Merge tag 'vfs-6.15-rc1.iomap' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs iomap updates from Christian Brauner:

 - Allow the filesystem to submit the writeback bios.

    - Allow the filsystem to track completions on a per-bio bases
      instead of the entire I/O.

    - Change writeback_ops so that ->submit_bio can be done by the
      filesystem.

    - A new ANON_WRITE flag for writes that don't have a block number
      assigned to them at the iomap level leaving the filesystem to do
      that work in the submission handler.

 - Incremental iterator advance

   The folio_batch support for zero range where the filesystem provides
   a batch of folios to process that might not be logically continguous
   requires more flexibility than the current offset based iteration
   currently offers.

   Update all iomap operations to advance the iterator within the
   operation and thus remove the need to advance from the core iomap
   iterator.

 - Make buffered writes work with RWF_DONTCACHE

   If RWF_DONTCACHE is set for a write, mark the folios being written as
   uncached. On writeback completion the pages will be dropped.

 - Introduce infrastructure for large atomic writes

   This will eventually be used by xfs and ext4.

* tag 'vfs-6.15-rc1.iomap' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (42 commits)
  iomap: rework IOMAP atomic flags
  iomap: comment on atomic write checks in iomap_dio_bio_iter()
  iomap: inline iomap_dio_bio_opflags()
  iomap: fix inline data on buffered read
  iomap: Lift blocksize restriction on atomic writes
  iomap: Support SW-based atomic writes
  iomap: Rename IOMAP_ATOMIC -> IOMAP_ATOMIC_HW
  xfs: flag as supporting FOP_DONTCACHE
  iomap: make buffered writes work with RWF_DONTCACHE
  iomap: introduce a full map advance helper
  iomap: rename iomap_iter processed field to status
  iomap: remove unnecessary advance from iomap_iter()
  dax: advance the iomap_iter on pte and pmd faults
  dax: advance the iomap_iter on dedupe range
  dax: advance the iomap_iter on unshare range
  dax: advance the iomap_iter on zero range
  dax: push advance down into dax_iomap_iter() for read and write
  dax: advance the iomap_iter in the read/write path
  iomap: convert misc simple ops to incremental advance
  iomap: advance the iter on direct I/O
  ...

1 files changed, 95 insertions, 21 deletions

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 75bf54e76f3b..02fe001feebb 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -56,6 +56,13 @@ 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.
+ *
+ * IOMAP_F_ATOMIC_BIO indicates that (write) I/O will be issued as an atomic
+ * bio, i.e. set REQ_ATOMIC.
  */
 #define IOMAP_F_NEW		(1U << 0)
 #define IOMAP_F_DIRTY		(1U << 1)
@@ -68,6 +75,8 @@ 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)
+#define IOMAP_F_ATOMIC_BIO	(1U << 8)
 
 /*
  * Flags set by the core iomap code during operations:
@@ -111,6 +120,8 @@ 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;
 }
 
@@ -182,7 +193,8 @@ struct iomap_folio_ops {
 #else
 #define IOMAP_DAX		0
 #endif /* CONFIG_FS_DAX */
-#define IOMAP_ATOMIC		(1 << 9)
+#define IOMAP_ATOMIC		(1 << 9) /* torn-write protection */
+#define IOMAP_DONTCACHE		(1 << 10)
 
 struct iomap_ops {
 	/*
@@ -211,8 +223,10 @@ struct iomap_ops {
  *	calls to iomap_iter().  Treat as read-only in the body.
  * @len: The remaining length of the file segment we're operating on.
  *	It is updated at the same time as @pos.
- * @processed: The number of bytes processed by the body in the most recent
- *	iteration, or a negative errno. 0 causes the iteration to stop.
+ * @iter_start_pos: The original start pos for the current iomap. Used for
+ *	incremental iter advance.
+ * @status: Status of the most recent iteration. Zero on success or a negative
+ *	errno on error.
  * @flags: Zero or more of the iomap_begin flags above.
  * @iomap: Map describing the I/O iteration
  * @srcmap: Source map for COW operations
@@ -221,7 +235,8 @@ struct iomap_iter {
 	struct inode *inode;
 	loff_t pos;
 	u64 len;
-	s64 processed;
+	loff_t iter_start_pos;
+	int status;
 	unsigned flags;
 	struct iomap iomap;
 	struct iomap srcmap;
@@ -229,20 +244,46 @@ struct iomap_iter {
 };
 
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops);
+int iomap_iter_advance(struct iomap_iter *iter, u64 *count);
 
 /**
- * iomap_length - length of the current iomap iteration
+ * iomap_length_trim - trimmed length of the current iomap iteration
  * @iter: iteration structure
+ * @pos: File position to trim from.
+ * @len: Length of the mapping to trim to.
  *
- * Returns the length that the operation applies to for the current iteration.
+ * Returns a trimmed length that the operation applies to for the current
+ * iteration.
  */
-static inline u64 iomap_length(const struct iomap_iter *iter)
+static inline u64 iomap_length_trim(const struct iomap_iter *iter, loff_t pos,
+		u64 len)
 {
 	u64 end = iter->iomap.offset + iter->iomap.length;
 
 	if (iter->srcmap.type != IOMAP_HOLE)
 		end = min(end, iter->srcmap.offset + iter->srcmap.length);
-	return min(iter->len, end - iter->pos);
+	return min(len, end - pos);
+}
+
+/**
+ * iomap_length - length of the current iomap iteration
+ * @iter: iteration structure
+ *
+ * Returns the length that the operation applies to for the current iteration.
+ */
+static inline u64 iomap_length(const struct iomap_iter *iter)
+{
+	return iomap_length_trim(iter, iter->pos, iter->len);
+}
+
+/**
+ * iomap_iter_advance_full - advance by the full length of current map
+ */
+static inline int iomap_iter_advance_full(struct iomap_iter *iter)
+{
+	u64 length = iomap_length(iter);
+
+	return iomap_iter_advance(iter, &length);
 }
 
 /**
@@ -306,12 +347,11 @@ 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 +368,42 @@ 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 +428,14 @@ 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 +451,10 @@ 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 +526,6 @@ 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 */