1 files changed, 107 insertions, 106 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 68a58bc07c..be5266007b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -540,7 +540,7 @@ static void unix_write_space(struct sock *sk)
 		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait,
 				EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
-		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+		sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
 	rcu_read_unlock();
 }
@@ -749,7 +749,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int);
 static int unix_stream_connect(struct socket *, struct sockaddr *,
 			       int addr_len, int flags);
 static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int, bool);
+static int unix_accept(struct socket *, struct socket *, struct proto_accept_arg *arg);
 static int unix_getname(struct socket *, struct sockaddr *, int);
 static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
 static __poll_t unix_dgram_poll(struct file *, struct socket *,
@@ -973,11 +973,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	sk->sk_max_ack_backlog	= READ_ONCE(net->unx.sysctl_max_dgram_qlen);
 	sk->sk_destruct		= unix_sock_destructor;
 	u = unix_sk(sk);
-	u->inflight = 0;
+	u->listener = NULL;
+	u->vertex = NULL;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	spin_lock_init(&u->lock);
-	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->iolock); /* single task reading lock */
 	mutex_init(&u->bindlock); /* single task binding lock */
 	init_waitqueue_head(&u->peer_wait);
@@ -1473,6 +1473,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct unix_sock *u = unix_sk(sk), *newu, *otheru;
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb = NULL;
+	unsigned char state;
 	long timeo;
 	int err;
 
@@ -1523,7 +1524,6 @@ restart:
 		goto out;
 	}
 
-	/* Latch state of peer */
 	unix_state_lock(other);
 
 	/* Apparently VFS overslept socket death. Retry. */
@@ -1553,37 +1553,21 @@ restart:
 		goto restart;
 	}
 
-	/* Latch our state.
-
-	   It is tricky place. We need to grab our state lock and cannot
-	   drop lock on peer. It is dangerous because deadlock is
-	   possible. Connect to self case and simultaneous
-	   attempt to connect are eliminated by checking socket
-	   state. other is TCP_LISTEN, if sk is TCP_LISTEN we
-	   check this before attempt to grab lock.
-
-	   Well, and we have to recheck the state after socket locked.
+	/* self connect and simultaneous connect are eliminated
+	 * by rejecting TCP_LISTEN socket to avoid deadlock.
 	 */
-	switch (READ_ONCE(sk->sk_state)) {
-	case TCP_CLOSE:
-		/* This is ok... continue with connect */
-		break;
-	case TCP_ESTABLISHED:
-		/* Socket is already connected */
-		err = -EISCONN;
-		goto out_unlock;
-	default:
-		err = -EINVAL;
+	state = READ_ONCE(sk->sk_state);
+	if (unlikely(state != TCP_CLOSE)) {
+		err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
 		goto out_unlock;
 	}
 
 	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
-	if (sk->sk_state != TCP_CLOSE) {
+	if (unlikely(sk->sk_state != TCP_CLOSE)) {
+		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
 		unix_state_unlock(sk);
-		unix_state_unlock(other);
-		sock_put(other);
-		goto restart;
+		goto out_unlock;
 	}
 
 	err = security_unix_stream_connect(sk, other, newsk);
@@ -1600,6 +1584,7 @@ restart:
 	newsk->sk_type		= sk->sk_type;
 	init_peercred(newsk);
 	newu = unix_sk(newsk);
+	newu->listener = other;
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
 	otheru = unix_sk(other);
 
@@ -1691,19 +1676,18 @@ static void unix_sock_inherit_flags(const struct socket *old,
 		set_bit(SOCK_PASSSEC, &new->flags);
 }
 
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
-		       bool kern)
+static int unix_accept(struct socket *sock, struct socket *newsock,
+		       struct proto_accept_arg *arg)
 {
 	struct sock *sk = sock->sk;
-	struct sock *tsk;
 	struct sk_buff *skb;
-	int err;
+	struct sock *tsk;
 
