xfs: add dedupe range vfs function
Define a VFS function which allows userspace to request that the kernel reflink a range of blocks between two files if the ranges' contents match. The function fits the new VFS ioctl that standardizes the checking for the btrfs EXTENT SAME ioctl. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
parent
9fe26045e9
commit
cc714660bb
|
@ -1010,7 +1010,8 @@ xfs_file_share_range(
|
|||
loff_t pos_in,
|
||||
struct file *file_out,
|
||||
loff_t pos_out,
|
||||
u64 len)
|
||||
u64 len,
|
||||
bool is_dedupe)
|
||||
{
|
||||
struct inode *inode_in;
|
||||
struct inode *inode_out;
|
||||
|
@ -1019,6 +1020,7 @@ xfs_file_share_range(
|
|||
loff_t isize;
|
||||
int same_inode;
|
||||
loff_t blen;
|
||||
unsigned int flags = 0;
|
||||
|
||||
inode_in = file_inode(file_in);
|
||||
inode_out = file_inode(file_out);
|
||||
|
@ -1056,6 +1058,15 @@ xfs_file_share_range(
|
|||
pos_in + len > isize)
|
||||
return -EINVAL;
|
||||
|
||||
/* Don't allow dedupe past EOF in the dest file */
|
||||
if (is_dedupe) {
|
||||
loff_t disize;
|
||||
|
||||
disize = i_size_read(inode_out);
|
||||
if (pos_out >= disize || pos_out + len > disize)
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
/* If we're linking to EOF, continue to the block boundary. */
|
||||
if (pos_in + len == isize)
|
||||
blen = ALIGN(isize, bs) - pos_in;
|
||||
|
@ -1079,8 +1090,10 @@ xfs_file_share_range(
|
|||
if (ret)
|
||||
goto out_unlock;
|
||||
|
||||
if (is_dedupe)
|
||||
flags |= XFS_REFLINK_DEDUPE;
|
||||
ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
|
||||
pos_out, len);
|
||||
pos_out, len, flags);
|
||||
if (ret < 0)
|
||||
goto out_unlock;
|
||||
|
||||
|
@ -1100,7 +1113,7 @@ xfs_file_copy_range(
|
|||
int error;
|
||||
|
||||
error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
|
||||
len);
|
||||
len, false);
|
||||
if (error)
|
||||
return error;
|
||||
return len;
|
||||
|
@ -1115,7 +1128,33 @@ xfs_file_clone_range(
|
|||
u64 len)
|
||||
{
|
||||
return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
|
||||
len);
|
||||
len, false);
|
||||
}
|
||||
|
||||
#define XFS_MAX_DEDUPE_LEN (16 * 1024 * 1024)
|
||||
STATIC ssize_t
|
||||
xfs_file_dedupe_range(
|
||||
struct file *src_file,
|
||||
u64 loff,
|
||||
u64 len,
|
||||
struct file *dst_file,
|
||||
u64 dst_loff)
|
||||
{
|
||||
int error;
|
||||
|
||||
/*
|
||||
* Limit the total length we will dedupe for each operation.
|
||||
* This is intended to bound the total time spent in this
|
||||
* ioctl to something sane.
|
||||
*/
|
||||
if (len > XFS_MAX_DEDUPE_LEN)
|
||||
len = XFS_MAX_DEDUPE_LEN;
|
||||
|
||||
error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
|
||||
len, true);
|
||||
if (error)
|
||||
return error;
|
||||
return len;
|
||||
}
|
||||
|
||||
STATIC int
|
||||
|
@ -1779,6 +1818,7 @@ const struct file_operations xfs_file_operations = {
|
|||
.fallocate = xfs_file_fallocate,
|
||||
.copy_file_range = xfs_file_copy_range,
|
||||
.clone_file_range = xfs_file_clone_range,
|
||||
.dedupe_file_range = xfs_file_dedupe_range,
|
||||
};
|
||||
|
||||
const struct file_operations xfs_dir_file_operations = {
|
||||
|
|
|
@ -1149,6 +1149,111 @@ err:
|
|||
return error;
|
||||
}
|
||||
|
||||
/*
|
||||
* Read a page's worth of file data into the page cache. Return the page
|
||||
* locked.
|
||||
*/
|
||||
static struct page *
|
||||
xfs_get_page(
|
||||
struct inode *inode,
|
||||
xfs_off_t offset)
|
||||
{
|
||||
struct address_space *mapping;
|
||||
struct page *page;
|
||||
pgoff_t n;
|
||||
|
||||
n = offset >> PAGE_SHIFT;
|
||||
mapping = inode->i_mapping;
|
||||
page = read_mapping_page(mapping, n, NULL);
|
||||
if (IS_ERR(page))
|
||||
return page;
|
||||
if (!PageUptodate(page)) {
|
||||
put_page(page);
|
||||
return ERR_PTR(-EIO);
|
||||
}
|
||||
lock_page(page);
|
||||
return page;
|
||||
}
|
||||
|
||||
/*
|
||||
* Compare extents of two files to see if they are the same.
