Merge tag 'net-6.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Happy Wear a Dress Day.

  Fairly standard-sized batch of fixes, accounting for the lack of
  sub-tree submissions this week. The mlx5 IRQ fixes are notable, people
  were complaining about that. No fires burning.

  Current release - regressions:

   - eth: mlx5e:
      - multiple fixes for dynamic IRQ allocation
      - prevent encap offload when neigh update is running

   - eth: mana: fix perf regression: remove rx_cqes, tx_cqes counters

  Current release - new code bugs:

   - eth: mlx5e: DR, add missing mutex init/destroy in pattern manager

  Previous releases - always broken:

   - tcp: deny tcp_disconnect() when threads are waiting

   - sched: prevent ingress Qdiscs from getting installed in random
     locations in the hierarchy and moving around

   - sched: flower: fix possible OOB write in fl_set_geneve_opt()

   - netlink: fix NETLINK_LIST_MEMBERSHIPS length report

   - udp6: fix race condition in udp6_sendmsg & connect

   - tcp: fix mishandling when the sack compression is deferred

   - rtnetlink: validate link attributes set at creation time

   - mptcp: fix connect timeout handling

   - eth: stmmac: fix call trace when stmmac_xdp_xmit() is invoked

   - eth: amd-xgbe: fix the false linkup in xgbe_phy_status

   - eth: mlx5e:
      - fix corner cases in internal buffer configuration
      - drain health before unregistering devlink

   - usb: qmi_wwan: set DTR quirk for BroadMobi BM818

  Misc:

   - tcp: return user_mss for TCP_MAXSEG in CLOSE/LISTEN state if
     user_mss set"

* tag 'net-6.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits)
  mptcp: fix active subflow finalization
  mptcp: add annotations around sk->sk_shutdown accesses
  mptcp: fix data race around msk->first access
  mptcp: consolidate passive msk socket initialization
  mptcp: add annotations around msk->subflow accesses
  mptcp: fix connect timeout handling
  rtnetlink: add the missing IFLA_GRO_ tb check in validate_linkmsg
  rtnetlink: move IFLA_GSO_ tb check to validate_linkmsg
  rtnetlink: call validate_linkmsg in rtnl_create_link
  ice: recycle/free all of the fragments from multi-buffer frame
  net: phy: mxl-gpy: extend interrupt fix to all impacted variants
  net: renesas: rswitch: Fix return value in error path of xmit
  net: dsa: mv88e6xxx: Increase wait after reset deactivation
  net: ipa: Use correct value for IPA_STATUS_SIZE
  tcp: fix mishandling when the sack compression is deferred.
  net/sched: flower: fix possible OOB write in fl_set_geneve_opt()
  sfc: fix error unwinds in TC offload
  net/mlx5: Read embedded cpu after init bit cleared
  net/mlx5e: Fix error handling in mlx5e_refresh_tirs
  net/mlx5: Ensure af_desc.mask is properly initialized
  ...

5 files changed, 25 insertions, 5 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c4aab3aacbd8..4a76ebf793b8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 
 	add_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending += writebias;
+	sk->sk_wait_pending++;
 
 	/* Basic assumption: if someone sets sk->sk_err, he _must_
 	 * change state of the socket from TCP_SYN_*.
@@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
 	}
 	remove_wait_queue(sk_sleep(sk), &wait);
 	sk->sk_write_pending -= writebias;
+	sk->sk_wait_pending--;
 	return timeo;
 }
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 65ad4251f6fd..1386787eaf1a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	if (newsk) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
 
+		newsk->sk_wait_pending = 0;
 		inet_sk_set_state(newsk, TCP_SYN_RECV);
 		newicsk->icsk_bind_hash = NULL;
 		newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a60f6f4e7cd9..8d20d9221238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3081,6 +3081,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	int old_state = sk->sk_state;
 	u32 seq;
 
+	/* Deny disconnect if other threads are blocked in sk_wait_event()
+	 * or inet_wait_for_connect().
+	 */
+	if (sk->sk_wait_pending)
+		return -EBUSY;
+
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
 
@@ -4072,7 +4078,8 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	switch (optname) {
 	case TCP_MAXSEG:
 		val = tp->mss_cache;
-		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+		if (tp->rx_opt.user_mss &&
+		    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 			val = tp->rx_opt.user_mss;
 		if (tp->repair)
 			val = tp->rx_opt.mss_clamp;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 61b6710f337a..bf8b22218dd4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
 	}
 }
 
-static void tcp_sack_compress_send_ack(struct sock *sk)
+void tcp_sack_compress_send_ack(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b839c2f91292..39eb947fe392 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk)
 void tcp_delack_timer_handler(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
-	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+		return;
+
+	/* Handling the sack compression case */
+	if (tp->compressed_ack) {
+		tcp_mstamp_refresh(tp);
+		tcp_sack_compress_send_ack(sk);
+		return;
+	}
+
+	if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		return;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk)
 			inet_csk_exit_pingpong_mode(sk);
 			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
-		tcp_mstamp_refresh(tcp_sk(sk));
+		tcp_mstamp_refresh(tp);
 		tcp_send_ack(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
 	}