mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 12:42:02 +00:00
cbfce4c7fb
The current code to store the final logical to physical mapping for a zone append write in the extent tree is rather inefficient. It first has to split the ordered extent so that there is one ordered extent per bio, so that it can look up the ordered extent on I/O completion in btrfs_record_physical_zoned and store the physical LBA returned by the block driver in the ordered extent. btrfs_rewrite_logical_zoned then has to do a lookup in the chunk tree to see what physical address the logical address for this bio / ordered extent is mapped to, and then rewrite it in the extent tree. To optimize this process, we can store the physical address assigned in the chunk tree to the original logical address and a pointer to btrfs_ordered_sum structure the in the btrfs_bio structure, and then use this information to rewrite the logical address in the btrfs_ordered_sum structure directly at I/O completion time in btrfs_record_physical_zoned. btrfs_rewrite_logical_zoned then simply updates the logical address in the extent tree and the ordered_extent itself. The code in btrfs_rewrite_logical_zoned now runs for all data I/O completions in zoned file systems, which is fine as there is no remapping to do for non-append writes to conventional zones or for relocation, and the overhead for quickly breaking out of the loop is very low. Because zoned file systems now need the ordered_sums structure to record the actual write location returned by zone append, allocate dummy structures without the csum array for them when the I/O doesn't use checksums, and free them when completing the ordered_extent. Note that the btrfs_bio doesn't grow as the new field are places into a union that is so far not used for data writes and has plenty of space left in it. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
118 lines
3.0 KiB
C
118 lines
3.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
* Copyright (C) 2022 Christoph Hellwig.
|
|
*/
|
|
|
|
#ifndef BTRFS_BIO_H
|
|
#define BTRFS_BIO_H
|
|
|
|
#include <linux/bio.h>
|
|
#include <linux/workqueue.h>
|
|
#include "tree-checker.h"
|
|
|
|
struct btrfs_bio;
|
|
struct btrfs_fs_info;
|
|
|
|
#define BTRFS_BIO_INLINE_CSUM_SIZE 64
|
|
|
|
/*
|
|
* Maximum number of sectors for a single bio to limit the size of the
|
|
* checksum array. This matches the number of bio_vecs per bio and thus the
|
|
* I/O size for buffered I/O.
|
|
*/
|
|
#define BTRFS_MAX_BIO_SECTORS (256)
|
|
|
|
typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
|
|
|
|
/*
|
|
* Highlevel btrfs I/O structure. It is allocated by btrfs_bio_alloc and
|
|
* passed to btrfs_submit_bio for mapping to the physical devices.
|
|
*/
|
|
struct btrfs_bio {
|
|
/*
|
|
* Inode and offset into it that this I/O operates on.
|
|
* Only set for data I/O.
|
|
*/
|
|
struct btrfs_inode *inode;
|
|
u64 file_offset;
|
|
|
|
union {
|
|
/*
|
|
* For data reads: checksumming and original I/O information.
|
|
* (for internal use in the btrfs_submit_bio machinery only)
|
|
*/
|
|
struct {
|
|
u8 *csum;
|
|
u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
|
|
struct bvec_iter saved_iter;
|
|
};
|
|
|
|
/*
|
|
* For data writes:
|
|
* - pointer to the checksums for this bio
|
|
* - original physical address from the allocator
|
|
* (for zone append only)
|
|
*/
|
|
struct {
|
|
struct btrfs_ordered_sum *sums;
|
|
u64 orig_physical;
|
|
};
|
|
|
|
/* For metadata reads: parentness verification. */
|
|
struct btrfs_tree_parent_check parent_check;
|
|
};
|
|
|
|
/* End I/O information supplied to btrfs_bio_alloc */
|
|
btrfs_bio_end_io_t end_io;
|
|
void *private;
|
|
|
|
/* For internal use in read end I/O handling */
|
|
unsigned int mirror_num;
|
|
atomic_t pending_ios;
|
|
struct work_struct end_io_work;
|
|
|
|
/* File system that this I/O operates on. */
|
|
struct btrfs_fs_info *fs_info;
|
|
|
|
/*
|
|
* This member must come last, bio_alloc_bioset will allocate enough
|
|
* bytes for entire btrfs_bio but relies on bio being last.
|
|
*/
|
|
struct bio bio;
|
|
};
|
|
|
|
static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
|
|
{
|
|
return container_of(bio, struct btrfs_bio, bio);
|
|
}
|
|
|
|
int __init btrfs_bioset_init(void);
|
|
void __cold btrfs_bioset_exit(void);
|
|
|
|
void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info,
|
|
btrfs_bio_end_io_t end_io, void *private);
|
|
struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
|
|
struct btrfs_fs_info *fs_info,
|
|
btrfs_bio_end_io_t end_io, void *private);
|
|
|
|
static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
|
|
{
|
|
bbio->bio.bi_status = status;
|
|
bbio->end_io(bbio);
|
|
}
|
|
|
|
/* Bio only refers to one ordered extent. */
|
|
#define REQ_BTRFS_ONE_ORDERED REQ_DRV
|
|
|
|
/* Submit using blkcg_punt_bio_submit. */
|
|
#define REQ_BTRFS_CGROUP_PUNT REQ_FS_PRIVATE
|
|
|
|
void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num);
|
|
void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace);
|
|
int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
|
|
u64 length, u64 logical, struct page *page,
|
|
unsigned int pg_offset, int mirror_num);
|
|
|
|
#endif
|