bh = bh->b_this_page;
} while (bh != head);
}
-EXPORT_SYMBOL(buffer_check_dirty_writeback);
/*
* Block until a buffer comes unlocked. This doesn't stop it
pgoff_t index;
struct buffer_head *bh;
struct buffer_head *head;
- struct page *page;
+ struct folio *folio;
int all_mapped = 1;
static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);
index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
- page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
- if (!page)
+ folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0);
+ if (IS_ERR(folio))
goto out;
spin_lock(&bd_mapping->private_lock);
- if (!page_has_buffers(page))
+ head = folio_buffers(folio);
+ if (!head)
goto out_unlock;
- head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh))
}
out_unlock:
spin_unlock(&bd_mapping->private_lock);
- put_page(page);
+ folio_put(folio);
out:
return ret;
}
}
EXPORT_SYMBOL(sync_mapping_buffers);
+ /**
+ * generic_buffers_fsync_noflush - generic buffer fsync implementation
+ * for simple filesystems with no inode lock
+ *
+ * @file: file to synchronize
+ * @start: start offset in bytes
+ * @end: end offset in bytes (inclusive)
+ * @datasync: only synchronize essential metadata if true
+ *
+ * This is a generic implementation of the fsync method for simple
+ * filesystems which track all non-inode metadata in the buffers list
+ * hanging off the address_space structure.
+ */
+ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
+ bool datasync)
+ {
+ struct inode *inode = file->f_mapping->host;
+ int err;
+ int ret;
+
+ err = file_write_and_wait_range(file, start, end);
+ if (err)
+ return err;
+
+ ret = sync_mapping_buffers(inode->i_mapping);
+ if (!(inode->i_state & I_DIRTY_ALL))
+ goto out;
+ if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+ goto out;
+
+ err = sync_inode_metadata(inode, 1);
+ if (ret == 0)
+ ret = err;
+
+ out:
+ /* check and advance again to catch errors after syncing out buffers */
+ err = file_check_and_advance_wb_err(file);
+ if (ret == 0)
+ ret = err;
+ return ret;
+ }
+ EXPORT_SYMBOL(generic_buffers_fsync_noflush);
+
+ /**
+ * generic_buffers_fsync - generic buffer fsync implementation
+ * for simple filesystems with no inode lock
+ *
+ * @file: file to synchronize
+ * @start: start offset in bytes
+ * @end: end offset in bytes (inclusive)
+ * @datasync: only synchronize essential metadata if true
+ *
+ * This is a generic implementation of the fsync method for simple
+ * filesystems which track all non-inode metadata in the buffers list
+ * hanging off the address_space structure. This also makes sure that
+ * a device cache flush operation is called at the end.
+ */
+ int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
+ bool datasync)
+ {
+ struct inode *inode = file->f_mapping->host;
+ int ret;
+
+ ret = generic_buffers_fsync_noflush(file, start, end, datasync);
+ if (!ret)
+ ret = blkdev_issue_flush(inode->i_sb->s_bdev);
+ return ret;
+ }
+ EXPORT_SYMBOL(generic_buffers_fsync);
+
/*
* Called when we've recently written block `bblock', and it is known that
* `bblock' was for a buffer_boundary() buffer. This means that the block at
}
EXPORT_SYMBOL_GPL(alloc_page_buffers);
-static inline void
-link_dev_buffers(struct page *page, struct buffer_head *head)
+static inline void link_dev_buffers(struct folio *folio,
+ struct buffer_head *head)
{
struct buffer_head *bh, *tail;
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
- attach_page_private(page, head);
+ folio_attach_private(folio, head);
}
static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
}
/*
- * Initialise the state of a blockdev page's buffers.
+ * Initialise the state of a blockdev folio's buffers.
*/
-static sector_t
-init_page_buffers(struct page *page, struct block_device *bdev,
- sector_t block, int size)
+static sector_t folio_init_buffers(struct folio *folio,
+ struct block_device *bdev, sector_t block, int size)
{
- struct buffer_head *head = page_buffers(page);
+ struct buffer_head *head = folio_buffers(folio);
struct buffer_head *bh = head;
- int uptodate = PageUptodate(page);
+ bool uptodate = folio_test_uptodate(folio);
sector_t end_block = blkdev_max_block(bdev, size);
do {
pgoff_t index, int size, int sizebits, gfp_t gfp)
{
struct inode *inode = bdev->bd_inode;
- struct page *page;
+ struct folio *folio;
struct buffer_head *bh;
sector_t end_block;
int ret = 0;
*/
gfp_mask |= __GFP_NOFAIL;
- page = find_or_create_page(inode->i_mapping, index, gfp_mask);
+ folio = __filemap_get_folio(inode->i_mapping, index,
+ FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp_mask);
- BUG_ON(!PageLocked(page));
-
- if (page_has_buffers(page)) {
- bh = page_buffers(page);
+ bh = folio_buffers(folio);
+ if (bh) {
if (bh->b_size == size) {
- end_block = init_page_buffers(page, bdev,
- (sector_t)index << sizebits,
- size);
+ end_block = folio_init_buffers(folio, bdev,
+ (sector_t)index << sizebits, size);
goto done;
}
- if (!try_to_free_buffers(page_folio(page)))
+ if (!try_to_free_buffers(folio))
goto failed;
}
- /*
- * Allocate some buffers for this page
- */
- bh = alloc_page_buffers(page, size, true);
+ bh = folio_alloc_buffers(folio, size, true);
/*
- * Link the page to the buffers and initialise them. Take the
+ * Link the folio to the buffers and initialise them. Take the
* lock to be atomic wrt __find_get_block(), which does not
- * run under the page lock.
