Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:
 "I was battling a cold after some recent trips, so quite a bit piled up
  meanwhile, sorry about that.

  Highlights:

   1) Fix fd leak in various bpf selftests, from Brian Vazquez.

   2) Fix crash in xsk when device doesn't support some methods, from
      Magnus Karlsson.

   3) Fix various leaks and use-after-free in rxrpc, from David Howells.

   4) Fix several SKB leaks due to confusion of who owns an SKB and who
      should release it in the llc code. From Eric Biggers.

   5) Kill a bunc of KCSAN warnings in TCP, from Eric Dumazet.

   6) Jumbo packets don't work after resume on r8169, as the BIOS resets
      the chip into non-jumbo mode during suspend. From Heiner Kallweit.

   7) Corrupt L2 header during MPLS push, from Davide Caratti.

   8) Prevent possible infinite loop in tc_ctl_action, from Eric
      Dumazet.

   9) Get register bits right in bcmgenet driver, based upon chip
      version. From Florian Fainelli.

  10) Fix mutex problems in microchip DSA driver, from Marek Vasut.

  11) Cure race between route lookup and invalidation in ipv4, from Wei
      Wang.

  12) Fix performance regression due to false sharing in 'net'
      structure, from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (145 commits)
  net: reorder 'struct net' fields to avoid false sharing
  net: dsa: fix switch tree list
  net: ethernet: dwmac-sun8i: show message only when switching to promisc
  net: aquantia: add an error handling in aq_nic_set_multicast_list
  net: netem: correct the parent's backlog when corrupted packet was dropped
  net: netem: fix error path for corrupted GSO frames
  macb: propagate errors when getting optional clocks
  xen/netback: fix error path of xenvif_connect_data()
  net: hns3: fix mis-counting IRQ vector numbers issue
  net: usb: lan78xx: Connect PHY before registering MAC
  vsock/virtio: discard packets if credit is not respected
  vsock/virtio: send a credit update when buffer size is changed
  mlxsw: spectrum_trap: Push Ethernet header before reporting trap
  net: ensure correct skb->tstamp in various fragmenters
  net: bcmgenet: reset 40nm EPHY on energy detect
  net: bcmgenet: soft reset 40nm EPHYs before MAC init
  net: phy: bcm7xxx: define soft_reset for 40nm EPHY
  net: bcmgenet: don't set phydev->link from MAC
  net: Update address for MediaTek ethernet driver in MAINTAINERS
  ipv4: fix race condition between route lookup and invalidation
  ...

1 files changed, 22 insertions, 15 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3578357abe30..a2e52ad7cdab 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -359,7 +359,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
 	sndmem *= nr_segs * per_mss;
 
 	if (sk->sk_sndbuf < sndmem)
-		sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
+		WRITE_ONCE(sk->sk_sndbuf,
+			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -483,8 +484,9 @@ static void tcp_clamp_window(struct sock *sk)
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
-		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
-				    net->ipv4.sysctl_tcp_rmem[2]);
+		WRITE_ONCE(sk->sk_rcvbuf,
+			   min(atomic_read(&sk->sk_rmem_alloc),
+			       net->ipv4.sysctl_tcp_rmem[2]));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -648,7 +650,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
 			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
-			sk->sk_rcvbuf = rcvbuf;
+			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make the window clamp follow along.  */
 			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
@@ -2666,7 +2668,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
-	if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) &&
+	if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
 	    tcp_try_undo_loss(sk, false))
 		return;
 
@@ -2990,7 +2992,7 @@ void tcp_rearm_rto(struct sock *sk)
 	/* If the retrans timer is currently being used by Fast Open
 	 * for SYN-ACK retrans purpose, stay put.
 	 */
-	if (tp->fastopen_rsk)
+	if (rcu_access_pointer(tp->fastopen_rsk))
 		return;
 
 	if (!tp->packets_out) {
@@ -3362,7 +3364,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_received += delta;
-	tp->rcv_nxt = seq;
+	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
 /* Update our send window.
@@ -5356,7 +5358,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	}
 
 	tp->urg_data = TCP_URG_NOTYET;
-	tp->urg_seq = ptr;
+	WRITE_ONCE(tp->urg_seq, ptr);
 
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
@@ -5932,7 +5934,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Ok.. it's good. Set up sequence numbers and
 		 * move to established.
 		 */
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -5961,7 +5963,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 
 		smc_check_reset_syn(tp);
 
@@ -6035,8 +6037,8 @@ discard:
 			tp->tcp_header_len = sizeof(struct tcphdr);
 		}
 
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6087,6 +6089,8 @@ reset_and_undo:
 
 static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 {
+	struct request_sock *req;
+
 	tcp_try_undo_loss(sk, false);
 
 	/* Reset rtx states to prevent spurious retransmits_timed_out() */
@@ -6096,7 +6100,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
 	 */
-	reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false);
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	reqsk_fastopen_remove(sk, req, false);
 
 	/* Re-arm the timer because data may have been sent out.
 	 * This is similar to the regular data transmission case
@@ -6171,7 +6177,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	tcp_mstamp_refresh(tp);
 	tp->rx_opt.saw_tstamp = 0;
-	req = tp->fastopen_rsk;
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
 	if (req) {
 		bool req_stolen;
 
@@ -6211,7 +6218,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			tcp_try_undo_spurious_syn(sk);
 			tp->retrans_stamp = 0;
 			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tp->copied_seq = tp->rcv_nxt;
+			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);