diff options
author | David S. Miller <davem@davemloft.net> | 2012-07-12 10:49:19 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2012-07-12 10:49:19 (GMT) |
commit | 3ec5a261aef55a32664bffd335e5c32aeadf3215 (patch) | |
tree | a2ddd1e4c432d7300396814320608ee946030fc1 | |
parent | 46d3ceabd8d98ed0ad10f20c595ca784e34786c5 (diff) | |
parent | 1ed5c48f231cd00eac0b3d2350ac61e3c825063e (diff) | |
download | linux-fsl-qoriq-3ec5a261aef55a32664bffd335e5c32aeadf3215.tar.xz |
Merge branch 'redirect_via_sock'
As described in my patch series from the other day, we need to
rearrange redirect handling so that the local initiators of packets
(sockets, tunnels, xfrms, etc.) that implement the protocols compute
the route and pass this down into the ipv4/ipv6 routing code.
These changes here do so by implementing a new dst_ops->redirect
method.
No more do we have this funny code that tries several different sets
of routing keys to try and figure out which route the redirect should
actually be applied to.
No more do we have the problem wherein TOS rewriting causes problems
for us.
Signed-off-by: David S. Miller <davem@davemloft.net>
36 files changed, 447 insertions, 351 deletions
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 4badc86..085931f 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -25,6 +25,7 @@ struct dst_ops { struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, u32 mtu); + void (*redirect)(struct dst_entry *dst, struct sk_buff *skb); int (*local_out)(struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 58cb3fc..b6b6f7d 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -133,17 +133,12 @@ extern int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr); -extern void rt6_redirect(const struct in6_addr *dest, - const struct in6_addr *src, - const struct in6_addr *saddr, - struct neighbour *neigh, - u8 *lladdr, - int on_link); - extern void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark); extern void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); +extern void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark); +extern void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); struct netlink_callback; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d4261d4..f695f39 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -251,6 +251,8 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl) atomic_dec(&fl->users); } +extern void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); + extern int ip6_ra_control(struct sock *sk, int sel); extern int ipv6_parse_hopopts(struct sk_buff *skb); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index c02b6ad..96a3b5c 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -47,6 +47,8 @@ enum { #include <linux/icmpv6.h> #include <linux/in6.h> #include <linux/types.h> +#include <linux/if_arp.h> +#include <linux/netdevice.h> #include <net/neighbour.h> @@ -80,6 +82,54 @@ struct nd_opt_hdr { __u8 nd_opt_len; } __packed; +/* ND options */ +struct ndisc_options { + struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; +#ifdef CONFIG_IPV6_ROUTE_INFO + struct nd_opt_hdr *nd_opts_ri; + struct nd_opt_hdr *nd_opts_ri_end; +#endif + struct nd_opt_hdr *nd_useropts; + struct nd_opt_hdr *nd_useropts_end; +}; + +#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] +#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] +#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] +#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] +#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] +#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] + +#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) + +extern struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, + struct ndisc_options *ndopts); + +/* + * Return the padding between the option length and the start of the + * link addr. Currently only IP-over-InfiniBand needs this, although + * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may + * also need a pad of 2. + */ +static int ndisc_addr_option_pad(unsigned short type) +{ + switch (type) { + case ARPHRD_INFINIBAND: return 2; + default: return 0; + } +} + +static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, + struct net_device *dev) +{ + u8 *lladdr = (u8 *)(p + 1); + int lladdrlen = p->nd_opt_len << 3; + int prepad = ndisc_addr_option_pad(dev->type); + if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) + return NULL; + return lladdr + prepad; +} + static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; diff --git a/include/net/route.h b/include/net/route.h index 5236236..ace3cb4 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -108,8 +108,6 @@ extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; extern int ip_rt_init(void); -extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, - __be32 src, struct net_device *dev); extern void rt_cache_flush(struct net *net, int how); extern void rt_cache_flush_batch(struct net *net); extern struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); @@ -181,6 +179,9 @@ static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 s extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u32 mark, u8 protocol, int flow_flags); extern void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu); +extern void ipv4_redirect(struct sk_buff *skb, struct net *net, + int oif, u32 mark, u8 protocol, int flow_flags); +extern void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk); extern void ip_rt_send_redirect(struct sk_buff *skb); extern unsigned int inet_addr_type(struct net *net, __be32 addr); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a2ef814..1f2735d 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -162,6 +162,8 @@ struct sock *sctp_err_lookup(int family, struct sk_buff *, void sctp_err_finish(struct sock *, struct sctp_association *); void sctp_icmp_frag_needed(struct sock *, struct sctp_association *, struct sctp_transport *t, __u32 pmtu); +void sctp_icmp_redirect(struct sock *, struct sctp_transport *, + struct sk_buff *); void sctp_icmp_proto_unreachable(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index b98d3d7..81f76c4 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -115,6 +115,10 @@ static void fake_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static void fake_redirect(struct dst_entry *dst, struct sk_buff *skb) +{ +} + static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) { return NULL; @@ -136,6 +140,7 @@ static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, + .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, .mtu = fake_mtu, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 3eb76b5..129ed8f 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -195,6 +195,14 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, } /* else let the usual retransmit timer handle it */ } +static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + + if (dst) + dst->ops->redirect(dst, skb); +} + /* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error @@ -259,6 +267,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } switch (type) { + case ICMP_REDIRECT: + dccp_do_redirect(skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 02162cf..090c080 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -130,6 +130,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst) + dst->ops->redirect(dst, skb); + } + if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index b5594cc..e9c4e2e 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -118,6 +118,7 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu); +static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); @@ -145,6 +146,7 @@ static struct dst_ops dn_dst_ops = { .negative_advice = dn_dst_negative_advice, .link_failure = dn_dst_link_failure, .update_pmtu = dn_dst_update_pmtu, + .redirect = dn_dst_redirect, .neigh_lookup = dn_dst_neigh_lookup, }; @@ -292,6 +294,10 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) } } +static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb) +{ +} + /* * When a route has been marked obsolete. (e.g. routing cache flush) */ diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 916d5ec..a0d8392 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -398,17 +398,25 @@ static void ah4_err(struct sk_buff *skb, u32 info) struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; - if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || - icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return; + case ICMP_REDIRECT: + break; + default: return; + } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) return; - pr_debug("pmtu discovery on SA AH/%08x/%08x\n", - ntohl(ah->spi), ntohl(iph->daddr)); - ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); + else + ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 7b95b49..b61e9de 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -484,17 +484,25 @@ static void esp4_err(struct sk_buff *skb, u32 info) struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; - if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || - icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return; + case ICMP_REDIRECT: + break; + default: return; + } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n", - ntohl(esph->spi), ntohl(iph->daddr)); - ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); + else + ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4a04944..d01aeb4 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -634,18 +634,31 @@ out:; EXPORT_SYMBOL(icmp_send); +static void icmp_socket_deliver(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct net_protocol *ipprot; + int protocol = iph->protocol; + + raw_icmp_error(skb, protocol, info); + + rcu_read_lock(); + ipprot = rcu_dereference(inet_protos[protocol]); + if (ipprot && ipprot->err_handler) + ipprot->err_handler(skb, info); + rcu_read_unlock(); +} + /* * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH. */ static void icmp_unreach(struct sk_buff *skb) { - const struct net_protocol *ipprot; const struct iphdr *iph; struct icmphdr *icmph; struct net *net; u32 info = 0; - int