mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 19:29:37 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
- Adjust the final parameter of iomap_dio_rw. - Add a new flag to request that iomap directio writes return EAGAIN if the write is not a pure overwrite within EOF; this will be used to reduce lock contention with unaligned direct writes on XFS. - Amend XFS' directio code to eliminate exclusive locking for unaligned direct writes if the circumstances permit -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEUzaAxoMeQq6m2jMV+H93GTRKtOsFAmAZgQAACgkQ+H93GTRK tOtNqw/+KPff1NjQVK2k361R0+LjlEHfe2nxh7+kS10IiR5nbBz4Fu+GwEosZKq+ H9ficBbZ0wIveV+5CEt2xZLEJFC4LZUpNPVVrUf8XPLKiVexP/U3wtKzmv9Z7D5J 5walMWQycVeR+ycomynV36giqekvARL7KCQG5By2ITfSNxfnb/wvKhn1d61ZDOF6 f4xzq7F6+cEOrSZt2LcFzGSfsTl6oakYMAomPU57sqGmw7MHRqoPTErbdh2HnVJy yQ47eiZgSKWKA+Qm+VvHHePYCYnu0nvA2rbNerjTN70hnO8rK9S0Vle6Sp5CUqAX sXOy8zxOLYKqyM4S/QkIN2TGIyWg+CHiakVLZGF3Q4AUDDYfpD0cHvAe9N3v9euL qt8ypT8dz2C3qiTg5E31xy033wlAP0wg3FZiLAqEjL5o3fzD+qbplTiSmYbMV2Fb xuu7a2T6u1MHaIn1IhaL0cB49Fzn+5EMyp6BlAucAOakyuqJCyJiXokdk0Looy5e jUshvcwWcmHMpI/YYYY6t56KV6tl2exGq5sySY5U6dr8/r5lwc0SI+TrYFG0jTR8 59DGd5CkKgdBFcuys+eaZDXgr7A4ymkVE+pE0QNDz9UwNP20tLb3dQNlhgxchUgu NgPaFgQkoNM3HmQNyU2wX/t1aFlC/doqSkb/96UWQSxq6IrajMU= =AR07 -----END PGP SIGNATURE----- Merge tag 'iomap-5.12-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux Pull iomap updates from Darrick Wong: "The big change in this cycle is some new code to make it possible for XFS to try unaligned directio overwrites without taking locks. If the block is fully written and within EOF (i.e. doesn't require any further fs intervention) then we can let the unlocked write proceed. If not, we fall back to synchronizing direct writes. Summary: - Adjust the final parameter of iomap_dio_rw. - Add a new flag to request that iomap directio writes return EAGAIN if the write is not a pure overwrite within EOF; this will be used to reduce lock contention with unaligned direct writes on XFS. - Amend XFS' directio code to eliminate exclusive locking for unaligned direct writes if the circumstances permit" * tag 'iomap-5.12-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: xfs: reduce exclusive locking on unaligned dio xfs: split the unaligned DIO write code out xfs: improve the reflink_bounce_dio_write tracepoint xfs: simplify the read/write tracepoints xfs: remove the buffered I/O fallback assert xfs: cleanup the read/write helper naming xfs: make xfs_file_aio_write_checks IOCB_NOWAIT-aware xfs: factor out a xfs_ilock_iocb helper iomap: add a IOMAP_DIO_OVERWRITE_ONLY flag iomap: pass a flags argument to iomap_dio_rw iomap: rename the flags variable in __iomap_dio_rw
294 lines
9.9 KiB
C
294 lines
9.9 KiB
C
/* 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>
|
|
|
|
struct address_space;
|
|
struct fiemap_extent_info;
|
|
struct inode;
|
|
struct iomap_dio;
|
|
struct iomap_writepage_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.
|
|
*/
|
|
#define IOMAP_F_NEW 0x01
|
|
#define IOMAP_F_DIRTY 0x02
|
|
#define IOMAP_F_SHARED 0x04
|
|
#define IOMAP_F_MERGED 0x08
|
|
#define IOMAP_F_BUFFER_HEAD 0x10
|
|
#define IOMAP_F_ZONE_APPEND 0x20
|
|
|
|
/*
|
|
* Flags set by the core iomap code during operations:
|
|
*
|
|
* IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size
|
|
* has changed as the result of this write operation.
|
|
*/
|
|
#define IOMAP_F_SIZE_CHANGED 0x100
|
|
|
|
/*
|
|
* Flags from 0x1000 up are for file system specific usage:
|
|
*/
|
|
#define IOMAP_F_PRIVATE 0x1000
|
|
|
|
|
|
/*
|
|
* Magic value for addr:
|
|
*/
|
|
#define IOMAP_NULL_ADDR -1ULL /* addr is not valid */
|
|
|
|
struct iomap_page_ops;
|
|
|
|
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 */
|
|
const struct iomap_page_ops *page_ops;
|
|
};
|
|
|
|
static inline sector_t
|
|
iomap_sector(struct iomap *iomap, loff_t pos)
|
|
{
|
|
return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
|
|
}
|
|
|
|
/*
|
|
* When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
|
|
* and page_done will be called for each page written to. This only applies to
|
|
* buffered writes as unbuffered writes will not typically have pages
|
|
* associated with them.
