iomap: add caller-provided callbacks for read and readahead

Add caller-provided callbacks for read and readahead so that it can be
used generically, especially by filesystems that are not block-based.

In particular, this:
* Modifies the read and readahead interface to take in a
struct iomap_read_folio_ctx that is publicly defined as:

struct iomap_read_folio_ctx {
const struct iomap_read_ops *ops;
struct folio *cur_folio;
struct readahead_control *rac;
void *read_ctx;
};

where struct iomap_read_ops is defined as:

struct iomap_read_ops {
int (*read_folio_range)(const struct iomap_iter *iter,
struct iomap_read_folio_ctx *ctx,
size_t len);
void (*read_submit)(struct iomap_read_folio_ctx *ctx);
};

read_folio_range() reads in the folio range and is required by the
caller to provide. read_submit() is optional and is used for
submitting any pending read requests.

* Modifies existing filesystems that use iomap for read and readahead to
use the new API, through the new statically inlined helpers
iomap_bio_read_folio() and iomap_bio_readahead(). There is no change
in functionality for those filesystems.

Signed-off-by: Joanne Koong <[e-mail]>
Signed-off-by: Christian Brauner <[e-mail]>

Documentation/filesystems/iomap/operations.rst

···
 
  * ``IOCB_DONTCACHE``: Turns on ``IOMAP_DONTCACHE``.
 
+``struct iomap_read_ops``
+--------------------------
+
+.. code-block:: c
+
+ struct iomap_read_ops {
+     int (*read_folio_range)(const struct iomap_iter *iter,
+                             struct iomap_read_folio_ctx *ctx, size_t len);
+     void (*submit_read)(struct iomap_read_folio_ctx *ctx);
+ };
+
+iomap calls these functions:
+
+  - ``read_folio_range``: Called to read in the range. This must be provided
+    by the caller. The caller is responsible for calling
+    iomap_finish_folio_read() after reading in the folio range. This should be
+    done even if an error is encountered during the read. This returns 0 on
+    success or a negative error on failure.
+
+  - ``submit_read``: Submit any pending read requests. This function is
+    optional.
+
 Internal per-Folio State
 ------------------------
 
···
 The ``flags`` argument to ``->iomap_begin`` will be set to zero.
 The pagecache takes whatever locks it needs before calling the
 filesystem.
+
+Both ``iomap_readahead`` and ``iomap_read_folio`` pass in a ``struct
+iomap_read_folio_ctx``:
+
+.. code-block:: c
+
+ struct iomap_read_folio_ctx {
+    const struct iomap_read_ops *ops;
+    struct folio *cur_folio;
+    struct readahead_control *rac;
+    void *read_ctx;
+ };
+
+``iomap_readahead`` must set:
+ * ``ops->read_folio_range()`` and ``rac``
+
+``iomap_read_folio`` must set:
+ * ``ops->read_folio_range()`` and ``cur_folio``
+
+``ops->submit_read()`` and ``read_ctx`` are optional. ``read_ctx`` is used to
+pass in any custom data the caller needs accessible in the ops callbacks for
+fulfilling reads.
 
 Buffered Writes
 ---------------

block/fops.c

···
 #else /* CONFIG_BUFFER_HEAD */
 static int blkdev_read_folio(struct file *file, struct folio *folio)
 {
-	return iomap_read_folio(folio, &blkdev_iomap_ops);
+	iomap_bio_read_folio(folio, &blkdev_iomap_ops);
+	return 0;
 }
 
 static void blkdev_readahead(struct readahead_control *rac)
 {
-	iomap_readahead(rac, &blkdev_iomap_ops);
+	iomap_bio_readahead(rac, &blkdev_iomap_ops);
 }
 
 static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,

fs/erofs/data.c

···
 {
 	trace_erofs_read_folio(folio, true);
 
-	return iomap_read_folio(folio, &erofs_iomap_ops);
+	iomap_bio_read_folio(folio, &erofs_iomap_ops);
+	return 0;
 }
 
 static void erofs_readahead(struct readahead_control *rac)
···
 	trace_erofs_readahead(rac->mapping->host, readahead_index(rac),
 					readahead_count(rac), true);
 
