Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Bobby Eshleman <bobby.eshleman@bytedance.com>
Date:   Wed, 19 Jul 2023 00:50:13 +0000
Subject: [PATCH RFC net-next v5 09/14] virtio/vsock: add common datagram
 recv path
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Message-Id: <20230413-b4-vsock-dgram-v5-9-581bd37fdb26@bytedance.com>
References: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
To:     Stefan Hajnoczi <stefanha@redhat.com>,
        Stefano Garzarella <sgarzare@redhat.com>,
        "Michael S. Tsirkin" <mst@redhat.com>,
        Jason Wang <jasowang@redhat.com>,
        Xuan Zhuo <xuanzhuo@linux.alibaba.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        "K. Y. Srinivasan" <kys@microsoft.com>,
        Haiyang Zhang <haiyangz@microsoft.com>,
        Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.com>,
        Bryan Tan <bryantan@vmware.com>,
        Vishnu Dasa <vdasa@vmware.com>,
        VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
Cc:     Dan Carpenter <dan.carpenter@linaro.org>,
        Simon Horman <simon.horman@corigine.com>,
        Krasnov Arseniy <oxffffaa@gmail.com>, kvm@vger.kernel.org,
        virtualization@lists.linux-foundation.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-hyperv@vger.kernel.org,
        bpf@vger.kernel.org, Bobby Eshleman <bobby.eshleman@bytedance.com>
Precedence: bulk

This commit adds the common datagram receive functionality for virtio
transports. It does not add the vhost/virtio users of that
functionality.

This functionality includes:
- changes to the virtio_transport_recv_pkt() path for finding the
  bound socket receiver for incoming packets.
- a virtio_transport_dgram_addr_init() function to be used as the
  ->dgram_addr_init callback for initializing sockaddr_vm inside
  the generic recvmsg() caller.

Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
 include/linux/virtio_vsock.h            |  2 +
 net/vmw_vsock/virtio_transport_common.c | 92 ++++++++++++++++++++++++++++-----
 2 files changed, 81 insertions(+), 13 deletions(-)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 7632552bee58..b3856b8a42b3 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -212,6 +212,8 @@ u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
 bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
 bool virtio_transport_stream_allow(u32 cid, u32 port);
 bool virtio_transport_dgram_allow(u32 cid, u32 port);
+void virtio_transport_dgram_addr_init(struct sk_buff *skb,
+				      struct sockaddr_vm *addr);
 
 int virtio_transport_connect(struct vsock_sock *vsk);
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 3bfaff758433..96118e258097 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -183,7 +183,9 @@ EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
 
 static u16 virtio_transport_get_type(struct sock *sk)
 {
-	if (sk->sk_type == SOCK_STREAM)
+	if (sk->sk_type == SOCK_DGRAM)
+		return VIRTIO_VSOCK_TYPE_DGRAM;
+	else if (sk->sk_type == SOCK_STREAM)
 		return VIRTIO_VSOCK_TYPE_STREAM;
 	else
 		return VIRTIO_VSOCK_TYPE_SEQPACKET;
@@ -1184,6 +1186,35 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk,
 		kfree_skb(skb);
 }
 
+static void
+virtio_transport_dgram_kfree_skb(struct sk_buff *skb, int err)
+{
+	if (err == -ENOMEM)
+		kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_RCVBUFF);
+	else if (err == -ENOBUFS)
+		kfree_skb_reason(skb, SKB_DROP_REASON_PROTO_MEM);
+	else
+		kfree_skb(skb);
+}
+
+/* This function takes ownership of the skb.
+ *
+ * It either places the skb on the sk_receive_queue or frees it.
+ */
+static void
+virtio_transport_recv_dgram(struct sock *sk, struct sk_buff *skb)
+{
+	int err;
+
+	err = sock_queue_rcv_skb(sk, skb);
+	if (err) {
+		virtio_transport_dgram_kfree_skb(skb, err);
+		return;
+	}
+
+	sk->sk_data_ready(sk);
+}
+
 static int
 virtio_transport_recv_connected(struct sock *sk,
 				struct sk_buff *skb)
@@ -1347,7 +1378,8 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
 static bool virtio_transport_valid_type(u16 type)
 {
 	return (type == VIRTIO_VSOCK_TYPE_STREAM) ||
-	       (type == VIRTIO_VSOCK_TYPE_SEQPACKET);
+	       (type == VIRTIO_VSOCK_TYPE_SEQPACKET) ||
+	       (type == VIRTIO_VSOCK_TYPE_DGRAM);
 }
 
