1 files changed, 199 insertions, 133 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e4af6616e1df..b0a4c6d08e0a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -126,6 +126,81 @@ static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
  *    hash table is protected with spinlock.
  *    each socket state is protected by separate spinlock.
  */
+#ifdef CONFIG_PROVE_LOCKING
+#define cmp_ptr(l, r)	(((l) > (r)) - ((l) < (r)))
+
+static int unix_table_lock_cmp_fn(const struct lockdep_map *a,
+				  const struct lockdep_map *b)
+{
+	return cmp_ptr(a, b);
+}
+
+static int unix_state_lock_cmp_fn(const struct lockdep_map *_a,
+				  const struct lockdep_map *_b)
+{
+	const struct unix_sock *a, *b;
+
+	a = container_of(_a, struct unix_sock, lock.dep_map);
+	b = container_of(_b, struct unix_sock, lock.dep_map);
+
+	if (a->sk.sk_state == TCP_LISTEN) {
+		/* unix_stream_connect(): Before the 2nd unix_state_lock(),
+		 *
+		 *   1. a is TCP_LISTEN.
+		 *   2. b is not a.
+		 *   3. concurrent connect(b -> a) must fail.
+		 *
+		 * Except for 2. & 3., the b's state can be any possible
+		 * value due to concurrent connect() or listen().
+		 *
+		 * 2. is detected in debug_spin_lock_before(), and 3. cannot
+		 * be expressed as lock_cmp_fn.
+		 */
+		switch (b->sk.sk_state) {
+		case TCP_CLOSE:
+		case TCP_ESTABLISHED:
+		case TCP_LISTEN:
+			return -1;
+		default:
+			/* Invalid case. */
+			return 0;
+		}
+	}
+
+	/* Should never happen.  Just to be symmetric. */
+	if (b->sk.sk_state == TCP_LISTEN) {
+		switch (b->sk.sk_state) {
+		case TCP_CLOSE:
+		case TCP_ESTABLISHED:
+			return 1;
+		default:
+			return 0;
+		}
+	}
+
+	/* unix_state_double_lock(): ascending address order. */
+	return cmp_ptr(a, b);
+}
+
+static int unix_recvq_lock_cmp_fn(const struct lockdep_map *_a,
+				  const struct lockdep_map *_b)
+{
+	const struct sock *a, *b;
+
+	a = container_of(_a, struct sock, sk_receive_queue.lock.dep_map);
+	b = container_of(_b, struct sock, sk_receive_queue.lock.dep_map);
+
+	/* unix_collect_skb(): listener -> embryo order. */
+	if (a->sk_state == TCP_LISTEN && unix_sk(b)->listener == a)
+		return -1;
+
+	/* Should never happen.  Just to be symmetric. */
+	if (b->sk_state == TCP_LISTEN && unix_sk(a)->listener == b)
+		return 1;
+
+	return 0;
+}
+#endif
 
 static unsigned int unix_unbound_hash(struct sock *sk)
 {
@@ -168,7 +243,7 @@ static void unix_table_double_lock(struct net *net,
 		swap(hash1, hash2);
 
 	spin_lock(&net->unx.table.locks[hash1]);
-	spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING);
+	spin_lock(&net->unx.table.locks[hash2]);
 }
 
 static void unix_table_double_unlock(struct net *net,
@@ -221,15 +296,9 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk)
 	return unix_peer(osk) == NULL || unix_our_peer(sk, osk);
 }
 
-static inline int unix_recvq_full(const struct sock *sk)
-{
-	return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
-}
-
 static inline int unix_recvq_full_lockless(const struct sock *sk)
 {
-	return skb_queue_len_lockless(&sk->sk_receive_queue) >
-		READ_ONCE(sk->sk_max_ack_backlog);
+	return skb_queue_len_lockless(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
 }
 
 struct sock *unix_peer_get(struct sock *s)
@@ -530,10 +599,10 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
 	return 0;
 }
 