+ * run under the folio lock.
*/
spin_lock(&inode->i_mapping->private_lock);
- link_dev_buffers(page, bh);
- end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
- size);
+ link_dev_buffers(folio, bh);
+ end_block = folio_init_buffers(folio, bdev,
+ (sector_t)index << sizebits, size);
spin_unlock(&inode->i_mapping->private_lock);
done:
ret = (block < end_block) ? 1 : -ENXIO;
failed:
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
return ret;
}
* WB_SYNC_ALL, the writes are posted using REQ_SYNC; this
* causes the writes to be flagged as synchronous writes.
*/
-int __block_write_full_page(struct inode *inode, struct page *page,
+int __block_write_full_folio(struct inode *inode, struct folio *folio,
get_block_t *get_block, struct writeback_control *wbc,
bh_end_io_t *handler)
{
int nr_underway = 0;
blk_opf_t write_flags = wbc_to_write_flags(wbc);
- head = folio_create_buffers(page_folio(page), inode,
+ head = folio_create_buffers(folio, inode,
(1 << BH_Dirty) | (1 << BH_Uptodate));
/*
* Be very careful. We have no exclusion from block_dirty_folio
* here, and the (potentially unmapped) buffers may become dirty at
* any time. If a buffer becomes dirty here after we've inspected it
- * then we just miss that fact, and the page stays dirty.
+ * then we just miss that fact, and the folio stays dirty.
*
* Buffers outside i_size may be dirtied by block_dirty_folio;
* handle that here by just cleaning them.
blocksize = bh->b_size;
bbits = block_size_bits(blocksize);
- block = (sector_t)page->index << (PAGE_SHIFT - bbits);
+ block = (sector_t)folio->index << (PAGE_SHIFT - bbits);
last_block = (i_size_read(inode) - 1) >> bbits;
/*
if (block > last_block) {
/*
* mapped buffers outside i_size will occur, because
- * this page can be outside i_size when there is a
+ * this folio can be outside i_size when there is a
* truncate in progress.
*/
/*
continue;
/*
* If it's a fully non-blocking write attempt and we cannot
- * lock the buffer then redirty the page. Note that this can
+ * lock the buffer then redirty the folio. Note that this can
* potentially cause a busy-wait loop from writeback threads
* and kswapd activity, but those code paths have their own
* higher-level throttling.
if (wbc->sync_mode != WB_SYNC_NONE) {
lock_buffer(bh);
} else if (!trylock_buffer(bh)) {
- redirty_page_for_writepage(wbc, page);
+ folio_redirty_for_writepage(wbc, folio);
continue;
}
if (test_clear_buffer_dirty(bh)) {
} while ((bh = bh->b_this_page) != head);
/*
- * The page and its buffers are protected by PageWriteback(), so we can
- * drop the bh refcounts early.
+ * The folio and its buffers are protected by the writeback flag,
+ * so we can drop the bh refcounts early.
*/
- BUG_ON(PageWriteback(page));
- set_page_writeback(page);
+ BUG_ON(folio_test_writeback(folio));
+ folio_start_writeback(folio);
do {
struct buffer_head *next = bh->b_this_page;
}
bh = next;
} while (bh != head);
- unlock_page(page);
+ folio_unlock(folio);
err = 0;
done:
if (nr_underway == 0) {
/*
- * The page was marked dirty, but the buffers were
+ * The folio was marked dirty, but the buffers were
* clean. Someone wrote them back by hand with
* write_dirty_buffer/submit_bh. A rare case.
*/
- end_page_writeback(page);
+ folio_end_writeback(folio);
/*
- * The page and buffer_heads can be released at any time from
+ * The folio and buffer_heads can be released at any time from
* here on.
*/
}
* ENOSPC, or some other error. We may already have added some
* blocks to the file, so we need to write these out to avoid
* exposing stale data.
- * The page is currently locked and not marked for writeback
+ * The folio is currently locked and not marked for writeback
*/
bh = head;
/* Recovery: lock and submit the mapped buffers */
} else {
/*
* The buffer may have been set dirty during
- * attachment to a dirty page.
+ * attachment to a dirty folio.
*/
clear_buffer_dirty(bh);
}
} while ((bh = bh->b_this_page) != head);
- SetPageError(page);
- BUG_ON(PageWriteback(page));
- mapping_set_error(page->mapping, err);
- set_page_writeback(page);
+ folio_set_error(folio);
+ BUG_ON(folio_test_writeback(folio));
+ mapping_set_error(folio->mapping, err);
+ folio_start_writeback(folio);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
}
bh = next;
} while (bh != head);
- unlock_page(page);
+ folio_unlock(folio);
goto done;
}
-EXPORT_SYMBOL(__block_write_full_page);
+EXPORT_SYMBOL(__block_write_full_folio);
/*
- * If a page has any new buffers, zero them out here, and mark them uptodate
+ * If a folio has any new buffers, zero them out here, and mark them uptodate
* and dirty so they'll be written out (in order to prevent uninitialised
* block data from leaking). And clear the new bit.
