This allows us to have an in-kernel copy mechanism that avoids frequent switches between kernel and user space. This is especially useful so NFSD can support server-side copies. The default (flags=0) means to first attempt copy acceleration, but use the pagecache if that fails. I moved the rw_verify_area() calls into the fallback code since some filesystems can handle reflinking a large range. Signed-off-by: Anna Schumaker <Anna.Schumaker@xxxxxxxxxx> Reviewed-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx> Reviewed-by: Padraig Brady <P@xxxxxxxxxxxxxx> --- v6: - Don't reflink by default. - Reword commit message. --- fs/read_write.c | 36 ++++++++++++++++++++++++++---------- 1 file changed, 26 insertions(+), 10 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index 20f147d..1fd555c 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1329,6 +1329,24 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, } #endif +static ssize_t vfs_copy_fr_copy(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len) +{ + ssize_t ret = rw_verify_area(READ, file_in, &pos_in, len); + + if (ret >= 0) { + len = ret; + ret = rw_verify_area(WRITE, file_out, &pos_out, len); + if (ret >= 0) + len = ret; + } + if (ret < 0) + return ret; + + return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len, 0); +} + /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to @@ -1345,17 +1363,10 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (flags & ~(COPY_FR_REFLINK)) return -EINVAL; - /* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT */ - ret = rw_verify_area(READ, file_in, &pos_in, len); - if (ret >= 0) - ret = rw_verify_area(WRITE, file_out, &pos_out, len); - if (ret < 0) - return ret; - if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND) || - !file_out->f_op || !file_out->f_op->copy_file_range) + !file_out->f_op) return -EBADF; /* this could be relaxed once a method supports cross-fs copies */ @@ -1370,8 +1381,13 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (ret) return ret; - ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, - len, flags); + ret = -EOPNOTSUPP; + if (file_out->f_op->copy_file_range) + ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, + pos_out, len, flags); + if ((ret == -EOPNOTSUPP) && !(flags & COPY_FR_REFLINK)) + ret = vfs_copy_fr_copy(file_in, pos_in, file_out, pos_out, len); + if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); -- 2.6.1 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html