linux-kernel - [RFC PATCH v4 04/17] af_vsock: implement SEQPACKET receive loop

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

Message-ID: <20210207151526.804741-1-arseny.krasnov@kaspersky.com>
Date:   Sun, 7 Feb 2021 18:15:22 +0300
From:   Arseny Krasnov <arseny.krasnov@...persky.com>
To:     Stefan Hajnoczi <stefanha@...hat.com>,
        Stefano Garzarella <sgarzare@...hat.com>,
        "Michael S. Tsirkin" <mst@...hat.com>,
        Jason Wang <jasowang@...hat.com>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        Arseny Krasnov <arseny.krasnov@...persky.com>,
        Jorgen Hansen <jhansen@...are.com>,
        Colin Ian King <colin.king@...onical.com>,
        Andra Paraschiv <andraprs@...zon.com>,
        Alexander Popov <alex.popov@...ux.com>
CC:     <kvm@...r.kernel.org>, <virtualization@...ts.linux-foundation.org>,
        <netdev@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <stsp2@...dex.ru>, <oxffffaa@...il.com>
Subject: [RFC PATCH v4 04/17] af_vsock: implement SEQPACKET receive loop

This adds receive loop for SEQPACKET. It looks like receive loop for
STREAM, but there is a little bit difference:
1) It doesn't call notify callbacks.
2) It doesn't care about 'SO_SNDLOWAT' and 'SO_RCVLOWAT' values, because
   there is no sense for these values in SEQPACKET case.
3) It waits until whole record is received or error is found during
   receiving.
4) It processes and sets 'MSG_TRUNC' flag.

So to avoid extra conditions for two types of socket inside one loop, two
independent functions were created.

Signed-off-by: Arseny Krasnov <arseny.krasnov@...persky.com>
---
 include/net/af_vsock.h   |  5 +++
 net/vmw_vsock/af_vsock.c | 96 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 100 insertions(+), 1 deletion(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index b1c717286993..bb6a0e52be86 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -135,6 +135,11 @@ struct vsock_transport {
 	bool (*stream_is_active)(struct vsock_sock *);
 	bool (*stream_allow)(u32 cid, u32 port);
 
+	/* SEQ_PACKET. */
+	size_t (*seqpacket_seq_get_len)(struct vsock_sock *);
+	int (*seqpacket_dequeue)(struct vsock_sock *, struct msghdr *,
+				     int flags, bool *msg_ready);
+
 	/* Notification. */
 	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
 	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 66c8a932f49b..3d8af987216a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1977,6 +1977,97 @@ static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg,
 	return err;
 }
 
+static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
+				     size_t len, int flags)
+{
+	const struct vsock_transport *transport;
+	const struct iovec *orig_iov;
+	unsigned long orig_nr_segs;
+	bool msg_ready;
+	struct vsock_sock *vsk;
+	size_t record_len;
+	long timeout;
+	int err = 0;
+	DEFINE_WAIT(wait);
+
+	vsk = vsock_sk(sk);
+	transport = vsk->transport;
+
+	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	orig_nr_segs = msg->msg_iter.nr_segs;
+	orig_iov = msg->msg_iter.iov;
+	msg_ready = false;
+	record_len = 0;
+
+	while (1) {
+		err = vsock_wait_data(sk, &wait, timeout, NULL, 0);
+
+		if (err <= 0) {
+			/* In case of any loop break(timeout, signal
+			 * interrupt or shutdown), we report user that
+			 * nothing was copied.
+			 */
+			err = 0;
+			break;
+		}
+
+		if (record_len == 0) {
+			record_len =
+				transport->seqpacket_seq_get_len(vsk);
+
+			if (record_len == 0)
+				continue;
+		}
+
+		err = transport->seqpacket_dequeue(vsk, msg,
+					flags, &msg_ready);
+		if (err < 0) {
+			if (err == -EAGAIN) {
+				iov_iter_init(&msg->msg_iter, READ,
+					      orig_iov, orig_nr_segs,
+					      len);
+				/* Clear 'MSG_EOR' here, because dequeue
+				 * callback above set it again if it was
+				 * set by sender. This 'MSG_EOR' is from
+				 * dropped record.
+				 */
+				msg->msg_flags &= ~MSG_EOR;
+				record_len = 0;
+				continue;
+			}
+
+			err = -ENOMEM;
+			break;
+		}
+
+		if (msg_ready)
+			break;
+	}
+
+	if (sk->sk_err)
+		err = -sk->sk_err;
+	else if (sk->sk_shutdown & RCV_SHUTDOWN)
+		err = 0;
+
+	if (msg_ready) {
+		/* User sets MSG_TRUNC, so return real length of
+		 * packet.
+		 */
+		if (flags & MSG_TRUNC)
+			err = record_len;
+		else
+			err = len - msg->msg_iter.count;
+
+		/* Always set MSG_TRUNC if real length of packet is
+		 * bigger than user's buffer.
+		 */
+		if (record_len > len)
+			msg->msg_flags |= MSG_TRUNC;
+	}
+
+	return err;
+}
+
 static int
 vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			  int flags)
@@ -2032,7 +2123,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		goto out;
 	}
 
-	err = __vsock_stream_recvmsg(sk, msg, len, flags);
+	if (sk->sk_type == SOCK_STREAM)
+		err = __vsock_stream_recvmsg(sk, msg, len, flags);
+	else
+		err = __vsock_seqpacket_recvmsg(sk, msg, len, flags);
 
 out:
 	release_sock(sk);
-- 
2.25.1