1 files changed, 50 insertions, 44 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 248e615270..d465589902 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -825,12 +825,11 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos,
 
 out_unlock:
 	__iomap_put_folio(iter, pos, 0, folio);
-	iomap_write_failed(iter->inode, pos, len);
 
 	return status;
 }
 
-static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
+static bool __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
 		size_t copied, struct folio *folio)
 {
 	flush_dcache_folio(folio);
@@ -847,14 +846,14 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
 	 * redo the whole thing.
 	 */
 	if (unlikely(copied < len && !folio_test_uptodate(folio)))
-		return 0;
+		return false;
 	iomap_set_range_uptodate(folio, offset_in_folio(folio, pos), len);
 	iomap_set_range_dirty(folio, offset_in_folio(folio, pos), copied);
 	filemap_dirty_folio(inode->i_mapping, folio);
-	return copied;
+	return true;
 }
 
-static size_t iomap_write_end_inline(const struct iomap_iter *iter,
+static void iomap_write_end_inline(const struct iomap_iter *iter,
 		struct folio *folio, loff_t pos, size_t copied)
 {
 	const struct iomap *iomap = &iter->iomap;
@@ -869,49 +868,54 @@ static size_t iomap_write_end_inline(const struct iomap_iter *iter,
 	kunmap_local(addr);
 
 	mark_inode_dirty(iter->inode);
-	return copied;
 }
 
-/* Returns the number of bytes copied.  May be 0.  Cannot be an errno. */
-static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
+/*
+ * Returns true if all copied bytes have been written to the pagecache,
+ * otherwise return false.
+ */
+static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 		size_t copied, struct folio *folio)
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t old_size = iter->inode->i_size;
-	size_t ret;
+	size_t written;
 
 	if (srcmap->type == IOMAP_INLINE) {
-		ret = iomap_write_end_inline(iter, folio, pos, copied);
+		iomap_write_end_inline(iter, folio, pos, copied);
+		written = copied;
 	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
-		ret = block_write_end(NULL, iter->inode->i_mapping, pos, len,
-				copied, &folio->page, NULL);
+		written = block_write_end(NULL, iter->inode->i_mapping, pos,
+					len, copied, &folio->page, NULL);
+		WARN_ON_ONCE(written != copied && written != 0);
 	} else {
-		ret = __iomap_write_end(iter->inode, pos, len, copied, folio);
+		written = __iomap_write_end(iter->inode, pos, len, copied,
+					    folio) ? copied : 0;
 	}
 
 	/*
 	 * Update the in-memory inode size after copying the data into the page
 	 * cache.  It's up to the file system to write the updated size to disk,
 	 * preferably after I/O completion so that no stale data is exposed.
+	 * Only once that's done can we unlock and release the folio.
 	 */
-	if (pos + ret > old_size) {
-		i_size_write(iter->inode, pos + ret);
+	if (pos + written > old_size) {
+		i_size_write(iter->inode, pos + written);
 		iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
 	}
-	__iomap_put_folio(iter, pos, ret, folio);
+	__iomap_put_folio(iter, pos, written, folio);
 
 	if (old_size < pos)
 		pagecache_isize_extended(iter->inode, old_size, pos);
-	if (ret < len)
-		iomap_write_failed(iter->inode, pos + ret, len - ret);
-	return ret;
+
+	return written == copied;
 }
 
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
 	loff_t length = iomap_length(iter);
 	loff_t pos = iter->pos;
-	ssize_t written = 0;
+	ssize_t total_written = 0;
 	long status = 0;
 	struct address_space *mapping = iter->inode->i_mapping;
 	size_t chunk = mapping_max_folio_size(mapping);
@@ -922,6 +926,7 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		size_t offset;		/* Offset into folio */
 		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
+		size_t written;		/* Bytes have been written */
 
 		bytes = iov_iter_count(i);
 retry:
@@ -951,8 +956,10 @@ retry:
 		}
 
 		status = iomap_write_begin(iter, pos, bytes, &folio);
-		if (unlikely(status))
+		if (unlikely(status)) {
+			iomap_write_failed(iter->inode, pos, bytes);
 			break;
+		}
 		if (iter->iomap.flags & IOMAP_F_STALE)
 			break;
 
@@ -964,19 +971,20 @@ retry:
 			flush_dcache_folio(folio);
 
 		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
-		status = iomap_write_end(iter, pos, bytes, copied, folio);
-
-		if (unlikely(copied != status))
-			iov_iter_revert(i, copied - status);
+		written = iomap_write_end(iter, pos, bytes, copied, folio) ?
+			  copied : 0;
 
 		cond_resched();
-		if (unlikely(status == 0)) {
+		if (unlikely(written == 0)) {
 			/*
 			 * A short copy made iomap_write_end() reject the
 			 * thing entirely.  Might be memory poisoning
 			 * halfway through, might be a race with munmap,
 			 * might be severe memory pressure.
 			 */
+			iomap_write_failed(iter->inode, pos, bytes);
+			iov_iter_revert(i, copied);
+
 			if (chunk > PAGE_SIZE)
 				chunk /= 2;
 			if (copied) {
@@ -984,17 +992,17 @@ retry:
 				goto retry;
 			}
 		} else {
-			pos += status;
-			written += status;
-			length -= status;
+			pos += written;
+			total_written += written;
+			length -= written;
 		}
 	} while (iov_iter_count(i) && length);
 
 	if (status == -EAGAIN) {
-		iov_iter_revert(i, written);
+		iov_iter_revert(i, total_written);
 		return -EAGAIN;
 	}
-	return written ? written : status;
+	return total_written ? total_written : status;
 }
 
 ssize_t
@@ -1323,6 +1331,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 		int status;
 		size_t offset;
 		size_t bytes = min_t(u64, SIZE_MAX, length);
+		bool ret;
 
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (unlikely(status))
@@ -1334,8 +1343,8 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 		if (bytes > folio_size(folio) - offset)
 			bytes = folio_size(folio) - offset;
 
-		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
-		if (WARN_ON_ONCE(bytes == 0))
+		ret = iomap_write_end(iter, pos, bytes, bytes, folio);
+		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
 		cond_resched();
@@ -1384,6 +1393,7 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		int status;
 		size_t offset;
 		size_t bytes = min_t(u64, SIZE_MAX, length);
+		bool ret;
 
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (status)
@@ -1398,8 +1408,8 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		folio_zero_range(folio, offset, bytes);
 		folio_mark_accessed(folio);
 
-		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
-		if (WARN_ON_ONCE(bytes == 0))
+		ret = iomap_write_end(iter, pos, bytes, bytes, folio);
+		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
 		pos += bytes;
@@ -1959,18 +1969,13 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	return error;
 }
 
-static int iomap_do_writepage(struct folio *folio,
-		struct writeback_control *wbc, void *data)
-{
-	return iomap_writepage_map(data, wbc, folio);
-}
-
 int
 iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 		struct iomap_writepage_ctx *wpc,
 		const struct iomap_writeback_ops *ops)
 {
-	int			ret;
+	struct folio *folio = NULL;
+	int error;
 
 	/*
 	 * Writeback from reclaim context should never happen except in the case
@@ -1981,8 +1986,9 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 		return -EIO;
 
 	wpc->ops = ops;
-	ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc);
-	return iomap_submit_ioend(wpc, ret);
+	while ((folio = writeback_iter(mapping, wbc, folio, &error)))
+		error = iomap_writepage_map(wpc, wbc, folio);
+	return iomap_submit_ioend(wpc, error);
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);