|
||||
*/
|
||||
static int
|
||||
xfs_compare_extents(
|
||||
struct inode *src,
|
||||
xfs_off_t srcoff,
|
||||
struct inode *dest,
|
||||
xfs_off_t destoff,
|
||||
xfs_off_t len,
|
||||
bool *is_same)
|
||||
{
|
||||
xfs_off_t src_poff;
|
||||
xfs_off_t dest_poff;
|
||||
void *src_addr;
|
||||
void *dest_addr;
|
||||
struct page *src_page;
|
||||
struct page *dest_page;
|
||||
xfs_off_t cmp_len;
|
||||
bool same;
|
||||
int error;
|
||||
|
||||
error = -EINVAL;
|
||||
same = true;
|
||||
while (len) {
|
||||
src_poff = srcoff & (PAGE_SIZE - 1);
|
||||
dest_poff = destoff & (PAGE_SIZE - 1);
|
||||
cmp_len = min(PAGE_SIZE - src_poff,
|
||||
PAGE_SIZE - dest_poff);
|
||||
cmp_len = min(cmp_len, len);
|
||||
ASSERT(cmp_len > 0);
|
||||
|
||||
trace_xfs_reflink_compare_extents(XFS_I(src), srcoff, cmp_len,
|
||||
XFS_I(dest), destoff);
|
||||
|
||||
src_page = xfs_get_page(src, srcoff);
|
||||
if (IS_ERR(src_page)) {
|
||||
error = PTR_ERR(src_page);
|
||||
goto out_error;
|
||||
}
|
||||
dest_page = xfs_get_page(dest, destoff);
|
||||
if (IS_ERR(dest_page)) {
|
||||
error = PTR_ERR(dest_page);
|
||||
unlock_page(src_page);
|
||||
put_page(src_page);
|
||||
goto out_error;
|
||||
}
|
||||
src_addr = kmap_atomic(src_page);
|
||||
dest_addr = kmap_atomic(dest_page);
|
||||
|
||||
flush_dcache_page(src_page);
|
||||
flush_dcache_page(dest_page);
|
||||
|
||||
if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
|
||||
same = false;
|
||||
|
||||
kunmap_atomic(dest_addr);
|
||||
kunmap_atomic(src_addr);
|
||||
unlock_page(dest_page);
|
||||
unlock_page(src_page);
|
||||
put_page(dest_page);
|
||||
put_page(src_page);
|
||||
|
||||
if (!same)
|
||||
break;
|
||||
|
||||
srcoff += cmp_len;
|
||||
destoff += cmp_len;
|
||||
len -= cmp_len;
|
||||
}
|
||||
|
||||
*is_same = same;
|
||||
return 0;
|
||||
|
||||
out_error:
|
||||
trace_xfs_reflink_compare_extents_error(XFS_I(dest), error, _RET_IP_);
|
||||
return error;
|
||||
}
|
||||
|
||||
/*
|
||||
* Link a range of blocks from one file to another.
|
||||
*/
|
||||
|
@ -1158,12 +1263,14 @@ xfs_reflink_remap_range(
|
|||
xfs_off_t srcoff,
|
||||
struct xfs_inode *dest,
|
||||
xfs_off_t destoff,
|
||||
xfs_off_t len)
|
||||
xfs_off_t len,
|
||||
unsigned int flags)
|
||||
{
|
||||
struct xfs_mount *mp = src->i_mount;
|
||||
xfs_fileoff_t sfsbno, dfsbno;
|
||||
xfs_filblks_t fsblen;
|
||||
int error;
|
||||
bool is_same;
|
||||
|
||||
if (!xfs_sb_version_hasreflink(&mp->m_sb))
|
||||
return -EOPNOTSUPP;
|
||||
|
@ -1175,6 +1282,9 @@ xfs_reflink_remap_range(
|
|||
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
|
||||
return -EINVAL;
|
||||
|
||||
if (flags & ~XFS_REFLINK_ALL)
|
||||
return -EINVAL;
|
||||
|
||||
trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff);
|
||||
|
||||
/* Lock both files against IO */
|
||||
|
@ -1186,6 +1296,21 @@ xfs_reflink_remap_range(
|
|||
xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
|
||||
}
|
||||
|
||||
/*
|
||||
* Check that the extents are the same.
|
||||
*/
|
||||
if (flags & XFS_REFLINK_DEDUPE) {
|
||||
is_same = false;
|
||||
error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest),
|
||||
destoff, len, &is_same);
|
||||
if (error)
|
||||
goto out_error;
|
||||
if (!is_same) {
|
||||
error = -EBADE;
|
||||
goto out_error;
|
||||
}
|
||||
}
|
||||
|
||||
error = xfs_reflink_set_inode_flag(src, dest);
|
||||
if (error)
|
||||
goto out_error;
|
||||
|
|
|
@ -43,7 +43,10 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
|
|||
extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
|
||||
xfs_off_t count);
|
||||
extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
|
||||
#define XFS_REFLINK_DEDUPE 1 /* only reflink if contents match */
|
||||
#define XFS_REFLINK_ALL (XFS_REFLINK_DEDUPE)
|
||||
extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
|
||||
struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len);
|
||||
struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
|
||||
unsigned int flags);
|
||||
|
||||
#endif /* __XFS_REFLINK_H */
|
||||
|
|
Loading…
Reference in New Issue