-static int unix_writable(const struct sock *sk)
+static int unix_writable(const struct sock *sk, unsigned char state)
 {
-	return sk->sk_state != TCP_LISTEN &&
-	       (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
+	return state != TCP_LISTEN &&
+		(refcount_read(&sk->sk_wmem_alloc) << 2) <= READ_ONCE(sk->sk_sndbuf);
 }
 
 static void unix_write_space(struct sock *sk)
@@ -541,7 +610,7 @@ static void unix_write_space(struct sock *sk)
 	struct socket_wq *wq;
 
 	rcu_read_lock();
-	if (unix_writable(sk)) {
+	if (unix_writable(sk, READ_ONCE(sk->sk_state))) {
 		wq = rcu_dereference(sk->sk_wq);
 		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait,
@@ -570,7 +639,6 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
 			sk_error_report(other);
 		}
 	}
-	other->sk_state = TCP_CLOSE;
 }
 
 static void unix_sock_destructor(struct sock *sk)
@@ -617,7 +685,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	state = sk->sk_state;
-	sk->sk_state = TCP_CLOSE;
+	WRITE_ONCE(sk->sk_state, TCP_CLOSE);
 
 	skpair = unix_peer(sk);
 	unix_peer(sk) = NULL;
@@ -638,7 +706,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 			unix_state_lock(skpair);
 			/* No more writes */
 			WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
-			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
+			if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion)
 				WRITE_ONCE(skpair->sk_err, ECONNRESET);
 			unix_state_unlock(skpair);
 			skpair->sk_state_change(skpair);
@@ -654,8 +722,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 		if (state == TCP_LISTEN)
 			unix_release_sock(skb->sk, 1);
+
 		/* passed fds are erased in the kfree_skb hook	      */
-		UNIXCB(skb).consumed = skb->len;
 		kfree_skb(skb);
 	}
 
@@ -683,14 +751,19 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 static void init_peercred(struct sock *sk)
 {
+	sk->sk_peer_pid = get_pid(task_tgid(current));
+	sk->sk_peer_cred = get_current_cred();
+}
+
+static void update_peercred(struct sock *sk)
+{
 	const struct cred *old_cred;
 	struct pid *old_pid;
 
 	spin_lock(&sk->sk_peer_lock);
 	old_pid = sk->sk_peer_pid;
 	old_cred = sk->sk_peer_cred;
-	sk->sk_peer_pid  = get_pid(task_tgid(current));
-	sk->sk_peer_cred = get_current_cred();
+	init_peercred(sk);
 	spin_unlock(&sk->sk_peer_lock);
 
 	put_pid(old_pid);
@@ -699,26 +772,12 @@ static void init_peercred(struct sock *sk)
 
 static void copy_peercred(struct sock *sk, struct sock *peersk)
 {
-	const struct cred *old_cred;
-	struct pid *old_pid;
+	lockdep_assert_held(&unix_sk(peersk)->lock);
 
-	if (sk < peersk) {
-		spin_lock(&sk->sk_peer_lock);
-		spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
-	} else {
-		spin_lock(&peersk->sk_peer_lock);
-		spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
-	}
-	old_pid = sk->sk_peer_pid;
-	old_cred = sk->sk_peer_cred;
-	sk->sk_peer_pid  = get_pid(peersk->sk_peer_pid);
+	spin_lock(&sk->sk_peer_lock);
+	sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
 	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
-
 	spin_unlock(&sk->sk_peer_lock);
-	spin_unlock(&peersk->sk_peer_lock);
-
-	put_pid(old_pid);
-	put_cred(old_cred);
 }
 
 static int unix_listen(struct socket *sock, int backlog)
@@ -731,7 +790,7 @@ static int unix_listen(struct socket *sock, int backlog)
 	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
 		goto out;	/* Only stream/seqpacket sockets accept */
 	err = -EINVAL;
-	if (!u->addr)
+	if (!READ_ONCE(u->addr))
 		goto out;	/* No listens on an unbound socket */
 	unix_state_lock(sk);
 	if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN)
@@ -739,9 +798,10 @@ static int unix_listen(struct socket *sock, int backlog)
 	if (backlog > sk->sk_max_ack_backlog)
 		wake_up_interruptible_all(&u->peer_wait);
 	sk->sk_max_ack_backlog	= backlog;
-	sk->sk_state		= TCP_LISTEN;
+	WRITE_ONCE(sk->sk_state, TCP_LISTEN);
+
 	/* set credentials so connect can copy them */
-	init_peercred(sk);
+	update_peercred(sk);
 	err = 0;
 