|
|
*
|
|
* When page_prepare succeeds, page_done will always be called to do any
|
|
* cleanup work necessary. In that page_done call, @page will be NULL if the
|
|
* associated page could not be obtained.
|
|
*/
|
|
struct iomap_page_ops {
|
|
int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
|
|
struct iomap *iomap);
|
|
void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
|
|
struct page *page, struct iomap *iomap);
|
|
};
|
|
|
|
/*
|
|
* Flags for iomap_begin / iomap_end. 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 */
|
|
|
|
struct iomap_ops {
|
|
/*
|
|
* 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.
|
|
*/
|
|
int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length,
|
|
unsigned flags, struct iomap *iomap,
|
|
struct iomap *srcmap);
|
|
|
|
/*
|
|
* Commit and/or unreserve space previous allocated using iomap_begin.
|
|
* Written indicates the length of the successful write operation which
|
|
* needs to be commited, while the rest needs to be unreserved.
|
|
* Written might be zero if no data was written.
|
|
*/
|
|
int (*iomap_end)(struct inode *inode, loff_t pos, loff_t length,
|
|
ssize_t written, unsigned flags, struct iomap *iomap);
|
|
};
|
|
|
|
/*
|
|
* Main iomap iterator function.
|
|
*/
|
|
typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
|
|
void *data, struct iomap *iomap, struct iomap *srcmap);
|
|
|
|
loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
|
|
unsigned flags, const struct iomap_ops *ops, void *data,
|
|
iomap_actor_t actor);
|
|
|
|
ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
|
|
const struct iomap_ops *ops);
|
|
int iomap_readpage(struct page *page, const struct iomap_ops *ops);
|
|
void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
|
|
int iomap_set_page_dirty(struct page *page);
|
|
int iomap_is_partially_uptodate(struct page *page, unsigned long from,
|
|
unsigned long count);
|
|
int iomap_releasepage(struct page *page, gfp_t gfp_mask);
|
|
void iomap_invalidatepage(struct page *page, unsigned int offset,
|
|
unsigned int len);
|
|
#ifdef CONFIG_MIGRATION
|
|
int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
|
|
struct page *page, enum migrate_mode mode);
|
|
#else
|
|
#define iomap_migrate_page NULL
|
|
#endif
|
|
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);
|
|
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);
|
|
int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
|
|
u64 start, u64 len, const struct iomap_ops *ops);
|
|
loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
|
|
const struct iomap_ops *ops);
|
|
loff_t iomap_seek_data(struct inode *inode, loff_t offset,
|
|
const struct iomap_ops *ops);
|
|
sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
|
|
const struct iomap_ops *ops);
|
|
|
|
/*
|
|
* Structure for writeback I/O completions.
|
|
*/
|
|
struct iomap_ioend {
|
|
struct list_head io_list; /* next ioend in chain */
|
|
u16 io_type;
|
|
u16 io_flags; /* IOMAP_F_* */
|
|
struct inode *io_inode; /* file being written to */
|
|
size_t io_size; /* size of the extent */
|
|
loff_t io_offset; /* offset in the file */
|
|
void *io_private; /* file system private data */
|
|
struct bio *io_bio; /* bio being built */
|
|
struct bio io_inline_bio; /* MUST BE LAST! */
|
|
};
|
|
|
|
struct iomap_writeback_ops {
|
|
/*
|
|
* Required, maps the blocks so that writeback can be performed on
|
|
* the range starting at offset.
|
|
*/
|
|
int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
|
|
loff_t offset);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
int (*prepare_ioend)(struct iomap_ioend *ioend, int status);
|
|
|
|
/*
|
|
* Optional, allows the file system to discard state on a page where
|
|
* we failed to submit any I/O.
|
|
*/
|
|
void (*discard_page)(struct page *page, loff_t fileoff);
|
|
};
|
|
|
|
struct iomap_writepage_ctx {
|
|
struct iomap iomap;
|
|
struct iomap_ioend *ioend;
|
|
const struct iomap_writeback_ops *ops;
|
|
};
|
|
|
|
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 (*merge_private)(struct iomap_ioend *ioend,
|
|
struct iomap_ioend *next));
|
|
void iomap_sort_ioends(struct list_head *ioend_list);
|
|
int iomap_writepage(struct page *page, struct writeback_control *wbc,
|
|
struct iomap_writepage_ctx *wpc,
|
|
const struct iomap_writeback_ops *ops);
|
|
int iomap_writepages(struct address_space *mapping,
|
|
struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
|
|
const struct iomap_writeback_ops *ops);
|
|
|
|
/*
|
|
* 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);
|
|
blk_qc_t (*submit_io)(struct inode *inode, struct iomap *iomap,
|
|
struct bio *bio, loff_t file_offset);
|
|
};
|
|
|
|
/*
|
|
* 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)
|
|
|
|
ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
|
|
const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
|
|
unsigned int dio_flags);
|
|
struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
|
|
const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
|
|
unsigned int dio_flags);
|
|
ssize_t iomap_dio_complete(struct iomap_dio *dio);
|
|
int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
|
|
|
|
#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,
|
|
const struct iomap_ops *ops);
|
|
#else
|
|
# define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO)
|
|
#endif /* CONFIG_SWAP */
|
|
|
|
#endif /* LINUX_IOMAP_H */
|