1 files changed, 222 insertions, 168 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3f255534986a..3e19b87049db 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2325,18 +2325,18 @@ void __init page_writeback_init(void)
 }
 
 /**
- * tag_pages_for_writeback - tag pages to be written by write_cache_pages
+ * tag_pages_for_writeback - tag pages to be written by writeback
  * @mapping: address space structure to write
  * @start: starting page index
  * @end: ending page index (inclusive)
  *
  * This function scans the page range from @start to @end (inclusive) and tags
- * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is
- * that write_cache_pages (or whoever calls this function) will then use
- * TOWRITE tag to identify pages eligible for writeback.  This mechanism is
- * used to avoid livelocking of writeback by a process steadily creating new
- * dirty pages in the file (thus it is important for this function to be quick
- * so that it can tag pages faster than a dirtying process can create them).
+ * all pages that have DIRTY tag set with a special TOWRITE tag.  The caller
+ * can then use the TOWRITE tag to identify pages eligible for writeback.
+ * This mechanism is used to avoid livelocking of writeback by a process
+ * steadily creating new dirty pages in the file (thus it is important for this
+ * function to be quick so that it can tag pages faster than a dirtying process
+ * can create them).
  */
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end)
@@ -2360,183 +2360,242 @@ void tag_pages_for_writeback(struct address_space *mapping,
 }
 EXPORT_SYMBOL(tag_pages_for_writeback);
 
+static bool folio_prepare_writeback(struct address_space *mapping,
+		struct writeback_control *wbc, struct folio *folio)
+{
+	/*
+	 * Folio truncated or invalidated. We can freely skip it then,
+	 * even for data integrity operations: the folio has disappeared
+	 * concurrently, so there could be no real expectation of this
+	 * data integrity operation even if there is now a new, dirty
+	 * folio at the same pagecache index.
+	 */
+	if (unlikely(folio->mapping != mapping))
+		return false;
+
+	/*
+	 * Did somebody else write it for us?
+	 */
+	if (!folio_test_dirty(folio))
+		return false;
+
+	if (folio_test_writeback(folio)) {
+		if (wbc->sync_mode == WB_SYNC_NONE)
+			return false;
+		folio_wait_writeback(folio);
+	}
+	BUG_ON(folio_test_writeback(folio));
+
+	if (!folio_clear_dirty_for_io(folio))
+		return false;
+
+	return true;
+}
+
+static xa_mark_t wbc_to_tag(struct writeback_control *wbc)
+{
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		return PAGECACHE_TAG_TOWRITE;
+	return PAGECACHE_TAG_DIRTY;
+}
+
+static pgoff_t wbc_end(struct writeback_control *wbc)
+{
+	if (wbc->range_cyclic)
+		return -1;
+	return wbc->range_end >> PAGE_SHIFT;
+}
+
+static struct folio *writeback_get_folio(struct address_space *mapping,
+		struct writeback_control *wbc)
+{
+	struct folio *folio;
+
+retry:
+	folio = folio_batch_next(&wbc->fbatch);
+	if (!folio) {
+		folio_batch_release(&wbc->fbatch);
+		cond_resched();
+		filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc),
+				wbc_to_tag(wbc), &wbc->fbatch);
+		folio = folio_batch_next(&wbc->fbatch);
+		if (!folio)
+			return NULL;
+	}
+
+	folio_lock(folio);
+	if (unlikely(!folio_prepare_writeback(mapping, wbc, folio))) {
+		folio_unlock(folio);
+		goto retry;
+	}
+
+	trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
+	return folio;
+}
+
 /**
- * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
+ * writeback_iter - iterate folio of a mapping for writeback
  * @mapping: address space structure to write
- * @wbc: subtract the number of written pages from *@wbc->nr_to_write
- * @writepage: function called for each page
- * @data: data passed to writepage function
+ * @wbc: writeback context
+ * @folio: previously iterated folio (%NULL to start)
+ * @error: in-out pointer for writeback errors (see below)
  *
- * If a page is already under I/O, write_cache_pages() skips it, even
- * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
- * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
- * and msync() need to guarantee that all the data which was dirty at the time
- * the call was made get new I/O started against them.  If wbc->sync_mode is
- * WB_SYNC_ALL then we were called for data integrity and we must wait for
- * existing IO to complete.
- *
- * To avoid livelocks (when other process dirties new pages), we first tag
- * pages which should be written back with TOWRITE tag and only then start
- * writing them. For data-integrity sync we have to be careful so that we do
- * not miss some pages (e.g., because some other process has cleared TOWRITE
- * tag we set). The rule we follow is that TOWRITE tag can be cleared only
- * by the process clearing the DIRTY tag (and submitting the page for IO).
- *
- * To avoid deadlocks between range_cyclic writeback and callers that hold
- * pages in PageWriteback to aggregate IO until write_cache_pages() returns,
- * we do not loop back to the start of the file. Doing so causes a page
- * lock/page writeback access order inversion - we should only ever lock
- * multiple pages in ascending page->index order, and looping back to the start
- * of the file violates that rule and causes deadlocks.
+ * This function returns the next folio for the writeback operation described by
+ * @wbc on @mapping and  should be called in a while loop in the ->writepages
+ * implementation.
  *
- * Return: %0 on success, negative error code otherwise
+ * To start the writeback operation, %NULL is passed in the @folio argument, and
+ * for every subsequent iteration the folio returned previously should be passed
+ * back in.
+ *
+ * If there was an error in the per-folio writeback inside the writeback_iter()
+ * loop, @error should be set to the error value.
+ *
+ * Once the writeback described in @wbc has finished, this function will return
+ * %NULL and if there was an error in any iteration restore it to @error.
+ *
+ * Note: callers should not manually break out of the loop using break or goto
+ * but must keep calling writeback_iter() until it returns %NULL.
+ *
+ * Return: the folio to write or %NULL if the loop is done.
  */
-int write_cache_pages(struct address_space *mapping,
-		      struct writeback_control *wbc, writepage_t writepage,
-		      void *data)
+struct folio *writeback_iter(struct address_space *mapping,
+		struct writeback_control *wbc, struct folio *folio, int *error)
 {
-	int ret = 0;
-	int done = 0;
-	int error;
-	struct folio_batch fbatch;
-	int nr_folios;
-	pgoff_t index;
-	pgoff_t end;		/* Inclusive */
-	pgoff_t done_index;
-	int range_whole = 0;
-	xa_mark_t tag;
-
-	folio_batch_init(&fbatch);
-	if (wbc->range_cyclic) {
-		index = mapping->writeback_index; /* prev offset */
-		end = -1;
-	} else {
-		index = wbc->range_start >> PAGE_SHIFT;
-		end = wbc->range_end >> PAGE_SHIFT;
-		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
-			range_whole = 1;
-	}
-	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) {
-		tag_pages_for_writeback(mapping, index, end);
-		tag = PAGECACHE_TAG_TOWRITE;
-	} else {
-		tag = PAGECACHE_TAG_DIRTY;
-	}
-	done_index = index;
-	while (!done && (index <= end)) {
-		int i;
-
-		nr_folios = filemap_get_folios_tag(mapping, &index, end,
-				tag, &fbatch);
-
-		if (nr_folios == 0)
-			break;
+	if (!folio) {
+		folio_batch_init(&wbc->fbatch);
+		wbc->saved_err = *error = 0;
 
