From: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx> copy_file_range calls do_splice_direct() if fs->clone_file_range or fs->copy_file_range() is not available. However, do_splice_direct() converts holes to zeros. Detect holes in the file_in range, and create them in the corresponding file_out range. If there is already data present at the offset in file_out, attempt to punch a hole there. If the operation is not supported, fall back to performing splice on the whole range. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx> --- fs/read_write.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 60 insertions(+), 2 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index e71270033402..6866e2a27594 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -20,6 +20,7 @@ #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> +#include <linux/falloc.h> #include "internal.h" #include <linux/uaccess.h> @@ -1541,6 +1542,63 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, } #endif + +static ssize_t splice_with_holes(struct file *file_in, loff_t *pos_in, + struct file *file_out, loff_t *pos_out, size_t len) +{ + ssize_t ret = 0, total = 0; + loff_t size, end; + + while (total < len) { + end = vfs_llseek(file_in, *pos_in, SEEK_HOLE); + if (end == *pos_in) + goto hole; + size = end - *pos_in; +splice: + ret = do_splice_direct(file_in, pos_in, file_out, pos_out, + size, 0); + if (ret < 0) + goto out; + total += ret; + if (total == len) + break; +hole: + end = vfs_llseek(file_in, *pos_in, SEEK_DATA); + if (end < 0) { + ret = end; + goto out; + } + size = end - *pos_in; + /* For files already containing data, punch holes */ + if (i_size_read(file_out->f_inode) > *pos_out) { + ret = vfs_fallocate(file_out, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + *pos_out, size); + if (ret < 0) { + /* + * The filesystem does not support punching + * holes. Perform splice on the entire range. + */ + if (ret == -EOPNOTSUPP) { + size = len - total; + goto splice; + } + goto out; + } + } + if (ret < 0) { + ret = end; + goto out; + } + *pos_out += size; + *pos_in = end; + total += size; + } + +out: + return total ? total : ret; +} + /* * 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 @@ -1604,8 +1662,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, } do_splice: - ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, - len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); + ret = splice_with_holes(file_in, &pos_in, file_out, &pos_out, + len > MAX_RW_COUNT ? MAX_RW_COUNT : len); done: if (ret > 0) { -- 2.16.3