1 files changed, 80 insertions, 58 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index b794943bce76..2723104cc06a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -99,7 +99,7 @@
  *    ->i_pages lock		(__sync_single_inode)
  *
  *  ->i_mmap_rwsem
- *    ->anon_vma.lock		(vma_adjust)
+ *    ->anon_vma.lock		(vma_merge)
  *
  *  ->anon_vma.lock
  *    ->page_table_lock or pte_lock	(anon_vma_prepare and various)
@@ -472,7 +472,7 @@ EXPORT_SYMBOL(filemap_flush);
 bool filemap_range_has_page(struct address_space *mapping,
 			   loff_t start_byte, loff_t end_byte)
 {
-	struct page *page;
+	struct folio *folio;
 	XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
 	pgoff_t max = end_byte >> PAGE_SHIFT;
 
@@ -481,11 +481,11 @@ bool filemap_range_has_page(struct address_space *mapping,
 
 	rcu_read_lock();
 	for (;;) {
-		page = xas_find(&xas, max);
-		if (xas_retry(&xas, page))
+		folio = xas_find(&xas, max);
+		if (xas_retry(&xas, folio))
 			continue;
 		/* Shadow entries don't count */
-		if (xa_is_value(page))
+		if (xa_is_value(folio))
 			continue;
 		/*
 		 * We don't need to try to pin this page; we're about to
@@ -496,7 +496,7 @@ bool filemap_range_has_page(struct address_space *mapping,
 	}
 	rcu_read_unlock();
 
-	return page != NULL;
+	return folio != NULL;
 }
 EXPORT_SYMBOL(filemap_range_has_page);
 
@@ -505,25 +505,27 @@ static void __filemap_fdatawait_range(struct address_space *mapping,
 {
 	pgoff_t index = start_byte >> PAGE_SHIFT;
 	pgoff_t end = end_byte >> PAGE_SHIFT;
-	struct pagevec pvec;
-	int nr_pages;
+	struct folio_batch fbatch;
+	unsigned nr_folios;
+
+	folio_batch_init(&fbatch);
 
-	pagevec_init(&pvec);
 	while (index <= end) {
 		unsigned i;
 
-		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index,
-				end, PAGECACHE_TAG_WRITEBACK);
-		if (!nr_pages)
+		nr_folios = filemap_get_folios_tag(mapping, &index, end,
+				PAGECACHE_TAG_WRITEBACK, &fbatch);
+
+		if (!nr_folios)
 			break;
 
-		for (i = 0; i < nr_pages; i++) {
-			struct page *page = pvec.pages[i];
+		for (i = 0; i < nr_folios; i++) {
+			struct folio *folio = fbatch.folios[i];
 
-			wait_on_page_writeback(page);
-			ClearPageError(page);
+			folio_wait_writeback(folio);
+			folio_clear_error(folio);
 		}
-		pagevec_release(&pvec);
+		folio_batch_release(&fbatch);
 		cond_resched();
 	}
 }
@@ -2284,64 +2286,58 @@ out:
 EXPORT_SYMBOL(filemap_get_folios_contig);
 
 /**
- * find_get_pages_range_tag - Find and return head pages matching @tag.
- * @mapping:	the address_space to search
- * @index:	the starting page index
- * @end:	The final page index (inclusive)
- * @tag:	the tag index
- * @nr_pages:	the maximum number of pages
- * @pages:	where the resulting pages are placed
+ * filemap_get_folios_tag - Get a batch of folios matching @tag
+ * @mapping:    The address_space to search
+ * @start:      The starting page index
+ * @end:        The final page index (inclusive)
+ * @tag:        The tag index
+ * @fbatch:     The batch to fill
  *
- * Like find_get_pages_range(), except we only return head pages which are
- * tagged with @tag.  @index is updated to the index immediately after the
- * last page we return, ready for the next iteration.
+ * Same as filemap_get_folios(), but only returning folios tagged with @tag.
  *
- * Return: the number of pages which were found.
+ * Return: The number of folios found.
+ * Also update @start to index the next folio for traversal.
  */
-unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
-			pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
-			struct page **pages)
+unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
+			pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch)
 {
-	XA_STATE(xas, &mapping->i_pages, *index);
+	XA_STATE(xas, &mapping->i_pages, *start);
 	struct folio *folio;
-	unsigned ret = 0;
-
-	if (unlikely(!nr_pages))
-		return 0;
 