 out_unlock:
@@ -976,14 +1036,17 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	sk->sk_hash		= unix_unbound_hash(sk);
 	sk->sk_allocation	= GFP_KERNEL_ACCOUNT;
 	sk->sk_write_space	= unix_write_space;
-	sk->sk_max_ack_backlog	= net->unx.sysctl_max_dgram_qlen;
+	sk->sk_max_ack_backlog	= READ_ONCE(net->unx.sysctl_max_dgram_qlen);
 	sk->sk_destruct		= unix_sock_destructor;
+	lock_set_cmp_fn(&sk->sk_receive_queue.lock, unix_recvq_lock_cmp_fn, NULL);
+
 	u = unix_sk(sk);
 	u->listener = NULL;
 	u->vertex = NULL;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	spin_lock_init(&u->lock);
+	lock_set_cmp_fn(&u->lock, unix_state_lock_cmp_fn, NULL);
 	mutex_init(&u->iolock); /* single task reading lock */
 	mutex_init(&u->bindlock); /* single task binding lock */
 	init_waitqueue_head(&u->peer_wait);
@@ -1131,8 +1194,8 @@ static struct sock *unix_find_other(struct net *net,
 
 static int unix_autobind(struct sock *sk)
 {
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct unix_address *addr;
 	u32 lastnum, ordernum;
@@ -1155,6 +1218,7 @@ static int unix_autobind(struct sock *sk)
 	addr->name->sun_family = AF_UNIX;
 	refcount_set(&addr->refcnt, 1);
 
+	old_hash = sk->sk_hash;
 	ordernum = get_random_u32();
 	lastnum = ordernum & 0xFFFFF;
 retry:
@@ -1195,8 +1259,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 {
 	umode_t mode = S_IFSOCK |
 	       (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct mnt_idmap *idmap;
 	struct unix_address *addr;
@@ -1234,6 +1298,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 	if (u->addr)
 		goto out_unlock;
 
+	old_hash = sk->sk_hash;
 	new_hash = unix_bsd_hash(d_backing_inode(dentry));
 	unix_table_double_lock(net, old_hash, new_hash);
 	u->path.mnt = mntget(parent.mnt);
@@ -1261,8 +1326,8 @@ out:
 static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr,
 			      int addr_len)
 {
-	unsigned int new_hash, old_hash = sk->sk_hash;
 	struct unix_sock *u = unix_sk(sk);
+	unsigned int new_hash, old_hash;
 	struct net *net = sock_net(sk);
 	struct unix_address *addr;
 	int err;
@@ -1280,6 +1345,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr,
 		goto out_mutex;
 	}
 
+	old_hash = sk->sk_hash;
 	new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type);
 	unix_table_double_lock(net, old_hash, new_hash);
 
@@ -1329,11 +1395,12 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
+
 	if (sk1 > sk2)
 		swap(sk1, sk2);
 
 	unix_state_lock(sk1);
-	unix_state_lock_nested(sk2, U_LOCK_SECOND);
+	unix_state_lock(sk2);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1369,7 +1436,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 
 		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
 		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
-		    !unix_sk(sk)->addr) {
+		    !READ_ONCE(unix_sk(sk)->addr)) {
 			err = unix_autobind(sk);
 			if (err)
 				goto out;
@@ -1399,7 +1466,8 @@ restart:
 		if (err)
 			goto out_unlock;
 
-		sk->sk_state = other->sk_state = TCP_ESTABLISHED;
+		WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED);
+		WRITE_ONCE(other->sk_state, TCP_ESTABLISHED);
 	} else {
 		/*
 		 *	1003.1g breaking connected state with AF_UNSPEC
@@ -1416,13 +1484,20 @@ restart:
 
 		unix_peer(sk) = other;
 		if (!other)
-			sk->sk_state = TCP_CLOSE;
+			WRITE_ONCE(sk->sk_state, TCP_CLOSE);
 		unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
 
 		unix_state_double_unlock(sk, other);
 
-		if (other != old_peer)
+		if (other != old_peer) {
 			unix_dgram_disconnected(sk, old_peer);
+
+			unix_state_lock(old_peer);
+			if (!unix_peer(old_peer))
+				WRITE_ONCE(old_peer->sk_state, TCP_CLOSE);
+			unix_state_unlock(old_peer);
+		}
+
 		sock_put(old_peer);
 	} else {
 		unix_peer(sk) = other;
@@ -1468,9 +1543,9 @@ 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;
-	int st;
 
 	err = unix_validate_addr(sunaddr, addr_len);
 	if (err)
@@ -1481,7 +1556,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
+	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
+	    !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
@@ -1518,7 +1594,6 @@ restart:
 		goto out;
 	}
 
