github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-24 23:22:31 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

ext4: make regular file's buffered write path support large folios

Browse Source 
The current buffered write path in ext4 can only allocate and handle
folios of PAGE_SIZE size. To support larger folios, modify
ext4_da_write_begin() and ext4_write_begin() to allocate higher-order
folios, and trim the write length if it exceeds the folio size.
Additionally, in ext4_da_do_write_end(), use offset_in_folio() instead
of PAGE_SIZE.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Link: https://patch.msgid.link/20250512063319.3539411-3-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
This commit is contained in:
Zhang Yi 2025-05-12 14:33:13 +08:00 committed by Theodore Ts'o
parent fdbd0df9d4
commit 16705e52e6
1 changed files with 21 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
fs/ext4/inode.c
View File

@ -1066,7 +1066,7 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
loff_t pos, unsigned len,
get_block_t *get_block)
{
unsigned from = pos & (PAGE_SIZE - 1);
unsigned int from = offset_in_folio(folio, pos);
unsigned to = from + len;
struct inode *inode = folio->mapping->host;
unsigned block_start, block_end;
@ -1080,8 +1080,7 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
bool should_journal_data = ext4_should_journal_data(inode);
BUG_ON(!folio_test_locked(folio));
BUG_ON(from > PAGE_SIZE);
BUG_ON(to > PAGE_SIZE);
BUG_ON(to > folio_size(folio));
BUG_ON(from > to);
head = folio_buffers(folio);
@ -1191,6 +1190,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
struct folio *folio;
pgoff_t index;
unsigned from, to;
fgf_t fgp = FGP_WRITEBEGIN;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
@ -1203,8 +1203,6 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
*/
needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_SHIFT;
from = pos & (PAGE_SIZE - 1);
to = from + len;
if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
@ -1223,10 +1221,18 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
* the folio (if needed) without using GFP_NOFS.
*/
retry_grab:
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
fgp |= fgf_set_order(len);
folio = __filemap_get_folio(mapping, index, fgp,
mapping_gfp_mask(mapping));
if (IS_ERR(folio))
return PTR_ERR(folio);
if (pos + len > folio_pos(folio) + folio_size(folio))
len = folio_pos(folio) + folio_size(folio) - pos;
from = offset_in_folio(folio, pos);
to = from + len;
/*
* The same as page allocation, we prealloc buffer heads before
* starting the handle.
@ -2965,6 +2971,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
struct folio *folio;
pgoff_t index;
struct inode *inode = mapping->host;
fgf_t fgp = FGP_WRITEBEGIN;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
@ -2990,11 +2997,15 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
}
retry:
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
fgp |= fgf_set_order(len);
folio = __filemap_get_folio(mapping, index, fgp,
mapping_gfp_mask(mapping));
if (IS_ERR(folio))
return PTR_ERR(folio);
if (pos + len > folio_pos(folio) + folio_size(folio))
len = folio_pos(folio) + folio_size(folio) - pos;
ret = ext4_block_write_begin(NULL, folio, pos, len,
ext4_da_get_block_prep);
if (ret < 0) {
@ -3083,7 +3094,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
unsigned long end;
i_size_write(inode, new_i_size);
end = (new_i_size - 1) & (PAGE_SIZE - 1);
end = offset_in_folio(folio, new_i_size - 1);
if (copied && ext4_da_should_update_i_disksize(folio, end)) {
ext4_update_i_disksize(inode, new_i_size);
disksize_changed = true;