sctp: disable BH before calling udp_tunnel_xmit_skb()

udp_tunnel_xmit_skb() / udp_tunnel6_xmit_skb() are expected to run with
BH disabled.  After commit 6f1a9140ecda ("add xmit recursion limit to
tunnel xmit functions"), on the path:

  udp(6)_tunnel_xmit_skb() -> ip(6)tunnel_xmit()

dev_xmit_recursion_inc()/dec() must stay balanced on the same CPU.

Without local_bh_disable(), the context may move between CPUs, which can
break the inc/dec pairing. This may lead to incorrect recursion level
detection and cause packets to be dropped in ip(6)_tunnel_xmit() or
__dev_queue_xmit().

Fix it by disabling BH around both IPv4 and IPv6 SCTP UDP xmit paths.

In my testing, after enabling the SCTP over UDP:

  # ip net exec ha sysctl -w net.sctp.udp_port=9899
  # ip net exec ha sysctl -w net.sctp.encap_port=9899
  # ip net exec hb sysctl -w net.sctp.udp_port=9899
  # ip net exec hb sysctl -w net.sctp.encap_port=9899

  # ip net exec ha iperf3 -s

- without this patch:

  # ip net exec hb iperf3 -c 192.168.0.1 --sctp
  [  5]   0.00-10.00  sec  37.2 MBytes  31.2 Mbits/sec  sender
  [  5]   0.00-10.00  sec  37.1 MBytes  31.1 Mbits/sec  receiver

- with this patch:

  # ip net exec hb iperf3 -c 192.168.0.1 --sctp
  [  5]   0.00-10.00  sec  3.14 GBytes  2.69 Gbits/sec  sender
  [  5]   0.00-10.00  sec  3.14 GBytes  2.69 Gbits/sec  receiver

Fixes: 6f1a9140ecda ("net: add xmit recursion limit to tunnel xmit functions")
Fixes: 046c052b475e ("sctp: enable udp tunneling socks")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Link: https://patch.msgid.link/c874a8548221dcd56ff03c65ba75a74e6cf99119.1776017727.git.lucien.xin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 53a5c027f8e318b609b3f98f70d19997aa9258fb..cd15b695607ebeee4bdaf8685e621b3e2275512d 100644 (file)
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -261,9 +261,11 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
        skb_set_inner_ipproto(skb, IPPROTO_SCTP);
        label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6);
 
+       local_bh_disable();
        udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, &fl6->daddr,
                             tclass, ip6_dst_hoplimit(dst), label,
                             sctp_sk(sk)->udp_port, t->encap_port, false, 0);
+       local_bh_enable();
        return 0;
 }
 

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 828a59b8e7bf8d110f1ffd724c9f6574b1cd62b8..5800e7ee7ea0229de6e25f1967de571650c11be3 100644 (file)
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1070,10 +1070,12 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
        skb_reset_inner_mac_header(skb);
        skb_reset_inner_transport_header(skb);
        skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+       local_bh_disable();
        udp_tunnel_xmit_skb(dst_rtable(dst), sk, skb, fl4->saddr,
                            fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
                            sctp_sk(sk)->udp_port, t->encap_port, false, false,
                            0);
+       local_bh_enable();
        return 0;
 }