Merge tag 'net-5.19-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth and netfilter, no known blockers for
  the release.

  Current release - regressions:

   - wifi: mac80211: do not abuse fq.lock in ieee80211_do_stop(), fix
     taking the lock before its initialized

   - Bluetooth: mgmt: fix double free on error path

  Current release - new code bugs:

   - eth: ice: fix tunnel checksum offload with fragmented traffic

  Previous releases - regressions:

   - tcp: md5: fix IPv4-mapped support after refactoring, don't take the
     pure v6 path

   - Revert "tcp: change pingpong threshold to 3", improving detection
     of interactive sessions

   - mld: fix netdev refcount leak in mld_{query | report}_work() due to
     a race

   - Bluetooth:
      - always set event mask on suspend, avoid early wake ups
      - L2CAP: fix use-after-free caused by l2cap_chan_put

   - bridge: do not send empty IFLA_AF_SPEC attribute

  Previous releases - always broken:

   - ping6: fix memleak in ipv6_renew_options()

   - sctp: prevent null-deref caused by over-eager error paths

   - virtio-net: fix the race between refill work and close, resulting
     in NAPI scheduled after close and a BUG()

   - macsec:
      - fix three netlink parsing bugs
      - avoid breaking the device state on invalid change requests
      - fix a memleak in another error path

  Misc:

   - dt-bindings: net: ethernet-controller: rework 'fixed-link' schema

   - two more batches of sysctl data race adornment"

* tag 'net-5.19-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits)
  stmmac: dwmac-mediatek: fix resource leak in probe
  ipv6/addrconf: fix a null-ptr-deref bug for ip6_ptr
  net: ping6: Fix memleak in ipv6_renew_options().
  net/funeth: Fix fun_xdp_tx() and XDP packet reclaim
  sctp: leave the err path free in sctp_stream_init to sctp_stream_free
  sfc: disable softirqs for ptp TX
  ptp: ocp: Select CRC16 in the Kconfig.
  tcp: md5: fix IPv4-mapped support
  virtio-net: fix the race between refill work and close
  mptcp: Do not return EINPROGRESS when subflow creation succeeds
  Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put
  Bluetooth: Always set event mask on suspend
  Bluetooth: mgmt: Fix double free on error path
  wifi: mac80211: do not abuse fq.lock in ieee80211_do_stop()
  ice: do not setup vlan for loopback VSI
  ice: check (DD | EOF) bits on Rx descriptor rather than (EOP | RS)
  ice: Fix VSIs unable to share unicast MAC
  ice: Fix tunnel checksum offload with fragmented traffic
  ice: Fix max VLANs available for VF
  netfilter: nft_queue: only allow supported familes and hooks
  ...

1 files changed, 12 insertions, 15 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c38e07b50639..4c376b6d8764 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 	if (tcp_packets_in_flight(tp) == 0)
 		tcp_ca_event(sk, CA_EVENT_TX_START);
 
-	/* If this is the first data packet sent in response to the
-	 * previous received data,
-	 * and it is a reply for ato after last received packet,
-	 * increase pingpong count.
-	 */
-	if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
-	    (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
-		inet_csk_inc_pingpong_cnt(sk);
-
 	tp->lsndtime = now;
+
+	/* If it is a reply for ato after last received
+	 * packet, enter pingpong mode.
+	 */
+	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+		inet_csk_enter_pingpong_mode(sk);
 }
 
 /* Account for an ACK we sent. */
@@ -230,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	 * which we interpret as a sign the remote TCP is not
 	 * misinterpreting the window field as a signed quantity.
 	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
 		(*rcv_wnd) = min_t(u32, space, U16_MAX);
@@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	*rcv_wscale = 0;
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
-		space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
@@ -285,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk)
 	 * scaled window.
 	 */
 	if (!tp->rx_opt.rcv_wscale &&
-	    sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		new_win = min(new_win, MAX_TCP_WINDOW);
 	else
 		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -1976,7 +1973,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 
 	bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
 
-	r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log;
+	r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
 	if (r < BITS_PER_TYPE(sk->sk_gso_max_size))
 		bytes += sk->sk_gso_max_size >> r;
 
@@ -1995,7 +1992,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 
 	min_tso = ca_ops->min_tso_segs ?
 			ca_ops->min_tso_segs(sk) :
-			sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+			READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
 
 	tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
 	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2507,7 +2504,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
 	if (sk->sk_pacing_status == SK_PACING_NONE)
 		limit = min_t(unsigned long, limit,
-			      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+			      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
 	limit <<= factor;
 
 	if (static_branch_unlikely(&tcp_tx_delay_enabled) &&