-		for (i = 0; i < nr_folios; i++) {
-			struct folio *folio = fbatch.folios[i];
-			unsigned long nr;
+		/*
+		 * For range cyclic writeback we remember where we stopped so
+		 * that we can continue where we stopped.
+		 *
+		 * For non-cyclic writeback we always start at the beginning of
+		 * the passed in range.
+		 */
+		if (wbc->range_cyclic)
+			wbc->index = mapping->writeback_index;
+		else
+			wbc->index = wbc->range_start >> PAGE_SHIFT;
 
-			done_index = folio->index;
+		/*
+		 * To avoid livelocks when other processes dirty new pages, we
+		 * first tag pages which should be written back and only then
+		 * start writing them.
+		 *
+		 * For data-integrity writeback we have to be careful so that we
+		 * do not miss some pages (e.g., because some other process has
+		 * cleared the TOWRITE tag we set).  The rule we follow is that
+		 * TOWRITE tag can be cleared only by the process clearing the
+		 * DIRTY tag (and submitting the page for I/O).
+		 */
+		if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+			tag_pages_for_writeback(mapping, wbc->index,
+					wbc_end(wbc));
+	} else {
+		wbc->nr_to_write -= folio_nr_pages(folio);
 
-			folio_lock(folio);
+		WARN_ON_ONCE(*error > 0);
 
-			/*
-			 * Page truncated or invalidated. We can freely skip it
-			 * then, even for data integrity operations: the page
-			 * has disappeared concurrently, so there could be no
-			 * real expectation of this data integrity operation
-			 * even if there is now a new, dirty page at the same
-			 * pagecache address.
-			 */
-			if (unlikely(folio->mapping != mapping)) {
-continue_unlock:
-				folio_unlock(folio);
-				continue;
-			}
+		/*
+		 * For integrity writeback we have to keep going until we have
+		 * written all the folios we tagged for writeback above, even if
+		 * we run past wbc->nr_to_write or encounter errors.
+		 * We stash away the first error we encounter in wbc->saved_err
+		 * so that it can be retrieved when we're done.  This is because
+		 * the file system may still have state to clear for each folio.
+		 *
+		 * For background writeback we exit as soon as we run past
+		 * wbc->nr_to_write or encounter the first error.
+		 */
+		if (wbc->sync_mode == WB_SYNC_ALL) {
+			if (*error && !wbc->saved_err)
+				wbc->saved_err = *error;
+		} else {
+			if (*error || wbc->nr_to_write <= 0)
+				goto done;
+		}
+	}
 