protocol; net = dev_net(skb_dst(skb)->dev); @@ -726,19 +739,7 @@ static void icmp_unreach(struct sk_buff *skb) if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) goto out; - iph = (const struct iphdr *)skb->data; - protocol = iph->protocol; - - /* - * Deliver ICMP message to raw sockets. Pretty useless feature? - */ - raw_icmp_error(skb, protocol, info); - - rcu_read_lock(); - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && ipprot->err_handler) - ipprot->err_handler(skb, info); - rcu_read_unlock(); + icmp_socket_deliver(skb, info); out: return; @@ -754,46 +755,15 @@ out_err: static void icmp_redirect(struct sk_buff *skb) { - const struct iphdr *iph; - - if (skb->len < sizeof(struct iphdr)) - goto out_err; - - /* - * Get the copied header of the packet that caused the redirect - */ - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - - iph = (const struct iphdr *)skb->data; - - switch (icmp_hdr(skb)->code & 7) { - case ICMP_REDIR_NET: - case ICMP_REDIR_NETTOS: - /* - * As per RFC recommendations now handle it as a host redirect. - */ - case ICMP_REDIR_HOST: - case ICMP_REDIR_HOSTTOS: - ip_rt_redirect(ip_hdr(skb)->saddr, iph->daddr, - icmp_hdr(skb)->un.gateway, - iph->saddr, skb->dev); - break; + if (skb->len < sizeof(struct iphdr)) { + ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); + return; } - /* Ping wants to see redirects. - * Let's pretend they are errors of sorts... */ - if (iph->protocol == IPPROTO_ICMP && - iph->ihl >= 5 && - pskb_may_pull(skb, (iph->ihl<<2)+8)) { - ping_err(skb, icmp_hdr(skb)->un.gateway); - } + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return; -out: - return; -out_err: - ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); - goto out; + icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway); } /* diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 594cec3..0c31235 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -528,6 +528,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return; break; + + case ICMP_REDIRECT: + break; } rcu_read_lock(); @@ -543,7 +546,11 @@ static void ipgre_err(struct sk_buff *skb, u32 info) t->parms.link, 0, IPPROTO_GRE, 0); goto out; } - + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, + IPPROTO_GRE, 0); + goto out; + } if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) goto out; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index b913754..d3ab47e 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -31,18 +31,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; - if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || - icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return; + case ICMP_REDIRECT: + break; + default: return; + } spi = htonl(ntohs(ipch->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI4\n", - spi, &iph->daddr); - ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); + else + ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 715338a..c2d0e6d 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -360,6 +360,8 @@ static int ipip_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return 0; break; + case ICMP_REDIRECT: + break; } err = -ENOENT; @@ -376,6 +378,13 @@ static int ipip_err(struct sk_buff *skb, u32 info) goto out; } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + IPPROTO_IPIP, 0); + err = 0; + goto out; + } + if (t->parms.iph.daddr == 0) goto out; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 340fcf2..6232d47 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -387,6 +387,7 @@ void ping_err(struct sk_buff *skb, u32 info) break; case ICMP_REDIRECT: /* See ICMP_SOURCE_QUENCH */ + ipv4_sk_redirect(skb, sk); err = EREMOTEIO; break; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 659ddfb..ff0f071 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -218,6 +218,8 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); + else if (type == ICMP_REDIRECT) + ipv4_sk_redirect(skb, sk); /* Report error on raw socket, if: 1. User requested ip_recverr. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 95bfa1b..23bbe29 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -149,6 +149,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); +static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb); static int rt_garbage_collect(struct dst_ops *ops); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -179,6 +180,7 @@ static struct dst_ops ipv4_dst_ops = { .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, + .