io_uring: add support for sendmsg()

commit 0fa03c624d8fc9932d0f27c39a9deca6a37e0e17 upstream.

This is done through IORING_OP_SENDMSG. There's a new sqe->msg_flags
for the flags argument, and the msghdr struct is passed in the
sqe->addr field.

We use MSG_DONTWAIT to force an inline fast path if sendmsg() doesn't
block, and punt to async execution if it would have.
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NJoseph Qi <joseph.qi@linux.alibaba.com>
Reviewed-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>

fs/io_uring.c

@@ -1388,6 +1388,43 @@ static int io_sync_file_range(struct io_kiocb *req,
 	return 0;
 }
 
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	struct socket *sock;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
+	sock = sock_from_file(req->file, &ret);
+	if (sock) {
+		struct user_msghdr __user *msg;
+		unsigned flags;
+
+		flags = READ_ONCE(sqe->msg_flags);
+		if (flags & MSG_DONTWAIT)
+			req->flags |= REQ_F_NOWAIT;
+		else if (force_nonblock)
+			flags |= MSG_DONTWAIT;
+
+		msg = (struct user_msghdr __user *) (unsigned long)
+			READ_ONCE(sqe->addr);
+
+		ret = __sys_sendmsg_sock(sock, msg, flags);
+		if (force_nonblock && ret == -EAGAIN)
+			return ret;
+	}
+
+	io_cqring_add_event(req->ctx, sqe->user_data, ret);
+	io_put_req(req);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
 static void io_poll_remove_one(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = &req->poll;
@@ -1673,6 +1710,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_SYNC_FILE_RANGE:
 		ret = io_sync_file_range(req, s->sqe, force_nonblock);
 		break;
+	case IORING_OP_SENDMSG:
+		ret = io_sendmsg(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

include/linux/socket.h

@@ -12,6 +12,7 @@
 
 struct pid;
 struct cred;
+struct socket;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -362,6 +363,9 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen
 extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
 			  unsigned int vlen, unsigned int flags,
 			  bool forbid_cmsg_compat);
+extern long __sys_sendmsg_sock(struct socket *sock,
+			       struct user_msghdr __user *msg,
+			       unsigned int flags);
 
 /* helpers which do the actual work for syscalls */
 extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,

include/uapi/linux/io_uring.h

@@ -27,6 +27,7 @@ struct io_uring_sqe {
 		__u32		fsync_flags;
 		__u16		poll_events;
 		__u32		sync_range_flags;
+		__u32		msg_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
@@ -58,6 +59,7 @@ struct io_uring_sqe {
 #define IORING_OP_POLL_ADD	6
 #define IORING_OP_POLL_REMOVE	7
 #define IORING_OP_SYNC_FILE_RANGE	8
+#define IORING_OP_SENDMSG	9
 
 /*
  * sqe->fsync_flags

net/socket.c

@@ -2136,6 +2136,13 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
 /*
  *	BSD sendmsg interface
  */
+long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0);
+}
 
 long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)