admin/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-12-07 20:06:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge patch series "filemap_* writeback interface cleanups v2"

Browse Source 
Christoph Hellwig <hch@lst.de> says:

While looking at the filemap writeback code, I think adding
filemap_fdatawrite_wbc ended up being a mistake, as all but the original
btrfs caller should be using better high level interfaces instead.  This
series removes all these, switches btrfs to a more specific interfaces
and also cleans up another too low-level interface.  With this the
writeback_control that is passed to the writeback code is only
initialized in three places, although there are a lot more places in
file system code that never reach the common writeback code.

* patches from https://patch.msgid.link/20251024080431.324236-1-hch@lst.de:
  mm: rename filemap_fdatawrite_range_kick to filemap_flush_range
  mm: remove __filemap_fdatawrite_range
  mm: remove filemap_fdatawrite_wbc
  mm: remove __filemap_fdatawrite
  mm,btrfs: add a filemap_flush_nr helper
  btrfs: push struct writeback_control into start_delalloc_inodes
  btrfs: use the local tmp_inode variable in start_delalloc_inodes
  ocfs2: don't opencode filemap_fdatawrite_range in ocfs2_journal_submit_inode_data_buffers
  9p: don't opencode filemap_fdatawrite_range in v9fs_mmap_vm_close
  mm: don't opencode filemap_fdatawrite_range in filemap_invalidate_inode

Link: https://patch.msgid.link/20251024080431.324236-1-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
This commit is contained in:
Christian Brauner
2025-10-29 15:50:48 +01:00
parent d6e6215907 c28d67b33c
commit 211c43d093
9 changed files with 79 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
fs/9p/vfs_file.c
View File

@@ -483,24 +483,15 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf)
static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
{
struct inode *inode;
struct writeback_control wbc = {
.nr_to_write = LONG_MAX,
.sync_mode = WB_SYNC_ALL,
.range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE,
/* absolute end, byte at end included */
.range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE +
(vma->vm_end - vma->vm_start - 1),
};
if (!(vma->vm_flags & VM_SHARED))
return;
p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);
inode = file_inode(vma->vm_file);
filemap_fdatawrite_wbc(inode->i_mapping, &wbc);
filemap_fdatawrite_range(file_inode(vma->vm_file)->i_mapping,
(loff_t)vma->vm_pgoff * PAGE_SIZE,
(loff_t)vma->vm_pgoff * PAGE_SIZE +
(vma->vm_end - vma->vm_start - 1));
}
static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {

46
fs/btrfs/inode.c
View File

@@ -8709,15 +8709,13 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
static int start_delalloc_inodes(struct btrfs_root *root,
struct writeback_control *wbc, bool snapshot,
bool in_reclaim_context)
static int start_delalloc_inodes(struct btrfs_root *root, long *nr_to_write,
bool snapshot, bool in_reclaim_context)
{
struct btrfs_delalloc_work *work, *next;
LIST_HEAD(works);
LIST_HEAD(splice);
int ret = 0;
bool full_flush = wbc->nr_to_write == LONG_MAX;
mutex_lock(&root->delalloc_mutex);
spin_lock(&root->delalloc_lock);
@@ -8743,10 +8741,10 @@ static int start_delalloc_inodes(struct btrfs_root *root,
if (snapshot)
set_bit(BTRFS_INODE_SNAPSHOT_FLUSH, &inode->runtime_flags);
if (full_flush) {
work = btrfs_alloc_delalloc_work(&inode->vfs_inode);
if (nr_to_write == NULL) {
work = btrfs_alloc_delalloc_work(tmp_inode);
if (!work) {
iput(&inode->vfs_inode);
iput(tmp_inode);
ret = -ENOMEM;
goto out;
}
@@ -8754,9 +8752,11 @@ static int start_delalloc_inodes(struct btrfs_root *root,
btrfs_queue_work(root->fs_info->flush_workers,
&work->work);
} else {
ret = filemap_fdatawrite_wbc(inode->vfs_inode.i_mapping, wbc);
ret = filemap_flush_nr(tmp_inode->i_mapping,
nr_to_write);
btrfs_add_delayed_iput(inode);
if (ret || wbc->nr_to_write <= 0)
if (ret || *nr_to_write <= 0)
goto out;
}
cond_resched();
@@ -8782,29 +8782,17 @@ out:
int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context)
{
struct writeback_control wbc = {
.nr_to_write = LONG_MAX,
.sync_mode = WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
};
struct btrfs_fs_info *fs_info = root->fs_info;
if (BTRFS_FS_ERROR(fs_info))
return -EROFS;
return start_delalloc_inodes(root, &wbc, true, in_reclaim_context);
return start_delalloc_inodes(root, NULL, true, in_reclaim_context);
}
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
bool in_reclaim_context)
{
struct writeback_control wbc = {
.nr_to_write = nr,
.sync_mode = WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
};
long *nr_to_write = nr == LONG_MAX ? NULL : &nr;
struct btrfs_root *root;
LIST_HEAD(splice);
int ret;
@@ -8816,13 +8804,6 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
spin_lock(&fs_info->delalloc_root_lock);
list_splice_init(&fs_info->delalloc_roots, &splice);
while (!list_empty(&splice)) {
/*
* Reset nr_to_write here so we know that we're doing a full
* flush.
*/
if (nr == LONG_MAX)
wbc.nr_to_write = LONG_MAX;
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
root = btrfs_grab_root(root);
@@ -8831,9 +8812,10 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context);
ret = start_delalloc_inodes(root, nr_to_write, false,
in_reclaim_context);
btrfs_put_root(root);
if (ret < 0 || wbc.nr_to_write <= 0)
if (ret < 0 || nr <= 0)
goto out;
spin_lock(&fs_info->delalloc_root_lock);
}

