From patchwork Fri Mar 20 15:42:50 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Robert Shearman X-Patchwork-Id: 452695 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 15C05140079 for ; Sat, 21 Mar 2015 02:44:29 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751899AbbCTPoX (ORCPT ); Fri, 20 Mar 2015 11:44:23 -0400 Received: from mx0a-000f0801.pphosted.com ([67.231.144.122]:38936 "EHLO mx0a-000f0801.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751849AbbCTPoU (ORCPT ); Fri, 20 Mar 2015 11:44:20 -0400 Received: from pps.filterd (m0000542.ppops.net [127.0.0.1]) by mx0a-000f0801.pphosted.com (8.14.7/8.14.7) with SMTP id t2KF3M8Z007366; Fri, 20 Mar 2015 08:44:19 -0700 Received: from hq1wp-exchub02.corp.brocade.com ([144.49.131.13]) by mx0a-000f0801.pphosted.com with ESMTP id 1t8nek8434-16 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NOT); Fri, 20 Mar 2015 08:44:18 -0700 Received: from BRMWP-EXCHUB02.corp.brocade.com (172.16.187.99) by HQ1WP-EXCHUB02.corp.brocade.com (10.70.38.101) with Microsoft SMTP Server (TLS) id 14.3.123.3; Fri, 20 Mar 2015 08:44:18 -0700 Received: from brm-excashub-1.corp.brocade.com (172.16.186.49) by BRMWP-EXCHUB02.corp.brocade.com (172.16.187.99) with Microsoft SMTP Server (TLS) id 14.3.123.3; Fri, 20 Mar 2015 09:44:11 -0600 Received: from EMEAWP-CASH01.corp.brocade.com (172.29.18.10) by brm-excashub-1.corp.brocade.com (172.16.186.74) with Microsoft SMTP Server (TLS) id 8.3.298.1; Fri, 20 Mar 2015 09:44:11 -0600 Received: from BRA-2XN4P12.brocade.com (10.72.36.3) by imapeu.brocade.com (172.29.18.15) with Microsoft SMTP Server (TLS) id 8.3.298.1; Fri, 20 Mar 2015 16:44:08 +0100 From: Robert Shearman To: CC: , Robert Shearman , "Eric W. Biederman" Subject: [PATCH net-next v2 5/5] mpls: Allow payload type to be associated with label routes Date: Fri, 20 Mar 2015 15:42:50 +0000 Message-ID: <1426866170-28739-6-git-send-email-rshearma@brocade.com> X-Mailer: git-send-email 2.1.4 In-Reply-To: <1426866170-28739-1-git-send-email-rshearma@brocade.com> References: <1426800772-22378-1-git-send-email-rshearma@brocade.com> <1426866170-28739-1-git-send-email-rshearma@brocade.com> MIME-Version: 1.0 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:5.13.68, 1.0.33, 0.0.0000 definitions=2015-03-05_07:2015-03-05, 2015-03-05, 1970-01-01 signatures=0 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 spamscore=0 suspectscore=1 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=7.0.1-1402240000 definitions=main-1503050223 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org RFC 4182 s2 states that if an IPv4 Explicit NULL label is the only label on the stack, then after popping the resulting packet must be treated as a IPv4 packet and forwarded based on the IPv4 header. The same is true for IPv6 Explicit NULL with an IPv6 packet following. Therefore, when installing the IPv4/IPv6 Explicit NULL label routes, add an attribute that specifies the expected payload type for use at forwarding time for determining the type of the encapsulated packet instead of inspecting the first nibble of the packet. Cc: "Eric W. Biederman" Signed-off-by: Robert Shearman --- net/mpls/af_mpls.c | 87 ++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 55 insertions(+), 32 deletions(-) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 14c7e76..653bae1 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -23,13 +23,20 @@ /* This maximum ha length copied from the definition of struct neighbour */ #define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) +enum mpls_payload_type { + MPT_UNSPEC, /* IPv4 or IPv6 */ + MPT_IPV4, + MPT_IPV6, +}; + struct mpls_route { /* next hop label forwarding entry */ struct net_device __rcu *rt_dev; struct rcu_head rt_rcu; u32 rt_label[MAX_NEW_LABELS]; u8 rt_protocol; /* routing protocol that