Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Arseny Krasnov <arseny.krasnov@kaspersky.com>
To:     Stefan Hajnoczi <stefanha@redhat.com>,
        Stefano Garzarella <sgarzare@redhat.com>,
        "Michael S. Tsirkin" <mst@redhat.com>,
        Jason Wang <jasowang@redhat.com>,
        "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Arseny Krasnov <arseny.krasnov@kaspersky.com>,
        Jorgen Hansen <jhansen@vmware.com>,
        Colin Ian King <colin.king@canonical.com>,
        Norbert Slusarek <nslusarek@gmx.net>,
        Andra Paraschiv <andraprs@amazon.com>
CC:     <kvm@vger.kernel.org>, <virtualization@lists.linux-foundation.org>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <stsp2@yandex.ru>, <oxffffaa@gmail.com>
Subject: [RFC PATCH v6 04/22] af_vsock: implement SEQPACKET receive loop
Date:   Sun, 7 Mar 2021 20:59:45 +0300
Message-ID: <20210307175948.3464885-1-arseny.krasnov@kaspersky.com>
In-Reply-To: <20210307175722.3464068-1-arseny.krasnov@kaspersky.com>
References: <20210307175722.3464068-1-arseny.krasnov@kaspersky.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-KSE-AttachmentFiltering-Interceptor-Info: no applicable attachment filtering
 rules found
X-KSE-Antivirus-Interceptor-Info: scan successful
X-KSE-Antivirus-Info: Clean, bases: 07.03.2021 15:50:00
X-KSE-BulkMessagesFiltering-Scan-Result: InTheLimit
X-KSE-AttachmentFiltering-Interceptor-Info: no applicable attachment filtering
 rules found
X-KSE-BulkMessagesFiltering-Scan-Result: InTheLimit
X-KLMS-Rule-ID: 52
X-KLMS-Message-Action: clean
X-KLMS-AntiSpam-Status: not scanned, disabled by settings
X-KLMS-AntiSpam-Interceptor-Info: not scanned
X-KLMS-AntiPhishing: Clean, bases: 2021/03/07 17:11:00
X-KLMS-AntiVirus: Kaspersky Security for Linux Mail Server, version 8.0.3.30, bases: 2021/03/07 15:50:00 #16360637
X-KLMS-AntiVirus-Status: Clean, skipped
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

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@kaspersky.com>
---
 include/net/af_vsock.h   |  5 +++
 net/vmw_vsock/af_vsock.c | 95 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 99 insertions(+), 1 deletion(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index b1c717286993..5ad7ee7f78fd 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 *vsk);
+	int (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
+				 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 0bc661e54262..ac2f69362f2e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1973,6 +1973,96 @@ 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)
@@ -2028,7 +2118,10 @@ 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