Merge patch series "iomap: allow the file system to submit the writeback bios"

Christoph Hellwig <hch@lst.de> says:

This series contains the iomap prep work to support zoned XFS.

The biggest changes are:

 - an option to reuse the ioend code for direct writes in addition to the
   current use for buffered writeback, which allows the file system to
   track completions on a per-bio basis instead of the current end_io
   callback which operates on the entire I/O.
   Note that it might make sense to split the ioend code from
   buffered-io.c into its own file with this.  Let me know what you think
   of that and I can include it in the next version
 - change of the writeback_ops so that the submit_bio call can be done by
   the file system.  Note that btrfs will also need this eventually when
   it starts using iomap
 - helpers to split ioend to the zone append queue_limits that plug
   into the previous item above.
 - a new ANON_WRITE flags for writes that don't have a block number
   assigned to them at the iomap level, leaving the file system to do
   that work in the submission handler.  Note that btrfs wants something
   similar also for compressed I/O, which should be able to reuse this,
   maybe with minor tweaks.
 - passing private data to a few more helper

The XFS changes to use this will be posted to the xfs list only to not
spam fsdevel too much.

* patches from https://lore.kernel.org/r/20250206064035.2323428-2-hch@lst.de:
  iomap: pass private data to iomap_truncate_page
  iomap: pass private data to iomap_zero_range
  iomap: pass private data to iomap_page_mkwrite
  iomap: add a io_private field to struct iomap_ioend
  iomap: optionally use ioends for direct I/O
  iomap: factor out a iomap_dio_done helper
  iomap: move common ioend code to ioend.c
  iomap: split bios to zone append limits in the submission handlers
  iomap: add a IOMAP_F_ANON_WRITE flag
  iomap: simplify io_flags and io_type in struct iomap_ioend
  iomap: allow the file system to submit the writeback bios

Link: https://lore.kernel.org/r/20250206064035.2323428-2-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 53 insertions, 13 deletions

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 75bf54e76f3b..022d7f338c68 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -56,6 +56,10 @@ struct vm_fault;
  *
  * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must
  * never be merged with the mapping before it.
+ *
+ * IOMAP_F_ANON_WRITE indicates that (write) I/O does not have a target block
+ * assigned to it yet and the file system will do that in the bio submission
+ * handler, splitting the I/O as needed.
  */
 #define IOMAP_F_NEW		(1U << 0)
 #define IOMAP_F_DIRTY		(1U << 1)
@@ -68,6 +72,7 @@ struct vm_fault;
 #endif /* CONFIG_BUFFER_HEAD */
 #define IOMAP_F_XATTR		(1U << 5)
 #define IOMAP_F_BOUNDARY	(1U << 6)
+#define IOMAP_F_ANON_WRITE	(1U << 7)
 
 /*
  * Flags set by the core iomap code during operations:
@@ -111,6 +116,8 @@ struct iomap {
 
 static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos)
 {
+	if (iomap->flags & IOMAP_F_ANON_WRITE)
+		return U64_MAX; /* invalid */
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
@@ -306,12 +313,11 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-		bool *did_zero, const struct iomap_ops *ops);
+		bool *did_zero, const struct iomap_ops *ops, void *private);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops);
-vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
-			const struct iomap_ops *ops);
-
+		const struct iomap_ops *ops, void *private);
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
+		void *private);
 typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length,
 		struct iomap *iomap);
 void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
@@ -328,16 +334,42 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 		const struct iomap_ops *ops);
 
 /*
+ * Flags for iomap_ioend->io_flags.
+ */
+/* shared COW extent */
+#define IOMAP_IOEND_SHARED		(1U << 0)
+/* unwritten extent */
+#define IOMAP_IOEND_UNWRITTEN		(1U << 1)
+/* don't merge into previous ioend */
+#define IOMAP_IOEND_BOUNDARY		(1U << 2)
+/* is direct I/O */
+#define IOMAP_IOEND_DIRECT		(1U << 3)
+
+/*
+ * Flags that if set on either ioend prevent the merge of two ioends.
+ * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way)
+ */
+#define IOMAP_IOEND_NOMERGE_FLAGS \
+	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT)
+
+/*
  * Structure for writeback I/O completions.
+ *
+ * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io
+ * for direct I/O) can split a bio generated by iomap.  In that case the parent
+ * ioend it was split from is recorded in ioend->io_parent.
  */
 struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
-	u16			io_type;
-	u16			io_flags;	/* IOMAP_F_* */
+	u16			io_flags;	/* IOMAP_IOEND_* */
 	struct inode		*io_inode;	/* file being written to */
-	size_t			io_size;	/* size of data within eof */
+	size_t			io_size;	/* size of the extent */
+	atomic_t		io_remaining;	/* completetion defer count */
+	int			io_error;	/* stashed away status */
+	struct iomap_ioend	*io_parent;	/* parent for completions */
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
+	void			*io_private;	/* file system private data */
 	struct bio		io_bio;		/* MUST BE LAST! */
 };
 
@@ -362,12 +394,14 @@ struct iomap_writeback_ops {
 			  loff_t offset, unsigned len);
 
 	/*
-	 * Optional, allows the file systems to perform actions just before
-	 * submitting the bio and/or override the bio end_io handler for complex
-	 * operations like copy on write extent manipulation or unwritten extent
-	 * conversions.
+	 * Optional, allows the file systems to hook into bio submission,
+	 * including overriding the bi_end_io handler.
+	 *
+	 * Returns 0 if the bio was successfully submitted, or a negative
+	 * error code if status was non-zero or another error happened and
+	 * the bio could not be submitted.
 	 */
-	int (*prepare_ioend)(struct iomap_ioend *ioend, int status);
+	int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
 
 	/*
 	 * Optional, allows the file system to discard state on a page where
@@ -383,6 +417,10 @@ struct iomap_writepage_ctx {
 	u32			nr_folios;	/* folios added to the ioend */
 };
 
+struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio,
+		loff_t file_offset, u16 ioend_flags);
+struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
+		unsigned int max_len, bool is_append);
 void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
@@ -454,4 +492,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
 # define iomap_swapfile_activate(sis, swapfile, pagespan, ops)	(-EIO)
 #endif /* CONFIG_SWAP */
 
+extern struct bio_set iomap_ioend_bioset;
+
 #endif /* LINUX_IOMAP_H */