-	/* Latch state of peer */
 	unix_state_lock(other);
 
 	/* Apparently VFS overslept socket death. Retry. */
@@ -1534,7 +1609,7 @@ restart:
 	if (other->sk_shutdown & RCV_SHUTDOWN)
 		goto out_unlock;
 
-	if (unix_recvq_full(other)) {
+	if (unix_recvq_full_lockless(other)) {
 		err = -EAGAIN;
 		if (!timeo)
 			goto out_unlock;
@@ -1548,39 +1623,21 @@ 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.
 	 */
-	st = sk->sk_state;
-
-	switch (st) {
-	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);
+	unix_state_lock(sk);
 
-	if (sk->sk_state != st) {
+	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);
@@ -1629,7 +1686,7 @@ restart:
 	copy_peercred(sk, other);
 
 	sock->state	= SS_CONNECTED;
-	sk->sk_state	= TCP_ESTABLISHED;
+	WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED);
 	sock_hold(newsk);
 
 	smp_mb__after_atomic();	/* sock_hold() does an atomic_inc() */
@@ -1701,7 +1758,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock,
 		goto out;
 
 	arg->err = -EINVAL;
-	if (sk->sk_state != TCP_LISTEN)
+	if (READ_ONCE(sk->sk_state) != TCP_LISTEN)
 		goto out;
 
 	/* If socket state is TCP_LISTEN it cannot change (for now...),
@@ -1950,14 +2007,15 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
-	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
+	     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
+	    !READ_ONCE(u->addr)) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
 	}
 
 	err = -EMSGSIZE;
-	if (len > sk->sk_sndbuf - 32)
+	if (len > READ_ONCE(sk->sk_sndbuf) - 32)
 		goto out;
 
 	if (len > SKB_MAX_ALLOC) {
@@ -2039,7 +2097,7 @@ restart_locked:
 			unix_peer(sk) = NULL;
 			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
 
-			sk->sk_state = TCP_CLOSE;
+			WRITE_ONCE(sk->sk_state, TCP_CLOSE);
 			unix_state_unlock(sk);
 
 			unix_dgram_disconnected(sk, other);
@@ -2216,7 +2274,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 	if (msg->msg_namelen) {
-		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
+		err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out_err;
 	} else {
 		err = -ENOTCONN;
@@ -2237,7 +2295,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 						   &err, 0);
 		} else {
 			/* Keep two messages in the pipe so it schedules better */
-			size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
+			size = min_t(int, size, (READ_ONCE(sk->sk_sndbuf) >> 1) - 64);
 
 			/* allow fallback to order-0 allocations */
 			size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
@@ -2330,7 +2388,7 @@ static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (err)
 		return err;
 
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)
 		return -ENOTCONN;
 
 	if (msg->msg_namelen)
@@ -2344,7 +2402,7 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)
 		return -ENOTCONN;
 
 	return unix_dgram_recvmsg(sock, msg, size, flags);
@@ -2609,10 +2667,24 @@ 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;
 
@@ -2621,18 +2693,18 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		if (skb == u->oob_skb) {
 			if (copied) {
 				skb = NULL;
-			} else if (sock_flag(sk, SOCK_URGINLINE)) {
-				if (!(flags & MSG_PEEK)) {
+			} else if (!(flags & MSG_PEEK)) {
+				if (sock_flag(sk, SOCK_URGINLINE)) {
 					WRITE_ONCE(u->oob_skb, NULL);
 					consume_skb(skb);
+				} else {
+					__skb_unlink(skb, &sk->sk_receive_queue);
+					WRITE_ONCE(u->oob_skb, NULL);
+					unlinked_skb = skb;
+					skb = skb_peek(&sk->sk_receive_queue);
 				}
-			} else if (flags & MSG_PEEK) {
-				skb = NULL;
-			} else {
-				__skb_unlink(skb, &sk->sk_receive_queue);
-				WRITE_ONCE(u->oob_skb, NULL);
-				unlinked_skb = skb;
-				skb = skb_peek(&sk->sk_receive_queue);
+			} else if (!sock_flag(sk, SOCK_URGINLINE)) {
+				skb = skb_peek_next(skb, &sk->sk_receive_queue);
 			}
 		}
 
