Merge tag 'net-5.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.10-rc6, including fixes from the WiFi driver,
  and CAN subtrees.

  Current release - regressions:

   - gro_cells: reduce number of synchronize_net() calls

   - ch_ktls: release a lock before jumping to an error path

  Current release - always broken:

   - tcp: Allow full IP tos/IPv6 tclass to be reflected in L3 header

  Previous release - regressions:

   - net/tls: fix missing received data after fast remote close

   - vsock/virtio: discard packets only when socket is really closed

   - sock: set sk_err to ee_errno on dequeue from errq

   - cxgb4: fix the panic caused by non smac rewrite

  Previous release - always broken:

   - tcp: fix corner cases around setting ECN with BPF selection of
     congestion control

   - tcp: fix race condition when creating child sockets from syncookies
     on loopback interface

   - usbnet: ipheth: fix connectivity with iOS 14

   - tun: honor IOCB_NOWAIT flag

   - net/packet: fix packet receive on L3 devices without visible hard
     header

   - devlink: Make sure devlink instance and port are in same net
     namespace

   - net: openvswitch: fix TTL decrement action netlink message format

   - bonding: wait for sysfs kobject destruction before freeing struct
     slave

   - net: stmmac: fix upstream patch applied to the wrong context

   - bnxt_en: fix return value and unwind in probe error paths

  Misc:

   - devlink: add extra layer of categorization to the reload stats uAPI
     before it's released"

* tag 'net-5.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (68 commits)
  sock: set sk_err to ee_errno on dequeue from errq
  mptcp: fix NULL ptr dereference on bad MPJ
  net: openvswitch: fix TTL decrement action netlink message format
  can: af_can: can_rx_unregister(): remove WARN() statement from list operation sanity check
  can: m_can: m_can_dev_setup(): add support for bosch mcan version 3.3.0
  can: m_can: fix nominal bitiming tseg2 min for version >= 3.1
  can: m_can: m_can_open(): remove IRQF_TRIGGER_FALLING from request_threaded_irq()'s flags
  can: mcp251xfd: mcp251xfd_probe(): bail out if no IRQ was given
  can: gs_usb: fix endianess problem with candleLight firmware
  ch_ktls: lock is not freed
  net/tls: Protect from calling tls_dev_del for TLS RX twice
  devlink: Make sure devlink instance and port are in same net namespace
  devlink: Hold rtnl lock while reading netdev attributes
  ptp: clockmatrix: bug fix for idtcm_strverscmp
  enetc: Let the hardware auto-advance the taprio base-time of 0
  gro_cells: reduce number of synchronize_net() calls
  net: stmmac: fix incorrect merge of patch upstream
  ipv6: addrlabel: fix possible memory leak in ip6addrlbl_net_init
  Documentation: netdev-FAQ: suggest how to post co-dependent series
  ibmvnic: enhance resetting status check during module exit
  ...

1 files changed, 22 insertions, 6 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7352c097ae48..8391aa29e7a4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -980,17 +980,22 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 	skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
 
-	tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
-			tcp_rsk(req)->syn_tos : inet_sk(sk)->tos;
-
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
+		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+				tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :
+				inet_sk(sk)->tos;
+
+		if (!INET_ECN_is_capable(tos) &&
+		    tcp_bpf_ca_needs_ecn((struct sock *)req))
+			tos |= INET_ECN_ECT_0;
+
 		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
 					    rcu_dereference(ireq->ireq_opt),
-					    tos & ~INET_ECN_MASK);
+					    tos);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -1498,6 +1503,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  bool *own_req)
 {
 	struct inet_request_sock *ireq;
+	bool found_dup_sk = false;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1575,12 +1581,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+				       &found_dup_sk);
 	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
 		ireq->ireq_opt = NULL;
 	} else {
-		newinet->inet_opt = NULL;
+		if (!req_unhash && found_dup_sk) {
+			/* This code path should only be executed in the
+			 * syncookie case only
+			 */
+			bh_unlock_sock(newsk);
+			sock_put(newsk);
+			newsk = NULL;
+		} else {
+			newinet->inet_opt = NULL;
+		}
 	}
 	return newsk;