-			if (!folio_test_dirty(folio)) {
-				/* someone wrote it for us */
-				goto continue_unlock;
-			}
+	folio = writeback_get_folio(mapping, wbc);
+	if (!folio) {
+		/*
+		 * To avoid deadlocks between range_cyclic writeback and callers
+		 * that hold pages in PageWriteback to aggregate I/O until
+		 * the writeback iteration finishes, we do not loop back to the
+		 * start of the file.  Doing so causes a page lock/page
+		 * writeback access order inversion - we should only ever lock
+		 * multiple pages in ascending page->index order, and looping
+		 * back to the start of the file violates that rule and causes
+		 * deadlocks.
+		 */
+		if (wbc->range_cyclic)
+			mapping->writeback_index = 0;
 
-			if (folio_test_writeback(folio)) {
-				if (wbc->sync_mode != WB_SYNC_NONE)
-					folio_wait_writeback(folio);
-				else
-					goto continue_unlock;
-			}
+		/*
+		 * Return the first error we encountered (if there was any) to
+		 * the caller.
+		 */
+		*error = wbc->saved_err;
+	}
+	return folio;
 
-			BUG_ON(folio_test_writeback(folio));
-			if (!folio_clear_dirty_for_io(folio))
-				goto continue_unlock;
+done:
+	if (wbc->range_cyclic)
+		mapping->writeback_index = folio->index + folio_nr_pages(folio);
+	folio_batch_release(&wbc->fbatch);
+	return NULL;
+}
 
-			trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
-			error = writepage(folio, wbc, data);
-			nr = folio_nr_pages(folio);
-			if (unlikely(error)) {
-				/*
-				 * Handle errors according to the type of
-				 * writeback. There's no need to continue for
-				 * background writeback. Just push done_index
-				 * past this page so media errors won't choke
-				 * writeout for the entire file. For integrity
-				 * writeback, we must process the entire dirty
-				 * set regardless of errors because the fs may
-				 * still have state to clear for each page. In
-				 * that case we continue processing and return
-				 * the first error.
-				 */
-				if (error == AOP_WRITEPAGE_ACTIVATE) {
-					folio_unlock(folio);
-					error = 0;
-				} else if (wbc->sync_mode != WB_SYNC_ALL) {
-					ret = error;
-					done_index = folio->index + nr;
-					done = 1;
-					break;
-				}
-				if (!ret)
-					ret = error;
-			}
+/**
+ * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
+ * @mapping: address space structure to write
+ * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ * @writepage: function called for each page
+ * @data: data passed to writepage function
+ *
+ * Return: %0 on success, negative error code otherwise
+ *
+ * Note: please use writeback_iter() instead.
+ */
+int write_cache_pages(struct address_space *mapping,
+		      struct writeback_control *wbc, writepage_t writepage,
+		      void *data)
+{
+	struct folio *folio = NULL;
+	int error;
 
-			/*
-			 * We stop writing back only if we are not doing
-			 * integrity sync. In case of integrity sync we have to
-			 * keep going until we have written all the pages
-			 * we tagged for writeback prior to entering this loop.
-			 */
-			wbc->nr_to_write -= nr;
-			if (wbc->nr_to_write <= 0 &&
-			    wbc->sync_mode == WB_SYNC_NONE) {
-				done = 1;
-				break;
-			}
+	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
+		error = writepage(folio, wbc, data);
+		if (error == AOP_WRITEPAGE_ACTIVATE) {
+			folio_unlock(folio);
+			error = 0;
 		}
-		folio_batch_release(&fbatch);
-		cond_resched();
 	}
 
-	/*
-	 * If we hit the last page and there is more work to be done: wrap
-	 * back the index back to the start of the file for the next
-	 * time we are called.
-	 */
-	if (wbc->range_cyclic && !done)
-		done_index = 0;
-	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = done_index;
-
-	return ret;
+	return error;
 }
 EXPORT_SYMBOL(write_cache_pages);
 
-static int writepage_cb(struct folio *folio, struct writeback_control *wbc,
-		void *data)
+static int writeback_use_writepage(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	struct address_space *mapping = data;
-	int ret = mapping->a_ops->writepage(&folio->page, wbc);
-	mapping_set_error(mapping, ret);
-	return ret;
+	struct folio *folio = NULL;
+	struct blk_plug plug;
+	int err;
+
+	blk_start_plug(&plug);
+	while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
+		err = mapping->a_ops->writepage(&folio->page, wbc);
+		if (err == AOP_WRITEPAGE_ACTIVATE) {
+			folio_unlock(folio);
+			err = 0;
+		}
+		mapping_set_error(mapping, err);
+	}
+	blk_finish_plug(&plug);
+
+	return err;
 }
 
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
@@ -2552,12 +2611,7 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 		if (mapping->a_ops->writepages) {
 			ret = mapping->a_ops->writepages(mapping, wbc);
 		} else if (mapping->a_ops->writepage) {
-			struct blk_plug plug;
-
-			blk_start_plug(&plug);
-			ret = write_cache_pages(mapping, wbc, writepage_cb,
-						mapping);
-			blk_finish_plug(&plug);
+			ret = writeback_use_writepage(mapping, wbc);
 		} else {
 			/* deal with chardevs and other special files */
 			ret = 0;