 	rcu_read_lock();
-	while ((folio = find_get_entry(&xas, end, tag))) {
+	while ((folio = find_get_entry(&xas, end, tag)) != NULL) {
 		/*
 		 * Shadow entries should never be tagged, but this iteration
 		 * is lockless so there is a window for page reclaim to evict
-		 * a page we saw tagged.  Skip over it.
+		 * a page we saw tagged. Skip over it.
 		 */
 		if (xa_is_value(folio))
 			continue;
+		if (!folio_batch_add(fbatch, folio)) {
+			unsigned long nr = folio_nr_pages(folio);
 
-		pages[ret] = &folio->page;
-		if (++ret == nr_pages) {
-			*index = folio->index + folio_nr_pages(folio);
+			if (folio_test_hugetlb(folio))
+				nr = 1;
+			*start = folio->index + nr;
 			goto out;
 		}
 	}
-
 	/*
-	 * We come here when we got to @end. We take care to not overflow the
-	 * index @index as it confuses some of the callers. This breaks the
-	 * iteration when there is a page at index -1 but that is already
-	 * broken anyway.
+	 * We come here when there is no page beyond @end. We take care to not
+	 * overflow the index @start as it confuses some of the callers. This
+	 * breaks the iteration when there is a page at index -1 but that is
+	 * already broke anyway.
 	 */
 	if (end == (pgoff_t)-1)
-		*index = (pgoff_t)-1;
+		*start = (pgoff_t)-1;
 	else
-		*index = end + 1;
+		*start = end + 1;
 out:
 	rcu_read_unlock();
 
-	return ret;
+	return folio_batch_count(fbatch);
 }
-EXPORT_SYMBOL(find_get_pages_range_tag);
+EXPORT_SYMBOL(filemap_get_folios_tag);
 
 /*
  * CD/DVDs are error prone. When a medium error occurs, the driver may fail
@@ -3395,22 +3391,24 @@ out_retry:
 }
 EXPORT_SYMBOL(filemap_fault);
 
-static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
+static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
+		pgoff_t start)
 {
 	struct mm_struct *mm = vmf->vma->vm_mm;
 
 	/* Huge page is mapped? No need to proceed. */
 	if (pmd_trans_huge(*vmf->pmd)) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		return true;
 	}
 
-	if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
+	if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) {
+		struct page *page = folio_file_page(folio, start);
 		vm_fault_t ret = do_set_pmd(vmf, page);
 		if (!ret) {
 			/* The page is mapped successfully, reference consumed. */
-			unlock_page(page);
+			folio_unlock(folio);
 			return true;
 		}
 	}
@@ -3420,8 +3418,8 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
 
 	/* See comment in handle_pte_fault() */
 	if (pmd_devmap_trans_unstable(vmf->pmd)) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		return true;
 	}
 
@@ -3504,7 +3502,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	if (!folio)
 		goto out;
 
-	if (filemap_map_pmd(vmf, &folio->page)) {
+	if (filemap_map_pmd(vmf, folio, start_pgoff)) {
 		ret = VM_FAULT_NOPAGE;
 		goto out;
 	}
@@ -3719,6 +3717,30 @@ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index,
 }
 EXPORT_SYMBOL(read_cache_folio);
 
+/**
+ * mapping_read_folio_gfp - Read into page cache, using specified allocation flags.
+ * @mapping:	The address_space for the folio.
+ * @index:	The index that the allocated folio will contain.
+ * @gfp:	The page allocator flags to use if allocating.
+ *
+ * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with
+ * any new memory allocations done using the specified allocation flags.
+ *
+ * The most likely error from this function is EIO, but ENOMEM is
+ * possible and so is EINTR.  If ->read_folio returns another error,
+ * that will be returned to the caller.
+ *
+ * The function expects mapping->invalidate_lock to be already held.
+ *
+ * Return: Uptodate folio on success, ERR_PTR() on failure.
+ */
+struct folio *mapping_read_folio_gfp(struct address_space *mapping,
+		pgoff_t index, gfp_t gfp)
+{
+	return do_read_cache_folio(mapping, index, NULL, NULL, gfp);
+}
+EXPORT_SYMBOL(mapping_read_folio_gfp);
+
 static struct page *do_read_cache_page(struct address_space *mapping,
 		pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp)
 {