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
  ...

4 files changed, 19 insertions, 14 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 5662dff3d381..176eb5834746 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -807,18 +807,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	__poll_t mask;
+	u8 shutdown;
 
 	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* exceptional events? */
-	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
+	if (READ_ONCE(sk->sk_err) ||
+	    !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
-	if (sk->sk_shutdown & RCV_SHUTDOWN)
+	shutdown = READ_ONCE(sk->sk_shutdown);
+	if (shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
-	if (sk->sk_shutdown == SHUTDOWN_MASK)
+	if (shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
 
 	/* readable? */
@@ -827,10 +830,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 
 	/* Connection-based need to check for termination and startup */
 	if (connection_based(sk)) {
-		if (sk->sk_state == TCP_CLOSE)
+		int state = READ_ONCE(sk->sk_state);
+
+		if (state == TCP_CLOSE)
 			mask |= EPOLLHUP;
 		/* connection hasn't started yet? */
-		if (sk->sk_state == TCP_SYN_SENT)
+		if (state == TCP_SYN_SENT)
 			return mask;
 	}
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 735096d42c1d..b3c13e041935 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3335,7 +3335,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		type = eth->h_proto;
 	}
 
-	return __vlan_get_protocol(skb, type, depth);
+	return vlan_get_protocol_and_depth(skb, type, depth);
 }
 
 /* openvswitch calls this on rx path, so we need a different check.
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 26a586007d8b..515ec5cdc79c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5298,7 +5298,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 	u32 csum_end = (u32)start + (u32)off + sizeof(__sum16);
 	u32 csum_start = skb_headroom(skb) + (u32)start;
 
-	if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) {
+	if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) {
 		net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n",
 				     start, off, skb_headroom(skb), skb_headlen(skb));
 		return false;
@@ -5306,7 +5306,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	skb->csum_start = csum_start;
 	skb->csum_offset = off;
-	skb_set_transport_header(skb, start);
+	skb->transport_header = csum_start;
 	return true;
 }
 EXPORT_SYMBOL_GPL(skb_partial_csum_set);
diff --git a/net/core/stream.c b/net/core/stream.c
index 434446ab14c5..f5c4e47df165 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -73,8 +73,8 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
 		add_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending++;
 		done = sk_wait_event(sk, timeo_p,
-				     !sk->sk_err &&
-				     !((1 << sk->sk_state) &
+				     !READ_ONCE(sk->sk_err) &&
+				     !((1 << READ_ONCE(sk->sk_state)) &
 				       ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait);
 		remove_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending--;
@@ -87,9 +87,9 @@ EXPORT_SYMBOL(sk_stream_wait_connect);
  * sk_stream_closing - Return 1 if we still have things to send in our buffers.
  * @sk: socket to verify
  */
-static inline int sk_stream_closing(struct sock *sk)
+static int sk_stream_closing(const struct sock *sk)
 {
-	return (1 << sk->sk_state) &
+	return (1 << READ_ONCE(sk->sk_state)) &
 	       (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK);
 }
 
@@ -142,8 +142,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		sk->sk_write_pending++;
-		sk_wait_event(sk, &current_timeo, sk->sk_err ||
-						  (sk->sk_shutdown & SEND_SHUTDOWN) ||
+		sk_wait_event(sk, &current_timeo, READ_ONCE(sk->sk_err) ||
+						  (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
 						  (sk_stream_memory_free(sk) &&
 						  !vm_wait), &wait);
 		sk->sk_write_pending--;