linux/fs/btrfs/subpage.h
Qu Wenruo bd610c0937 btrfs: only unlock the to-be-submitted ranges inside a folio
[SUBPAGE COMPRESSION LIMITS]
Currently inside writepage_delalloc(), if a delalloc range is going to
be submitted asynchronously (inline or compression, the page
dirty/writeback/unlock are all handled in at different time, not at the
submission time), then we return 1 and extent_writepage() will skip the
submission.

This is fine if every sector matches page size, but if a sector is
smaller than page size (aka, subpage case), then it can be very
problematic, for example for the following 64K page:

     0     16K     32K    48K     64K
     |/|   |///////|      |/|
       |                    |
       4K                   52K

Where |/| is the dirty range we need to submit.

In the above case, we need the following different handling for the 3
ranges:

- [0, 4K) needs to be submitted for regular write
  A single sector cannot be compressed.

- [16K, 32K) needs to be submitted for compressed write

- [48K, 52K) needs to be submitted for regular write.

Above, if we try to submit [16K, 32K) for compressed write, we will
return 1 and immediately, and without submitting the remaining
[48K, 52K) range.

Furthermore, since extent_writepage() will exit without unlocking any
sectors, the submitted range [0, 4K) will not have sector unlocked.

That's the reason why for now subpage is only allowed for full page
range.

[ENHANCEMENT]
- Introduce a submission bitmap at btrfs_bio_ctrl::submit_bitmap
  This records which sectors will be submitted by extent_writepage_io().
  This allows us to track which sectors needs to be submitted thus later
  to be properly unlocked.

  For asynchronously submitted range (inline/compression), the
  corresponding bits will be cleared from that bitmap.

- Only return 1 if no sector needs to be submitted in
  writepage_delalloc()

- Only submit sectors marked by submission bitmap inside
  extent_writepage_io()
  So we won't touch the asynchronously submitted part.

- Introduce btrfs_folio_end_writer_lock_bitmap() helper
  This will only unlock the involved sectors specified by @bitmap
  parameter, to avoid touching the range asynchronously submitted.

Please note that, since subpage compression is still limited to page
aligned range, this change is only a preparation for future sector
perfect compression support for subpage.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2024-09-10 16:51:22 +02:00

167 lines
5.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_SUBPAGE_H
#define BTRFS_SUBPAGE_H
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/sizes.h>
struct address_space;
struct folio;
struct btrfs_fs_info;
/*
* Extra info for subpapge bitmap.
*
* For subpage we pack all uptodate/dirty/writeback/ordered bitmaps into
* one larger bitmap.
*
* This structure records how they are organized in the bitmap:
*
* /- uptodate /- dirty /- ordered
* | | |
* v v v
* |u|u|u|u|........|u|u|d|d|.......|d|d|o|o|.......|o|o|
* |< sectors_per_page >|
*
* Unlike regular macro-like enums, here we do not go upper-case names, as
* these names will be utilized in various macros to define function names.
*/
enum {
btrfs_bitmap_nr_uptodate = 0,
btrfs_bitmap_nr_dirty,
btrfs_bitmap_nr_writeback,
btrfs_bitmap_nr_ordered,
btrfs_bitmap_nr_checked,
btrfs_bitmap_nr_locked,
btrfs_bitmap_nr_max
};
/*
* Structure to trace status of each sector inside a page, attached to
* page::private for both data and metadata inodes.
*/
struct btrfs_subpage {
/* Common members for both data and metadata pages */
spinlock_t lock;
/*
* Both data and metadata needs to track how many readers are for the
* page.
* Data relies on @readers to unlock the page when last reader finished.
* While metadata doesn't need page unlock, it needs to prevent
* page::private get cleared before the last end_page_read().
*/
atomic_t readers;
union {
/*
* Structures only used by metadata
*
* @eb_refs should only be operated under private_lock, as it
* manages whether the subpage can be detached.
*/
atomic_t eb_refs;
/* Structures only used by data */
atomic_t writers;
};
unsigned long bitmaps[];
};
enum btrfs_subpage_type {
BTRFS_SUBPAGE_METADATA,
BTRFS_SUBPAGE_DATA,
};
#if PAGE_SIZE > SZ_4K
bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping);
#else
static inline bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info,
struct address_space *mapping)
{
return false;
}
#endif
int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
struct folio *folio, enum btrfs_subpage_type type);
void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio);
/* Allocate additional data where page represents more than one sector */
struct btrfs_subpage *btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info,
enum btrfs_subpage_type type);
void btrfs_free_subpage(struct btrfs_subpage *subpage);
void btrfs_folio_inc_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio);
void btrfs_folio_dec_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio);
void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
void btrfs_folio_set_writer_lock(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
void btrfs_folio_end_writer_lock_bitmap(const struct btrfs_fs_info *fs_info,
struct folio *folio, unsigned long bitmap);
bool btrfs_subpage_find_writer_locked(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 search_start,
u64 *found_start_ret, u32 *found_len_ret);
/*
* Template for subpage related operations.
*
* btrfs_subpage_*() are for call sites where the folio has subpage attached and
* the range is ensured to be inside the folio's single page.
*
* btrfs_folio_*() are for call sites where the page can either be subpage
* specific or regular folios. The function will handle both cases.
* But the range still needs to be inside one single page.
*
* btrfs_folio_clamp_*() are similar to btrfs_folio_*(), except the range doesn't
* need to be inside the page. Those functions will truncate the range
* automatically.
*/
#define DECLARE_BTRFS_SUBPAGE_OPS(name) \
void btrfs_subpage_set_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
void btrfs_subpage_clear_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
void btrfs_folio_set_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
void btrfs_folio_clear_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
bool btrfs_folio_test_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
void btrfs_folio_clamp_set_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
void btrfs_folio_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len); \
bool btrfs_folio_clamp_test_##name(const struct btrfs_fs_info *fs_info, \
struct folio *folio, u64 start, u32 len);
DECLARE_BTRFS_SUBPAGE_OPS(uptodate);
DECLARE_BTRFS_SUBPAGE_OPS(dirty);
DECLARE_BTRFS_SUBPAGE_OPS(writeback);
DECLARE_BTRFS_SUBPAGE_OPS(ordered);
DECLARE_BTRFS_SUBPAGE_OPS(checked);
bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
void btrfs_get_subpage_dirty_bitmap(struct btrfs_fs_info *fs_info,
struct folio *folio,
unsigned long *ret_bitmap);
void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
struct folio *folio, u64 start, u32 len);
#endif