/* SPDX-License-Identifier: GPL-2.0 */
#ifndef LINUX_IOMAP_H
#define LINUX_IOMAP_H 1

#include <linux/atomic.h>
#include <linux/bitmap.h>
#include <linux/blk_types.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <linux/mm_types.h>
#include <linux/blkdev.h>
#include <linux/folio_batch.h>
#include <linux/pagemap.h>

struct address_space;
struct fiemap_extent_info;
struct inode;
struct iomap_iter;
struct iomap_dio;
struct iomap_writepage_ctx;
struct iomap_read_folio_ctx;
struct iov_iter;
struct kiocb;
struct page;
struct vm_area_struct;
struct vm_fault;

/*
 * Types of block ranges for iomap mappings:
 */
#define IOMAP_HOLE	0	/* no blocks allocated, need allocation */
#define IOMAP_DELALLOC	1	/* delayed allocation blocks */
#define IOMAP_MAPPED	2	/* blocks allocated at @addr */
#define IOMAP_UNWRITTEN	3	/* blocks allocated at @addr in unwritten state */
#define IOMAP_INLINE	4	/* data inline in the inode */

/*
 * Flags reported by the file system from iomap_begin:
 *
 * IOMAP_F_NEW indicates that the blocks have been newly allocated and need
 * zeroing for areas that no data is copied to.
 *
 * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access
 * written data and requires fdatasync to commit them to persistent storage.
 * This needs to take into account metadata changes that *may* be made at IO
 * completion, such as file size updates from direct IO.
 *
 * IOMAP_F_SHARED indicates that the blocks are shared, and will need to be
 * unshared as part a write.
 *
 * IOMAP_F_MERGED indicates that the iomap contains the merge of multiple block
 * mappings.
 *
 * IOMAP_F_BUFFER_HEAD indicates that the file system requires the use of
 * buffer heads for this mapping.
 *
 * IOMAP_F_XATTR indicates that the iomap is for an extended attribute extent
 * rather than a file data extent.
 *
 * 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.
 *
 * IOMAP_F_INTEGRITY indicates that the filesystems handles integrity metadata.
 *
 * IOMAP_F_ZERO_TAIL indicates the remainder of the block after the data
 * written should be zeroed.
 */
#define IOMAP_F_NEW		(1U << 0)
#define IOMAP_F_DIRTY		(1U << 1)
#define IOMAP_F_SHARED		(1U << 2)
#define IOMAP_F_MERGED		(1U << 3)
#ifdef CONFIG_BUFFER_HEAD
#define IOMAP_F_BUFFER_HEAD	(1U << 4)
#else
#define IOMAP_F_BUFFER_HEAD	0
#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)
#ifdef CONFIG_BLK_DEV_INTEGRITY
#define IOMAP_F_INTEGRITY	(1U << 9)
#else
#define IOMAP_F_INTEGRITY	0
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#define IOMAP_F_ZERO_TAIL	(1U << 10)

/*
 * Indicates reads and writes of fsverity metadata.
 *
 * Fsverity metadata is stored after the regular file data and thus beyond
 * i_size.
 */
#define IOMAP_F_FSVERITY	(1U << 11)

/*
 * Flag reserved for file system specific usage
 */
#define IOMAP_F_PRIVATE		(1U << 12)

/*
 * Flags set by the core iomap code during operations:
 *
 * IOMAP_F_FOLIO_BATCH indicates that the folio batch mechanism is active
 * for this operation, set by iomap_fill_dirty_folios().
 *
 * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size
 * has changed as the result of this write operation.
 *
 * IOMAP_F_STALE indicates that the iomap is not valid any longer and the file
 * range it covers needs to be remapped by the high level before the operation
 * can proceed.
 */
#define IOMAP_F_FOLIO_BATCH	(1U << 13)
#define IOMAP_F_SIZE_CHANGED	(1U << 14)
#define IOMAP_F_STALE		(1U << 15)