 /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
@@ -1361,40 +1393,52 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 	struct vsock_sock *vsk;
 	struct sock *sk;
 	bool space_available;
+	u16 type;
 
 	vsock_addr_init(&src, le64_to_cpu(hdr->src_cid),
 			le32_to_cpu(hdr->src_port));
 	vsock_addr_init(&dst, le64_to_cpu(hdr->dst_cid),
 			le32_to_cpu(hdr->dst_port));
 
+	type = le16_to_cpu(hdr->type);
+
 	trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
 					dst.svm_cid, dst.svm_port,
 					le32_to_cpu(hdr->len),
-					le16_to_cpu(hdr->type),
+					type,
 					le16_to_cpu(hdr->op),
 					le32_to_cpu(hdr->flags),
 					le32_to_cpu(hdr->buf_alloc),
 					le32_to_cpu(hdr->fwd_cnt));
 
-	if (!virtio_transport_valid_type(le16_to_cpu(hdr->type))) {
+	if (!virtio_transport_valid_type(type)) {
 		(void)virtio_transport_reset_no_sock(t, skb);
 		goto free_pkt;
 	}
 
-	/* The socket must be in connected or bound table
-	 * otherwise send reset back
+	/* For stream/seqpacket, the socket must be in connected or bound table
+	 * otherwise send reset back.
+	 *
+	 * For datagrams, no reset is sent back.
 	 */
 	sk = vsock_find_connected_socket(&src, &dst);
 	if (!sk) {
-		sk = vsock_find_bound_socket(&dst);
-		if (!sk) {
-			(void)virtio_transport_reset_no_sock(t, skb);
-			goto free_pkt;
+		if (type == VIRTIO_VSOCK_TYPE_DGRAM) {
+			sk = vsock_find_bound_dgram_socket(&dst);
+			if (!sk)
+				goto free_pkt;
+		} else {
+			sk = vsock_find_bound_socket(&dst);
+			if (!sk) {
+				(void)virtio_transport_reset_no_sock(t, skb);
+				goto free_pkt;
+			}
 		}
 	}
 
-	if (virtio_transport_get_type(sk) != le16_to_cpu(hdr->type)) {
-		(void)virtio_transport_reset_no_sock(t, skb);
+	if (virtio_transport_get_type(sk) != type) {
+		if (type != VIRTIO_VSOCK_TYPE_DGRAM)
+			(void)virtio_transport_reset_no_sock(t, skb);
 		sock_put(sk);
 		goto free_pkt;
 	}
@@ -1410,12 +1454,18 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 
 	/* Check if sk has been closed before lock_sock */
 	if (sock_flag(sk, SOCK_DONE)) {
-		(void)virtio_transport_reset_no_sock(t, skb);
+		if (type != VIRTIO_VSOCK_TYPE_DGRAM)
+			(void)virtio_transport_reset_no_sock(t, skb);
 		release_sock(sk);
 		sock_put(sk);
 		goto free_pkt;
 	}
 
+	if (sk->sk_type == SOCK_DGRAM) {
+		virtio_transport_recv_dgram(sk, skb);
+		goto out;
+	}
+
 	space_available = virtio_transport_space_update(sk, skb);
 
 	/* Update CID in case it has changed after a transport reset event */
@@ -1447,6 +1497,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 		break;
 	}
 
+out:
 	release_sock(sk);
 
 	/* Release refcnt obtained when we fetched this socket out of the
@@ -1515,6 +1566,21 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
 }
 EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
 
+void virtio_transport_dgram_addr_init(struct sk_buff *skb,
+				      struct sockaddr_vm *addr)
+{
+	struct virtio_vsock_hdr *hdr;
+	unsigned int cid, port;
+
+	WARN_ONCE(skb->head == skb->data, "virtio vsock bug: bad dgram skb");
+
+	hdr = virtio_vsock_hdr(skb);
+	cid = le64_to_cpu(hdr->src_cid);
+	port = le32_to_cpu(hdr->src_port);
+	vsock_addr_init(addr, cid, port);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dgram_addr_init);
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Asias He");
 MODULE_DESCRIPTION("common code for virtio vsock");

-- 
2.30.2