-	err = -EOPNOTSUPP;
+	arg->err = -EOPNOTSUPP;
 	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
 		goto out;
 
-	err = -EINVAL;
+	arg->err = -EINVAL;
 	if (READ_ONCE(sk->sk_state) != TCP_LISTEN)
 		goto out;
 
@@ -1711,12 +1695,12 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 	 * so that no locks are necessary.
 	 */
 
-	skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0,
-				&err);
+	skb = skb_recv_datagram(sk, (arg->flags & O_NONBLOCK) ? MSG_DONTWAIT : 0,
+				&arg->err);
 	if (!skb) {
 		/* This means receive shutdown. */
-		if (err == 0)
-			err = -EINVAL;
+		if (arg->err == 0)
+			arg->err = -EINVAL;
 		goto out;
 	}
 
@@ -1726,6 +1710,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 
 	/* attach accepted sock to socket */
 	unix_state_lock(tsk);
+	unix_update_edges(unix_sk(tsk));
 	newsock->state = SS_CONNECTED;
 	unix_sock_inherit_flags(sock, newsock);
 	sock_graft(tsk, newsock);
@@ -1733,7 +1718,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 	return 0;
 
 out:
-	return err;
+	return arg->err;
 }
 
 
@@ -1792,81 +1777,29 @@ static inline bool too_many_unix_fds(struct task_struct *p)
 
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
-	int i;
-
 	if (too_many_unix_fds(current))
 		return -ETOOMANYREFS;
 
-	/* Need to duplicate file references for the sake of garbage
-	 * collection.  Otherwise a socket in the fps might become a
-	 * candidate for GC while the skb is not yet queued.
-	 */
-	UNIXCB(skb).fp = scm_fp_dup(scm->fp);
-	if (!UNIXCB(skb).fp)
-		return -ENOMEM;
+	UNIXCB(skb).fp = scm->fp;
+	scm->fp = NULL;
 
-	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->user, scm->fp->fp[i]);
+	if (unix_prepare_fpl(UNIXCB(skb).fp))
+		return -ENOMEM;
 
 	return 0;
 }
 
 static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
-	int i;
-
 	scm->fp = UNIXCB(skb).fp;
 	UNIXCB(skb).fp = NULL;
 
-	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
+	unix_destroy_fpl(scm->fp);
 }
 
 static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
 	scm->fp = scm_fp_dup(UNIXCB(skb).fp);
-
-	/*
-	 * Garbage collection of unix sockets starts by selecting a set of
-	 * candidate sockets which have reference only from being in flight
-	 * (total_refs == inflight_refs).  This condition is checked once during
-	 * the candidate collection phase, and candidates are marked as such, so
-	 * that non-candidates can later be ignored.  While inflight_refs is
-	 * protected by unix_gc_lock, total_refs (file count) is not, hence this
-	 * is an instantaneous decision.
-	 *
-	 * Once a candidate, however, the socket must not be reinstalled into a
-	 * file descriptor while the garbage collection is in progress.
-	 *
-	 * If the above conditions are met, then the directed graph of
-	 * candidates (*) does not change while unix_gc_lock is held.
-	 *
-	 * Any operations that changes the file count through file descriptors
-	 * (dup, close, sendmsg) does not change the graph since candidates are
-	 * not installed in fds.
-	 *
-	 * Dequeing a candidate via recvmsg would install it into an fd, but
-	 * that takes unix_gc_lock to decrement the inflight count, so it's
-	 * serialized with garbage collection.
-	 *
-	 * MSG_PEEK is special in that it does not change the inflight count,
-	 * yet does install the socket into an fd.  The following lock/unlock
-	 * pair is to ensure serialization with garbage collection.  It must be
-	 * done between incrementing the file count and installing the file into
-	 * an fd.
-	 *
-	 * If garbage collection starts after the barrier provided by the
-	 * lock/unlock, then it will see the elevated refcount and not mark this
-	 * as a candidate.  If a garbage collection is already in progress
-	 * before the file count was incremented, then the lock/unlock pair will
-	 * ensure that garbage collection is finished before progressing to
-	 * installing the fd.
-	 *
-	 * (*) A -> B where B is on the queue of A or B is on the queue of C
-	 * which is on the queue of listening socket A.
-	 */
-	spin_lock(&unix_gc_lock);
-	spin_unlock(&unix_gc_lock);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
@@ -1940,8 +1873,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb)
 	struct scm_fp_list *fp = UNIXCB(skb).fp;
 	struct unix_sock *u = unix_sk(sk);
 
