diff options
author | Jens Axboe <axboe@kernel.dk> | 2024-02-19 10:46:44 -0700 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2024-04-22 11:25:56 -0600 |
commit | ac5f71a3d9d7eb540f6bf7e794eb4a3e4c3f11dd (patch) | |
tree | 7360167d540a3da389a0e5577084b731f1777c6c /io_uring | |
parent | 3e747dedd47b6250390abfc08dc0aa4817d3c052 (diff) |
io_uring/net: add provided buffer support for IORING_OP_SEND
It's pretty trivial to wire up provided buffer support for the send
side, just like how it's done the receive side. This enables setting up
a buffer ring that an application can use to push pending sends to,
and then have a send pick a buffer from that ring.
One of the challenges with async IO and networking sends is that you
can get into reordering conditions if you have more than one inflight
at the same time. Consider the following scenario where everything is
fine:
1) App queues sendA for socket1
2) App queues sendB for socket1
3) App does io_uring_submit()
4) sendA is issued, completes successfully, posts CQE
5) sendB is issued, completes successfully, posts CQE
All is fine. Requests are always issued in-order, and both complete
inline as most sends do.
However, if we're flooding socket1 with sends, the following could
also result from the same sequence:
1) App queues sendA for socket1
2) App queues sendB for socket1
3) App does io_uring_submit()
4) sendA is issued, socket1 is full, poll is armed for retry
5) Space frees up in socket1, this triggers sendA retry via task_work
6) sendB is issued, completes successfully, posts CQE
7) sendA is retried, completes successfully, posts CQE
Now we've sent sendB before sendA, which can make things unhappy. If
both sendA and sendB had been using provided buffers, then it would look
as follows instead:
1) App queues dataA for sendA, queues sendA for socket1
2) App queues dataB for sendB queues sendB for socket1
3) App does io_uring_submit()
4) sendA is issued, socket1 is full, poll is armed for retry
5) Space frees up in socket1, this triggers sendA retry via task_work
6) sendB is issued, picks first buffer (dataA), completes successfully,
posts CQE (which says "I sent dataA")
7) sendA is retried, picks first buffer (dataB), completes successfully,
posts CQE (which says "I sent dataB")
Now we've sent the data in order, and everybody is happy.
It's worth noting that this also opens the door for supporting multishot
sends, as provided buffers would be a prerequisite for that. Those can
trigger either when new buffers are added to the outgoing ring, or (if
stalled due to lack of space) when space frees up in the socket.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'io_uring')
-rw-r--r-- | io_uring/net.c | 25 | ||||
-rw-r--r-- | io_uring/opdef.c | 1 |
2 files changed, 21 insertions, 5 deletions
diff --git a/io_uring/net.c b/io_uring/net.c index dc310f0bfe4c..13685d133582 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -364,10 +364,12 @@ static int io_send_setup(struct io_kiocb *req) kmsg->msg.msg_name = &kmsg->addr; kmsg->msg.msg_namelen = sr->addr_len; } - ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter); - if (unlikely(ret < 0)) - return ret; - + if (!io_do_buffer_select(req)) { + ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, + &kmsg->msg.msg_iter); + if (unlikely(ret < 0)) + return ret; + } return 0; } @@ -480,6 +482,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); struct io_async_msghdr *kmsg = req->async_data; struct socket *sock; + unsigned int cflags; unsigned flags; int min_ret = 0; int ret; @@ -492,6 +495,17 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return -EAGAIN; + if (io_do_buffer_select(req)) { + size_t len = sr->len; + void __user *buf; + + buf = io_buffer_select(req, &len, issue_flags); + if (unlikely(!buf)) + return -ENOBUFS; + sr->buf = buf; + sr->len = len; + } + flags = sr->msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; @@ -521,7 +535,8 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) else if (sr->done_io) ret = sr->done_io; io_req_msg_cleanup(req, issue_flags); - io_req_set_res(req, ret, 0); + cflags = io_put_kbuf(req, issue_flags); + io_req_set_res(req, ret, cflags); return IOU_OK; } diff --git a/io_uring/opdef.c b/io_uring/opdef.c index a16f73938ebb..2de5cca9504e 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -281,6 +281,7 @@ const struct io_issue_def io_issue_defs[] = { .pollout = 1, .audit_skip = 1, .ioprio = 1, + .buffer_select = 1, #if defined(CONFIG_NET) .async_size = sizeof(struct io_async_msghdr), .prep = io_sendmsg_prep, |