*/
-void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
+void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to)
{
- unsigned int block_start, block_end;
+ size_t block_start, block_end;
struct buffer_head *head, *bh;
- BUG_ON(!PageLocked(page));
- if (!page_has_buffers(page))
+ BUG_ON(!folio_test_locked(folio));
+ head = folio_buffers(folio);
+ if (!head)
return;
- bh = head = page_buffers(page);
+ bh = head;
block_start = 0;
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
- if (!PageUptodate(page)) {
- unsigned start, size;
+ if (!folio_test_uptodate(folio)) {
+ size_t start, xend;
start = max(from, block_start);
- size = min(to, block_end) - start;
+ xend = min(to, block_end);
- zero_user(page, start, size);
+ folio_zero_segment(folio, start, xend);
set_buffer_uptodate(bh);
}
bh = bh->b_this_page;
} while (bh != head);
}
-EXPORT_SYMBOL(page_zero_new_buffers);
+EXPORT_SYMBOL(folio_zero_new_buffers);
static void
iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
err = -EIO;
}
if (unlikely(err))
- page_zero_new_buffers(&folio->page, from, to);
+ folio_zero_new_buffers(folio, from, to);
return err;
}
}
EXPORT_SYMBOL(__block_write_begin);
-static int __block_commit_write(struct inode *inode, struct page *page,
- unsigned from, unsigned to)
+static int __block_commit_write(struct inode *inode, struct folio *folio,
+ size_t from, size_t to)
{
- unsigned block_start, block_end;
- int partial = 0;
+ size_t block_start, block_end;
+ bool partial = false;
unsigned blocksize;
struct buffer_head *bh, *head;
- bh = head = page_buffers(page);
+ bh = head = folio_buffers(folio);
blocksize = bh->b_size;
block_start = 0;
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (!buffer_uptodate(bh))
- partial = 1;
+ partial = true;
} else {
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
/*
* If this is a partial write which happened to make all buffers
* uptodate then we can optimize away a bogus read_folio() for
- * the next read(). Here we 'discover' whether the page went
+ * the next read(). Here we 'discover' whether the folio went
* uptodate as a result of this (potentially partial) write.
*/
if (!partial)
- SetPageUptodate(page);
+ folio_mark_uptodate(folio);
return 0;
}
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
+ struct folio *folio = page_folio(page);
struct inode *inode = mapping->host;
- unsigned start;
-
- start = pos & (PAGE_SIZE - 1);
+ size_t start = pos - folio_pos(folio);
if (unlikely(copied < len)) {
/*
* read_folio might come in and destroy our partial write.
*
* Do the simplest thing, and just treat any short write to a
- * non uptodate page as a zero-length write, and force the
+ * non uptodate folio as a zero-length write, and force the
* caller to redo the whole thing.
*/
- if (!PageUptodate(page))
+ if (!folio_test_uptodate(folio))
copied = 0;
- page_zero_new_buffers(page, start+copied, start+len);
+ folio_zero_new_buffers(folio, start+copied, start+len);
}
- flush_dcache_page(page);
+ flush_dcache_folio(folio);
/* This could be a short (even 0-length) commit */
- __block_commit_write(inode, page, start, start+copied);
+ __block_commit_write(inode, folio, start, start + copied);
return copied;
}
int block_commit_write(struct page *page, unsigned from, unsigned to)
{
- struct inode *inode = page->mapping->host;
- __block_commit_write(inode,page,from,to);
+ struct folio *folio = page_folio(page);
+ struct inode *inode = folio->mapping->host;
+ __block_commit_write(inode, folio, from, to);
return 0;
}
EXPORT_SYMBOL(block_commit_write);
int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
- struct page *page = vmf->page;
+ struct folio *folio = page_folio(vmf->page);
struct inode *inode = file_inode(vma->vm_file);
unsigned long end;
loff_t size;
int ret;
- lock_page(page);
+ folio_lock(folio);
size = i_size_read(inode);
- if ((page->mapping != inode->i_mapping) ||
- (page_offset(page) > size)) {
+ if ((folio->mapping != inode->i_mapping) ||
+ (folio_pos(folio) >= size)) {
/* We overload EFAULT to mean page got truncated */
ret = -EFAULT;
goto out_unlock;
}
- /* page is wholly or partially inside EOF */
- if (((page->index + 1) << PAGE_SHIFT) > size)
- end = size & ~PAGE_MASK;
- else
- end = PAGE_SIZE;
+ end = folio_size(folio);
+ /* folio is wholly or partially inside EOF */
+ if (folio_pos(folio) + end > size)
+ end = size - folio_pos(folio);
- ret = __block_write_begin(page, 0, end, get_block);
+ ret = __block_write_begin_int(folio, 0, end, get_block, NULL);
if (!ret)
- ret = block_commit_write(page, 0, end);
+ ret = __block_commit_write(inode, folio, 0, end);
if (unlikely(ret < 0))
goto out_unlock;
- set_page_dirty(page);
- wait_for_stable_page(page);
+ folio_mark_dirty(folio);
+ folio_wait_stable(folio);
return 0;
out_unlock:
- unlock_page(page);
+ folio_unlock(folio);
return ret;
}
EXPORT_SYMBOL(block_page_mkwrite);
loff_t from, get_block_t *get_block)
