diff options
| author | David Wei <dw@davidwei.uk> | 2025-02-23 20:13:18 -0800 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2025-02-24 12:55:58 -0700 |
| commit | 6699ec9a23f85f1764183430209c741847c45f12 (patch) | |
| tree | 5d511cfcbffe1ae674a5e4000d7a68d67a5ad3ec /io_uring/net.c | |
| parent | 92ade52f26555f15880b42405e35f0cfbb8ea7db (diff) | |
io_uring/zcrx: add a read limit to recvzc requests
Currently multishot recvzc requests have no read limit and will remain
active so as long as the socket remains open. But, there are sometimes a
need to do a fixed length read e.g. peeking at some data in the socket.
Add a length limit to recvzc requests `len`. A value of 0 means no limit
which is the previous behaviour. A positive value N specifies how many
bytes to read from the socket.
Data will still be posted in aux completions, as before. This could be
split across multiple frags. But the primary recvzc request will now
complete once N bytes have been read. The completion of the recvzc
request will have res and cflags both set to 0.
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/20250224041319.2389785-2-dw@davidwei.uk
[axboe: fixup io_zcrx_recv() for !CONFIG_NET]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'io_uring/net.c')
| -rw-r--r-- | io_uring/net.c | 16 |
1 files changed, 13 insertions, 3 deletions
diff --git a/io_uring/net.c b/io_uring/net.c index 000dc70d08d0..4850d4d898f9 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -94,6 +94,7 @@ struct io_recvzc { struct file *file; unsigned msg_flags; u16 flags; + u32 len; struct io_zcrx_ifq *ifq; }; @@ -1241,7 +1242,7 @@ int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) unsigned ifq_idx; if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr || - sqe->len || sqe->addr3)) + sqe->addr3)) return -EINVAL; ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx); @@ -1250,7 +1251,7 @@ int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) zc->ifq = req->ctx->ifq; if (!zc->ifq) return -EINVAL; - + zc->len = READ_ONCE(sqe->len); zc->flags = READ_ONCE(sqe->ioprio); zc->msg_flags = READ_ONCE(sqe->msg_flags); if (zc->msg_flags) @@ -1270,6 +1271,7 @@ int io_recvzc(struct io_kiocb *req, unsigned int issue_flags) { struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc); struct socket *sock; + unsigned int len; int ret; if (!(req->flags & REQ_F_POLLED) && @@ -1280,8 +1282,16 @@ int io_recvzc(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!sock)) return -ENOTSOCK; + len = zc->len; ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT, - issue_flags); + issue_flags, &zc->len); + if (len && zc->len == 0) { + io_req_set_res(req, 0, 0); + + if (issue_flags & IO_URING_F_MULTISHOT) + return IOU_STOP_MULTISHOT; + return IOU_OK; + } if (unlikely(ret <= 0) && ret != -EAGAIN) { if (ret == -ERESTARTSYS) ret = -EINTR; |