Files
linux/fs/btrfs/compression.h
Linus Torvalds 7696286034 Merge tag 'for-6.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
 "Features:

   - shutdown ioctl support (needs CONFIG_BTRFS_EXPERIMENTAL for now):
      - set filesystem state as being shut down (also named going down
        in other filesystems), where all active operations return EIO
        and this cannot be changed until unmount
      - pending operations are attempted to be finished but error
        messages may still show up depending on where exactly the
        shutdown happened

   - scrub (and device replace) vs suspend/hibernate:
      - a running scrub will prevent suspend, which can be annoying as
        suspend is an immediate request and scrub is not critical
      - filesystem freezing before suspend was not sufficient as the
        problem was in process freezing
      - behaviour change: on suspend scrub and device replace are
        cancelled, where scrub can record the last state and continue
        from there; the device replace has to be restarted from the
        beginning

   - zone stats exported in sysfs, from the perspective of the
     filesystem this includes active, reclaimable, relocation etc zones

  Performance:

   - improvements when processing space reservation tickets by
     optimizing locking and shrinking critical sections, cumulative
     improvements in lockstat numbers show +15%

  Notable fixes:

   - use vmalloc fallback when allocating bios as high order allocations
     can happen with wide checksums (like sha256)

   - scrub will always track the last position of progress so it's not
     starting from zero after an error

  Core:

   - under experimental config, checksum calculations are offloaded to
     process context, simplifies locking and allows to remove
     compression write worker kthread(s):
      - speed improvement in direct IO throughput with buffered IO
        fallback is +15% when not offloaded but this is more related to
        internal crypto subsystem improvements
      - this will be probably default in the future removing the sysfs
        tunable

   - (experimental) block size > page size updates:
      - support more operations when not using large folios (encoded
        read/write and send)
      - raid56

   - more preparations for fscrypt support

  Other:

   - more conversions to auto-cleaned variables

   - parameter cleanups and removals

   - extended warning fixes

   - improved printing of structured values like keys

   - lots of other cleanups and refactoring"

* tag 'for-6.19-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (147 commits)
  btrfs: remove unnecessary inode key in btrfs_log_all_parents()
  btrfs: remove redundant zero/NULL initializations in btrfs_alloc_root()
  btrfs: remaining BTRFS_PATH_AUTO_FREE conversions
  btrfs: send: do not allocate memory for xattr data when checking it exists
  btrfs: send: add unlikely to all unexpected overflow checks
  btrfs: reduce arguments to btrfs_del_inode_ref_in_log()
  btrfs: remove root argument from btrfs_del_dir_entries_in_log()
  btrfs: use test_and_set_bit() in btrfs_delayed_delete_inode_ref()
  btrfs: don't search back for dir inode item in INO_LOOKUP_USER
  btrfs: don't rewrite ret from inode_permission
  btrfs: add orig_logical to btrfs_bio for encryption
  btrfs: disable verity on encrypted inodes
  btrfs: disable various operations on encrypted inodes
  btrfs: remove redundant level reset in btrfs_del_items()
  btrfs: simplify leaf traversal after path release in btrfs_next_old_leaf()
  btrfs: optimize balance_level() path reference handling
  btrfs: factor out root promotion logic into promote_child_to_root()
  btrfs: raid56: remove the "_step" infix
  btrfs: raid56: enable bs > ps support
  btrfs: raid56: prepare finish_parity_scrub() to support bs > ps cases
  ...
2025-12-03 20:03:46 -08:00

