mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
0b166a57e6
* Fix performance problems found in dioread_nolock now that it is the default, caused by transaction leaks. * Clean up fiemap handling in ext4 * Clean up and refactor multiple block allocator (mballoc) code * Fix a problem with mballoc with a smaller file systems running out of blocks because they couldn't properly use blocks that had been reserved by inode preallocation. * Fixed a race in ext4_sync_parent() versus rename() * Simplify the error handling in the extent manipulation code * Make sure all metadata I/O errors are felected to ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers. * Avoid passing an error pointer to brelse in ext4_xattr_set() * Fix race which could result to freeing an inode on the dirty last in data=journal mode. * Fix refcount handling if ext4_iget() fails * Fix a crash in generic/019 caused by a corrupted extent node -----BEGIN PGP SIGNATURE----- iQEyBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAl7Ze8kACgkQ8vlZVpUN gaNChAf4xn0ytFSrweI/S2Sp05G/2L/ocZ2TZZk2ZdGeN1E+ABdSIv/zIF9zuFgZ /pY/C+fyEZWt4E3FlNO8gJzoEedkzMCMnUhSIfI+wZbcclyTOSNMJtnrnJKAEtVH HOvGZJmg357jy407RCGhZpJ773nwU2xhBTr5OFxvSf9mt/vzebxIOnw5D7HPlC1V Fgm6Du8q+tRrPsyjv1Yu4pUEVXMJ7qUcvt326AXVM3kCZO1Aa5GrURX0w3J4mzW1 tc1tKmtbLcVVYTo9CwHXhk/edbxrhAydSP2iACand3tK6IJuI6j9x+bBJnxXitnr vsxsfTYMG18+2SxrJ9LwmagqmrRq =HMTs -----END PGP SIGNATURE----- Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 Pull ext4 updates from Ted Ts'o: "A lot of bug fixes and cleanups for ext4, including: - Fix performance problems found in dioread_nolock now that it is the default, caused by transaction leaks. - Clean up fiemap handling in ext4 - Clean up and refactor multiple block allocator (mballoc) code - Fix a problem with mballoc with a smaller file systems running out of blocks because they couldn't properly use blocks that had been reserved by inode preallocation. - Fixed a race in ext4_sync_parent() versus rename() - Simplify the error handling in the extent manipulation code - Make sure all metadata I/O errors are felected to ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers. - Avoid passing an error pointer to brelse in ext4_xattr_set() - Fix race which could result to freeing an inode on the dirty last in data=journal mode. - Fix refcount handling if ext4_iget() fails - Fix a crash in generic/019 caused by a corrupted extent node" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits) ext4: avoid unnecessary transaction starts during writeback ext4: don't block for O_DIRECT if IOCB_NOWAIT is set ext4: remove the access_ok() check in ext4_ioctl_get_es_cache fs: remove the access_ok() check in ioctl_fiemap fs: handle FIEMAP_FLAG_SYNC in fiemap_prep fs: move fiemap range validation into the file systems instances iomap: fix the iomap_fiemap prototype fs: move the fiemap definitions out of fs.h fs: mark __generic_block_fiemap static ext4: remove the call to fiemap_check_flags in ext4_fiemap ext4: split _ext4_fiemap ext4: fix fiemap size checks for bitmap files ext4: fix EXT4_MAX_LOGICAL_BLOCK macro add comment for ext4_dir_entry_2 file_type member jbd2: avoid leaking transaction credits when unreserving handle ext4: drop ext4_journal_free_reserved() ext4: mballoc: use lock for checking free blocks while retrying ext4: mballoc: refactor ext4_mb_good_group() ext4: mballoc: introduce pcpu seqcnt for freeing PA to improve ENOSPC handling ext4: mballoc: refactor ext4_mb_discard_preallocations() ...
275 lines
9.1 KiB
C
275 lines
9.1 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_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
|
|
|
|
/*
|
|
* 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 */
|
|
|
|
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);
|
|
};
|
|
|
|
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);
|
|
};
|
|
|
|
ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
|
|
const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
|
|
bool wait_for_completion);
|
|
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 */
|