| Message ID | 20240614163047.31581-3-krisman@suse.de (mailing list archive) |
|---|---|
| State | Handled Elsewhere |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [v2,1/4] net: Split a __sys_bind helper for io_uring | expand |
From: Gabriel Krisman Bertazi <krisman@suse.de> Date: Fri, 14 Jun 2024 12:30:46 -0400 > IORING_OP_BIND provides the semantic of bind(2) via io_uring. While > this is an essentially synchronous system call, the main point is to > enable a network path to execute fully with io_uring registered and > descriptorless files. > > Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de> > > --- > changes since v1: > - drop explocit error handling for move_addr_to_kernel (jens) > - Remove empty line ahead of return; > --- > include/uapi/linux/io_uring.h | 1 + > io_uring/net.c | 36 +++++++++++++++++++++++++++++++++++ > io_uring/net.h | 3 +++ > io_uring/opdef.c | 13 +++++++++++++ > 4 files changed, 53 insertions(+) > > diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h > index 994bf7af0efe..4ef153d95c87 100644 > --- a/include/uapi/linux/io_uring.h > +++ b/include/uapi/linux/io_uring.h > @@ -257,6 +257,7 @@ enum io_uring_op { > IORING_OP_FUTEX_WAITV, > IORING_OP_FIXED_FD_INSTALL, > IORING_OP_FTRUNCATE, > + IORING_OP_BIND, > > /* this goes last, obviously */ > IORING_OP_LAST, > diff --git a/io_uring/net.c b/io_uring/net.c > index 0a48596429d9..8cbc29aff15c 100644 > --- a/io_uring/net.c > +++ b/io_uring/net.c > @@ -51,6 +51,11 @@ struct io_connect { > bool seen_econnaborted; > }; > > +struct io_bind { > + struct file *file; > + int addr_len; > +}; > + > struct io_sr_msg { > struct file *file; > union { > @@ -1715,6 +1720,37 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) > return IOU_OK; > } > > +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) > +{ > + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); > + struct sockaddr __user *uaddr; > + struct io_async_msghdr *io; > + > + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) > + return -EINVAL; > + > + uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); > + bind->addr_len = READ_ONCE(sqe->addr2); ^^ nit: double space > + > + io = io_msg_alloc_async(req); > + if (unlikely(!io)) > + return -ENOMEM; > + return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); > +} > + > +int io_bind(struct io_kiocb *req, unsigned int issue_flags) > +{ > + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); > + struct io_async_msghdr *io = req->async_data; > + int ret; > + > + ret = __sys_bind_socket(sock_from_file(req->file), &io->addr, bind->addr_len); ^^ ditto > + if (ret < 0) > + req_set_fail(req); > + io_req_set_res(req, ret, 0); > + return 0; > +} > + > void io_netmsg_cache_free(const void *entry) > { > struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; > diff --git a/io_uring/net.h b/io_uring/net.h > index 0eb1c1920fc9..49f9a7bc1113 100644 > --- a/io_uring/net.h > +++ b/io_uring/net.h > @@ -49,6 +49,9 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags); > int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); > void io_send_zc_cleanup(struct io_kiocb *req); > > +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); > +int io_bind(struct io_kiocb *req, unsigned int issue_flags); > + > void io_netmsg_cache_free(const void *entry); > #else > static inline void io_netmsg_cache_free(const void *entry) > diff --git a/io_uring/opdef.c b/io_uring/opdef.c > index 2de5cca9504e..19ee9445f024 100644 > --- a/io_uring/opdef.c > +++ b/io_uring/opdef.c > @@ -495,6 +495,16 @@ const struct io_issue_def io_issue_defs[] = { > .prep = io_ftruncate_prep, > .issue = io_ftruncate, > }, > + [IORING_OP_BIND] = { > +#if defined(CONFIG_NET) > + .needs_file = 1, > + .prep = io_bind_prep, > + .issue = io_bind, > + .async_size = sizeof(struct io_async_msghdr), > +#else > + .prep = io_eopnotsupp_prep, > +#endif > + }, > }; > > const struct io_cold_def io_cold_defs[] = { > @@ -711,6 +721,9 @@ const struct io_cold_def io_cold_defs[] = { > [IORING_OP_FTRUNCATE] = { > .name = "FTRUNCATE", > }, > + [IORING_OP_BIND] = { > + .name = "BIND", > + }, > }; > > const char *io_uring_get_opcode(u8 opcode) > -- > 2.45.2