{
pgoff_t index = from >> PAGE_SHIFT;
- unsigned offset = from & (PAGE_SIZE-1);
unsigned blocksize;
sector_t iblock;
- unsigned length, pos;
+ size_t offset, length, pos;
struct inode *inode = mapping->host;
- struct page *page;
+ struct folio *folio;
struct buffer_head *bh;
int err = 0;
blocksize = i_blocksize(inode);
- length = offset & (blocksize - 1);
+ length = from & (blocksize - 1);
/* Block boundary? Nothing to do */
if (!length)
length = blocksize - length;
iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits);
- page = grab_cache_page(mapping, index);
- if (!page)
- return -ENOMEM;
-
- if (!page_has_buffers(page))
- create_empty_buffers(page, blocksize, 0);
+ folio = filemap_grab_folio(mapping, index);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
+
+ bh = folio_buffers(folio);
+ if (!bh) {
+ folio_create_empty_buffers(folio, blocksize, 0);
+ bh = folio_buffers(folio);
+ }
/* Find the buffer that contains "offset" */
- bh = page_buffers(page);
+ offset = offset_in_folio(folio, from);
pos = blocksize;
while (offset >= pos) {
bh = bh->b_this_page;
}
/* Ok, it's mapped. Make sure it's up-to-date */
- if (PageUptodate(page))
+ if (folio_test_uptodate(folio))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
goto unlock;
}
- zero_user(page, offset, length);
+ folio_zero_range(folio, offset, length);
mark_buffer_dirty(bh);
unlock:
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
return err;
}
int block_write_full_page(struct page *page, get_block_t *get_block,
struct writeback_control *wbc)
{
- struct inode * const inode = page->mapping->host;
+ struct folio *folio = page_folio(page);
+ struct inode * const inode = folio->mapping->host;
loff_t i_size = i_size_read(inode);
- const pgoff_t end_index = i_size >> PAGE_SHIFT;
- unsigned offset;
- /* Is the page fully inside i_size? */
- if (page->index < end_index)
- return __block_write_full_page(inode, page, get_block, wbc,
+ /* Is the folio fully inside i_size? */
+ if (folio_pos(folio) + folio_size(folio) <= i_size)
+ return __block_write_full_folio(inode, folio, get_block, wbc,
end_buffer_async_write);
- /* Is the page fully outside i_size? (truncate in progress) */
- offset = i_size & (PAGE_SIZE-1);
- if (page->index >= end_index+1 || !offset) {
- unlock_page(page);
+ /* Is the folio fully outside i_size? (truncate in progress) */
+ if (folio_pos(folio) >= i_size) {
+ folio_unlock(folio);
return 0; /* don't care */
}
/*
- * The page straddles i_size. It must be zeroed out on each and every
+ * The folio straddles i_size. It must be zeroed out on each and every
* writepage invocation because it may be mmapped. "A file is mapped
* in multiples of the page size. For a file that is not a multiple of
- * the page size, the remaining memory is zeroed when mapped, and
+ * the page size, the remaining memory is zeroed when mapped, and
* writes to that region are not written out to the file."
*/
- zero_user_segment(page, offset, PAGE_SIZE);
- return __block_write_full_page(inode, page, get_block, wbc,
- end_buffer_async_write);
+ folio_zero_segment(folio, offset_in_folio(folio, i_size),
+ folio_size(folio));
+ return __block_write_full_folio(inode, folio, get_block, wbc,
+ end_buffer_async_write);
}
EXPORT_SYMBOL(block_write_full_page);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
- BUG_ON(bio->bi_iter.bi_size != bh->b_size);
+ __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
#include <linux/quotaops.h>
#include <linux/iomap.h>
#include <linux/uio.h>
+ #include <linux/buffer_head.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
+ #include "trace.h"
#ifdef CONFIG_FS_DAX
static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
int ret;
struct super_block *sb = file->f_mapping->host->i_sb;
- ret = generic_file_fsync(file, start, end, datasync);
+ ret = generic_buffers_fsync(file, start, end, datasync);
if (ret == -EIO)
/* We don't really know where the IO error happened... */
ext2_error(sb, __func__,
return ret;
}
+ static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+ {
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+
+ trace_ext2_dio_read_begin(iocb, to, 0);
+ inode_lock_shared(inode);
+ ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0);
+ inode_unlock_shared(inode);
+ trace_ext2_dio_read_end(iocb, to, ret);
+
+ return ret;
+ }
+
+ static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
+ {
+ loff_t pos = iocb->ki_pos;
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ if (error)
+ goto out;
+
+ /*
+ * If we are extending the file, we have to update i_size here before
+ * page cache gets invalidated in iomap_dio_rw(). This prevents racing
+ * buffered reads from zeroing out too much from page cache pages.
+ * Note that all extending writes always happens synchronously with
+ * inode lock held by ext2_dio_write_iter(). So it is safe to update
+ * inode size here for extending file writes.