set this entry */ u8 rt_unlabeled : 1; - u8 rt_labels : 7; + u8 rt_payload_type : 3; + u8 rt_labels : 4; u8 rt_via_alen; u8 rt_via_table; u8 rt_via[0]; @@ -87,19 +94,24 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) return true; } -static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, - struct mpls_entry_decoded dec) +static enum mpls_payload_type mpls_pkt_determine_af(struct sk_buff *skb) { - /* RFC4385 and RFC5586 encode other packets in mpls such that - * they don't conflict with the ip version number, making - * decoding by examining the ip version correct in everything - * except for the strangest cases. - * - * The strange cases if we choose to support them will require - * manual configuration. - */ - struct iphdr *hdr4; - bool success = true; + struct iphdr *hdr4 = ip_hdr(skb); + + switch (hdr4->version) { + case 4: + return MPT_IPV4; + case 6: + return MPT_IPV6; + } + + return MPT_UNSPEC; +} + +static bool mpls_bos_egress(struct mpls_route *rt, struct sk_buff *skb, + struct mpls_entry_decoded dec) +{ + enum mpls_payload_type payload_type; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. @@ -114,24 +126,31 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, if (!pskb_may_pull(skb, 12)) return false; - /* Use ip_hdr to find the ip protocol version */ - hdr4 = ip_hdr(skb); - if (hdr4->version == 4) { + payload_type = rt->rt_payload_type; + if (payload_type == MPT_UNSPEC) + payload_type = mpls_pkt_determine_af(skb); + + switch (payload_type) { + case MPT_IPV4: { + struct iphdr *hdr4 = ip_hdr(skb); skb->protocol = htons(ETH_P_IP); csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(dec.ttl << 8)); hdr4->ttl = dec.ttl; + return true; } - else if (hdr4->version == 6) { + case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); hdr6->hop_limit = dec.ttl; + return true; } - else - /* version 0 and version 1 are used by pseudo wires */ - success = false; - return success; + case MPT_UNSPEC: + break; + } + + return false; } static int mpls_forward(struct sk_buff *skb, struct net_device *dev, @@ -210,7 +229,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, skb->protocol = htons(ETH_P_MPLS_UC); if (unlikely(!new_header_size && dec.bos)) { - if (!mpls_egress(rt, skb, dec)) + if (!mpls_bos_egress(rt, skb, dec)) goto drop; } else if (rt->rt_unlabeled) { /* Labeled traffic destined to unlabeled peer should @@ -253,16 +272,17 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { }; struct mpls_route_config { - u32 rc_protocol; - u32 rc_ifindex; - u16 rc_via_table; - u16 rc_via_alen; - u8 rc_via[MAX_VIA_ALEN]; - u32 rc_label; - u32 rc_output_labels; - u32 rc_output_label[MAX_NEW_LABELS]; - u32 rc_nlflags; - struct nl_info rc_nlinfo; + u32 rc_protocol; + u32 rc_ifindex; + u16 rc_via_table; + u16 rc_via_alen; + u8 rc_via[MAX_VIA_ALEN]; + u32 rc_label; + u32 rc_output_labels; + u32 rc_output_label[MAX_NEW_LABELS]; + u32 rc_nlflags; + enum mpls_payload_type rc_payload_type; + struct nl_info rc_nlinfo; }; static struct mpls_route *mpls_rt_alloc(size_t alen) @@ -413,6 +433,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) } rt->rt_protocol = cfg->rc_protocol; RCU_INIT_POINTER(rt->rt_dev, dev); + rt->rt_payload_type = cfg->rc_payload_type; rt->rt_via_table = cfg->rc_via_table; memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); @@ -948,6 +969,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort0; RCU_INIT_POINTER(rt0->rt_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; + rt0->rt_payload_type = MPT_IPV4; rt0->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); } @@ -958,6 +980,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort2; RCU_INIT_POINTER(rt2->rt_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; + rt2->rt_payload_type = MPT_IPV6; rt2->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); }