@@ -2649,7 +2721,7 @@ 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)
 {
-	if (unlikely(sk->sk_state != TCP_ESTABLISHED))
+	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
 		return -ENOTCONN;
 
 	return unix_read_skb(sk, recv_actor);
@@ -2673,7 +2745,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 	size_t size = state->size;
 	unsigned int last_len;
 
-	if (unlikely(sk->sk_state != TCP_ESTABLISHED)) {
+	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -2699,9 +2771,8 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,
 	skip = max(sk_peek_offset(sk, flags), 0);
 
 	do {
-		int chunk;
-		bool drop_skb;
 		struct sk_buff *skb, *last;
+		int chunk;
 
 redo:
 		unix_state_lock(sk);
@@ -2797,11 +2868,7 @@ unlock:
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
-		skb_get(skb);
 		chunk = state->recv_actor(skb, skip, chunk, state);
-		drop_skb = !unix_skb_len(skb);
-		/* skb is only safe to use if !drop_skb */
-		consume_skb(skb);
 		if (chunk < 0) {
 			if (copied == 0)
 				copied = -EFAULT;
@@ -2810,18 +2877,6 @@ unlock:
 		copied += chunk;
 		size -= chunk;
 
-		if (drop_skb) {
-			/* the skb was touched by a concurrent reader;
-			 * we should not expect anything from this skb
-			 * anymore and assume it invalid - we can be
-			 * sure it was dropped from the socket queue
-			 *
-			 * let's report a short read
-			 */
-			err = 0;
-			break;
-		}
-
 		/* Mark read part of skb as used */
 		if (!(flags & MSG_PEEK)) {
 			UNIXCB(skb).consumed += chunk;
@@ -3004,7 +3059,7 @@ long unix_inq_len(struct sock *sk)
 	struct sk_buff *skb;
 	long amount = 0;
 
-	if (sk->sk_state == TCP_LISTEN)
+	if (READ_ONCE(sk->sk_state) == TCP_LISTEN)
 		return -EINVAL;
 
 	spin_lock(&sk->sk_receive_queue.lock);
@@ -3089,12 +3144,23 @@ 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;
@@ -3116,12 +3182,14 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon
 static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	struct sock *sk = sock->sk;
+	unsigned char state;
 	__poll_t mask;
 	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
 	shutdown = READ_ONCE(sk->sk_shutdown);
+	state = READ_ONCE(sk->sk_state);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err))
@@ -3143,14 +3211,14 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
-	    sk->sk_state == TCP_CLOSE)
+	    state == TCP_CLOSE)
 		mask |= EPOLLHUP;
 
 	/*
 	 * we set writable also when the other side has shut down the
 	 * connection. This prevents stuck sockets.
 	 */
-	if (unix_writable(sk))
+	if (unix_writable(sk, state))
 		mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
 
 	return mask;
@@ -3161,12 +3229,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 {
 	struct sock *sk = sock->sk, *other;
 	unsigned int writable;
+	unsigned char state;
 	__poll_t mask;
 	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
 	shutdown = READ_ONCE(sk->sk_shutdown);
+	state = READ_ONCE(sk->sk_state);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err) ||
@@ -3186,19 +3256,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
-	if (sk->sk_type == SOCK_SEQPACKET) {
-		if (sk->sk_state == TCP_CLOSE)
-			mask |= EPOLLHUP;
-		/* connection hasn't started yet? */
-		if (sk->sk_state == TCP_SYN_SENT)
-			return mask;
-	}
+	if (sk->sk_type == SOCK_SEQPACKET && state == TCP_CLOSE)
+		mask |= EPOLLHUP;
 
 	/* No write status requested, avoid expensive OUT tests. */
 	if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
 		return mask;
 
-	writable = unix_writable(sk);
+	writable = unix_writable(sk, state);
 	if (writable) {
 		unix_state_lock(sk);
 
@@ -3592,6 +3657,7 @@ static int __net_init unix_net_init(struct net *net)
 
 	for (i = 0; i < UNIX_HASH_SIZE; i++) {
 		spin_lock_init(&net->unx.table.locks[i]);
+		lock_set_cmp_fn(&net->unx.table.locks[i], unix_table_lock_cmp_fn, NULL);
 		INIT_HLIST_HEAD(&net->unx.table.buckets[i]);
 	}