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, }; @@ -1271,16 +1273,35 @@ static void rt_del(unsigned int hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } -/* called in rcu_read_lock() section */ -void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, - __be32 saddr, struct net_device *dev) +static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb) { - int s, i; - struct in_device *in_dev = __in_dev_get_rcu(dev); - __be32 skeys[2] = { saddr, 0 }; - int ikeys[2] = { dev->ifindex, 0 }; + const struct iphdr *iph = (const struct iphdr *) skb->data; + __be32 new_gw = icmp_hdr(skb)->un.gateway; + __be32 old_gw = ip_hdr(skb)->saddr; + struct net_device *dev = skb->dev; + __be32 daddr = iph->daddr; + __be32 saddr = iph->saddr; + struct in_device *in_dev; + struct neighbour *n; + struct rtable *rt; struct net *net; + switch (icmp_hdr(skb)->code & 7) { + case ICMP_REDIR_NET: + case ICMP_REDIR_NETTOS: + case ICMP_REDIR_HOST: + case ICMP_REDIR_HOSTTOS: + break; + + default: + return; + } + + rt = (struct rtable *) dst; + if (rt->rt_gateway != old_gw) + return; + + in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; @@ -1300,45 +1321,16 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - for (s = 0; s < 2; s++) { - for (i = 0; i < 2; i++) { - unsigned int hash; - struct rtable __rcu **rthp; - struct rtable *rt; - - hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); - - rthp = &rt_hash_table[hash].chain; - - while ((rt = rcu_dereference(*rthp)) != NULL) { - struct neighbour *n; - - rthp = &rt->dst.rt_next; - - if (rt->rt_key_dst != daddr || - rt->rt_key_src != skeys[s] || - rt->rt_oif != ikeys[i] || - rt_is_input_route(rt) || - rt_is_expired(rt) || - !net_eq(dev_net(rt->dst.dev), net) || - rt->dst.error || - rt->dst.dev != dev || - rt->rt_gateway != old_gw) - continue; - - n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); - if (n) { - if (!(n->nud_state & NUD_VALID)) { - neigh_event_send(n, NULL); - } else { - rt->rt_gateway = new_gw; - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } - neigh_release(n); - } - } + n = ipv4_neigh_lookup(dst, NULL, &new_gw); + if (n) { + if (!(n->nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + } else { + rt->rt_gateway = new_gw; + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } + neigh_release(n); } return; @@ -1554,6 +1546,34 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); +void ipv4_redirect(struct sk_buff *skb, struct net *net, + int oif, u32 mark, u8 protocol, int flow_flags) +{ + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct flowi4 fl4; + struct rtable *rt; + + flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE, + protocol, flow_flags, iph->daddr, iph->saddr, 0, 0); + rt = __ip_route_output_key(net, &fl4); + if (!IS_ERR(rt)) { + ip_do_redirect(&rt->dst, skb); + ip_rt_put(rt); + } +} +EXPORT_SYMBOL_GPL(ipv4_redirect); + +void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + + return ipv4_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + sk->sk_mark, + inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + inet_sk_flowi_flags(sk)); +} +EXPORT_SYMBOL_GPL(ipv4_sk_redirect); + static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = (struct rtable *) dst; @@ -2571,6 +2591,10 @@ static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb) +{ +} + static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) { @@ -2585,6 +2609,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, + .redirect = ipv4_rt_blackhole_redirect, .cow_metrics = ipv4_rt_blackhole_cow_metrics, .neigh_lookup = ipv4_neigh_lookup, }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 01545a3..7a0062c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -321,6 +321,14 @@ static void do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) } /* else let the usual retransmit timer handle it */ } +static void do_redirect(struct sk_buff *skb, struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + + if (dst) + dst->ops->redirect(dst, skb); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -394,6 +402,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } switch (type) { + case ICMP_REDIRECT: + do_redirect(icmp_skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ee37d47..b4c3582 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -630,6 +630,9 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) err = icmp_err_convert[code].errno; } break; + case ICMP_REDIRECT: + ipv4_sk_redirect(skb, sk); + break; } /* diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 87d3fcc..737131c 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -202,6 +202,14 @@ static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) path->ops->update_pmtu(path, mtu); } +static void xfrm4_redirect(struct dst_entry *dst, struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->redirect(path, skb); +} + static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -225,6 +233,7 @@ static struct dst_ops xfrm4_dst_ops = { .protocol = cpu_to_be16(ETH_P_IP), .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, + .