diff options
author | Darrick J. Wong <darrick.wong@oracle.com> | 2018-10-30 10:42:10 +1100 |
---|---|---|
committer | Dave Chinner <david@fromorbit.com> | 2018-10-30 10:42:10 +1100 |
commit | eca3654e3cc7d93e9734d0fa96cfb15c7f356244 (patch) | |
tree | 00e5f8bd5de34435872d8cb222daaec79ede3961 /fs/read_write.c | |
parent | df3658361951e17364f1e1c3fa92862a990ad8bd (diff) | |
download | lwn-eca3654e3cc7d93e9734d0fa96cfb15c7f356244.tar.gz lwn-eca3654e3cc7d93e9734d0fa96cfb15c7f356244.zip |
vfs: enable remap callers that can handle short operations
Plumb in a remap flag that enables the filesystem remap handler to
shorten remapping requests for callers that can handle it. Now
copy_file_range can report partial success (in case we run up against
alignment problems, resource limits, etc.).
We also enable CAN_SHORTEN for fideduperange to maintain existing
userspace-visible behavior where xfs/btrfs shorten the dedupe range to
avoid stale post-eof data exposure.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs/read_write.c')
-rw-r--r-- | fs/read_write.c | 28 |
1 files changed, 20 insertions, 8 deletions
diff --git a/fs/read_write.c b/fs/read_write.c index ea30666013b0..c0bcc1a20650 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1593,7 +1593,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, cloned = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, - min_t(loff_t, MAX_RW_COUNT, len), 0); + min_t(loff_t, MAX_RW_COUNT, len), + REMAP_FILE_CAN_SHORTEN); if (cloned > 0) { ret = cloned; goto done; @@ -1721,6 +1722,8 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len, * can't meaningfully compare post-EOF contents. * * For clone we only link a partial EOF block above the destination file's EOF. + * + * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, @@ -1729,16 +1732,24 @@ static int generic_remap_check_len(struct inode *inode_in, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; + loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; - if (remap_flags & REMAP_FILE_DEDUP) - *len &= ~blkmask; - else if (pos_out + *len < i_size_read(inode_out)) - return -EINVAL; + if ((remap_flags & REMAP_FILE_DEDUP) || + pos_out + *len < i_size_read(inode_out)) + new_len &= ~blkmask; - return 0; + if (new_len == *len) + return 0; + + if (remap_flags & REMAP_FILE_CAN_SHORTEN) { + *len = new_len; + return 0; + } + + return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* @@ -2014,7 +2025,8 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, { loff_t ret; - WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP)); + WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | + REMAP_FILE_CAN_SHORTEN)); ret = mnt_want_write_file(dst_file); if (ret) @@ -2115,7 +2127,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) deduped = vfs_dedupe_file_range_one(file, off, dst_file, info->dest_offset, len, - 0); + REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) |