Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.32 as permitted sender) client-ip=23.128.96.32;
From:   Arseniy Krasnov <avkrasnov@salutedevices.com>
To:     Stefan Hajnoczi <stefanha@redhat.com>,
        Stefano Garzarella <sgarzare@redhat.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        "Michael S. Tsirkin" <mst@redhat.com>,
        Jason Wang <jasowang@redhat.com>,
        Bobby Eshleman <bobby.eshleman@bytedance.com>
CC:     <kvm@vger.kernel.org>, <virtualization@lists.linux-foundation.org>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <kernel@sberdevices.ru>, <oxffffaa@gmail.com>,
        <avkrasnov@salutedevices.com>
Subject: [PATCH net-next v2 08/12] vsock: enable setting SO_ZEROCOPY
Date:   Sun, 1 Oct 2023 00:03:04 +0300
Message-ID: <20230930210308.2394919-9-avkrasnov@salutedevices.com>
In-Reply-To: <20230930210308.2394919-1-avkrasnov@salutedevices.com>
References: <20230930210308.2394919-1-avkrasnov@salutedevices.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
Precedence: bulk

For AF_VSOCK, zerocopy tx mode depends on transport, so this option must
be set in AF_VSOCK implementation where transport is accessible (if
transport is not set during setting SO_ZEROCOPY: for example socket is
not connected, then SO_ZEROCOPY will be enabled, but once transport will
be assigned, support of this type of transmission will be checked).

To handle SO_ZEROCOPY, AF_VSOCK implementation uses SOCK_CUSTOM_SOCKOPT
bit, thus handling SOL_SOCKET option operations, but all of them except
SO_ZEROCOPY will be forwarded to the generic handler by calling
'sock_setsockopt()'.

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
---
 Changelog:
 v1 -> v2:
  * Place 'sock_valbool_flag()' in a single line.

 net/vmw_vsock/af_vsock.c | 45 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 43 insertions(+), 2 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ff44bab05191..a84f242466cf 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1406,8 +1406,16 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 			goto out;
 		}
 
-		if (vsock_msgzerocopy_allow(transport))
+		if (vsock_msgzerocopy_allow(transport)) {
 			set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+		} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+			/* If this option was set before 'connect()',
+			 * when transport was unknown, check that this
+			 * feature is supported here.
+			 */
+			err = -EOPNOTSUPP;
+			goto out;
+		}
 
 		err = vsock_auto_bind(vsk);
 		if (err)
@@ -1643,7 +1651,7 @@ static int vsock_connectible_setsockopt(struct socket *sock,
 	const struct vsock_transport *transport;
 	u64 val;
 
-	if (level != AF_VSOCK)
+	if (level != AF_VSOCK && level != SOL_SOCKET)
 		return -ENOPROTOOPT;
 
 #define COPY_IN(_v)                                       \
@@ -1666,6 +1674,33 @@ static int vsock_connectible_setsockopt(struct socket *sock,
 
 	transport = vsk->transport;
 
+	if (level == SOL_SOCKET) {
+		int zerocopy;
+
+		if (optname != SO_ZEROCOPY) {
+			release_sock(sk);
+			return sock_setsockopt(sock, level, optname, optval, optlen);
+		}
+
+		/* Use 'int' type here, because variable to
+		 * set this option usually has this type.
+		 */
+		COPY_IN(zerocopy);
+
+		if (zerocopy < 0 || zerocopy > 1) {
+			err = -EINVAL;
+			goto exit;
+		}
+
+		if (transport && !vsock_msgzerocopy_allow(transport)) {
+			err = -EOPNOTSUPP;
+			goto exit;
+		}
+
+		sock_valbool_flag(sk, SOCK_ZEROCOPY, zerocopy);
+		goto exit;
+	}
+
 	switch (optname) {
 	case SO_VM_SOCKETS_BUFFER_SIZE:
 		COPY_IN(val);
@@ -2322,6 +2357,12 @@ static int vsock_create(struct net *net, struct socket *sock,
 		}
 	}
 
+	/* SOCK_DGRAM doesn't have 'setsockopt' callback set in its
+	 * proto_ops, so there is no handler for custom logic.
+	 */
+	if (sock_type_connectible(sock->type))
+		set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
+
 	vsock_insert_unbound(vsk);
 
 	return 0;
-- 
2.25.1