6
fs/fs-writeback.c
View File

@@ -822,9 +822,9 @@ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
* @wbc: writeback_control of interest
* @inode: target inode
*
* This function is to be used by __filemap_fdatawrite_range(), which is an
* alternative entry point into writeback code, and first ensures @inode is
* associated with a bdi_writeback and attaches it to @wbc.
* This function is to be used by filemap_writeback(), which is an alternative
* entry point into writeback code, and first ensures @inode is associated with
* a bdi_writeback and attaches it to @wbc.
*/
void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
struct inode *inode)

11
fs/ocfs2/journal.c
View File

@@ -902,15 +902,8 @@ bail:
static int ocfs2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
{
struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = mapping->nrpages * 2,
.range_start = jinode->i_dirty_start,
.range_end = jinode->i_dirty_end,
};
return filemap_fdatawrite_wbc(mapping, &wbc);
return filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping,
jinode->i_dirty_start, jinode->i_dirty_end);
}
int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty)

10
fs/sync.c
View File

@@ -280,14 +280,12 @@ int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
}
if (flags & SYNC_FILE_RANGE_WRITE) {
int sync_mode = WB_SYNC_NONE;
if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) ==
SYNC_FILE_RANGE_WRITE_AND_WAIT)
sync_mode = WB_SYNC_ALL;
ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
sync_mode);
ret = filemap_fdatawrite_range(mapping, offset,
endbyte);
else
ret = filemap_flush_range(mapping, offset, endbyte);
if (ret < 0)
goto out;
}

6
include/linux/fs.h
View File

@@ -3014,7 +3014,7 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
extern int __must_check file_check_and_advance_wb_err(struct file *file);
extern int __must_check file_write_and_wait_range(struct file *file,
loff_t start, loff_t end);
int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
int filemap_flush_range(struct address_space *mapping, loff_t start,
loff_t end);
static inline int file_write_and_wait(struct file *file)
@@ -3051,8 +3051,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
} else if (iocb->ki_flags & IOCB_DONTCACHE) {
struct address_space *mapping = iocb->ki_filp->f_mapping;
filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count,
iocb->ki_pos - 1);
filemap_flush_range(mapping, iocb->ki_pos - count,
iocb->ki_pos - 1);
}
return count;

5
include/linux/pagemap.h
View File

@@ -38,6 +38,7 @@ int filemap_invalidate_pages(struct address_space *mapping,
int write_inode_now(struct inode *, int sync);
int filemap_fdatawrite(struct address_space *);
int filemap_flush(struct address_space *);
int filemap_flush_nr(struct address_space *mapping, long *nr_to_write);
int filemap_fdatawait_keep_errors(struct address_space *mapping);
int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend);
int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
@@ -53,14 +54,10 @@ static inline int filemap_fdatawait(struct address_space *mapping)
bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend);
int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
int __filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end, int sync_mode);
int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
int filemap_check_errors(struct address_space *mapping);
void __filemap_set_wb_err(struct address_space *mapping, int err);
int filemap_fdatawrite_wbc(struct address_space *mapping,
struct writeback_control *wbc);
int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
static inline int filemap_write_and_wait(struct address_space *mapping)

3
mm/fadvise.c
View File

@@ -111,8 +111,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
spin_unlock(&file->f_lock);
break;
case POSIX_FADV_DONTNEED:
__filemap_fdatawrite_range(mapping, offset, endbyte,
WB_SYNC_NONE);
filemap_flush_range(mapping, offset, endbyte);
/*
* First and last FULL page! Partial pages are deliberately