186 lines
6.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2008 Oracle. All rights reserved.
*/
#ifndef BTRFS_COMPRESSION_H
#define BTRFS_COMPRESSION_H
#include <linux/sizes.h>
#include <linux/mm.h>
#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/wait.h>
#include <linux/pagemap.h>
#include "bio.h"
#include "fs.h"
#include "btrfs_inode.h"
struct address_space;
struct inode;
struct btrfs_inode;
struct btrfs_ordered_extent;
/*
* We want to make sure that amount of RAM required to uncompress an extent is
* reasonable, so we limit the total size in ram of a compressed extent to
* 128k. This is a crucial number because it also controls how easily we can
* spread reads across cpus for decompression.
*
* We also want to make sure the amount of IO required to do a random read is
* reasonably small, so we limit the size of a compressed extent to 128k.
*/
/* Maximum length of compressed data stored on disk */
#define BTRFS_MAX_COMPRESSED (SZ_128K)
#define BTRFS_MAX_COMPRESSED_PAGES (BTRFS_MAX_COMPRESSED / PAGE_SIZE)
static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
/* Maximum size of data before compression */
#define BTRFS_MAX_UNCOMPRESSED (SZ_128K)
#define BTRFS_ZLIB_DEFAULT_LEVEL 3
struct compressed_bio {
/* Number of compressed folios in the array. */
unsigned int nr_folios;
/* The folios with the compressed data on them. */
struct folio **compressed_folios;
/* starting offset in the inode for our pages */
u64 start;
/* Number of bytes in the inode we're working on */
unsigned int len;
/* Number of bytes on disk */
unsigned int compressed_len;
/* The compression algorithm for this bio */
u8 compress_type;
/* Whether this is a write for writeback. */
bool writeback;
/* For reads, this is the bio we are copying the data into. */
struct btrfs_bio *orig_bbio;
/* Must be last. */
struct btrfs_bio bbio;
};
static inline struct btrfs_fs_info *cb_to_fs_info(const struct compressed_bio *cb)
{
return cb->bbio.inode->root->fs_info;
}
/* @range_end must be exclusive. */
static inline u32 btrfs_calc_input_length(struct folio *folio, u64 range_end, u64 cur)
{
/* @cur must be inside the folio. */
ASSERT(folio_pos(folio) <= cur);
ASSERT(cur < folio_next_pos(folio));
return umin(range_end, folio_next_pos(folio)) - cur;
}
int btrfs_alloc_compress_wsm(struct btrfs_fs_info *fs_info);
void btrfs_free_compress_wsm(struct btrfs_fs_info *fs_info);
int __init btrfs_init_compress(void);
void __cold btrfs_exit_compress(void);
bool btrfs_compress_level_valid(unsigned int type, int level);
int btrfs_compress_folios(unsigned int type, int level, struct btrfs_inode *inode,
u64 start, struct folio **folios, unsigned long *out_folios,
unsigned long *total_in, unsigned long *total_out);
int btrfs_decompress(int type, const u8 *data_in, struct folio *dest_folio,
unsigned long dest_pgoff, size_t srclen, size_t destlen);
int btrfs_decompress_buf2page(const char *buf, u32 buf_len,
struct compressed_bio *cb, u32 decompressed);
void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
struct folio **compressed_folios,
unsigned int nr_folios, blk_opf_t write_flags,
bool writeback);
void btrfs_submit_compressed_read(struct btrfs_bio *bbio);
int btrfs_compress_str2level(unsigned int type, const char *str, int *level_ret);
struct folio *btrfs_alloc_compr_folio(struct btrfs_fs_info *fs_info);
void btrfs_free_compr_folio(struct folio *folio);
struct workspace_manager {
struct list_head idle_ws;
spinlock_t ws_lock;
/* Number of free workspaces */
int free_ws;
/* Total number of allocated workspaces */
atomic_t total_ws;
/* Waiters for a free workspace */
wait_queue_head_t ws_wait;
};
struct list_head *btrfs_get_workspace(struct btrfs_fs_info *fs_info, int type, int level);
void btrfs_put_workspace(struct btrfs_fs_info *fs_info, int type, struct list_head *ws);
struct btrfs_compress_levels {
/* Maximum level supported by the compression algorithm */
int min_level;
int max_level;
int default_level;
};
/* The heuristic workspaces are managed via the 0th workspace manager */
#define BTRFS_NR_WORKSPACE_MANAGERS BTRFS_NR_COMPRESS_TYPES
extern const struct btrfs_compress_levels btrfs_heuristic_compress;
extern const struct btrfs_compress_levels btrfs_zlib_compress;
extern const struct btrfs_compress_levels btrfs_lzo_compress;
extern const struct btrfs_compress_levels btrfs_zstd_compress;
const char* btrfs_compress_type2str(enum btrfs_compression_type type);
bool btrfs_compress_is_valid_type(const char *str, size_t len);
int btrfs_compress_heuristic(struct btrfs_inode *inode, u64 start, u64 end);
int btrfs_compress_filemap_get_folio(struct address_space *mapping, u64 start,
struct folio **in_folio_ret);
int zlib_compress_folios(struct list_head *ws, struct btrfs_inode *inode,
u64 start, struct folio **folios, unsigned long *out_folios,
unsigned long *total_in, unsigned long *total_out);
int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int zlib_decompress(struct list_head *ws, const u8 *data_in,
struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen,
size_t destlen);
struct list_head *zlib_alloc_workspace(struct btrfs_fs_info *fs_info, unsigned int level);
void zlib_free_workspace(struct list_head *ws);
struct list_head *zlib_get_workspace(struct btrfs_fs_info *fs_info, unsigned int level);
int lzo_compress_folios(struct list_head *ws, struct btrfs_inode *inode,
u64 start, struct folio **folios, unsigned long *out_folios,
unsigned long *total_in, unsigned long *total_out);
int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int lzo_decompress(struct list_head *ws, const u8 *data_in,
struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen,
size_t destlen);
struct list_head *lzo_alloc_workspace(struct btrfs_fs_info *fs_info);
void lzo_free_workspace(struct list_head *ws);
int zstd_compress_folios(struct list_head *ws, struct btrfs_inode *inode,
u64 start, struct folio **folios, unsigned long *out_folios,
unsigned long *total_in, unsigned long *total_out);
int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int zstd_decompress(struct list_head *ws, const u8 *data_in,
struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen,
size_t destlen);
int zstd_alloc_workspace_manager(struct btrfs_fs_info *fs_info);
void zstd_free_workspace_manager(struct btrfs_fs_info *fs_info);
struct list_head *zstd_alloc_workspace(struct btrfs_fs_info *fs_info, int level);
void zstd_free_workspace(struct list_head *ws);
struct list_head *zstd_get_workspace(struct btrfs_fs_info *fs_info, int level);
void zstd_put_workspace(struct btrfs_fs_info *fs_info, struct list_head *ws);
#endif