-	return iomap_readahead(rac, &erofs_iomap_ops);
+	iomap_bio_readahead(rac, &erofs_iomap_ops);
 }
 
 static sector_t erofs_bmap(struct address_space *mapping, sector_t block)

fs/gfs2/aops.c

···
 	struct inode *inode = folio->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int error;
+	int error = 0;
 
 	if (!gfs2_is_jdata(ip) ||
 	    (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) {
-		error = iomap_read_folio(folio, &gfs2_iomap_ops);
+		iomap_bio_read_folio(folio, &gfs2_iomap_ops);
 	} else if (gfs2_is_stuffed(ip)) {
 		error = stuffed_read_folio(ip, folio);
 	} else {
···
 	else if (gfs2_is_jdata(ip))
 		mpage_readahead(rac, gfs2_block_map);
 	else
-		iomap_readahead(rac, &gfs2_iomap_ops);
+		iomap_bio_readahead(rac, &gfs2_iomap_ops);
 }
 
 /**

fs/iomap/buffered-io.c

···
 }
 
 #ifdef CONFIG_BLOCK
-static void iomap_finish_folio_read(struct folio *folio, size_t off,
-		size_t len, int error)
+void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len,
+		int error)
 {
 	struct iomap_folio_state *ifs = folio->private;
 	bool uptodate = !error;
···
 	if (finished)
 		folio_end_read(folio, uptodate);
 }
+EXPORT_SYMBOL_GPL(iomap_finish_folio_read);
 
 static void iomap_read_end_io(struct bio *bio)
 {
···
 	bio_put(bio);
 }
 
-struct iomap_read_folio_ctx {
-	struct folio		*cur_folio;
-	void			*read_ctx;
-	struct readahead_control *rac;
-};
-
 static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx)
 {
 	struct bio *bio = ctx->read_ctx;
···
 		submit_bio(bio);
 }
 
-static void iomap_bio_read_folio_range(const struct iomap_iter *iter,
+static int iomap_bio_read_folio_range(const struct iomap_iter *iter,
 		struct iomap_read_folio_ctx *ctx, size_t plen)
 {
 	struct folio *folio = ctx->cur_folio;
···
 		bio_add_folio_nofail(bio, folio, plen, poff);
 		ctx->read_ctx = bio;
 	}
+	return 0;
 }
+
+const struct iomap_read_ops iomap_bio_read_ops = {
+	.read_folio_range	= iomap_bio_read_folio_range,
+	.submit_read		= iomap_bio_submit_read,
+};
+EXPORT_SYMBOL_GPL(iomap_bio_read_ops);
 
 static void iomap_read_init(struct folio *folio)
 {
···
 			if (!*bytes_pending)
 				iomap_read_init(folio);
 			*bytes_pending += plen;
-			iomap_bio_read_folio_range(iter, ctx, plen);
+			ret = ctx->ops->read_folio_range(iter, ctx, plen);
+			if (ret)
+				return ret;
 		}
 
 		ret = iomap_iter_advance(iter, plen);
···
 	return 0;
 }
 
-int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
+int iomap_read_folio(const struct iomap_ops *ops,
+		struct iomap_read_folio_ctx *ctx)
 {
+	struct folio *folio = ctx->cur_folio;
 	struct iomap_iter iter = {
 		.inode		= folio->mapping->host,
 		.pos		= folio_pos(folio),
 		.len		= folio_size(folio),
-	};
-	struct iomap_read_folio_ctx ctx = {
-		.cur_folio	= folio,
 	};
 	size_t bytes_pending = 0;
 	int ret;
···
 	trace_iomap_readpage(iter.inode, 1);
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.status = iomap_read_folio_iter(&iter, &ctx,
-				&bytes_pending);
+		iter.status = iomap_read_folio_iter(&iter, ctx, &bytes_pending);
 
-	iomap_bio_submit_read(&ctx);
+	if (ctx->ops->submit_read)
+		ctx->ops->submit_read(ctx);
 
 	iomap_read_end(folio, bytes_pending);
 
···
 
 /**
  * iomap_readahead - Attempt to read pages from a file.
- * @rac: Describes the pages to be read.
  * @ops: The operations vector for the filesystem.
+ * @ctx: The ctx used for issuing readahead.
  *
  * This function is for filesystems to call to implement their readahead
  * address_space operation.
···
  * function is called with memalloc_nofs set, so allocations will not cause
  * the filesystem to be reentered.
  */
-void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
+void iomap_readahead(const struct iomap_ops *ops,
+		struct iomap_read_folio_ctx *ctx)
 {
+	struct readahead_control *rac = ctx->rac;
 	struct iomap_iter iter = {
 		.inode	= rac->mapping->host,
 		.pos	= readahead_pos(rac),
 		.len	= readahead_length(rac),
-	};
-	struct iomap_read_folio_ctx ctx = {
-		.rac	= rac,
 	};
 	size_t cur_bytes_pending;
 
 	trace_iomap_readahead(rac->mapping->host, readahead_count(rac));
 
 	while (iomap_iter(&iter, ops) > 0)
-		iter.status = iomap_readahead_iter(&iter, &ctx,
+		iter.status = iomap_readahead_iter(&iter, ctx,
 					&cur_bytes_pending);
 