+ */
+ pos += size;
+ if (pos > i_size_read(inode)) {
+ i_size_write(inode, pos);
+ mark_inode_dirty(inode);
+ }
+ out:
+ trace_ext2_dio_write_endio(iocb, size, error);
+ return error;
+ }
+
+ static const struct iomap_dio_ops ext2_dio_write_ops = {
+ .end_io = ext2_dio_write_end_io,
+ };
+
+ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+ {
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+ unsigned int flags = 0;
+ unsigned long blocksize = inode->i_sb->s_blocksize;
+ loff_t offset = iocb->ki_pos;
+ loff_t count = iov_iter_count(from);
+ ssize_t status = 0;
+
+ trace_ext2_dio_write_begin(iocb, from, 0);
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out_unlock;
+
+ ret = kiocb_modified(iocb);
+ if (ret)
+ goto out_unlock;
+
+ /* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */
+ if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) ||
+ (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize)))
+ flags |= IOMAP_DIO_FORCE_WAIT;
+
+ ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops,
+ flags, NULL, 0);
+
+ /* ENOTBLK is magic return value for fallback to buffered-io */
+ if (ret == -ENOTBLK)
+ ret = 0;
+
+ if (ret < 0 && ret != -EIOCBQUEUED)
+ ext2_write_failed(inode->i_mapping, offset + count);
+
+ /* handle case for partial write and for fallback to buffered write */
+ if (ret >= 0 && iov_iter_count(from)) {
+ loff_t pos, endbyte;
+ int ret2;
+
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ pos = iocb->ki_pos;
+ status = generic_perform_write(iocb, from);
+ if (unlikely(status < 0)) {
+ ret = status;
+ goto out_unlock;
+ }
+
+ iocb->ki_pos += status;
+ ret += status;
+ endbyte = pos + status - 1;
+ ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
+ endbyte);
+ if (!ret2)
+ invalidate_mapping_pages(inode->i_mapping,
+ pos >> PAGE_SHIFT,
+ endbyte >> PAGE_SHIFT);
+ if (ret > 0)
+ generic_write_sync(iocb, ret);
+ }
+
+ out_unlock:
+ inode_unlock(inode);
+ if (status)
+ trace_ext2_dio_write_buff_end(iocb, from, status);
+ trace_ext2_dio_write_end(iocb, from, ret);
+ return ret;
+ }
+
static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
#ifdef CONFIG_FS_DAX
if (IS_DAX(iocb->ki_filp->f_mapping->host))
return ext2_dax_read_iter(iocb, to);
#endif
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return ext2_dio_read_iter(iocb, to);
+
return generic_file_read_iter(iocb, to);
}
if (IS_DAX(iocb->ki_filp->f_mapping->host))
return ext2_dax_write_iter(iocb, from);
#endif
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return ext2_dio_write_iter(iocb, from);
+
return generic_file_write_iter(iocb, from);
}
.release = ext2_release_file,
.fsync = ext2_fsync,
.get_unmapped_area = thp_get_unmapped_area,
- .splice_read = generic_file_splice_read,
+ .splice_read = filemap_splice_read,
.splice_write = iter_file_splice_write,
};
#include <linux/sched.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
+ #include <linux/buffer_head.h>
#include "ext4.h"
#include "ext4_jbd2.h"
return ret;
}
- static int ext4_fsync_nojournal(struct inode *inode, bool datasync,
- bool *needs_barrier)
+ static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
+ int datasync, bool *needs_barrier)
{
- int ret, err;
-
- ret = sync_mapping_buffers(inode->i_mapping);
- if (!(inode->i_state & I_DIRTY_ALL))
- return ret;
- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
- return ret;
-
- err = sync_inode_metadata(inode, 1);
- if (!ret)
- ret = err;
+ struct inode *inode = file->f_inode;
+ int ret;
+ ret = generic_buffers_fsync_noflush(file, start, end, datasync);
if (!ret)
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+ /*
+ * Fastcommit does not really support fsync on directories or other
+ * special files. Force a full commit.
+ */
+ if (!S_ISREG(inode->i_mode))
+ return ext4_force_commit(inode->i_sb);
+
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
*needs_barrier = true;
goto out;
}
+ if (!sbi->s_journal) {
+ ret = ext4_fsync_nojournal(file, start, end, datasync,
+ &needs_barrier);
+ if (needs_barrier)
+ goto issue_flush;
+ goto out;
+ }
+
ret = file_write_and_wait_range(file, start, end);
if (ret)
goto out;
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*/
- if (!sbi->s_journal)
- ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
- else
- ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
+ ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
+ issue_flush:
if (needs_barrier) {
err = blkdev_issue_flush(inode->i_sb->s_bdev);
if (!ret)
* One thing we have to be careful of with a per-sb shrinker is that we don't
* drop the last active reference to the superblock from within the shrinker.
* If that happens we could trigger unregistering the shrinker from within the
- * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we
+ * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
* take a passive reference to the superblock to avoid this from occurring.
*/
static unsigned long super_cache_scan(struct shrinker *shrink,
&type->s_writers_key[i]))
goto fail;
}
- init_waitqueue_head(&s->s_writers.wait_unfrozen);
s->s_bdi = &noop_backing_dev_info;
s->s_flags = flags;
if (s->s_user_ns != &init_user_ns)
fc->s_fs_info = NULL;
s->s_type = fc->fs_type;
s->s_iflags |= fc->s_iflags;
- strlcpy(s->s_id, s->s_type->name, sizeof(s->s_id));
+ strscpy(s->s_id, s->s_type->name, sizeof(s->s_id));
list_add_tail(&s->s_list, &super_blocks);
hlist_add_head(&s->s_instances, &s->s_type->fs_supers);
spin_unlock(&sb_lock);
return ERR_PTR(err);
}
s->s_type = type;
- strlcpy(s->s_id, type->name, sizeof(s->s_id));
+ strscpy(s->s_id, type->name, sizeof(s->s_id));
list_add_tail(&s->s_list, &super_blocks);
hlist_add_head(&s->s_instances, &type->fs_supers);
spin_unlock(&sb_lock);
struct super_block *sb = fc->root->d_sb;
int retval;
bool remount_ro = false;
+ bool remount_rw = false;
bool force = fc->sb_flags & SB_FORCE;
if (fc->sb_flags_mask & ~MS_RMT_MASK)
bdev_read_only(sb->s_bdev))
return -EACCES;
#endif
-
+ remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb);
remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb);
}
*/
if (remount_ro) {
if (force) {
- sb->s_readonly_remount = 1;
- smp_wmb();
+ sb_start_ro_state_change(sb);
} else {
retval = sb_prepare_remount_readonly(sb);
if (retval)
return retval;
}
+ } else if (remount_rw) {
+ /*
+ * Protect filesystem's reconfigure code from writes from
+ * userspace until reconfigure finishes.
