io_uring_prep_send_zc(3)

💖 io_uring_prep_send_zc — the zerocopy send glow-up 💖

okay bestie, this one lives in the liburing manual, and it's genuinely one of my faves. it's io_uring_prep_send_zc(3) and it's giving zerocopy send energy. let's get into it 🦋

---

✨ NAME ✨

io_uring_prep_send_zc — prepare a zerocopy send request

---

🌸 SYNOPSIS 🌸

#include <liburing.h>

void io_uring_prep_send_zc(struct io_uring_sqe *sqe,
                           int sockfd,
                           const void *buf,
                           size_t len,
                           int flags,
                           unsigned zc_flags);

void io_uring_prep_send_zc_fixed(struct io_uring_sqe *sqe,
                                 int sockfd,
                                 const void *buf,
                                 size_t len,
                                 int flags,
                                 unsigned zc_flags);
                                 unsigned buf_index);

yes that stray unsigned buf_index); line is exactly how it appears. we don't fix the source material, we respect it 💅

---

🎀 DESCRIPTION 🎀

So. io_uring_prep_send_zc(3) prepares a zerocopy send request. The submission queue entry sqe gets set up to use the file descriptor sockfd to start sending the data from buf of size len bytes, with send modifier flags flags and zerocopy modifier flags zc_flags. like, that's the whole vibe. 🔥

io_uring_prep_send_zc_fixed(3) is literally the same thing, no cap — except it requires buffers that have been registered with io_uring_register_buffers(3). The buf and len arguments must fall within a region specified by buf_index in the previously registered buffer. And good news bestie: the buffer does not need to be aligned with the start of the registered buffer. slay 🫶

Now, the flags. Go read io_uring_prep_send(3) for a description of the flags you can set in the SQE ioprio field, because we're not repeating all of that here. BUT — on top of those, the zero-copy send also supports setting IORING_SEND_ZC_REPORT_USAGE. If it's set, the notification CQE res field will report the number of bytes that were copied rather than sent with zero copy. A value of 0 indicates success. And if the value is IORING_NOTIF_USAGE_ZC_COPIED, then data was copied. noted 📝

Here's the iconic part that makes this different from a regular send, and you need to internalise it: as opposed to non-zerocopy send requests, a zerocopy send will usually generate two CQEs. The first CQE holds the result of the send operation itself, and if that CQE has IORING_CQE_F_MORE set in the CQE flags field, then a second notification CQE will be posted for the operation. That second notification tells the application that the memory associated with the send is safe to get reused. The second CQE will have IORING_CQE_F_NOTIF set in the CQE flags field. Also go see the io_uring_enter(2) man page for a fuller description of the notification CQE, iykyk 💜

⚠️ heads up: using IOSQE_IO_LINK with this request type requires the setting of MSG_WAITALL in the flags argument, because a short send isn't considered an error condition without that being set. don't skip this one, bestie, it will bite you 😭

These functions prepare an async zerocopy send(2) request. See that man page for details. For details on the zerocopy nature of it, see io_uring_enter(2). go read, it's worth it 🌈

---

💫 RETURN VALUE 💫

None. that's it. that's the answer. 💀

---

🦋 ERRORS 🦋

The CQE res field will contain the result of the operation. See the related man page for details on possible values. And listen — where synchronous system calls will return -1 on failure and set errno to the actual error value, io_uring never uses errno. Instead it returns the negated errno directly in the CQE res field. periodt. 👑

Some common error cases are:

• -ENOMEM — the ulimit(1) -l setting is too low to support the size of the attempted zero copy send. Increasing the limit may help.
• -ENOMEM — the kernel ran out of memory.

and yes, it's listed twice in the source. two separate entries, both real, both staying. we don't erase the lore 🙈

---

🌟 SEE ALSO 🌟

• io_uring_get_sqe(3)
• io_uring_submit(3)
• io_uring_prep_send(3)
• io_uring_enter(2)
• send(2)

---

okay that's the whole page, you're so welcome 💖 this one's from liburing-2.3, dated September 6, 2022. go forth and zerocopy responsibly, bestie — mwah 🎀✨🦋