/*
 * Magic value for addr:
 */
#define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */

struct iomap {
	u64			addr; /* disk offset of mapping, bytes */
	loff_t			offset;	/* file offset of mapping, bytes */
	u64			length;	/* length of mapping, bytes */
	u16			type;	/* type of mapping */
	u16			flags;	/* flags for mapping */
	struct block_device	*bdev;	/* block device for I/O */
	struct dax_device	*dax_dev; /* dax_dev for dax operations */
	void			*inline_data;
	void			*private; /* filesystem private */
	u64			validity_cookie; /* used with .iomap_valid() */
};

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;
}

/*
 * Returns the inline data pointer for logical offset @pos.
 */
static inline void *iomap_inline_data(const struct iomap *iomap, loff_t pos)
{
	return iomap->inline_data + pos - iomap->offset;
}

/*
 * When get_folio succeeds, put_folio will always be called to do any
 * cleanup work necessary.  put_folio is responsible for unlocking and putting
 * @folio.
 */
struct iomap_write_ops {
	struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos,
			unsigned len);
	void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
			struct folio *folio);

	/*
	 * Check that the cached iomap still maps correctly to the filesystem's
	 * internal extent map. FS internal extent maps can change while iomap
	 * is iterating a cached iomap, so this hook allows iomap to detect that
	 * the iomap needs to be refreshed during a long running write
	 * operation.
	 *
	 * The filesystem can store internal state (e.g. a sequence number) in
	 * iomap->validity_cookie when the iomap is first mapped to be able to
	 * detect changes between mapping time and whenever .iomap_valid() is
	 * called.
	 *
	 * This is called with the folio over the specified file position held
	 * locked by the iomap code.
	 */
	bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);

	/*
	 * Optional if the filesystem wishes to provide a custom handler for
	 * reading in the contents of a folio, otherwise iomap will default to
	 * submitting a bio read request.
	 *
	 * The read must be done synchronously.
	 */
	int (*read_folio_range)(const struct iomap_iter *iter,
			struct folio *folio, loff_t pos, size_t len);
};

/*
 * Flags for iomap_next.  No flag implies a read.
 */
#define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
#define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
#define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
#define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
#define IOMAP_DIRECT		(1 << 4) /* direct I/O */
#define IOMAP_NOWAIT		(1 << 5) /* do not block */
#define IOMAP_OVERWRITE_ONLY	(1 << 6) /* only pure overwrites allowed */
#define IOMAP_UNSHARE		(1 << 7) /* unshare_file_range */
#ifdef CONFIG_FS_DAX
#define IOMAP_DAX		(1 << 8) /* DAX mapping */
#else
#define IOMAP_DAX		0
#endif /* CONFIG_FS_DAX */
#define IOMAP_ATOMIC		(1 << 9) /* torn-write protection */
#define IOMAP_DONTCACHE		(1 << 10)

/*
 * Return the existing mapping at pos, or reserve space starting at pos for up
 * to length, as long as we can do it as a single mapping.
 * The actual length is returned in iomap->length.
 */
typedef int (*iomap_iter_begin_fn)(struct inode *inode, loff_t pos,
		loff_t length, unsigned flags, struct iomap *iomap,
		struct iomap *srcmap);

/*
 * Commit and/or unreserve space previously allocated by iomap_iter_begin_fn.
 * Written indicates the length of the successful write operation which needs
 * to be committed, while the rest needs to be unreserved.
 * Written might be zero if no data was written.
 */
typedef int (*iomap_iter_end_fn)(struct inode *inode, loff_t pos, loff_t length,
		ssize_t written, unsigned flags, struct iomap *iomap);

/*
 * Produce the next mapping (finishing the previous one if needed).
 * Return 1 to continue iterating, 0 if the range is fully consumed, or a
 * negative error on failure.
 */
typedef int (*iomap_iter_next_fn)(const struct iomap_iter *iter,
		struct iomap *iomap, struct iomap *srcmap);

/**
 * struct iomap_iter - Iterate through a range of a file
 * @inode: Set at the start of the iteration and should not change.
 * @pos: The current file position we are operating on.  It is updated by
 *	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.
 * @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_iter_next flags above.
 * @iomap: Map describing the I/O iteration
 * @srcmap: Source map for COW operations
 */
struct iomap_iter {
	struct inode *inode;
	loff_t pos;
	u64 len;
	loff_t iter_start_pos;
	int status;
	unsigned flags;
	struct iomap iomap;
	struct iomap srcmap;
	struct folio_batch *fbatch;
	void *private;
};

int iomap_iter(struct iomap_iter *iter, iomap_iter_next_fn next);
int iomap_iter_advance(struct iomap_iter *iter, u64 count);

