Merge tag 'for-5.19/io_uring-net-2022-05-22' of git://git.kernel.dk/linux-block

Pull io_uring 'more data in socket' support from Jens Axboe:
 "To be able to fully utilize the 'poll first' support in the core
  io_uring branch, it's advantageous knowing if the socket was empty
  after a receive. This adds support for that"

* tag 'for-5.19/io_uring-net-2022-05-22' of git://git.kernel.dk/linux-block:
  io_uring: return hint on whether more data is available after receive
  tcp: pass back data left in socket after receive

fs/io_uring.c

@@ -6115,6 +6115,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	struct io_async_msghdr iomsg, *kmsg;
 	struct io_sr_msg *sr = &req->sr_msg;
 	struct socket *sock;
+	unsigned int cflags;
 	unsigned flags;
 	int ret, min_ret = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
@@ -6154,6 +6155,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	if (flags & MSG_WAITALL)
 		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
 
+	kmsg->msg.msg_get_inq = 1;
 	ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags);
 	if (ret < min_ret) {
 		if (ret == -EAGAIN && force_nonblock)
@@ -6178,7 +6180,10 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 		ret += sr->done_io;
 	else if (sr->done_io)
 		ret = sr->done_io;
-	__io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags));
+	cflags = io_put_kbuf(req, issue_flags);
+	if (kmsg->msg.msg_inq)
+		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
+	__io_req_complete(req, issue_flags, ret, cflags);
 	return 0;
 }
 
@@ -6188,6 +6193,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	struct msghdr msg;
 	struct socket *sock;
 	struct iovec iov;
+	unsigned int cflags;
 	unsigned flags;
 	int ret, min_ret = 0;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
@@ -6214,11 +6220,12 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 		goto out_free;
 
 	msg.msg_name = NULL;
+	msg.msg_namelen = 0;
 	msg.msg_control = NULL;
+	msg.msg_get_inq = 1;
+	msg.msg_flags = 0;
 	msg.msg_controllen = 0;
-	msg.msg_namelen = 0;
 	msg.msg_iocb = NULL;
-	msg.msg_flags = 0;
 
 	flags = sr->msg_flags;
 	if (force_nonblock)
@@ -6249,7 +6256,10 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 		ret += sr->done_io;
 	else if (sr->done_io)
 		ret = sr->done_io;
-	__io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags));
+	cflags = io_put_kbuf(req, issue_flags);
+	if (msg.msg_inq)
+		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
+	__io_req_complete(req, issue_flags, ret, cflags);
 	return 0;
 }
 

include/linux/socket.h

@@ -50,6 +50,9 @@ struct linger {
 struct msghdr {
 	void		*msg_name;	/* ptr to socket address structure */
 	int		msg_namelen;	/* size of socket address structure */
+
+	int		msg_inq;	/* output, data left in socket */
+
 	struct iov_iter	msg_iter;	/* data */
 
 	/*
@@ -62,8 +65,9 @@ struct msghdr {
 		void __user	*msg_control_user;
 	};
 	bool		msg_control_is_user : 1;
-	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
+	bool		msg_get_inq : 1;/* return INQ after receive */
 	unsigned int	msg_flags;	/* flags on received message */
+	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
 };
 

include/uapi/linux/io_uring.h

@@ -258,9 +258,11 @@ struct io_uring_cqe {
  *
  * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
  * IORING_CQE_F_MORE	If set, parent SQE will generate more CQE entries
+ * IORING_CQE_F_SOCK_NONEMPTY	If set, more data to read after socket recv
  */
 #define IORING_CQE_F_BUFFER		(1U << 0)
 #define IORING_CQE_F_MORE		(1U << 1)
+#define IORING_CQE_F_SOCK_NONEMPTY	(1U << 2)
 
 enum {
 	IORING_CQE_BUFFER_SHIFT		= 16,

net/ipv4/tcp.c

@@ -2335,8 +2335,10 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	if (tp->recvmsg_inq)
+	if (tp->recvmsg_inq) {
 		*cmsg_flags = TCP_CMSG_INQ;
+		msg->msg_get_inq = 1;
+	}
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	/* Urgent data needs to be handled specially. */
@@ -2559,7 +2561,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 		int flags, int *addr_len)
 {
-	int cmsg_flags = 0, ret, inq;
+	int cmsg_flags = 0, ret;
 	struct scm_timestamping_internal tss;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
@@ -2576,12 +2578,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	release_sock(sk);
 	sk_defer_free_flush(sk);
 
-	if (cmsg_flags && ret >= 0) {
+	if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
 		if (cmsg_flags & TCP_CMSG_TS)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (cmsg_flags & TCP_CMSG_INQ) {
-			inq = tcp_inq_hint(sk);
-			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+		if (msg->msg_get_inq) {
+			msg->msg_inq = tcp_inq_hint(sk);
+			if (cmsg_flags & TCP_CMSG_INQ)
+				put_cmsg(msg, SOL_TCP, TCP_CM_INQ,
+					 sizeof(msg->msg_inq), &msg->msg_inq);
 		}
 	}
 	return ret;