On 6/14/24 4:46 PM, Kuniyuki Iwashima wrote: > From: Gabriel Krisman Bertazi <krisman@suse.de> > Date: Fri, 14 Jun 2024 12:30:46 -0400 >> IORING_OP_BIND provides the semantic of bind(2) via io_uring. While >> this is an essentially synchronous system call, the main point is to >> enable a network path to execute fully with io_uring registered and >> descriptorless files. >> >> Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de> >> >> --- >> changes since v1: >> - drop explocit error handling for move_addr_to_kernel (jens) >> - Remove empty line ahead of return; >> --- >> include/uapi/linux/io_uring.h | 1 + >> io_uring/net.c | 36 +++++++++++++++++++++++++++++++++++ >> io_uring/net.h | 3 +++ >> io_uring/opdef.c | 13 +++++++++++++ >> 4 files changed, 53 insertions(+) >> >> diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h >> index 994bf7af0efe..4ef153d95c87 100644 >> --- a/include/uapi/linux/io_uring.h >> +++ b/include/uapi/linux/io_uring.h >> @@ -257,6 +257,7 @@ enum io_uring_op { >> IORING_OP_FUTEX_WAITV, >> IORING_OP_FIXED_FD_INSTALL, >> IORING_OP_FTRUNCATE, >> + IORING_OP_BIND, >> >> /* this goes last, obviously */ >> IORING_OP_LAST, >> diff --git a/io_uring/net.c b/io_uring/net.c >> index 0a48596429d9..8cbc29aff15c 100644 >> --- a/io_uring/net.c >> +++ b/io_uring/net.c >> @@ -51,6 +51,11 @@ struct io_connect { >> bool seen_econnaborted; >> }; >> >> +struct io_bind { >> + struct file *file; >> + int addr_len; >> +}; >> + >> struct io_sr_msg { >> struct file *file; >> union { >> @@ -1715,6 +1720,37 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) >> return IOU_OK; >> } >> >> +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) >> +{ >> + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); >> + struct sockaddr __user *uaddr; >> + struct io_async_msghdr *io; >> + >> + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) >> + return -EINVAL; >> + >> + uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); >> + bind->addr_len = READ_ONCE(sqe->addr2); > ^^ > nit: double space Thanks for spotting those, I can just remove those two while applying. Mostly just a note to Grabriel, no need to re-post for that.
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 994bf7af0efe..4ef153d95c87 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -257,6 +257,7 @@ enum io_uring_op { IORING_OP_FUTEX_WAITV, IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, + IORING_OP_BIND, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/net.c b/io_uring/net.c index 0a48596429d9..8cbc29aff15c 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -51,6 +51,11 @@ struct io_connect { bool seen_econnaborted; }; +struct io_bind { + struct file *file; + int addr_len; +}; + struct io_sr_msg { struct file *file; union { @@ -1715,6 +1720,37 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); + struct sockaddr __user *uaddr; + struct io_async_msghdr *io; + + if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) + return -EINVAL; + + uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + bind->addr_len = READ_ONCE(sqe->addr2); + + io = io_msg_alloc_async(req); + if (unlikely(!io)) + return -ENOMEM; + return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); +} + +int io_bind(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); + struct io_async_msghdr *io = req->async_data; + int ret; + + ret = __sys_bind_socket(sock_from_file(req->file), &io->addr, bind->addr_len); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return 0; +} + void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; diff --git a/io_uring/net.h b/io_uring/net.h index 0eb1c1920fc9..49f9a7bc1113 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -49,6 +49,9 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags); int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); void io_send_zc_cleanup(struct io_kiocb *req); +int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_bind(struct io_kiocb *req, unsigned int issue_flags); + void io_netmsg_cache_free(const void *entry); #else static inline void io_netmsg_cache_free(const void *entry) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 2de5cca9504e..19ee9445f024 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -495,6 +495,16 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_ftruncate_prep, .issue = io_ftruncate, }, + [IORING_OP_BIND] = { +#if defined(CONFIG_NET) + .needs_file = 1, + .prep = io_bind_prep, + .issue = io_bind, + .async_size = sizeof(struct io_async_msghdr), +#else + .prep = io_eopnotsupp_prep, +#endif + }, }; const struct io_cold_def io_cold_defs[] = { @@ -711,6 +721,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FTRUNCATE] = { .name = "FTRUNCATE", }, + [IORING_OP_BIND] = { + .name = "BIND", + }, }; const char *io_uring_get_opcode(u8 opcode)
IORING_OP_BIND provides the semantic of bind(2) via io_uring. While this is an essentially synchronous system call, the main point is to enable a network path to execute fully with io_uring registered and descriptorless files. Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de> --- changes since v1: - drop explocit error handling for move_addr_to_kernel (jens) - Remove empty line ahead of return; --- include/uapi/linux/io_uring.h | 1 + io_uring/net.c | 36 +++++++++++++++++++++++++++++++++++ io_uring/net.h | 3 +++ io_uring/opdef.c | 13 +++++++++++++ 4 files changed, 53 insertions(+)