From mboxrd@z Thu Jan 1 00:00:00 1970 From: Simon Horman Subject: [PATCH v2 net-next 2/2] net/sched: allow flower to match tunnel options Date: Wed, 27 Sep 2017 10:16:34 +0200 Message-ID: <1506500194-17637-3-git-send-email-simon.horman@netronome.com> References: <1506500194-17637-1-git-send-email-simon.horman@netronome.com> Cc: Jamal Hadi Salim , Cong Wang , netdev@vger.kernel.org, oss-drivers@netronome.com, Simon Horman To: David Miller , Jiri Pirko Return-path: Received: from mail-qk0-f176.google.com ([209.85.220.176]:56491 "EHLO mail-qk0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751739AbdI0IQ4 (ORCPT ); Wed, 27 Sep 2017 04:16:56 -0400 Received: by mail-qk0-f176.google.com with SMTP id g128so12516600qke.13 for ; Wed, 27 Sep 2017 01:16:55 -0700 (PDT) In-Reply-To: <1506500194-17637-1-git-send-email-simon.horman@netronome.com> Sender: netdev-owner@vger.kernel.org List-ID: Allow matching on options in tunnel headers. This makes use of existing tunnel metadata support. Options are a bytestring of up to 256 bytes. Tunnel implementations may support less or more options, or no options at all. e.g. # ip link add name geneve0 type geneve dstport 0 external # tc qdisc add dev geneve0 ingress # tc filter add dev geneve0 protocol ip parent ffff: \ flower \ enc_src_ip 10.0.99.192 \ enc_dst_ip 10.0.99.193 \ enc_key_id 11 \ enc_opts 0102800100800020/fffffffffffffff0 \ ip_proto udp \ action mirred egress redirect dev eth1 Signed-off-by: Simon Horman Reviewed-by: Jakub Kicinski --- v2 * Correct example which was incorrectly described setting rather than matching tunnel options --- include/net/flow_dissector.h | 13 +++++++++++++ include/uapi/linux/pkt_cls.h | 3 +++ net/sched/cls_flower.c | 35 ++++++++++++++++++++++++++++++++++- 3 files changed, 50 insertions(+), 1 deletion(-) diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index fc3dce730a6b..43f98bf0b349 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -183,6 +183,18 @@ struct flow_dissector_key_ip { __u8 ttl; }; +/** + * struct flow_dissector_key_enc_opts: + * @data: data + * @len: len + */ +struct flow_dissector_key_enc_opts { + u8 data[256]; /* Using IP_TUNNEL_OPTS_MAX is desired here + * but seems difficult to #include + */ + u8 len; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -205,6 +217,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ + FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d5e2bf68d0d4..7a09a28f21e0 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -467,6 +467,9 @@ enum { TCA_FLOWER_KEY_IP_TTL, /* u8 */ TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_OPTS, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + __TCA_FLOWER_MAX, }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d230cb4c8094..e72a17c46f07 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -51,6 +51,7 @@ struct fl_flow_key { struct flow_dissector_key_mpls mpls; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ip ip; + struct flow_dissector_key_enc_opts enc_opts; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -181,6 +182,11 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); skb_key.enc_tp.src = key->tp_src; skb_key.enc_tp.dst = key->tp_dst; + + if (info->options_len) { + skb_key.enc_opts.len = info->options_len; + ip_tunnel_info_opts_get(skb_key.enc_opts.data, info); + } } skb_key.indev_ifindex = skb->skb_iif; @@ -421,6 +427,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_IP_TOS_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TTL] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_IP_TTL_MASK] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_BINARY }, + [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_BINARY }, }; static void fl_set_key_val(struct nlattr **tb, @@ -712,6 +720,26 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, sizeof(key->enc_tp.dst)); + if (tb[TCA_FLOWER_KEY_ENC_OPTS]) { + key->enc_opts.len = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]); + + if (key->enc_opts.len > sizeof(key->enc_opts.data)) + return -EINVAL; + + /* enc_opts is variable length. + * If present ensure the value and mask are the same length. + */ + if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK] && + nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) != key->enc_opts.len) + return -EINVAL; + + mask->enc_opts.len = key->enc_opts.len; + fl_set_key_val(tb, key->enc_opts.data, TCA_FLOWER_KEY_ENC_OPTS, + mask->enc_opts.data, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + key->enc_opts.len); + } + if (tb[TCA_FLOWER_KEY_FLAGS]) ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags); @@ -804,6 +832,8 @@ static void fl_init_dissector(struct cls_fl_head *head, enc_control); FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts); skb_flow_dissector_init(&head->dissector, keys, cnt); } @@ -1330,7 +1360,10 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, TCA_FLOWER_KEY_ENC_UDP_DST_PORT, &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, - sizeof(key->enc_tp.dst))) + sizeof(key->enc_tp.dst)) || + fl_dump_key_val(skb, key->enc_opts.data, TCA_FLOWER_KEY_ENC_OPTS, + mask->enc_opts.data, TCA_FLOWER_KEY_ENC_OPTS_MASK, + key->enc_opts.len)) goto nla_put_failure; if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) -- 2.1.4