+ */
+ sb_start_ro_state_change(sb);
}
if (fc->ops->reconfigure) {
WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) |
(fc->sb_flags & fc->sb_flags_mask)));
- /* Needs to be ordered wrt mnt_is_readonly() */
- smp_wmb();
- sb->s_readonly_remount = 0;
+ sb_end_ro_state_change(sb);
/*
* Some filesystems modify their metadata via some other path than the
return 0;
cancel_readonly:
- sb->s_readonly_remount = 0;
+ sb_end_ro_state_change(sb);
return retval;
}
EXPORT_SYMBOL(get_tree_keyed);
#ifdef CONFIG_BLOCK
+static void fs_mark_dead(struct block_device *bdev)
+{
+ struct super_block *sb;
+
+ sb = get_super(bdev);
+ if (!sb)
+ return;
+
+ if (sb->s_op->shutdown)
+ sb->s_op->shutdown(sb);
+ drop_super(sb);
+}
+
+static const struct blk_holder_ops fs_holder_ops = {
+ .mark_dead = fs_mark_dead,
+};
static int set_bdev_super(struct super_block *s, void *data)
{
{
struct block_device *bdev;
struct super_block *s;
- fmode_t mode = FMODE_READ | FMODE_EXCL;
int error = 0;
- if (!(fc->sb_flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
if (!fc->source)
return invalf(fc, "No source specified");
- bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type);
+ bdev = blkdev_get_by_path(fc->source, sb_open_mode(fc->sb_flags),
+ fc->fs_type, &fs_holder_ops);
if (IS_ERR(bdev)) {
errorf(fc, "%s: Can't open blockdev", fc->source);
return PTR_ERR(bdev);
if (bdev->bd_fsfreeze_count > 0) {
mutex_unlock(&bdev->bd_fsfreeze_mutex);
warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
return -EBUSY;
}
s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
if (IS_ERR(s)) {
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
return PTR_ERR(s);
}
if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) {
warnf(fc, "%pg: Can't mount, would change RO state", bdev);
deactivate_locked_super(s);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
return -EBUSY;
}
* holding an active reference.
*/
up_write(&s->s_umount);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
down_write(&s->s_umount);
} else {
- s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
fc->fs_type->name, s->s_id);
{
struct block_device *bdev;
struct super_block *s;
- fmode_t mode = FMODE_READ | FMODE_EXCL;
int error = 0;
- if (!(flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
- bdev = blkdev_get_by_path(dev_name, mode, fs_type);
+ bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type,
+ &fs_holder_ops);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
* holding an active reference.
*/
up_write(&s->s_umount);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fs_type);
down_write(&s->s_umount);
} else {
- s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
fs_type->name, s->s_id);
error_s:
error = PTR_ERR(s);
error_bdev:
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fs_type);
error:
return ERR_PTR(error);
}
void kill_block_super(struct super_block *sb)
{
struct block_device *bdev = sb->s_bdev;
- fmode_t mode = sb->s_mode;
bdev->bd_super = NULL;
generic_shutdown_super(sb);
sync_blockdev(bdev);
- WARN_ON_ONCE(!(mode & FMODE_EXCL));
- blkdev_put(bdev, mode | FMODE_EXCL);
+ blkdev_put(bdev, sb->s_type);
}
EXPORT_SYMBOL(kill_block_super);
if (ret) {
sb->s_writers.frozen = SB_UNFROZEN;
sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT);
- wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return ret;
}
"VFS:Filesystem freeze failed\n");
sb->s_writers.frozen = SB_UNFROZEN;
sb_freeze_unlock(sb, SB_FREEZE_FS);
- wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return ret;
}
sb->s_writers.frozen = SB_UNFROZEN;
sb_freeze_unlock(sb, SB_FREEZE_FS);
out:
- wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return 0;
}
+ // SPDX-License-Identifier: GPL-2.0-only
/*
* file.c
*
* File handling routines for the OSTA-UDF(tm) filesystem.
*
* COPYRIGHT
- * This file is distributed under the terms of the GNU General Public
- * License (GPL). Copies of the GPL can be obtained from:
- * ftp://prep.ai.mit.edu/pub/gnu/GPL
- * Each contributing author retains all rights to their own work.
- *
* (C) 1998-1999 Dave Boynton
* (C) 1998-2004 Ben Fennema
* (C) 1999-2000 Stelias Computing Inc
.write_iter = udf_file_write_iter,
.release = udf_release_file,
.fsync = generic_file_fsync,
- .splice_read = generic_file_splice_read,
+ .splice_read = filemap_splice_read,
.splice_write = iter_file_splice_write,
.llseek = generic_file_llseek,
};
+ // SPDX-License-Identifier: GPL-2.0-only
/*
* namei.c
*
* Inode name handling routines for the OSTA-UDF(tm) filesystem.
