This adds support for open_by_handle_at(2) to io_uring. First an attempt to do a non-blocking open by handle is made. If that fails, for example, because the target inode is not cached, a blocking attempt is made. Signed-off-by: Thomas Bertschinger --- include/uapi/linux/io_uring.h | 1 + io_uring/opdef.c | 15 +++++ io_uring/openclose.c | 111 ++++++++++++++++++++++++++++++++++ io_uring/openclose.h | 8 +++ 4 files changed, 135 insertions(+) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a4aa83ad9527..c571929e7807 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -291,6 +291,7 @@ enum io_uring_op { IORING_OP_WRITEV_FIXED, IORING_OP_PIPE, IORING_OP_NAME_TO_HANDLE_AT, + IORING_OP_OPEN_BY_HANDLE_AT, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 76306c9e0ecd..1aa36f3f30de 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -580,6 +580,15 @@ const struct io_issue_def io_issue_defs[] = { .issue = io_name_to_handle_at, #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_OPEN_BY_HANDLE_AT] = { +#if defined(CONFIG_FHANDLE) + .prep = io_open_by_handle_at_prep, + .issue = io_open_by_handle_at, + .async_size = sizeof(struct io_open_handle_async), +#else + .prep = io_eopnotsupp_prep, #endif }, }; @@ -835,6 +844,12 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_NAME_TO_HANDLE_AT] = { .name = "NAME_TO_HANDLE_AT", }, + [IORING_OP_OPEN_BY_HANDLE_AT] = { + .name = "OPEN_BY_HANDLE_AT", +#if defined(CONFIG_FHANDLE) + .cleanup = io_open_by_handle_cleanup, +#endif + } }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/openclose.c b/io_uring/openclose.c index 4da2afdb9773..289d61373567 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -245,6 +246,116 @@ int io_name_to_handle_at(struct io_kiocb *req, unsigned int issue_flags) io_req_set_res(req, ret, 0); return IOU_COMPLETE; } + +int io_open_by_handle_at_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_open *open = io_kiocb_to_cmd(req, struct io_open); + struct io_open_handle_async *ah; + u64 flags; + int ret; + + flags = READ_ONCE(sqe->open_flags); + open->how = build_open_how(flags, 0); + + ret = __io_open_prep(req, sqe); + if (ret) + return ret; + + ah = io_uring_alloc_async_data(NULL, req); + if (!ah) + return -ENOMEM; + memset(&ah->path, 0, sizeof(ah->path)); + ah->handle = get_user_handle(u64_to_user_ptr(READ_ONCE(sqe->addr))); + if (IS_ERR(ah->handle)) + return PTR_ERR(ah->handle); + + req->flags |= REQ_F_NEED_CLEANUP; + + return 0; +} + +int io_open_by_handle_at(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_open *open = io_kiocb_to_cmd(req, struct io_open); + struct io_open_handle_async *ah = req->async_data; + bool nonblock_set = open->how.flags & O_NONBLOCK; + bool fixed = !!open->file_slot; + struct file *file; + struct open_flags op; + int ret; + + ret = build_open_flags(&open->how, &op); + if (ret) + goto err; + + if (issue_flags & IO_URING_F_NONBLOCK) + ah->handle->handle_type |= FILEID_CACHED; + else + ah->handle->handle_type &= ~FILEID_CACHED; + + if (!ah->path.dentry) { + /* + * Handle has not yet been converted to path, either because + * this is our first try, or because we tried previously with + * IO_URING_F_NONBLOCK set, and failed. + */ + ret = handle_to_path(open->dfd, ah->handle, &ah->path, op.open_flag); + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + + if (ret) + goto err; + } + + if (!fixed) { + ret = __get_unused_fd_flags(open->how.flags, open->nofile); + if (ret < 0) + goto err; + } + + if (issue_flags & IO_URING_F_NONBLOCK) { + WARN_ON_ONCE(io_openat_force_async(open)); + op.lookup_flags |= LOOKUP_CACHED; + op.open_flag |= O_NONBLOCK; + } + file = do_file_handle_open(&ah->path, &op); + + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(ret); + ret = PTR_ERR(file); + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + goto err; + } + + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; + + if (!fixed) + fd_install(ret, file); + else + ret = io_fixed_fd_install(req, issue_flags, file, + open->file_slot); + +err: + io_open_by_handle_cleanup(req); + 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_open_by_handle_cleanup(struct io_kiocb *req) +{ + struct io_open_handle_async *ah = req->async_data; + + if (ah->path.dentry) + path_put(&ah->path); + + kfree(ah->handle); +} #endif /* CONFIG_FHANDLE */ int __io_close_fixed(struct io_ring_ctx *ctx, unsigned int issue_flags, diff --git a/io_uring/openclose.h b/io_uring/openclose.h index 2fc1c8d35d0b..f966859a8a92 100644 --- a/io_uring/openclose.h +++ b/io_uring/openclose.h @@ -10,9 +10,17 @@ void io_open_cleanup(struct io_kiocb *req); int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_openat2(struct io_kiocb *req, unsigned int issue_flags); +struct io_open_handle_async { + struct file_handle *handle; + struct path path; +}; + #if defined(CONFIG_FHANDLE) int io_name_to_handle_at_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_name_to_handle_at(struct io_kiocb *req, unsigned int issue_flags); +int io_open_by_handle_at_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_open_by_handle_at(struct io_kiocb *req, unsigned int issue_flags); +void io_open_by_handle_cleanup(struct io_kiocb *req); #endif /* CONFIG_FHANDLE */ int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); -- 2.51.0