115
mm/filemap.c
View File

@@ -366,83 +366,60 @@ static int filemap_check_and_keep_errors(struct address_space *mapping)
return 0;
}
/**
* filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @wbc: the writeback_control controlling the writeout
*
* Call writepages on the mapping using the provided wbc to control the
* writeout.
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_fdatawrite_wbc(struct address_space *mapping,
struct writeback_control *wbc)
static int filemap_writeback(struct address_space *mapping, loff_t start,
loff_t end, enum writeback_sync_modes sync_mode,
long *nr_to_write)
{
struct writeback_control wbc = {
.sync_mode = sync_mode,
.nr_to_write = nr_to_write ? *nr_to_write : LONG_MAX,
.range_start = start,
.range_end = end,
};
int ret;
if (!mapping_can_writeback(mapping) ||
!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
wbc_attach_fdatawrite_inode(wbc, mapping->host);
ret = do_writepages(mapping, wbc);
wbc_detach_inode(wbc);
wbc_attach_fdatawrite_inode(&wbc, mapping->host);
ret = do_writepages(mapping, &wbc);
wbc_detach_inode(&wbc);
if (!ret && nr_to_write)
*nr_to_write = wbc.nr_to_write;
return ret;
}
EXPORT_SYMBOL(filemap_fdatawrite_wbc);
/**
* __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* filemap_fdatawrite_range - start writeback on mapping dirty pages in range
* @mapping: address space structure to write
* @start: offset in bytes where the range starts
* @end: offset in bytes where the range ends (inclusive)
* @sync_mode: enable synchronous operation
*
* Start writeback against all of a mapping's dirty pages that lie
* within the byte offsets <start, end> inclusive.
*
* If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
* opposed to a regular memory cleansing writeback. The difference between
* these two operations is that if a dirty page/buffer is encountered, it must
* be waited upon, and not just skipped over.
* This is a data integrity operation that waits upon dirty or in writeback
* pages.
*
* Return: %0 on success, negative error code otherwise.
*/
int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end, int sync_mode)
{
struct writeback_control wbc = {
.sync_mode = sync_mode,
.nr_to_write = LONG_MAX,
.range_start = start,
.range_end = end,
};
return filemap_fdatawrite_wbc(mapping, &wbc);
}
static inline int __filemap_fdatawrite(struct address_space *mapping,
int sync_mode)
{
return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
}
int filemap_fdatawrite(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite);
int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end)
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
return filemap_writeback(mapping, start, end, WB_SYNC_ALL, NULL);
}
EXPORT_SYMBOL(filemap_fdatawrite_range);
int filemap_fdatawrite(struct address_space *mapping)
{
return filemap_fdatawrite_range(mapping, 0, LLONG_MAX);
}
EXPORT_SYMBOL(filemap_fdatawrite);
/**
* filemap_fdatawrite_range_kick - start writeback on a range
* filemap_flush_range - start writeback on a range
* @mapping: target address_space
* @start: index to start writeback on
* @end: last (inclusive) index for writeback
@@ -452,12 +429,12 @@ EXPORT_SYMBOL(filemap_fdatawrite_range);
*
* Return: %0 on success, negative error code otherwise.
*/
int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
int filemap_flush_range(struct address_space *mapping, loff_t start,
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
return filemap_writeback(mapping, start, end, WB_SYNC_NONE, NULL);
}
EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
EXPORT_SYMBOL_GPL(filemap_flush_range);
/**
* filemap_flush - mostly a non-blocking flush
@@ -470,10 +447,22 @@ EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
*/
int filemap_flush(struct address_space *mapping)
{
return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
return filemap_flush_range(mapping, 0, LLONG_MAX);
}
EXPORT_SYMBOL(filemap_flush);
/*
* Start writeback on @nr_to_write pages from @mapping. No one but the existing
* btrfs caller should be using this. Talk to linux-mm if you think adding a
* new caller is a good idea.
*/
int filemap_flush_nr(struct address_space *mapping, long *nr_to_write)
{
return filemap_writeback(mapping, 0, LLONG_MAX, WB_SYNC_NONE,
nr_to_write);
}
EXPORT_SYMBOL_FOR_MODULES(filemap_flush_nr, "btrfs");
/**
* filemap_range_has_page - check if a page exists in range.
* @mapping: address space within which to check
@@ -691,8 +680,7 @@ int filemap_write_and_wait_range(struct address_space *mapping,
return 0;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
err = filemap_fdatawrite_range(mapping, lstart, lend);
/*
* Even if the above returned error, the pages may be
* written partially (e.g. -ENOSPC), so we wait for it.
@@ -794,8 +782,7 @@ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
return 0;
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
err = filemap_fdatawrite_range(mapping, lstart, lend);
/* See comment of filemap_write_and_wait() */
if (err != -EIO)
__filemap_fdatawait_range(mapping, lstart, lend);
@@ -4457,16 +4444,8 @@ int filemap_invalidate_inode(struct inode *inode, bool flush,
unmap_mapping_pages(mapping, first, nr, false);
/* Write back the data if we're asked to. */
if (flush) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = start,
.range_end = end,
};
filemap_fdatawrite_wbc(mapping, &wbc);
}
if (flush)
filemap_fdatawrite_range(mapping, start, end);
/* Wait for writeback to complete on all folios and discard. */
invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE);