net: core: Add a UID field to struct sock.

Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.

Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().

Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:

1. Whenever sk_socket is non-null: sk_uid is the same as the UID
   in sk_socket, i.e., matches the return value of sock_i_uid.
   Specifically, the UID is set when userspace calls socket(),
   fchown(), or accept().
2. When sk_socket is NULL, sk_uid is defined as follows:
   - For a socket that no longer has a sk_socket because
     userspace has called close(): the previous UID.
   - For a cloned socket (e.g., an incoming connection that is
     established but on which userspace has not yet called
     accept): the UID of the socket it was cloned from.
   - For a socket that has never had an sk_socket: UID 0 inside
     the user namespace corresponding to the network namespace
     the socket belongs to.

Kernel sockets created by sock_create_kern are a special case
of #1 and sk_uid is the user that created them. For kernel
sockets created at network namespace creation time, such as the
per-processor ICMP and TCP sockets, this is the user that created
the network namespace.

Signed-off-by: Lorenzo Colitti <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: lcolitti

include/net/sock.h

@@ -419,6 +419,7 @@ struct sock {
 	u32			sk_max_ack_backlog;
 	__u32			sk_priority;
 	__u32			sk_mark;
+	kuid_t			sk_uid;
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
@@ -1664,13 +1665,19 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	sk->sk_wq = parent->wq;
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
+	sk->sk_uid = SOCK_INODE(parent)->i_uid;
 	security_sock_graft(sk, parent);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
 kuid_t sock_i_uid(struct sock *sk);
 unsigned long sock_i_ino(struct sock *sk);
 
+static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
+{
+	return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
+}
+
 static inline u32 net_tx_rndhash(void)
 {
 	u32 v = prandom_u32();

net/core/sock.c

@@ -2460,8 +2460,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 		sk->sk_type	=	sock->type;
 		sk->sk_wq	=	sock->wq;
 		sock->sk	=	sk;
-	} else
+		sk->sk_uid	=	SOCK_INODE(sock)->i_uid;
+	} else {
 		sk->sk_wq	=	NULL;
+		sk->sk_uid	=	make_kuid(sock_net(sk)->user_ns, 0);
+	}
 
 	rwlock_init(&sk->sk_callback_lock);
 	lockdep_set_class_and_name(&sk->sk_callback_lock,

net/socket.c

@@ -518,8 +518,22 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
 	return used;
 }
 
+int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	int err = simple_setattr(dentry, iattr);
+
+	if (!err) {
+		struct socket *sock = SOCKET_I(d_inode(dentry));
+
+		sock->sk->sk_uid = iattr->ia_uid;
+	}
+
+	return err;
+}
+
 static const struct inode_operations sockfs_inode_ops = {
 	.listxattr = sockfs_listxattr,
+	.setattr = sockfs_setattr,
 };
 
 /**