netdev - [PATCH v3] tcp: pass back data left in socket after receive

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <650c22ca-cffc-0255-9a05-2413a1e20826@kernel.dk>
Date:   Thu, 28 Apr 2022 18:45:06 -0600
From:   Jens Axboe <axboe@...nel.dk>
To:     netdev <netdev@...r.kernel.org>
Cc:     Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Neal Cardwell <ncardwell@...gle.com>
Subject: [PATCH v3] tcp: pass back data left in socket after receive

This is currently done for CMSG_INQ, add an ability to do so via struct
msghdr as well and have CMSG_INQ use that too. If the caller sets
msghdr->msg_get_inq, then we'll pass back the hint in msghdr->msg_inq.

Rearrange struct msghdr a bit so we can add this member while shrinking
it at the same time. On a 64-bit build, it was 96 bytes before this
change and 88 bytes afterwards.

Reviewed-by: Eric Dumazet <edumazet@...gle.com>
Signed-off-by: Jens Axboe <axboe@...nel.dk>
---

v3: - put TP_CMSG_INQ branch inside msg->msg_get_inq
    - Add Eric's Reviewed-by

 include/linux/socket.h |  6 +++++-
 net/ipv4/tcp.c         | 16 ++++++++++------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6f85f5d957ef..12085c9a8544 100644
--- a/include/linux/socket.h
+++ b/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 */
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index db55af9eb37b..b44fde435bd1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2314,8 +2314,10 @@ 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, flags & MSG_DONTWAIT);
 
 	/* Urgent data needs to be handled specially. */
@@ -2537,7 +2539,7 @@ 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 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))
@@ -2552,12 +2554,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 	ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags);
 	release_sock(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;
-- 
2.35.1

-- 
Jens Axboe