(pmdval))
+		pmdswp = pmd_swp_mkuffd_wp(pmdswp);
 	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
 	page_remove_rmap(page, vma, true);
 	put_page(page);
@@ -3274,6 +3270,8 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot));
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
+	if (is_writable_migration_entry(entry))
+		pmde = pmd_mkwrite(pmde);
 	if (pmd_swp_uffd_wp(*pvmw->pmd))
 		pmde = pmd_mkuffd_wp(pmde);
 	if (!is_migration_entry_young(entry))
@@ -3281,10 +3279,6 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	/* NOTE: this may contain setting soft-dirty on some archs */
 	if (PageDirty(new) && is_migration_entry_dirty(entry))
 		pmde = pmd_mkdirty(pmde);
-	if (is_writable_migration_entry(entry))
-		pmde = maybe_pmd_mkwrite(pmde, vma);
-	else
-		pmde = pmd_wrprotect(pmde);
 
 	if (PageAnon(new)) {
 		rmap_t rmap_flags = RMAP_COMPOUND;