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 49d4d26..7e61395 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -613,16 +613,18 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct xfrm_state *x; if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n", - ntohl(ah->spi), &iph->daddr); - ip6_update_pmtu(skb, net, info, 0, 0); + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 89a615b..6dc7fd3 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -434,16 +434,19 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct xfrm_state *x; if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; - pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n", - ntohl(esph->spi), &iph->daddr); - ip6_update_pmtu(skb, net, info, 0, 0); + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index a113f7d..24d69db 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -598,7 +598,7 @@ out: icmpv6_xmit_unlock(sk); } -static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) +void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { const struct inet6_protocol *ipprot; int inner_offset; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 6af3fcf..61d1065 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -550,6 +550,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; + case NDISC_REDIRECT: + rel_type = ICMP_REDIRECT; + rel_code = ICMP_REDIR_HOST; default: return 0; } @@ -608,6 +611,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); } + if (rel_type == ICMP_REDIRECT) + skb_dst(skb2)->ops->redirect(skb_dst(skb2), skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 9283238..7af5aee 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -64,7 +64,9 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && type != ICMPV6_PKT_TOOBIG) + if (type != ICMPV6_DEST_UNREACH && + type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) return; spi = htonl(ntohs(ipcomph->cpi)); @@ -73,9 +75,10 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n", - spi, &iph->daddr); - ip6_update_pmtu(skb, net, info, 0, 0); + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0fddd57..ff36194 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -143,40 +143,6 @@ struct neigh_table nd_tbl = { .gc_thresh3 = 1024, }; -/* ND options */ -struct ndisc_options { - struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; -#ifdef CONFIG_IPV6_ROUTE_INFO - struct nd_opt_hdr *nd_opts_ri; - struct nd_opt_hdr *nd_opts_ri_end; -#endif - struct nd_opt_hdr *nd_useropts; - struct nd_opt_hdr *nd_useropts_end; -}; - -#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] -#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] -#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] -#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] -#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] -#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] - -#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) - -/* - * Return the padding between the option length and the start of the - * link addr. Currently only IP-over-InfiniBand needs this, although - * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may - * also need a pad of 2. - */ -static int ndisc_addr_option_pad(unsigned short type) -{ - switch (type) { - case ARPHRD_INFINIBAND: return 2; - default: return 0; - } -} - static inline int ndisc_opt_addr_space(struct net_device *dev) { return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type)); @@ -233,8 +199,8 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; } -static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, - struct ndisc_options *ndopts) +struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, + struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; @@ -297,17 +263,6 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, return ndopts; } -static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, - struct net_device *dev) -{ - u8 *lladdr = (u8 *)(p + 1); - int lladdrlen = p->nd_opt_len << 3; - int prepad = ndisc_addr_option_pad(dev->type); - if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) - return NULL; - return lladdr + prepad; -} - int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { @@ -1379,16 +1334,6 @@ out: static void ndisc_redirect_rcv(struct sk_buff *skb) { - struct inet6_dev *in6_dev; - struct icmp6hdr *icmph; - const struct in6_addr *dest; - const struct in6_addr *target; /* new first hop to destination */ - struct neighbour *neigh; - int on_link = 0; - struct ndisc_options ndopts; - int optlen; - u8 *lladdr = NULL; - #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: @@ -1405,65 +1350,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } - optlen = skb->tail - skb->transport_header; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - - if (optlen < 0) { - ND_PRINTK(2, warn, "Redirect: packet too short\n"); - return; - } - - icmph = icmp6_hdr(skb); - target = (const struct in6_addr *) (icmph + 1); - dest = target + 1; - - if (ipv6_addr_is_multicast(dest)) { - ND_PRINTK(2, warn, - "Redirect: destination address is multicast\n"); - return; - } - - if (ipv6_addr_equal(dest, target)) { - on_link = 1; - } else if (ipv6_addr_type(target) != - (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK(2, warn, - "Redirect: target address is not link-local unicast\n"); - return; - } - - in6_dev = __in6_dev_get(skb->dev); - if (!in6_dev) - return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) - return; - - /* RFC2461 8.1: - * The IP source address of the Redirect MUST be the same as the current - * first-hop router for the specified ICMP Destination Address. - */ - - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { - ND_PRINTK(2, warn, "Redirect: invalid ND options\n"); - return; - } - if (ndopts.nd_opts_tgt_lladdr) { - lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, - skb->dev); - if (!lladdr) { - ND_PRINTK(2, warn, - "Redirect: invalid link-layer address length\n"); - return; - } - } - - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); - if (neigh) { - rt6_redirect(dest, &ipv6_hdr(skb)->daddr, - &ipv6_hdr(skb)->saddr, neigh, lladdr, - on_link); - neigh_release(neigh); - } + icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index b5c1dcb..ef0579d 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -332,6 +332,8 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } + if (type == NDISC_REDIRECT) + ip6_sk_redirect(skb, sk); if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 563f12c..3151aab 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -79,6 +79,7 @@ static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); +static void rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -174,6 +175,7 @@ static struct dst_ops ip6_dst_ops_template = { .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, + .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_neigh_lookup, }; @@ -189,6 +191,10 @@ static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb) +{ +} + static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) { @@ -203,6 +209,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, + .redirect = ip6_rt_blackhole_redirect, .cow_metrics = ip6_rt_blackhole_cow_metrics, .neigh_lookup = ip6_neigh_lookup, }; @@ -1112,6 +1119,33 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); +void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.flowi6_flags = 0; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + + dst = ip6_route_output(net, NULL, &fl6); + if (!dst->error) + rt6_do_redirect(dst, skb); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_redirect); + +void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_redirect); + static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; @@ -1604,108 +1638,94 @@ static int ip6_route_del(struct fib6_config *cfg) return err; } -/* - * Handle redirects - */ -struct ip6rd_flowi { - struct flowi6 fl6; - struct in6_addr gateway; -}; - -static struct rt6_info *__ip6_route_redirect(struct net *net, - struct fib6_table *table, - struct flowi6 *fl6, - int flags) +static void rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb) { - struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; - struct fib6_node *fn; + struct net *net = dev_net(skb->dev); + struct netevent_redirect netevent; + struct rt6_info *rt, *nrt = NULL; + const struct in6_addr *target; + struct ndisc_options ndopts; + const struct in6_addr *dest; + struct neighbour *old_neigh; + struct inet6_dev *in6_dev; + struct neighbour *neigh; + struct icmp6hdr *icmph; + int optlen, on_link; + u8 *lladdr; - /* - * Get the "current" route for this destination and - * check if the redirect has come from approriate router. - * - * RFC 2461 specifies that redirects should only be - * accepted if they come from the nexthop to the target. - * Due to the way the routes are chosen, this notion - * is a bit fuzzy and one might need to check all possible - * routes. - */ + optlen = skb->tail - skb->transport_header; + optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); -restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - /* - * Current route is on-link; redirect is always invalid. - * - * Seems, previous statement is not true. It could - * be node, which looks for us as on-link (f.e. proxy ndisc) - * But then router serving it might decide, that we should - * know truth 8)8) --ANK (980726). - */ - if (rt6_check_expired(rt)) - continue; - if (!(rt->rt6i_flags & RTF_GATEWAY)) - continue; - if (fl6->flowi6_oif != rt->dst.dev->ifindex) - continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) - continue; - break; + if (optlen < 0) { + net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); + return; } - if (!rt) - rt = net->ipv6.ip6_null_entry; - BACKTRACK(net, &fl6->saddr); -out: - dst_hold(&rt->dst); + icmph = icmp6_hdr(skb); + target = (const struct in6_addr *) (icmph + 1); + dest = target + 1; - read_unlock_bh(&table->tb6_lock); - - return rt; -}; - -static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest, - const struct in6_addr *src, - const struct in6_addr *gateway, - struct net_device *dev) -{ - int flags = RT6_LOOKUP_F_HAS_SADDR; - struct net *net = dev_net(dev); - struct ip6rd_flowi rdfl = { - .fl6 = { - .flowi6_oif = dev->ifindex, - .daddr = *dest, - .saddr = *src, - }, - }; + if (ipv6_addr_is_multicast(dest)) { + net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); + return; + } - rdfl.gateway = *gateway; + on_link = 0; + if (ipv6_addr_equal(dest, target)) { + on_link = 1; + } else if (ipv6_addr_type(target) != + (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { + net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); + return; + } - if (rt6_need_strict(dest)) - flags |= RT6_LOOKUP_F_IFACE; + in6_dev = __in6_dev_get(skb->dev); + if (!in6_dev) + return; + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) + return; - return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6, - flags, __ip6_route_redirect); -} + /* RFC2461 8.1: + * The IP source address of the Redirect MUST be the same as the current + * first-hop router for the specified ICMP Destination Address. + */ -void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, - const struct in6_addr *saddr, - struct neighbour *neigh, u8 *lladdr, int on_link) -{ - struct rt6_info *rt, *nrt = NULL; - struct netevent_redirect netevent; - struct net *net = dev_net(neigh->dev); - struct neighbour *old_neigh; + if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { + net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); + return; + } - rt = ip6_route_redirect(dest, src, saddr, neigh->dev); + lladdr = NULL; + if (ndopts.nd_opts_tgt_lladdr) { + lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, + skb->dev); + if (!lladdr) { + net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); + return; + } + } + rt = (struct rt6_info *) dst; if (rt == net->ipv6.ip6_null_entry) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); - goto out; + return; } + /* Redirect received -> path was valid. + * Look, redirects are sent only in response to data packets, + * so that this nexthop apparently is reachable. --ANK + */ + dst_confirm(&rt->dst); + + neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); + if (!neigh) + return; + + /* Duplicate redirect: silently ignore. */ + old_neigh = rt->n; + if (neigh == old_neigh) + goto out; + /* * We have finally decided to accept it. */ @@ -1717,18 +1737,6 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, NEIGH_UPDATE_F_ISROUTER)) ); - /* - * Redirect received -> path was valid. - * Look, redirects are sent only in response to data packets, - * so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->dst); - - /* Duplicate redirect: silently ignore. */ - old_neigh = rt->n; - if (neigh == old_neigh) - goto out; - nrt = ip6_rt_copy(rt, dest); if (!nrt) goto out; @@ -1751,12 +1759,12 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags & RTF_CACHE) { + rt = (struct rt6_info *) dst_clone(&rt->dst); ip6_del_rt(rt); - return; } out: - dst_release(&rt->dst); + neigh_release(neigh); } /* diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 49aea94..fbf1622 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -539,6 +539,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (code != ICMP_EXC_TTL) return 0; break; + case ICMP_REDIRECT: + break; } err = -ENOENT; @@ -557,6 +559,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = 0; goto out; } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + IPPROTO_IPV6, 0); + err = 0; + goto out; + } if (t->parms.iph.daddr == 0) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 70458a9..3071f37 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -363,6 +363,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst) + dst->ops->redirect(dst,skb); + } + if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1ecd102..99d0077 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -483,6 +483,8 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) ip6_sk_update_pmtu(skb, sk, info); + if (type == NDISC_REDIRECT) + ip6_sk_redirect(skb, sk); np = inet6_sk(sk); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index bb02038..f5a9cb8 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -215,6 +215,14 @@ static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) path->ops->update_pmtu(path, mtu); } +static void xfrm6_redirect(struct dst_entry *dst, struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->redirect(path, skb); +} + static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -261,6 +269,7 @@ static struct dst_ops xfrm6_dst_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .redirect = xfrm6_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, diff --git a/net/sctp/input.c b/net/sctp/input.c index 80564fe..f050d45 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -423,6 +423,18 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD); } +void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, + struct sk_buff *skb) +{ + struct dst_entry *dst; + + if (!t) + return; + dst = sctp_transport_dst_check(t); + if (dst) + dst->ops->redirect(dst, skb); +} + /* * SCTP Implementer's Guide, 2.37 ICMP handling procedures * @@ -628,6 +640,10 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) err = EHOSTUNREACH; break; + case ICMP_REDIRECT: + sctp_icmp_redirect(sk, transport, skb); + err = 0; + break; default: goto out_unlock; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 91f4791..ed7139e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -185,6 +185,9 @@ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out_unlock; } break; + case NDISC_REDIRECT: + sctp_icmp_redirect(sk, transport, skb); + break; default: break; } |