Merge tag 'net-6.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  Current release - regressions:

   - mtk_eth_soc: fix NULL pointer dereference

  Previous releases - regressions:

   - core:
      - skb_partial_csum_set() fix against transport header magic value
      - fix load-tearing on sk->sk_stamp in sock_recv_cmsgs().
      - annotate sk->sk_err write from do_recvmmsg()
      - add vlan_get_protocol_and_depth() helper

   - netlink: annotate accesses to nlk->cb_running

   - netfilter: always release netdev hooks from notifier

  Previous releases - always broken:

   - core: deal with most data-races in sk_wait_event()

   - netfilter: fix possible bug_on with enable_hooks=1

   - eth: bonding: fix send_peer_notif overflow

   - eth: xpcs: fix incorrect number of interfaces

   - eth: ipvlan: fix out-of-bounds caused by unclear skb->cb

   - eth: stmmac: Initialize MAC_ONEUS_TIC_COUNTER register"

* tag 'net-6.4-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (31 commits)
  af_unix: Fix data races around sk->sk_shutdown.
  af_unix: Fix a data race of sk->sk_receive_queue->qlen.
  net: datagram: fix data-races in datagram_poll()
  net: mscc: ocelot: fix stat counter register values
  ipvlan:Fix out-of-bounds caused by unclear skb->cb
  docs: networking: fix x25-iface.rst heading & index order
  gve: Remove the code of clearing PBA bit
  tcp: add annotations around sk->sk_shutdown accesses
  net: add vlan_get_protocol_and_depth() helper
  net: pcs: xpcs: fix incorrect number of interfaces
  net: deal with most data-races in sk_wait_event()
  net: annotate sk->sk_err write from do_recvmmsg()
  netlink: annotate accesses to nlk->cb_running
  kselftest: bonding: add num_grat_arp test
  selftests: forwarding: lib: add netns support for tc rule handle stats get
  Documentation: bonding: fix the doc of peer_notif_delay
  bonding: fix send_peer_notif overflow
  net: ethernet: mtk_eth_soc: fix NULL pointer dereference
  selftests: nft_flowtable.sh: check ingress/egress chain too
  selftests: nft_flowtable.sh: monitor result file sizes
  ...

1 files changed, 13 insertions, 9 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index fb31e8a4409e..cc695c9f09ec 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -603,7 +603,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	/* Clear state */
 	unix_state_lock(sk);
 	sock_orphan(sk);
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
 	path	     = u->path;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
@@ -628,7 +628,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 		if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
 			unix_state_lock(skpair);
 			/* No more writes */
-			skpair->sk_shutdown = SHUTDOWN_MASK;
+			WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
 			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
 				WRITE_ONCE(skpair->sk_err, ECONNRESET);
 			unix_state_unlock(skpair);
@@ -1442,7 +1442,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo)
 
 	sched = !sock_flag(other, SOCK_DEAD) &&
 		!(other->sk_shutdown & RCV_SHUTDOWN) &&
-		unix_recvq_full(other);
+		unix_recvq_full_lockless(other);
 
 	unix_state_unlock(other);
 
@@ -3008,7 +3008,7 @@ static int unix_shutdown(struct socket *sock, int mode)
 	++mode;
 
 	unix_state_lock(sk);
-	sk->sk_shutdown |= mode;
+	WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode);
 	other = unix_peer(sk);
 	if (other)
 		sock_hold(other);
@@ -3028,7 +3028,7 @@ static int unix_shutdown(struct socket *sock, int mode)
 		if (mode&SEND_SHUTDOWN)
 			peer_mode |= RCV_SHUTDOWN;
 		unix_state_lock(other);
-		other->sk_shutdown |= peer_mode;
+		WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode);
 		unix_state_unlock(other);
 		other->sk_state_change(other);
 		if (peer_mode == SHUTDOWN_MASK)
@@ -3160,16 +3160,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask;
+	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
+	shutdown = READ_ONCE(sk->sk_shutdown);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err))
 		mask |= EPOLLERR;
-	if (sk->sk_shutdown == SHUTDOWN_MASK)
+	if (shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
 
 	/* readable? */
@@ -3203,9 +3205,11 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk, *other;
 	unsigned int writable;
 	__poll_t mask;
+	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
+	shutdown = READ_ONCE(sk->sk_shutdown);
 
 	/* exceptional events? */
 	if (READ_ONCE(sk->sk_err) ||
@@ -3213,9 +3217,9 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
-	if (sk->sk_shutdown == SHUTDOWN_MASK)
+	if (shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
 
 	/* readable? */