/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @length: The number of bytes to zero
* @get_block: The filesystem method used to translate file offsets to blocks
*
* This function can be called by a filesystem when it is zeroing part of a
* page in a DAX file. This is intended for hole-punch operations. If
* you are truncating a file, the helper function dax_truncate_page() may be
* more convenient.
*
* We work in terms of PAGE_SIZE here for commonality with
* block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
* took care of disposing of the unnecessary blocks. Even if the filesystem
* block size is smaller than PAGE_SIZE, we have to zero the rest of the page
* since the file might be mmapped.
*/
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
get_block_t get_block)
{
struct buffer_head bh;
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
int err;
/* Block boundary? Nothing to do */
if (!length)
return 0;
BUG_ON((offset + length) > PAGE_SIZE);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
err = get_block(inode, index, &bh, 0);
if (err < 0)
return err;
if (buffer_written(&bh)) {
struct block_device *bdev = bh.b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(&bh, inode),
.size = PAGE_SIZE,
};
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
clear_pmem(dax.addr + offset, length);
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
}
return 0;
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);
/**
* dax_truncate_page - handle a partial page being truncated in a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @get_block: The filesystem method used to translate file offsets to blocks
*
* Similar to block_truncate_page(), this function can be called by a
* filesystem when it is truncating a DAX file to handle the partial page.
*
* We work in terms of PAGE_SIZE here for commonality with
* block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
* took care of disposing of the unnecessary blocks. Even if the filesystem
* block size is smaller than PAGE_SIZE, we have to zero the rest of the page
* since the file might be mmapped.
*/
int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
{
unsigned length = PAGE_ALIGN(from) - from;
return dax_zero_page_range(inode, from, length, get_block);
}
/*
* xfs_iozero clears the specified range supplied via the page cache (except in
* the DAX case). Writes through the page cache will allocate blocks over holes,
* though the callers usually map the holes first and avoid them. If a block is
* not completely zeroed, then it will be read from disk before being partially
* zeroed.
*
* In the DAX case, we can just directly write to the underlying pages. This
* will not allocate blocks, but will avoid holes and unwritten extents and so
* not do unnecessary work.
*/
int
xfs_iozero(
struct xfs_inode *ip, /* inode */
loff_t pos, /* offset in file */
size_t count) /* size of data to zero */
{
struct page *page;
struct address_space *mapping;
int status = 0;
mapping = VFS_I(ip)->i_mapping;
do {
unsigned offset, bytes;
void *fsdata;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
bytes = PAGE_CACHE_SIZE - offset;
if (bytes > count)
bytes = count;
if (IS_DAX(VFS_I(ip))) {
status = dax_zero_page_range(VFS_I(ip), pos, bytes,
xfs_get_blocks_direct);
if (status)
break;
} else {
status = pagecache_write_begin(NULL, mapping, pos, bytes,
AOP_FLAG_UNINTERRUPTIBLE,
&page, &fsdata);
if (status)
break;
zero_user(page, offset, bytes);
status = pagecache_write_end(NULL, mapping, pos, bytes,
bytes, page, fsdata);
WARN_ON(status <= 0); /* can't return less than zero! */
status = 0;
}
pos += bytes;
count -= bytes;
} while (count);
return status;
}
