Merge branch 'sockmap: add sockmap support for unix stream socket'

Jiang Wang says:

====================

This patch series add support for unix stream type
for sockmap. Sockmap already supports TCP, UDP,
unix dgram types. The unix stream support is similar
to unix dgram.

Also add selftests for unix stream type in sockmap tests.
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

1 files changed, 82 insertions, 13 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index bad8f19174e3..443c49081636 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -679,6 +679,8 @@ static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int);
 static int unix_read_sock(struct sock *sk, read_descriptor_t *desc,
 			  sk_read_actor_t recv_actor);
+static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc,
+				 sk_read_actor_t recv_actor);
 static int unix_dgram_connect(struct socket *, struct sockaddr *,
 			      int, int);
 static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -732,6 +734,7 @@ static const struct proto_ops unix_stream_ops = {
 	.shutdown =	unix_shutdown,
 	.sendmsg =	unix_stream_sendmsg,
 	.recvmsg =	unix_stream_recvmsg,
+	.read_sock =	unix_stream_read_sock,
 	.mmap =		sock_no_mmap,
 	.sendpage =	unix_stream_sendpage,
 	.splice_read =	unix_stream_splice_read,
@@ -795,17 +798,35 @@ static void unix_close(struct sock *sk, long timeout)
 	 */
 }
 
-struct proto unix_proto = {
-	.name			= "UNIX",
+static void unix_unhash(struct sock *sk)
+{
+	/* Nothing to do here, unix socket does not need a ->unhash().
+	 * This is merely for sockmap.
+	 */
+}
+
+struct proto unix_dgram_proto = {
+	.name			= "UNIX-DGRAM",
 	.owner			= THIS_MODULE,
 	.obj_size		= sizeof(struct unix_sock),
 	.close			= unix_close,
 #ifdef CONFIG_BPF_SYSCALL
-	.psock_update_sk_prot	= unix_bpf_update_proto,
+	.psock_update_sk_prot	= unix_dgram_bpf_update_proto,
 #endif
 };
 
-static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
+struct proto unix_stream_proto = {
+	.name			= "UNIX-STREAM",
+	.owner			= THIS_MODULE,
+	.obj_size		= sizeof(struct unix_sock),
+	.close			= unix_close,
+	.unhash			= unix_unhash,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= unix_stream_bpf_update_proto,
+#endif
+};
+
+static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type)
 {
 	struct sock *sk = NULL;
 	struct unix_sock *u;
@@ -814,7 +835,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files())
 		goto out;
 
-	sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto, kern);
+	if (type == SOCK_STREAM)
+		sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern);
+	else /*dgram and  seqpacket */
+		sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern);
+
 	if (!sk)
 		goto out;
 
@@ -876,7 +901,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol,
 		return -ESOCKTNOSUPPORT;
 	}
 
-	return unix_create1(net, sock, kern) ? 0 : -ENOMEM;
+	return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM;
 }
 
 static int unix_release(struct socket *sock)
@@ -1290,7 +1315,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	err = -ENOMEM;
 
 	/* create new sock for complete connection */
-	newsk = unix_create1(sock_net(sk), NULL, 0);
+	newsk = unix_create1(sock_net(sk), NULL, 0, sock->type);
 	if (newsk == NULL)
 		goto out;
 
@@ -2320,8 +2345,10 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t si
 	struct sock *sk = sock->sk;
 
 #ifdef CONFIG_BPF_SYSCALL
-	if (sk->sk_prot != &unix_proto)
-		return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot != &unix_dgram_proto)
+		return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
 					    flags & ~MSG_DONTWAIT, NULL);
 #endif
 	return __unix_dgram_recvmsg(sk, msg, size, flags);
@@ -2491,6 +2518,15 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 }
 #endif
 
+static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc,
+				 sk_read_actor_t recv_actor)
+{
+	if (unlikely(sk->sk_state != TCP_ESTABLISHED))
+		return -ENOTCONN;
+
+	return unix_read_sock(sk, desc, recv_actor);
+}
+
 static int unix_stream_read_generic(struct unix_stream_read_state *state,
 				    bool freezable)
 {
@@ -2716,6 +2752,20 @@ static int unix_stream_read_actor(struct sk_buff *skb,
 	return ret ?: chunk;
 }
 
+int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg,
+			  size_t size, int flags)
+{
+	struct unix_stream_read_state state = {
+		.recv_actor = unix_stream_read_actor,
+		.socket = sk->sk_socket,
+		.msg = msg,
+		.size = size,
+		.flags = flags
+	};
+
+	return unix_stream_read_generic(&state, true);
+}
+
 static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 			       size_t size, int flags)
 {
@@ -2727,6 +2777,14 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		.flags = flags
 	};
 
+#ifdef CONFIG_BPF_SYSCALL
+	struct sock *sk = sock->sk;
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot != &unix_stream_proto)
+		return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+					    flags & ~MSG_DONTWAIT, NULL);
+#endif
 	return unix_stream_read_generic(&state, true);
 }
 
@@ -2787,7 +2845,9 @@ static int unix_shutdown(struct socket *sock, int mode)
 		(sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {
 
 		int peer_mode = 0;
+		const struct proto *prot = READ_ONCE(other->sk_prot);
 
+		prot->unhash(other);
 		if (mode&RCV_SHUTDOWN)
 			peer_mode |= SEND_SHUTDOWN;
 		if (mode&SEND_SHUTDOWN)
@@ -2796,10 +2856,12 @@ static int unix_shutdown(struct socket *sock, int mode)
 		other->sk_shutdown |= peer_mode;
 		unix_state_unlock(other);
 		other->sk_state_change(other);
-		if (peer_mode == SHUTDOWN_MASK)
+		if (peer_mode == SHUTDOWN_MASK) {
 			sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
-		else if (peer_mode & RCV_SHUTDOWN)
+			other->sk_state = TCP_CLOSE;
+		} else if (peer_mode & RCV_SHUTDOWN) {
 			sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
+		}
 	}
 	if (other)
 		sock_put(other);
@@ -3277,7 +3339,13 @@ static int __init af_unix_init(void)
 
 	BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb));
 
-	rc = proto_register(&unix_proto, 1);
+	rc = proto_register(&unix_dgram_proto, 1);
+	if (rc != 0) {
+		pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
+		goto out;
+	}
+
+	rc = proto_register(&unix_stream_proto, 1);
 	if (rc != 0) {
 		pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__);
 		goto out;
@@ -3298,7 +3366,8 @@ out:
 static void __exit af_unix_exit(void)
 {
 	sock_unregister(PF_UNIX);
-	proto_unregister(&unix_proto);
+	proto_unregister(&unix_dgram_proto);
+	proto_unregister(&unix_stream_proto);
 	unregister_pernet_subsys(&unix_net_ops);
 }