/**
 * 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 a trimmed length that the operation applies to for the current
 * iteration.
 */
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(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)
{
	return iomap_iter_advance(iter, iomap_length(iter));
}

/**
 * iomap_iter_srcmap - return the source map for the current iomap iteration
 * @i: iteration structure
 *
 * Write operations on file systems with reflink support might require a
 * source and a destination map.  This function retourns the source map
 * for a given operation, which may or may no be identical to the destination
 * map in &i->iomap.
 */
static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
{
	if (i->srcmap.type != IOMAP_HOLE)
		return &i->srcmap;
	return &i->iomap;
}

int iomap_iter_continue(const struct iomap_iter *iter, struct iomap *iomap,
		struct iomap *srcmap, int ret);

/**
 * iomap_iter_next - finish the previous mapping and produce the next one
 * @iter: iteration structure
 * @iomap: mapping to finish and then repopulate
 * @srcmap: source mapping to finish and then repopulate
 * @begin: callback that produces a mapping for the current position
 * @end: optional callback that finishes the previous mapping, or NULL
 *
 * Inline helper that implements the common body of an iomap_iter_next_fn
 * callback: it finishes the previous mapping via @end (if present), decides
 * via iomap_iter_continue() whether to keep going, and obtains the next
 * mapping via @begin.
 *
 * This helper is marked __always_inline so that when a caller passes
 * compile-time-constant @begin and @end callbacks, the compiler can call them
 * directly, avoiding the indirect-call overhead.
 *
 * Returns 1 to continue iterating, 0 once the range is fully consumed, or a
 * negative errno on error.
 */
static __always_inline int iomap_iter_next(const struct iomap_iter *iter,
		struct iomap *iomap, struct iomap *srcmap,
		iomap_iter_begin_fn begin, iomap_iter_end_fn end)
{
	int ret = 0;

	if (iomap->length) {
		if (end) {
			/*
			 * Calculate how far the iter was advanced and the
			 * original length bytes for end().
			 */
			ssize_t advanced = iter->pos - iter->iter_start_pos;
			loff_t len;

			len = iomap_length_trim(iter, iter->iter_start_pos,
					iter->len + advanced);

			ret = end(iter->inode, iter->iter_start_pos, len,
					advanced, iter->flags, iomap);
		}
		ret = iomap_iter_continue(iter, iomap, srcmap, ret);
		if (ret <= 0)
			return ret;
	}

	ret = begin(iter->inode, iter->pos, iter->len, iter->flags, iomap,
			srcmap);

	return ret < 0 ? ret : 1;
}

#define DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, end_fn)		\
int name(const struct iomap_iter *iter, struct iomap *iomap,		\
		struct iomap *srcmap)					\
{									\
	return iomap_iter_next(iter, iomap, srcmap, begin_fn, end_fn);	\
}

#define DEFINE_IOMAP_ITER_NEXT(name, begin_fn)				\
	DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, NULL)

/*
 * Forward-declare an iomap_iter_next_fn callback generated by
 * DEFINE_IOMAP_ITER_NEXT().
 */
#define DECLARE_IOMAP_ITER_NEXT(name)					\
int name(const struct iomap_iter *iter, struct iomap *iomap,		\
		struct iomap *srcmap)

/*
 * Return the file offset for the first unchanged block after a short write.
 *
 * If nothing was written, round @pos down to point at the first block in
 * the range, else round up to include the partially written block.
 */
static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos,
		ssize_t written)
{
	if (unlikely(!written))
		return round_down(pos, i_blocksize(inode));
	return round_up(pos + written, i_blocksize(inode));
}

/*
 * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
 * operation.
 *
 * Don't bother with blocks that are not shared to start with; or mappings that
 * cannot be shared, such as inline data, delalloc reservations, holes or
 * unwritten extents.
 *
 * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
 * requires providing a separate source map, and the presence of one is a good
 * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
 * for any data that goes into the COW fork for XFS.
 */
static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
{
	return (iter->iomap.flags & IOMAP_F_SHARED) &&
		iter->srcmap.type == IOMAP_MAPPED;
}

ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
		iomap_iter_next_fn next,
		const struct iomap_write_ops *write_ops, void *private);
int iomap_fsverity_write(struct file *file, loff_t pos, size_t length,
		const void *buf, iomap_iter_next_fn next,
		const struct iomap_write_ops *write_ops);
void iomap_read_folio(iomap_iter_next_fn next, struct iomap_read_folio_ctx *ctx,
		void *private);
void iomap_readahead(iomap_iter_next_fn next, struct iomap_read_folio_ctx *ctx,
		void *private);
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);
void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
void iomap_folio_mark_uptodate(struct folio *folio);
int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
		iomap_iter_next_fn next,
		const struct iomap_write_ops *write_ops);
unsigned int iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t *start,
		loff_t end, unsigned int *iomap_flags);
int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
		bool *did_zero, iomap_iter_next_fn next,
		const struct iomap_write_ops *write_ops, void *private);
int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
		iomap_iter_next_fn next,
		const struct iomap_write_ops *write_ops, void *private);
vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, iomap_iter_next_fn next,
		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,
		loff_t end_byte, unsigned flags, struct iomap *iomap,
		iomap_punch_t punch);

int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		u64 start, u64 len, iomap_iter_next_fn next);
loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
		iomap_iter_next_fn next);
loff_t iomap_seek_data(struct inode *inode, loff_t offset,
		iomap_iter_next_fn next);
sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
		iomap_iter_next_fn next);

/*
 * 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)
/* generate integrity (PI) information */
#ifdef CONFIG_BLK_DEV_INTEGRITY
#define IOMAP_IOEND_INTEGRITY		(1U << 4)
#else
#define IOMAP_IOEND_INTEGRITY		0
#endif /* CONFIG_BLK_DEV_INTEGRITY */

/*
 * 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 | \
	 IOMAP_IOEND_INTEGRITY)

/* ioend flags directly implied by iomap flags */
static inline u16 iomap_ioend_flags(const struct iomap *iomap)
{
	unsigned int flags = 0;

	if (iomap->type == IOMAP_UNWRITTEN)
		flags |= IOMAP_IOEND_UNWRITTEN;
	if (iomap->flags & IOMAP_F_SHARED)
		flags |= IOMAP_IOEND_SHARED;
	if (iomap->flags & IOMAP_F_INTEGRITY)
		flags |= IOMAP_IOEND_INTEGRITY;

	return flags;
}

/*
 * Structure for writeback I/O completions.
 *
 * File systems 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_flags;	/* IOMAP_IOEND_* */
	u32			io_bvec_offset;	/* offset into first bvec */
	struct inode		*io_inode;	/* file being written to */
	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 fsverity_info	*io_vi;		/* fsverity info */
	struct bio		io_bio;		/* MUST BE LAST! */
};

static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
{
	return container_of(bio, struct iomap_ioend, io_bio);
}

#define BVEC_ITER_IOEND(_ioend)				\
{							\
	.bi_sector	= (_ioend)->io_sector,		\
	.bi_size	= (_ioend)->io_size,		\
	.bi_offset	= (_ioend)->io_bvec_offset,	\
}

struct iomap_writeback_ops {
	/*
	 * Performs writeback on the passed in range
	 *
	 * Can map arbitrarily large regions, but we need to call into it at
	 * least once per folio to allow the file systems to synchronize with
	 * the write path that could be invalidating mappings.
	 *
	 * An existing mapping from a previous call to this method can be reused
	 * by the file system if it is still valid.
	 *
	 * If this succeeds, iomap_finish_folio_write() must be called once
	 * writeback completes for the range, regardless of whether the
	 * writeback succeeded or failed.
	 *
	 * Returns the number of bytes processed or a negative errno.
	 */
	ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc,
			struct folio *folio, u64 pos, unsigned int len,
			u64 end_pos);