*
* COPYRIGHT
- * This file is distributed under the terms of the GNU General Public
- * License (GPL). Copies of the GPL can be obtained from:
- * ftp://prep.ai.mit.edu/pub/gnu/GPL
- * Each contributing author retains all rights to their own work.
- *
* (C) 1998-2004 Ben Fennema
* (C) 1999-2000 Stelias Computing Inc
*
if (!empty_dir(new_inode))
goto out_oiter;
}
- /*
- * We need to protect against old_inode getting converted from
- * ICB to normal directory.
- */
- inode_lock_nested(old_inode, I_MUTEX_NONDIR2);
retval = udf_fiiter_find_entry(old_inode, &dotdot_name,
&diriter);
if (retval == -ENOENT) {
old_inode->i_ino);
retval = -EFSCORRUPTED;
}
- if (retval) {
- inode_unlock(old_inode);
+ if (retval)
goto out_oiter;
- }
has_diriter = true;
tloc = lelb_to_cpu(diriter.fi.icb.extLocation);
if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) !=
udf_dir_entry_len(&diriter.fi));
udf_fiiter_write_fi(&diriter, NULL);
udf_fiiter_release(&diriter);
- inode_unlock(old_inode);
inode_dec_link_count(old_dir);
if (new_inode)
}
return 0;
out_oiter:
- if (has_diriter) {
+ if (has_diriter)
udf_fiiter_release(&diriter);
- inode_unlock(old_inode);
- }
udf_fiiter_release(&oiter);
return retval;
void invalidate_inode_buffers(struct inode *);
int remove_inode_buffers(struct inode *inode);
int sync_mapping_buffers(struct address_space *mapping);
+ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
+ bool datasync);
+ int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
+ bool datasync);
void clean_bdev_aliases(struct block_device *bdev, sector_t block,
sector_t len);
static inline void clean_bdev_bh_alias(struct buffer_head *bh)
void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
int block_write_full_page(struct page *page, get_block_t *get_block,
struct writeback_control *wbc);
-int __block_write_full_page(struct inode *inode, struct page *page,
+int __block_write_full_folio(struct inode *inode, struct folio *folio,
get_block_t *get_block, struct writeback_control *wbc,
bh_end_io_t *handler);
int block_read_full_folio(struct folio *, get_block_t *);
int generic_write_end(struct file *, struct address_space *,
loff_t, unsigned, unsigned,
struct page *, void *);
-void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
+void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
void clean_page_buffers(struct page *page);
int cont_write_begin(struct file *, struct address_space *, loff_t,
unsigned, struct page **, void **,
#define FMODE_PWRITE ((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC ((__force fmode_t)0x20)
-/* File is opened with O_NDELAY (only set for block devices) */
-#define FMODE_NDELAY ((__force fmode_t)0x40)
-/* File is opened with O_EXCL (only set for block devices) */
-#define FMODE_EXCL ((__force fmode_t)0x80)
-/* File is opened using open(.., 3, ..) and is writeable only for ioctls
- (specialy hack for floppy.c) */
-#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
/* File supports non-exclusive O_DIRECT writes from multiple threads */
#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000)
+/* File is embedded in backing_file object */
+#define FMODE_BACKING ((__force fmode_t)0x2000000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
index < ra->start + ra->size);
}
+/*
+ * f_{lock,count,pos_lock} members can be highly contended and share
+ * the same cacheline. f_{lock,mode} are very frequently used together
+ * and so share the same cacheline as well. The read-mostly
+ * f_{path,inode,op} are kept on a separate cacheline.
+ */
struct file {
union {
struct llist_node f_llist;
struct rcu_head f_rcuhead;
unsigned int f_iocb_flags;
};
- struct path f_path;
- struct inode *f_inode; /* cached value */
- const struct file_operations *f_op;
/*
* Protects f_ep, f_flags.
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
- atomic_long_t f_count;
- unsigned int f_flags;
fmode_t f_mode;
+ atomic_long_t f_count;
struct mutex f_pos_lock;
loff_t f_pos;
+ unsigned int f_flags;
struct fown_struct f_owner;
const struct cred *f_cred;
struct file_ra_state f_ra;
+ struct path f_path;
+ struct inode *f_inode; /* cached value */
+ const struct file_operations *f_op;
u64 f_version;
#ifdef CONFIG_SECURITY
* sb->s_flags. Note that these mirror the equivalent MS_* flags where
* represented in both.
