From: Méven Car A program that copies many files sets the times of every copy after its last write. On NFS and SMB each of those calls is a round trip to the server, and with io_uring it is one of the steps of the copy that still have to leave the ring and run one file at a time. IORING_OP_UTIMENSAT behaves like utimensat(2). sqe->fd is the directory fd, sqe->addr the path, sqe->addr2 a pointer to two struct __kernel_timespec, and sqe->utimes_flags takes AT_SYMLINK_NOFOLLOW and AT_EMPTY_PATH. An addr2 of zero sets both times to the current time, as a NULL times argument does. The times and the path are copied at submission. As with utimensat(2), a NULL path sets the times of the file that sqe->fd refers to, without a lookup, and takes no flags. Two UTIME_OMIT times complete with 0 without a lookup. Like the other path ops, the request is issued from io-wq, apart from the no-op, because the lookup and notify_change() can sleep. A fixed file is not accepted as the directory fd. A failed request fails the rest of its link. Signed-off-by: Méven Car --- include/uapi/linux/io_uring.h | 2 + io_uring/fs.c | 97 +++++++++++++++++++++++++++++++++++ io_uring/fs.h | 4 ++ io_uring/opdef.c | 8 +++ 4 files changed, 111 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b42b66b424a7..6a98c9282e0b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -76,6 +76,7 @@ struct io_uring_sqe { __u32 install_fd_flags; __u32 nop_flags; __u32 pipe_flags; + __u32 utimes_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -319,6 +320,7 @@ enum io_uring_op { IORING_OP_PIPE, IORING_OP_NOP128, IORING_OP_URING_CMD128, + IORING_OP_UTIMENSAT, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/fs.c b/io_uring/fs.c index 26ea841a22e7..71164bddd958 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -304,3 +304,100 @@ void io_link_cleanup(struct io_kiocb *req) dismiss_delayed_filename(&sl->oldpath); dismiss_delayed_filename(&sl->newpath); } + +/* Internal flags, above the AT_ flags of the SQE */ +#define IO_UTIMENSAT_NOOP BIT(30) /* both times UTIME_OMIT */ +#define IO_UTIMENSAT_NO_PATH BIT(31) /* NULL path: the dfd itself */ + +struct io_utimensat { + struct file *file; + int dfd; + unsigned int flags; + struct delayed_filename filename; + /* NULL sets both times to the current time */ + struct timespec64 *times; + struct timespec64 ts[2]; +}; + +int io_utimensat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_utimensat *ut = io_kiocb_to_cmd(req, struct io_utimensat); + struct __kernel_timespec __user *uts; + const char __user *fname; + int err; + + if (sqe->len || sqe->buf_index || sqe->splice_fd_in || sqe->addr3 || + sqe->__pad2[0]) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ut->dfd = READ_ONCE(sqe->fd); + ut->flags = READ_ONCE(sqe->utimes_flags); + if (ut->flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) + return -EINVAL; + + uts = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ut->times = NULL; + if (uts) { + if (get_timespec64(&ut->ts[0], &uts[0]) || + get_timespec64(&ut->ts[1], &uts[1])) + return -EFAULT; + ut->times = ut->ts; + if (ut->ts[0].tv_nsec == UTIME_OMIT && + ut->ts[1].tv_nsec == UTIME_OMIT) { + ut->flags |= IO_UTIMENSAT_NOOP; + return 0; + } + } + + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + if (!fname) { + if (ut->dfd == AT_FDCWD) + return -EFAULT; + if (ut->flags) + return -EINVAL; + ut->flags |= IO_UTIMENSAT_NO_PATH; + goto out; + } + err = delayed_getname_uflags(&ut->filename, fname, ut->flags); + if (unlikely(err)) + return err; + req->flags |= REQ_F_NEED_CLEANUP; +out: + req->flags |= REQ_F_FORCE_ASYNC; + return 0; +} + +int io_utimensat(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_utimensat *ut = io_kiocb_to_cmd(req, struct io_utimensat); + int ret = 0; + + WARN_ON_ONCE((issue_flags & IO_URING_F_NONBLOCK) && + !(ut->flags & IO_UTIMENSAT_NOOP)); + + if (ut->flags & IO_UTIMENSAT_NO_PATH) { + CLASS(fd, f)(ut->dfd); + + ret = -EBADF; + if (!fd_empty(f)) + ret = vfs_utimes(&fd_file(f)->f_path, ut->times); + } else if (!(ut->flags & IO_UTIMENSAT_NOOP)) { + CLASS(filename_complete_delayed, name)(&ut->filename); + ret = filename_utimensat(ut->dfd, name, ut->times, ut->flags); + } + + req->flags &= ~REQ_F_NEED_CLEANUP; + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_COMPLETE; +} + +void io_utimensat_cleanup(struct io_kiocb *req) +{ + struct io_utimensat *ut = io_kiocb_to_cmd(req, struct io_utimensat); + + dismiss_delayed_filename(&ut->filename); +} diff --git a/io_uring/fs.h b/io_uring/fs.h index 0bb5efe3d6bb..2812dc3b4b2f 100644 --- a/io_uring/fs.h +++ b/io_uring/fs.h @@ -18,3 +18,7 @@ int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags); int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_linkat(struct io_kiocb *req, unsigned int issue_flags); void io_link_cleanup(struct io_kiocb *req); + +int io_utimensat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_utimensat(struct io_kiocb *req, unsigned int issue_flags); +void io_utimensat_cleanup(struct io_kiocb *req); diff --git a/io_uring/opdef.c b/io_uring/opdef.c index cf3aa2242cd7..383a9b9d1df4 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -591,6 +591,10 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_uring_cmd_prep, .issue = io_uring_cmd, }, + [IORING_OP_UTIMENSAT] = { + .prep = io_utimensat_prep, + .issue = io_utimensat, + }, }; const struct io_cold_def io_cold_defs[] = { @@ -849,6 +853,10 @@ const struct io_cold_def io_cold_defs[] = { .sqe_copy = io_uring_cmd_sqe_copy, .cleanup = io_uring_cmd_cleanup, }, + [IORING_OP_UTIMENSAT] = { + .name = "UTIMENSAT", + .cleanup = io_utimensat_cleanup, + }, }; const char *io_uring_get_opcode(u8 opcode) -- 2.56.0