io_uring: wire send zc request type

Add a new io_uring opcode IORING_OP_SENDZC. The main distinction from
IORING_OP_SEND is that the user should specify a notification slot
index in sqe::notification_idx and the buffers are safe to reuse only
when the used notification is flushed and completes.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a80387c6a68ce9cf99b3b6ef6f71068468761fb7.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index dcfc7a0..82bf299 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -66,6 +66,10 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		struct {
+			__u16	notification_idx;
+			__u16	__pad;
+		};
 	};
 	union {
 		struct {
@@ -197,6 +201,7 @@ enum io_uring_op {
 	IORING_OP_GETXATTR,
 	IORING_OP_SOCKET,
 	IORING_OP_URING_CMD,
+	IORING_OP_SENDZC_NOTIF,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
diff --git a/io_uring/net.c b/io_uring/net.c
index bbc9c60..89a8678 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -14,6 +14,7 @@
 #include "kbuf.h"
 #include "alloc_cache.h"
 #include "net.h"
+#include "notif.h"
 
 #if defined(CONFIG_NET)
 struct io_shutdown {
@@ -59,6 +60,15 @@ struct io_sr_msg {
 	unsigned int			flags;
 };
 
+struct io_sendzc {
+	struct file			*file;
+	void __user			*buf;
+	size_t				len;
+	u16				slot_idx;
+	unsigned			msg_flags;
+	unsigned			flags;
+};
+
 #define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)
 
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -834,6 +844,90 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	return ret;
 }
 
+int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sendzc *zc = io_kiocb_to_cmd(req);
+
+	if (READ_ONCE(sqe->addr2) || READ_ONCE(sqe->__pad2[0]) ||
+	    READ_ONCE(sqe->addr3))
+		return -EINVAL;
+
+	zc->flags = READ_ONCE(sqe->ioprio);
+	if (zc->flags & ~IORING_RECVSEND_POLL_FIRST)
+		return -EINVAL;
+
+	zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	zc->len = READ_ONCE(sqe->len);
+	zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
+	zc->slot_idx = READ_ONCE(sqe->notification_idx);
+	if (zc->msg_flags & MSG_DONTWAIT)
+		req->flags |= REQ_F_NOWAIT;
+#ifdef CONFIG_COMPAT
+	if (req->ctx->compat)
+		zc->msg_flags |= MSG_CMSG_COMPAT;
+#endif
+	return 0;
+}
+
+int io_sendzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_sendzc *zc = io_kiocb_to_cmd(req);
+	struct io_notif_slot *notif_slot;
+	struct io_notif *notif;
+	struct msghdr msg;
+	struct iovec iov;
+	struct socket *sock;
+	unsigned msg_flags;
+	int ret, min_ret = 0;
+
+	if (!(req->flags & REQ_F_POLLED) &&
+	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
+		return -EAGAIN;
+
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		return -EAGAIN;
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	notif_slot = io_get_notif_slot(ctx, zc->slot_idx);
+	if (!notif_slot)
+		return -EINVAL;
+	notif = io_get_notif(ctx, notif_slot);
+	if (!notif)
+		return -ENOMEM;
+
+	msg.msg_name = NULL;
+	msg.msg_control = NULL;
+	msg.msg_controllen = 0;
+	msg.msg_namelen = 0;
+
+	ret = import_single_range(WRITE, zc->buf, zc->len, &iov, &msg.msg_iter);
+	if (unlikely(ret))
+		return ret;
+
+	msg_flags = zc->msg_flags | MSG_ZEROCOPY;
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		msg_flags |= MSG_DONTWAIT;
+	if (msg_flags & MSG_WAITALL)
+		min_ret = iov_iter_count(&msg.msg_iter);
+
+	msg.msg_flags = msg_flags;
+	msg.msg_ubuf = &notif->uarg;
+	msg.sg_from_iter = NULL;
+	ret = sock_sendmsg(sock, &msg);
+
+	if (unlikely(ret < min_ret)) {
+		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
+			return -EAGAIN;
+		return ret == -ERESTARTSYS ? -EINTR : ret;
+	}
+
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
+
 int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_accept *accept = io_kiocb_to_cmd(req);
diff --git a/io_uring/net.h b/io_uring/net.h
index db20ce9..7c438d3 100644
--- a/io_uring/net.h
+++ b/io_uring/net.h
@@ -52,6 +52,9 @@ int io_connect_prep_async(struct io_kiocb *req);
 int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_connect(struct io_kiocb *req, unsigned int issue_flags);
 
+int io_sendzc(struct io_kiocb *req, unsigned int issue_flags);
+int io_sendzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
 void io_netmsg_cache_free(struct io_cache_entry *entry);
 #else
 static inline void io_netmsg_cache_free(struct io_cache_entry *entry)
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index a7b84b43..7ab19bb 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -470,6 +470,21 @@ const struct io_op_def io_op_defs[] = {
 		.issue			= io_uring_cmd,
 		.prep_async		= io_uring_cmd_prep_async,
 	},
+	[IORING_OP_SENDZC_NOTIF] = {
+		.name			= "SENDZC_NOTIF",
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_sendzc_prep,
+		.issue			= io_sendzc,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)