	/*
	 * Submit a writeback context previously build up by ->writeback_range.
	 *
	 * Returns 0 if the context was successfully submitted, or a negative
	 * error code if not.  If @error is non-zero a failure occurred, and
	 * the writeback context should be completed with an error.
	 */
	int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error);
};

struct iomap_writepage_ctx {
	struct iomap		iomap;
	struct inode		*inode;
	struct writeback_control *wbc;
	const struct iomap_writeback_ops *ops;
	u32			nr_folios;	/* folios added to the ioend */
	void			*wb_ctx;	/* pending writeback context */
};

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);
void iomap_sort_ioends(struct list_head *ioend_list);
int iomap_ioend_integrity_verify(struct iomap_ioend *ioend);
ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
		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_finish_folio_write(struct inode *inode, struct folio *folio,
		size_t len);

int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
int iomap_writepages(struct iomap_writepage_ctx *wpc);

void iomap_bounce_read(struct iomap_ioend *orig_ioend, unsigned int minsize,
		void (*submit_ioend)(struct iomap_ioend *ioend));
void iomap_bounce_read_end_io(struct iomap_ioend *ioend, struct bio *orig_bio,
		int error);

struct iomap_read_folio_ctx {
	const struct iomap_read_ops *ops;
	struct folio		*cur_folio;
	struct readahead_control *rac;
	void			*read_ctx;
	loff_t			read_ctx_file_offset;
	struct fsverity_info	*vi;
};

struct iomap_read_ops {
	/*
	 * Read in a folio range.
	 *
	 * If this succeeds, iomap_finish_folio_read() must be called after the
	 * range is read in, regardless of whether the read succeeded or failed.
	 *
	 * 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)(const struct iomap_iter *iter,
			struct iomap_read_folio_ctx *ctx);

	/*
	 * Optional, allows filesystem to specify own bio_set, so new bio's
	 * can be allocated from the provided bio_set.
	 */
	struct bio_set *bio_set;
};

/*
 * Flags for direct I/O ->end_io:
 */
#define IOMAP_DIO_UNWRITTEN	(1 << 0)	/* covers unwritten extent(s) */
#define IOMAP_DIO_COW		(1 << 1)	/* covers COW extent(s) */

struct iomap_dio_ops {
	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
		      unsigned flags);
	void (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
		          loff_t file_offset);

	/*
	 * Filesystems wishing to attach private information to a direct io bio
	 * must provide a ->submit_io method that attaches the additional
	 * information to the bio and changes the ->bi_end_io callback to a
	 * custom function.  This function should, at a minimum, perform any
	 * relevant post-processing of the bio and end with a call to
	 * iomap_dio_bio_end_io.
	 */
	struct bio_set *bio_set;
};

/*
 * Wait for the I/O to complete in iomap_dio_rw even if the kiocb is not
 * synchronous.
 */
#define IOMAP_DIO_FORCE_WAIT	(1 << 0)

/*
 * Do not allocate blocks or zero partial blocks, but instead fall back to
 * the caller by returning -EAGAIN.  Used to optimize direct I/O writes that
 * are not aligned to the file system block size.
  */
#define IOMAP_DIO_OVERWRITE_ONLY	(1 << 1)

/*
 * When a page fault occurs, return a partial synchronous result and allow
 * the caller to retry the rest of the operation after dealing with the page
 * fault.
 */
#define IOMAP_DIO_PARTIAL		(1 << 2)

/*
 * Ensure every operation, including bio and hole zeroing, is aligned to fs
 * block size.
 *
 * For filesystems which need to calculate/verify the checksum of each fs
 * block. Otherwise they may not be able to handle unaligned bios.
 */
#define IOMAP_DIO_FSBLOCK_ALIGNED	(1 << 3)

/*
 * Bounce buffer instead of using zero copy access.
 *
 * This is needed if the device needs stable data to checksum or generate
 * parity.  The file system must hook into the I/O submission and offload
 * completions to user context for reads when this is set.
 */
#define IOMAP_DIO_BOUNCE		(1 << 4)

ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
		iomap_iter_next_fn next, const struct iomap_dio_ops *dops,
		unsigned int dio_flags, void *private, size_t done_before);
struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
		iomap_iter_next_fn next, const struct iomap_dio_ops *dops,
		unsigned int dio_flags, void *private, size_t done_before);
ssize_t iomap_dio_complete(struct iomap_dio *dio);
void iomap_dio_bio_end_io(struct bio *bio);