-	iomap_bio_submit_read(&ctx);
+	if (ctx->ops->submit_read)
+		ctx->ops->submit_read(ctx);
 
-	if (ctx.cur_folio)
-		iomap_read_end(ctx.cur_folio, cur_bytes_pending);
+	if (ctx->cur_folio)
+		iomap_read_end(ctx->cur_folio, cur_bytes_pending);
 }
 EXPORT_SYMBOL_GPL(iomap_readahead);
 

fs/xfs/xfs_aops.c

···
 	struct file		*unused,
 	struct folio		*folio)
 {
-	return iomap_read_folio(folio, &xfs_read_iomap_ops);
+	iomap_bio_read_folio(folio, &xfs_read_iomap_ops);
+	return 0;
 }
 
 STATIC void
 xfs_vm_readahead(
 	struct readahead_control	*rac)
 {
-	iomap_readahead(rac, &xfs_read_iomap_ops);
+	iomap_bio_readahead(rac, &xfs_read_iomap_ops);
 }
 
 static int

fs/zonefs/file.c

···
 
 static int zonefs_read_folio(struct file *unused, struct folio *folio)
 {
-	return iomap_read_folio(folio, &zonefs_read_iomap_ops);
+	iomap_bio_read_folio(folio, &zonefs_read_iomap_ops);
+	return 0;
 }
 
 static void zonefs_readahead(struct readahead_control *rac)
 {
-	iomap_readahead(rac, &zonefs_read_iomap_ops);
+	iomap_bio_readahead(rac, &zonefs_read_iomap_ops);
 }
 
 /*

include/linux/iomap.h

···
 struct iomap_iter;
 struct iomap_dio;
 struct iomap_writepage_ctx;
+struct iomap_read_folio_ctx;
 struct iov_iter;
 struct kiocb;
 struct page;
···
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops,
 		const struct iomap_write_ops *write_ops, void *private);
-int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
-void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
+int iomap_read_folio(const struct iomap_ops *ops,
+		struct iomap_read_folio_ctx *ctx);
+void iomap_readahead(const struct iomap_ops *ops,
+		struct iomap_read_folio_ctx *ctx);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
 struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len);
 bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
···
 		loff_t pos, loff_t end_pos, unsigned int dirty_len);
 int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
 
+void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len,
+		int error);
 void iomap_start_folio_write(struct inode *inode, struct folio *folio,
 		size_t len);
 void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
···
 
 int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
+
+struct iomap_read_folio_ctx {
+	const struct iomap_read_ops *ops;
+	struct folio		*cur_folio;
+	struct readahead_control *rac;
+	void			*read_ctx;
+};
+
+struct iomap_read_ops {
+	/*
+	 * Read in a folio range.
+	 *
+	 * The caller is responsible for calling iomap_finish_folio_read() after
+	 * reading in the folio range. This should be done even if an error is
+	 * encountered during the read.
+	 *
+	 * Returns 0 on success or a negative error on failure.
+	 */
+	int (*read_folio_range)(const struct iomap_iter *iter,
+			struct iomap_read_folio_ctx *ctx, size_t len);
+
+	/*
+	 * Submit any pending read requests.
+	 *
+	 * This is optional.
+	 */
+	void (*submit_read)(struct iomap_read_folio_ctx *ctx);
+};
 
 /*
  * Flags for direct I/O ->end_io:
···
 #endif /* CONFIG_SWAP */
 
 extern struct bio_set iomap_ioend_bioset;
+
+#ifdef CONFIG_BLOCK
+extern const struct iomap_read_ops iomap_bio_read_ops;
+
+static inline void iomap_bio_read_folio(struct folio *folio,
+		const struct iomap_ops *ops)
+{
+	struct iomap_read_folio_ctx ctx = {
+		.ops		= &iomap_bio_read_ops,
+		.cur_folio	= folio,
+	};
+
+	iomap_read_folio(ops, &ctx);
+}
+
+static inline void iomap_bio_readahead(struct readahead_control *rac,
+		const struct iomap_ops *ops)
+{
+	struct iomap_read_folio_ctx ctx = {
+		.ops		= &iomap_bio_read_ops,
+		.rac		= rac,
+	};
+
+	iomap_readahead(ops, &ctx);
+}
+#endif /* CONFIG_BLOCK */
 
 #endif /* LINUX_IOMAP_H */