-	if (unlikely(fp && fp->count))
+	if (unlikely(fp && fp->count)) {
 		atomic_add(fp->count, &u->scm_stat.nr_fds);
+		unix_add_edges(fp, u);
+	}
 }
 
 static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
@@ -1949,8 +1884,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
 	struct scm_fp_list *fp = UNIXCB(skb).fp;
 	struct unix_sock *u = unix_sk(sk);
 
-	if (unlikely(fp && fp->count))
+	if (unlikely(fp && fp->count)) {
 		atomic_sub(fp->count, &u->scm_stat.nr_fds);
+		unix_del_edges(fp);
+	}
 }
 
 /*
@@ -2660,10 +2597,24 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) {
-		skb_unlink(skb, &sk->sk_receive_queue);
-		consume_skb(skb);
-		skb = NULL;
+	if (!unix_skb_len(skb)) {
+		struct sk_buff *unlinked_skb = NULL;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
+		if (copied && (!u->oob_skb || skb == u->oob_skb)) {
+			skb = NULL;
+		} else if (flags & MSG_PEEK) {
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+		} else {
+			unlinked_skb = skb;
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			__skb_unlink(unlinked_skb, &sk->sk_receive_queue);
+		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		consume_skb(unlinked_skb);
 	} else {
 		struct sk_buff *unlinked_skb = NULL;
 
@@ -2700,10 +2651,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
+	struct unix_sock *u = unix_sk(sk);
+	struct sk_buff *skb;
+	int err;
+
 	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
 		return -ENOTCONN;
 
-	return unix_read_skb(sk, recv_actor);
+	mutex_lock(&u->iolock);
+	skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
+	mutex_unlock(&u->iolock);
+	if (!skb)
+		return err;
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (unlikely(skb == READ_ONCE(u->oob_skb))) {
+		bool drop = false;
+
+		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD)) {
+			unix_state_unlock(sk);
+			kfree_skb(skb);
+			return -ECONNRESET;
+		}
+
+		spin_lock(&sk->sk_receive_queue.lock);
+		if (likely(skb == u->oob_skb)) {
+			WRITE_ONCE(u->oob_skb, NULL);
+			drop = true;
+		}
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		unix_state_unlock(sk);
+
+		if (drop) {
+			WARN_ON_ONCE(skb_unref(skb));
+			kfree_skb(skb);
+			return -EAGAIN;
+		}
+	}
+#endif
+
+	return recv_actor(sk, skb);
 }
 
 static int unix_stream_read_generic(struct unix_stream_read_state *state,
@@ -3140,12 +3130,23 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 	case SIOCATMARK:
 		{
+			struct unix_sock *u = unix_sk(sk);
 			struct sk_buff *skb;
 			int answ = 0;
 
+			mutex_lock(&u->iolock);
+
 			skb = skb_peek(&sk->sk_receive_queue);
-			if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb))
-				answ = 1;
+			if (skb) {
+				struct sk_buff *oob_skb = READ_ONCE(u->oob_skb);
+
+				if (skb == oob_skb ||
+				    (!oob_skb && !unix_skb_len(skb)))
+					answ = 1;
+			}
+
+			mutex_unlock(&u->iolock);
+
 			err = put_user(answ, (int __user *)arg);
 		}
 		break;