@@ -87,7 +87,8 @@ struct btrfs_ioctl_received_subvol_args_32 {
static int btrfs_clone(struct inode *src, struct inode *inode,
- u64 off, u64 olen, u64 olen_aligned, u64 destoff);
+ u64 off, u64 olen, u64 olen_aligned, u64 destoff,
+ int flags);
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
@@ -2974,7 +2975,7 @@ static int extent_same_check_offsets(struct inode *inode, u64 off, u64 *plen,
}
static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
- struct inode *dst, u64 dst_loff)
+ struct inode *dst, u64 dst_loff, int flags)
{
int ret;
u64 len = olen;
@@ -3054,7 +3055,8 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
/* pass original length for comparison so we stay within i_size */
ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
if (ret == 0)
- ret = btrfs_clone(src, dst, loff, olen, len, dst_loff);
+ ret = btrfs_clone(src, dst, loff, olen, len, dst_loff,
+ flags);
if (same_inode)
unlock_extent(&BTRFS_I(src)->io_tree, same_lock_start,
@@ -3088,6 +3090,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
bool is_admin = capable(CAP_SYS_ADMIN);
u16 count;
+ int flags = 0;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
@@ -3139,6 +3142,11 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
if (!S_ISREG(src->i_mode))
goto out;
+ ret = -EINVAL;
+ if (same->flags & ~BTRFS_EXTENT_SAME_FLAG_MASK)
+ goto out;
+ flags = same->flags;
+
/* pre-format output fields to sane values */
for (i = 0; i < count; i++) {
same->info[i].bytes_deduped = 0ULL;
@@ -3164,7 +3172,8 @@ static long btrfs_ioctl_file_extent_same(struct file *file,
info->status = -EACCES;
} else {
info->status = btrfs_extent_same(src, off, len, dst,
- info->logical_offset);
+ info->logical_offset,
+ flags);
if (info->status == 0)
info->bytes_deduped += len;
}
@@ -3219,13 +3228,17 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
struct inode *inode,
u64 endoff,
const u64 destoff,
- const u64 olen)
+ const u64 olen,
+ int flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
inode_inc_iversion(inode);
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ if (flags & BTRFS_EXTENT_SAME_NO_MTIME)
+ inode->i_ctime = CURRENT_TIME;
+ else
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
/*
* We round up to the block size at eof when determining which
* extents to clone above, but shouldn't round up the file size.
@@ -3310,13 +3323,13 @@ static void clone_update_extent_map(struct inode *inode,
* @inode: Inode to clone to
* @off: Offset within source to start clone from
* @olen: Original length, passed by user, of range to clone
- * @olen_aligned: Block-aligned value of olen, extent_same uses
- * identical values here
+ * @olen_aligned: Block-aligned value of olen
* @destoff: Offset within @inode to start clone
+ * @flags: clone flags from extent-same
*/
static int btrfs_clone(struct inode *src, struct inode *inode,
const u64 off, const u64 olen, const u64 olen_aligned,
- const u64 destoff)
+ const u64 destoff, int flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path = NULL;
@@ -3640,7 +3653,7 @@ process_slot:
root->sectorsize);
ret = clone_finish_inode_update(trans, inode,
last_dest_end,
- destoff, olen);
+ destoff, olen, flags);
if (ret)
goto out;
if (new_key.offset + datal >= destoff + len)
@@ -3678,7 +3691,7 @@ process_slot:
clone_update_extent_map(inode, trans, NULL, last_dest_end,
destoff + len - last_dest_end);
ret = clone_finish_inode_update(trans, inode, destoff + len,
- destoff, olen);
+ destoff, olen, flags);
}
out:
@@ -3808,7 +3821,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
btrfs_double_extent_lock(src, off, inode, destoff, len);
}
- ret = btrfs_clone(src, inode, off, olen, len, destoff);
+ ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
if (same_inode) {
u64 lock_start = min_t(u64, off, destoff);
@@ -342,11 +342,14 @@ struct btrfs_ioctl_same_extent_info {
__u32 reserved;
};
+#define BTRFS_EXTENT_SAME_NO_MTIME 0x1
+#define BTRFS_EXTENT_SAME_FLAG_MASK (BTRFS_EXTENT_SAME_NO_MTIME)
+
struct btrfs_ioctl_same_args {
__u64 logical_offset; /* in - start of extent in source */
__u64 length; /* in - length of extent */
__u16 dest_count; /* in - total elements in info array */
- __u16 reserved1;
+ __u16 flags; /* in - see BTRFS_SAME_FLAGS */
__u32 reserved2;
struct btrfs_ioctl_same_extent_info info[0];
};
One issue users have reported is that dedupe changes mtime on files, resulting in tools like rsync thinking that their contents have changed when in fact the data is exactly the same. Clone still wants an mtime change, so we special case this in the code. With this patch an application can pass the BTRFS_SAME_NO_MTIME flag to a dedupe request and the kernel will honor it by only changing ctime. I have an updated version of the btrfs-extent-same test program with a switch to provide this flag at the 'no_time' branch of: https://github.com/markfasheh/duperemove/ Signed-off-by: Mark Fasheh <mfasheh@suse.de> --- fs/btrfs/ioctl.c | 37 +++++++++++++++++++++++++------------ include/uapi/linux/btrfs.h | 5 ++++- 2 files changed, 29 insertions(+), 13 deletions(-)