*/
-#define SB_RDONLY 1 /* Mount read-only */
-#define SB_NOSUID 2 /* Ignore suid and sgid bits */
-#define SB_NODEV 4 /* Disallow access to device special files */
-#define SB_NOEXEC 8 /* Disallow program execution */
-#define SB_SYNCHRONOUS 16 /* Writes are synced at once */
-#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */
-#define SB_DIRSYNC 128 /* Directory modifications are synchronous */
-#define SB_NOATIME 1024 /* Do not update access times. */
-#define SB_NODIRATIME 2048 /* Do not update directory access times */
-#define SB_SILENT 32768
-#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */
-#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */
-#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */
-#define SB_I_VERSION (1<<23) /* Update inode I_version field */
-#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */
+#define SB_RDONLY BIT(0) /* Mount read-only */
+#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */
+#define SB_NODEV BIT(2) /* Disallow access to device special files */
+#define SB_NOEXEC BIT(3) /* Disallow program execution */
+#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */
+#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */
+#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */
+#define SB_NOATIME BIT(10) /* Do not update access times. */
+#define SB_NODIRATIME BIT(11) /* Do not update directory access times */
+#define SB_SILENT BIT(15)
+#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */
+#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */
+#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */
+#define SB_I_VERSION BIT(23) /* Update inode I_version field */
+#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */
/* These sb flags are internal to the kernel */
-#define SB_SUBMOUNT (1<<26)
-#define SB_FORCE (1<<27)
-#define SB_NOSEC (1<<28)
-#define SB_BORN (1<<29)
-#define SB_ACTIVE (1<<30)
-#define SB_NOUSER (1<<31)
+#define SB_SUBMOUNT BIT(26)
+#define SB_FORCE BIT(27)
+#define SB_NOSEC BIT(28)
+#define SB_BORN BIT(29)
+#define SB_ACTIVE BIT(30)
+#define SB_NOUSER BIT(31)
/* These flags relate to encoding and casefolding */
#define SB_ENC_STRICT_MODE_FL (1 << 0)
struct sb_writers {
int frozen; /* Is sb frozen? */
- wait_queue_head_t wait_unfrozen; /* wait for thaw */
struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS];
};
uuid_t s_uuid; /* UUID */
unsigned int s_max_links;
- fmode_t s_mode;
/*
* The next field is for VFS *only*. No filesystems have any business
*/
atomic_long_t s_fsnotify_connectors;
- /* Being remounted read-only */
+ /* Read-only state of the superblock is being changed */
int s_readonly_remount;
/* per-sb errseq_t for reporting writeback errors via syncfs */
WHITEOUT_DEV);
}
-struct file *vfs_tmpfile_open(struct mnt_idmap *idmap,
- const struct path *parentpath,
- umode_t mode, int open_flag, const struct cred *cred);
+struct file *kernel_tmpfile_open(struct mnt_idmap *idmap,
+ const struct path *parentpath,
+ umode_t mode, int open_flag,
+ const struct cred *cred);
+struct file *kernel_file_open(const struct path *path, int flags,
+ struct inode *inode, const struct cred *cred);
int vfs_mkobj(struct dentry *, umode_t,
int (*f)(struct dentry *, umode_t, void *),
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
- ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
int (*check_flags)(int);
int (*flock) (struct file *, int, struct file_lock *);
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
+ void (*splice_eof)(struct file *file);
int (*setlease)(struct file *, long, struct file_lock **, void **);
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
struct shrink_control *);
long (*free_cached_objects)(struct super_block *,
struct shrink_control *);
+ void (*shutdown)(struct super_block *sb);
};
/*
return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root},
name, flags, mode);
}
-extern struct file * dentry_open(const struct path *, int, const struct cred *);
-extern struct file *dentry_create(const struct path *path, int flags,
- umode_t mode, const struct cred *cred);
-extern struct file * open_with_fake_path(const struct path *, int,
- struct inode*, const struct cred *);
+struct file *dentry_open(const struct path *path, int flags,
+ const struct cred *creds);
+struct file *dentry_create(const struct path *path, int flags, umode_t mode,
+ const struct cred *cred);
+struct file *backing_file_open(const struct path *path, int flags,
+ const struct path *real_path,
+ const struct cred *cred);
+struct path *backing_file_real_path(struct file *f);
+
+/*
+ * file_real_path - get the path corresponding to f_inode
+ *
+ * When opening a backing file for a stackable filesystem (e.g.,
+ * overlayfs) f_path may be on the stackable filesystem and f_inode on
+ * the underlying filesystem. When the path associated with f_inode is
+ * needed, this helper should be used instead of accessing f_path
+ * directly.
+*/
+static inline const struct path *file_real_path(struct file *f)
+{
+ if (unlikely(f->f_mode & FMODE_BACKING))
+ return backing_file_real_path(f);
+ return &f->f_path;
+}
+
static inline struct file *file_clone_open(struct file *file)
{
return dentry_open(&file->f_path, file->f_flags, file->f_cred);
void dump_mapping(const struct address_space *);
/*
- * Userspace may rely on the the inode number being non-zero. For example, glibc
+ * Userspace may rely on the inode number being non-zero. For example, glibc
* simply ignores files with zero i_ino in unlink() and other places.
*
* As an additional complication, if userspace was compiled with
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
ssize_t generic_perform_write(struct kiocb *, struct iov_iter *);
+ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter,
+ ssize_t direct_written, ssize_t buffered_written);
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags);
ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
-ssize_t direct_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len, unsigned int flags);
-extern ssize_t generic_file_splice_read(struct file *, loff_t *,
- struct pipe_inode_info *, size_t, unsigned int);
+ssize_t copy_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len, unsigned int flags);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
-extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
- struct file *out, loff_t *, size_t len, unsigned int flags);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
loff_t *opos, size_t len, unsigned int flags);
wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}
-/*
- * Warn about a page cache invalidation failure diring a direct I/O write.
- */
-void dio_warn_stale_pagecache(struct file *filp);
-
extern void inode_set_flags(struct inode *inode, unsigned int flags,
unsigned int mask);