1 files changed, 240 insertions, 159 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 9df15a7bc2..be5266007b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -118,8 +118,6 @@
 #include <linux/btf_ids.h>
 #include <linux/bpf-cgroup.h>
 
-#include "scm.h"
-
 static atomic_long_t unix_nr_socks;
 static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
 static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
@@ -223,15 +221,9 @@ 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)
@@ -532,10 +524,10 @@ 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)
@@ -543,12 +535,12 @@ 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,
 				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();
 }
@@ -572,7 +564,6 @@ 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)
@@ -619,7 +610,7 @@ 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;
@@ -640,7 +631,7 @@ 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);
@@ -733,7 +724,7 @@ 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)
@@ -741,7 +732,8 @@ 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);
 	err = 0;
@@ -757,7 +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 *,
@@ -978,14 +970,14 @@ 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;
 	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);
@@ -1133,8 +1125,8 @@ 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;
@@ -1157,6 +1149,7 @@ 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:
@@ -1197,8 +1190,8 @@ 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;
@@ -1236,6 +1229,7 @@ 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);
@@ -1263,8 +1257,8 @@ 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;
@@ -1282,6 +1276,7 @@ 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);
 
@@ -1371,7 +1366,7 @@ 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;
@@ -1401,7 +1396,8 @@ 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
@@ -1418,13 +1414,20 @@ 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;
@@ -1470,9 +1473,9 @@ 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)
@@ -1483,7 +1486,8 @@ 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;
@@ -1520,7 +1524,6 @@ restart:
 		goto out;
 	}
 
-	/* Latch state of peer */
 	unix_state_lock(other);
 
 	/* Apparently VFS overslept socket death. Retry. */
@@ -1536,7 +1539,7 @@ 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;
@@ -1550,39 +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.
 	 */
-	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);
 
-	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);
@@ -1599,6 +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);
 
@@ -1630,7 +1616,7 @@ 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() */
@@ -1690,32 +1676,31 @@ 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;
-	if (sk->sk_state != TCP_LISTEN)
+	arg->err = -EINVAL;
+	if (READ_ONCE(sk->sk_state) != TCP_LISTEN)
 		goto out;
 
 	/* If socket state is TCP_LISTEN it cannot change (for now...),
 	 * 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;
 	}
 
@@ -1725,6 +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);
@@ -1732,7 +1718,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 	return 0;
 
 out:
-	return err;
+	return arg->err;
 }
 
 
@@ -1775,51 +1761,60 @@ out:
 	return err;
 }
 
+/* The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
+static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
+	UNIXCB(skb).fp = scm->fp;
+	scm->fp = NULL;
+
+	if (unix_prepare_fpl(UNIXCB(skb).fp))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	scm->fp = UNIXCB(skb).fp;
+	UNIXCB(skb).fp = NULL;
+
+	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)
+{
+	struct scm_cookie scm;
+
+	memset(&scm, 0, sizeof(scm));
+	scm.pid  = UNIXCB(skb).pid;
+	if (UNIXCB(skb).fp)
+		unix_detach_fds(&scm, skb);
+
+	/* Alas, it calls VFS */
+	/* So fscking what? fput() had been SMP-safe since the last Summer */
+	scm_destroy(&scm);
+	sock_wfree(skb);
 }
 
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
@@ -1878,8 +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)
@@ -1887,8 +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);
+	}
 }
 
 /*
@@ -1908,11 +1907,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	long timeo;
 	int err;
 
-	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
+	wait_for_unix_gc(scm.fp);
+
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags&MSG_OOB)
 		goto out;
@@ -1937,14 +1937,15 @@ 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) {
@@ -2026,7 +2027,7 @@ 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);
@@ -2157,13 +2158,15 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	maybe_add_creds(skb, sock, other);
 	skb_get(skb);
 
+	scm_stat_add(other, skb);
+
+	spin_lock(&other->sk_receive_queue.lock);
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
-
 	WRITE_ONCE(ousk->oob_skb, skb);
+	__skb_queue_tail(&other->sk_receive_queue, skb);
+	spin_unlock(&other->sk_receive_queue.lock);
 
-	scm_stat_add(other, skb);
-	skb_queue_tail(&other->sk_receive_queue, skb);
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
@@ -2184,11 +2187,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	bool fds_sent = false;
 	int data_len;
 
-	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
+	wait_for_unix_gc(scm.fp);
+
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags & MSG_OOB) {
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
@@ -2200,7 +2204,7 @@ 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;
@@ -2209,7 +2213,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out_err;
 	}
 
-	if (sk->sk_shutdown & SEND_SHUTDOWN)
+	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 		goto pipe_err;
 
 	while (sent < len) {
@@ -2221,7 +2225,7 @@ 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);
@@ -2314,7 +2318,7 @@ 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)
@@ -2328,7 +2332,7 @@ 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);
@@ -2553,8 +2557,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	mutex_lock(&u->iolock);
 	unix_state_lock(sk);
+	spin_lock(&sk->sk_receive_queue.lock);
 
 	if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) {
+		spin_unlock(&sk->sk_receive_queue.lock);
 		unix_state_unlock(sk);
 		mutex_unlock(&u->iolock);
 		return -EINVAL;
@@ -2566,6 +2572,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 		WRITE_ONCE(u->oob_skb, NULL);
 	else
 		skb_get(oob_skb);
+
+	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
@@ -2589,29 +2597,53 @@ 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;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
 		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);
-				if (!WARN_ON_ONCE(skb_unref(skb)))
-					kfree_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);
 			}
 		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		if (unlinked_skb) {
+			WARN_ON_ONCE(skb_unref(unlinked_skb));
+			kfree_skb(unlinked_skb);
+		}
 	}
 	return skb;
 }
@@ -2619,10 +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)
 {
-	if (unlikely(sk->sk_state != TCP_ESTABLISHED))
+	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,
@@ -2643,7 +2714,7 @@ 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;
 	}
@@ -2974,7 +3045,7 @@ 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);
@@ -3059,12 +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;
@@ -3086,12 +3168,14 @@ 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))
@@ -3113,14 +3197,14 @@ 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;
@@ -3131,12 +3215,14 @@ 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) ||
@@ -3156,19 +3242,14 @@ 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);