From: Horms Subject: Re: [patch 3/3] Replace reverse_route() with a call to ip_route_me_harder() Date: Tue, 19 Sep 2006 12:56:08 +0900 Message-ID: <20060919035606.GA18377@verge.net.au> References: <20060919024507.458115000@tabatha.lab.ultramonkey.org> <20060919025203.875028000@tabatha.lab.ultramonkey.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Ken Brownfield , Roberto Nibali , Farid Sarwari , Patrick McHardy , Julian Anastasov , David Black , Joseph Mack NA3T , David Miller Return-path: To: netfilter-devel@lists.netfilter.org Content-Disposition: inline In-Reply-To: <20060919025203.875028000@tabatha.lab.ultramonkey.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: netfilter-devel-bounces@lists.netfilter.org Errors-To: netfilter-devel-bounces@lists.netfilter.org List-Id: netfilter-devel.vger.kernel.org Sorry, the previous invocation of this patch was hopelessly broken. This should be a little better. -- Horms H: http://www.vergenet.net/~horms/ W: http://www.valinux.co.jp/en/ *** Please review this patch carefully, I'm not sure that it is correct *** ip_route_me_harder() can now be passed the address type, which means that inet_addr_type() is not called internally, and thus ip_route_me_harder() is now reasonably cheap. Make use of this by replacing ipt_REJECT's the reverse route, which is largely a duplication of ip_route_me_harder(). Signed-Off-By: Simon Horman Index: net-2.6.19/net/ipv4/netfilter/ipt_REJECT.c =================================================================== --- net-2.6.19.orig/net/ipv4/netfilter/ipt_REJECT.c 2006-09-19 12:50:43.000000000 +0900 +++ net-2.6.19/net/ipv4/netfilter/ipt_REJECT.c 2006-09-19 12:53:42.000000000 +0900 @@ -38,13 +38,9 @@ #define DEBUGP(format, args...) #endif -static inline struct rtable *route_reverse(struct sk_buff *skb, - struct tcphdr *tcph, int hook) +static inline int send_reset_route(struct sk_buff **pskb, int hook) { - struct iphdr *iph = skb->nh.iph; - struct dst_entry *odst; - struct flowi fl = {}; - struct rtable *rt; + int addr_type; /* We don't require ip forwarding to be enabled to be able to * send a RST reply for bridged traffic. */ @@ -52,62 +48,23 @@ #ifdef CONFIG_BRIDGE_NETFILTER || (skb->nf_bridge && skb->nf_bridge->mask & BRNF_BRIDGED) #endif - ) { - fl.nl_u.ip4_u.daddr = iph->saddr; - if (hook == NF_IP_LOCAL_IN) - fl.nl_u.ip4_u.saddr = iph->daddr; - fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); + ) + addr_type = 1; + else + addr_type = 2; - if (ip_route_output_key(&rt, &fl) != 0) - return NULL; - } else { - /* non-local src, find valid iif to satisfy - * rp-filter when calling ip_route_input. */ - fl.nl_u.ip4_u.daddr = iph->daddr; - if (ip_route_output_key(&rt, &fl) != 0) - return NULL; - - odst = skb->dst; - if (ip_route_input(skb, iph->saddr, iph->daddr, - RT_TOS(iph->tos), rt->u.dst.dev) != 0) { - dst_release(&rt->u.dst); - return NULL; - } - dst_release(&rt->u.dst); - rt = (struct rtable *)skb->dst; - skb->dst = odst; - - fl.nl_u.ip4_u.daddr = iph->saddr; - fl.nl_u.ip4_u.saddr = iph->daddr; - fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); - } - - if (rt->u.dst.error) { - dst_release(&rt->u.dst); - return NULL; - } - - fl.proto = IPPROTO_TCP; - fl.fl_ip_sport = tcph->dest; - fl.fl_ip_dport = tcph->source; - security_skb_classify_flow(skb, &fl); - - xfrm_lookup((struct dst_entry **)&rt, &fl, NULL, 0); - - return rt; + return ip_route_me_harder(pskb, addr_type); } /* Send RST reply */ static void send_reset(struct sk_buff *oldskb, int hook) { - struct sk_buff *nskb; + struct sk_buff *nskb, **pnskb; struct iphdr *iph = oldskb->nh.iph; struct tcphdr _otcph, *oth, *tcph; - struct rtable *rt; u_int16_t tmp_port; u_int32_t tmp_addr; int needs_ack; - int hh_len; /* IP header checks: fragment. */ if (oldskb->nh.iph->frag_off & htons(IP_OFFSET)) @@ -126,23 +83,15 @@ if (nf_ip_checksum(oldskb, hook, iph->ihl * 4, IPPROTO_TCP)) return; - if ((rt = route_reverse(oldskb, oth, hook)) == NULL) - return; - - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); - /* We need a linear, writeable skb. We also need to expand headroom in case hh_len of incoming interface < hh_len of - outgoing interface */ - nskb = skb_copy_expand(oldskb, hh_len, skb_tailroom(oldskb), + outgoing interface. As routing happens later, using + ip_route_me_harder(), LL_MAX_HEADER is used as hh_len, + to ensure there will always be enough space. */ + nskb = skb_copy_expand(oldskb, LL_MAX_HEADER, skb_tailroom(oldskb), GFP_ATOMIC); - if (!nskb) { - dst_release(&rt->u.dst); + if (!nskb) return; - } - - dst_release(nskb->dst); - nskb->dst = &rt->u.dst; /* This packet will not be the same as the other: clear nf fields */ nf_reset(nskb); @@ -204,6 +153,12 @@ nskb->nh.iph->check = ip_fast_csum((unsigned char *)nskb->nh.iph, nskb->nh.iph->ihl); + /* Route - this may not need to be so late */ + pnskb = &nskb; + if (send_reset_route(pnskb, hook) < 0) + goto free_nskb; + nskb = *pnskb; + /* "Never happens" */ if (nskb->len > dst_mtu(nskb->dst)) goto free_nskb;