io_uring: add support for recvmsg()

commit aa1fa28fc73ea6b740ee7b62bf3b07141883dbb8 upstream.

This is done through IORING_OP_RECVMSG. This opcode uses the same
sqe->msg_flags that IORING_OP_SENDMSG added, and we pass in the
msghdr struct in the sqe->addr field as well.

We use MSG_DONTWAIT to force an inline fast path if recvmsg() 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

@@ -1388,10 +1388,12 @@ 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)
+static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+			   bool force_nonblock,
+		   long (*fn)(struct socket *, struct user_msghdr __user *,
+				unsigned int))
+{
 	struct socket *sock;
 	int ret;
 
@@ -1412,7 +1414,7 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		msg = (struct user_msghdr __user *) (unsigned long)
 			READ_ONCE(sqe->addr);
 
-		ret = __sys_sendmsg_sock(sock, msg, flags);
+		ret = fn(sock, msg, flags);
 		if (force_nonblock && ret == -EAGAIN)
 			return ret;
 	}
@@ -1420,6 +1422,24 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	io_cqring_add_event(req->ctx, sqe->user_data, ret);
 	io_put_req(req);
 	return 0;
+}
+#endif
+
+static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	return io_send_recvmsg(req, sqe, force_nonblock, __sys_sendmsg_sock);
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	return io_send_recvmsg(req, sqe, force_nonblock, __sys_recvmsg_sock);
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -1713,6 +1733,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_SENDMSG:
 		ret = io_sendmsg(req, s->sqe, force_nonblock);
 		break;
+	case IORING_OP_RECVMSG:
+		ret = io_recvmsg(req, s->sqe, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

include/linux/socket.h

@@ -366,6 +366,9 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
 extern long __sys_sendmsg_sock(struct socket *sock,
 			       struct user_msghdr __user *msg,
 			       unsigned int flags);
+extern long __sys_recvmsg_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

@@ -60,6 +60,7 @@ struct io_uring_sqe {
 #define IORING_OP_POLL_REMOVE	7
 #define IORING_OP_SYNC_FILE_RANGE	8
 #define IORING_OP_SENDMSG	9
+#define IORING_OP_RECVMSG	10
 
 /*
  * sqe->fsync_flags

net/socket.c

@@ -2317,6 +2317,14 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
  *	BSD recvmsg interface
  */
 
+long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *msg,
+			unsigned int flags)
+{
+	struct msghdr msg_sys;
+
+	return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0);
+}
+
 long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
 		   bool forbid_cmsg_compat)
 {