/*
 * Fast path for small, block-aligned direct I/Os that map to a single
 * contiguous on-disk extent.
 *
 * @iter must describe a non-empty READ no larger than the inode block size:
 * writes, zero-length I/O, and larger requests need the generic iomap direct
 * I/O path.
 *
 * Does not support iomap_dio_ops, dio_flags, done_before or private data.
 * The range must also stay within i_size and encrypted inodes must use the
 * generic iomap direct I/O path.
 *
 * -ENOTBLK indicates the generic path must be used by the caller instead.
 * Any other errno is a real result and is propagated as-is, in particular
 * -EAGAIN for IOCB_NOWAIT must reach the caller.
 *
 * The caller can only provide an iomap begin handler, and the iterator
 * is never advanced.
 */
ssize_t __iomap_dio_read_simple(struct kiocb *iocb, struct iov_iter *iter,
		struct iomap_iter *iomi);
static __always_inline ssize_t iomap_dio_read_simple(struct kiocb *iocb,
		struct iov_iter *iter, iomap_iter_begin_fn begin)
{
	struct iomap_iter iomi = {
		.inode		= file_inode(iocb->ki_filp),
		.pos		= iocb->ki_pos,
		.len		= iov_iter_count(iter),
		.flags		= IOMAP_DIRECT,
	};
	ssize_t ret;

	if (!iomi.len)
		return 0;

	/*
	 * Simple dio is an optimization for small IO. Filter out large IO
	 * early as it's the most common case to fail for typical direct IO
	 * workloads.
	 */
	if (iomi.len > iomi.inode->i_sb->s_blocksize)
		return -ENOTBLK;
	if (iocb->ki_pos + iomi.len > i_size_read(iomi.inode))
		return -ENOTBLK;
	if (IS_ENCRYPTED(iomi.inode))
		return -ENOTBLK;

	ret = kiocb_write_and_wait(iocb, iomi.len);
	if (ret)
		return ret;

	if (iocb->ki_flags & IOCB_NOWAIT)
		iomi.flags |= IOMAP_NOWAIT;

	inode_dio_begin(iomi.inode);
	ret = begin(iomi.inode, iomi.pos, iomi.len, iomi.flags, &iomi.iomap,
			&iomi.srcmap);
	if (ret) {
		inode_dio_end(iomi.inode);
		return ret;
	}

	return __iomap_dio_read_simple(iocb, iter, &iomi);
}

#ifdef CONFIG_SWAP
struct file;
struct swap_info_struct;

int iomap_swapfile_activate(struct swap_info_struct *sis,
		struct file *swap_file, sector_t *pagespan,
		iomap_iter_next_fn next);
#else
# define iomap_swapfile_activate(sis, swapfile, pagespan, next) (-EIO)
#endif /* CONFIG_SWAP */

extern struct bio_set iomap_ioend_bioset;

#ifdef CONFIG_BLOCK
int iomap_bio_read_folio_range(const struct iomap_iter *iter,
		struct iomap_read_folio_ctx *ctx, size_t plen);
void iomap_bio_submit_read_endio(const struct iomap_iter *iter,
		struct iomap_read_folio_ctx *ctx, bio_end_io_t end_io);

extern const struct iomap_read_ops iomap_bio_read_ops;

static inline void iomap_bio_read_folio(struct folio *folio,
		iomap_iter_next_fn next)
{
	struct iomap_read_folio_ctx ctx = {
		.ops		= &iomap_bio_read_ops,
		.cur_folio	= folio,
	};

	iomap_read_folio(next, &ctx, NULL);
}

static inline void iomap_bio_readahead(struct readahead_control *rac,
		iomap_iter_next_fn next)
{
	struct iomap_read_folio_ctx ctx = {
		.ops		= &iomap_bio_read_ops,
		.rac		= rac,
	};

	iomap_readahead(next, &ctx, NULL);
}
#endif /* CONFIG_BLOCK */

#endif /* LINUX_IOMAP_H */