X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv6%2Fxfrm6_policy.c;h=dbdc696f5fc5b5fbc207b48135fa768028f7e7f4;hb=e46b498c84163e86e2627c30bca298c968664f65;hp=15aa4c58c3159ef9ec2a844bcca0305c0b034ec8;hpb=2774c7aba6c97a2535be3309a2209770953780b3;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 15aa4c5..dbdc696 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -11,9 +11,11 @@ * */ -#include +#include +#include #include #include +#include #include #include #include @@ -22,38 +24,47 @@ #include #endif -static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static int xfrm6_dst_lookup(struct xfrm_dst **xdst, struct flowi *fl) +static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, + xfrm_address_t *saddr, + xfrm_address_t *daddr) { - struct dst_entry *dst = ip6_route_output(NULL, fl); - int err = dst->error; - if (!err) - *xdst = (struct xfrm_dst *) dst; - else + struct flowi fl = {}; + struct dst_entry *dst; + int err; + + memcpy(&fl.fl6_dst, daddr, sizeof(fl.fl6_dst)); + if (saddr) + memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src)); + + dst = ip6_route_output(net, NULL, &fl); + + err = dst->error; + if (dst->error) { dst_release(dst); - return err; + dst = ERR_PTR(err); + } + + return dst; } -static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) +static int xfrm6_get_saddr(struct net *net, + xfrm_address_t *saddr, xfrm_address_t *daddr) { - struct rt6_info *rt; - struct flowi fl_tunnel = { - .nl_u = { - .ip6_u = { - .daddr = *(struct in6_addr *)&daddr->a6, - }, - }, - }; - - if (!xfrm6_dst_lookup((struct xfrm_dst **)&rt, &fl_tunnel)) { - ipv6_get_saddr(&rt->u.dst, (struct in6_addr *)&daddr->a6, - (struct in6_addr *)&saddr->a6); - dst_release(&rt->u.dst); - return 0; - } - return -EHOSTUNREACH; + struct dst_entry *dst; + struct net_device *dev; + + dst = xfrm6_dst_lookup(net, 0, NULL, daddr); + if (IS_ERR(dst)) + return -EHOSTUNREACH; + + dev = ip6_dst_idev(dst)->dev; + ipv6_dev_get_saddr(dev_net(dev), dev, + (struct in6_addr *)&daddr->a6, 0, + (struct in6_addr *)&saddr->a6); + dst_release(dst); + return 0; } static struct dst_entry * @@ -86,191 +97,55 @@ __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) return dst; } -static inline struct in6_addr* -__xfrm6_bundle_addr_remote(struct xfrm_state *x, struct in6_addr *addr) +static int xfrm6_get_tos(struct flowi *fl) { - return (x->type->remote_addr) ? - (struct in6_addr*)x->type->remote_addr(x, (xfrm_address_t *)addr) : - (struct in6_addr*)&x->id.daddr; + return 0; } -static inline struct in6_addr* -__xfrm6_bundle_addr_local(struct xfrm_state *x, struct in6_addr *addr) +static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, + int nfheader_len) { - return (x->type->local_addr) ? - (struct in6_addr*)x->type->local_addr(x, (xfrm_address_t *)addr) : - (struct in6_addr*)&x->props.saddr; -} + if (dst->ops->family == AF_INET6) { + struct rt6_info *rt = (struct rt6_info*)dst; + if (rt->rt6i_node) + path->path_cookie = rt->rt6i_node->fn_sernum; + } -static inline void -__xfrm6_bundle_len_inc(int *len, int *nflen, struct xfrm_state *x) -{ - if (x->type->flags & XFRM_TYPE_NON_FRAGMENT) - *nflen += x->props.header_len; - else - *len += x->props.header_len; -} + path->u.rt6.rt6i_nfheader_len = nfheader_len; -static inline void -__xfrm6_bundle_len_dec(int *len, int *nflen, struct xfrm_state *x) -{ - if (x->type->flags & XFRM_TYPE_NON_FRAGMENT) - *nflen -= x->props.header_len; - else - *len -= x->props.header_len; + return 0; } -/* Allocate chain of dst_entry's, attach known xfrm's, calculate - * all the metrics... Shortly, bundle a bundle. - */ - -static int -__xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx, - struct flowi *fl, struct dst_entry **dst_p) +static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev) { - struct dst_entry *dst, *dst_prev; - struct rt6_info *rt0 = (struct rt6_info*)(*dst_p); - struct rt6_info *rt = rt0; - struct flowi fl_tunnel = { - .nl_u = { - .ip6_u = { - .saddr = fl->fl6_src, - .daddr = fl->fl6_dst, - } - } - }; - int i; - int err = 0; - int header_len = 0; - int nfheader_len = 0; - int trailer_len = 0; - - dst = dst_prev = NULL; - dst_hold(&rt->u.dst); - - for (i = 0; i < nx; i++) { - struct dst_entry *dst1 = dst_alloc(&xfrm6_dst_ops); - struct xfrm_dst *xdst; - - if (unlikely(dst1 == NULL)) { - err = -ENOBUFS; - dst_release(&rt->u.dst); - goto error; - } + struct rt6_info *rt = (struct rt6_info*)xdst->route; - if (!dst) - dst = dst1; - else { - dst_prev->child = dst1; - dst1->flags |= DST_NOHASH; - dst_clone(dst1); - } + xdst->u.dst.dev = dev; + dev_hold(dev); - xdst = (struct xfrm_dst *)dst1; - xdst->route = &rt->u.dst; - xdst->genid = xfrm[i]->genid; - if (rt->rt6i_node) - xdst->route_cookie = rt->rt6i_node->fn_sernum; - - dst1->next = dst_prev; - dst_prev = dst1; - - __xfrm6_bundle_len_inc(&header_len, &nfheader_len, xfrm[i]); - trailer_len += xfrm[i]->props.trailer_len; - - if (xfrm[i]->props.mode == XFRM_MODE_TUNNEL || - xfrm[i]->props.mode == XFRM_MODE_ROUTEOPTIMIZATION) { - unsigned short encap_family = xfrm[i]->props.family; - switch(encap_family) { - case AF_INET: - fl_tunnel.fl4_dst = xfrm[i]->id.daddr.a4; - fl_tunnel.fl4_src = xfrm[i]->props.saddr.a4; - break; - case AF_INET6: - ipv6_addr_copy(&fl_tunnel.fl6_dst, __xfrm6_bundle_addr_remote(xfrm[i], &fl->fl6_dst)); - - ipv6_addr_copy(&fl_tunnel.fl6_src, __xfrm6_bundle_addr_local(xfrm[i], &fl->fl6_src)); - break; - default: - BUG_ON(1); - } + xdst->u.rt6.rt6i_idev = in6_dev_get(rt->u.dst.dev); + if (!xdst->u.rt6.rt6i_idev) + return -ENODEV; - err = xfrm_dst_lookup((struct xfrm_dst **) &rt, - &fl_tunnel, encap_family); - if (err) - goto error; - } else - dst_hold(&rt->u.dst); - } - - dst_prev->child = &rt->u.dst; - dst->path = &rt->u.dst; + /* Sheit... I remember I did this right. Apparently, + * it was magically lost, so this code needs audit */ + xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | + RTF_LOCAL); + xdst->u.rt6.rt6i_metric = rt->rt6i_metric; + xdst->u.rt6.rt6i_node = rt->rt6i_node; if (rt->rt6i_node) - ((struct xfrm_dst *)dst)->path_cookie = rt->rt6i_node->fn_sernum; - - *dst_p = dst; - dst = dst_prev; - - dst_prev = *dst_p; - i = 0; - for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) { - struct xfrm_dst *x = (struct xfrm_dst*)dst_prev; - struct xfrm_state_afinfo *afinfo; - - dst_prev->xfrm = xfrm[i++]; - dst_prev->dev = rt->u.dst.dev; - if (rt->u.dst.dev) - dev_hold(rt->u.dst.dev); - dst_prev->obsolete = -1; - dst_prev->flags |= DST_HOST; - dst_prev->lastuse = jiffies; - dst_prev->header_len = header_len; - dst_prev->nfheader_len = nfheader_len; - dst_prev->trailer_len = trailer_len; - memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics)); - - /* Copy neighbour for reachability confirmation */ - dst_prev->neighbour = neigh_clone(rt->u.dst.neighbour); - dst_prev->input = rt->u.dst.input; - /* XXX: When IPv4 is implemented as module and can be unloaded, - * we should manage reference to xfrm4_output in afinfo->output. - * Miyazawa - */ - afinfo = xfrm_state_get_afinfo(dst_prev->xfrm->props.family); - if (!afinfo) { - dst = *dst_p; - goto error; - } + xdst->route_cookie = rt->rt6i_node->fn_sernum; + xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; + xdst->u.rt6.rt6i_dst = rt->rt6i_dst; + xdst->u.rt6.rt6i_src = rt->rt6i_src; - dst_prev->output = afinfo->output; - xfrm_state_put_afinfo(afinfo); - /* Sheit... I remember I did this right. Apparently, - * it was magically lost, so this code needs audit */ - x->u.rt6.rt6i_flags = rt0->rt6i_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL); - x->u.rt6.rt6i_metric = rt0->rt6i_metric; - x->u.rt6.rt6i_node = rt0->rt6i_node; - x->u.rt6.rt6i_gateway = rt0->rt6i_gateway; - memcpy(&x->u.rt6.rt6i_gateway, &rt0->rt6i_gateway, sizeof(x->u.rt6.rt6i_gateway)); - x->u.rt6.rt6i_dst = rt0->rt6i_dst; - x->u.rt6.rt6i_src = rt0->rt6i_src; - x->u.rt6.rt6i_idev = rt0->rt6i_idev; - in6_dev_hold(rt0->rt6i_idev); - __xfrm6_bundle_len_dec(&header_len, &nfheader_len, x->u.dst.xfrm); - trailer_len -= x->u.dst.xfrm->props.trailer_len; - } - - xfrm_init_pmtu(dst); return 0; - -error: - if (dst) - dst_free(dst); - return err; } static inline void -_decode_session6(struct sk_buff *skb, struct flowi *fl) +_decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) { + int onlyproto = 0; u16 offset = skb_network_header_len(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct ipv6_opt_hdr *exthdr; @@ -278,14 +153,17 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) u8 nexthdr = nh[IP6CB(skb)->nhoff]; memset(fl, 0, sizeof(struct flowi)); - ipv6_addr_copy(&fl->fl6_dst, &hdr->daddr); - ipv6_addr_copy(&fl->fl6_src, &hdr->saddr); + ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr); + ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr); - while (pskb_may_pull(skb, nh + offset + 1 - skb->data)) { + while (nh + offset + 1 < skb->data || + pskb_may_pull(skb, nh + offset + 1 - skb->data)) { nh = skb_network_header(skb); exthdr = (struct ipv6_opt_hdr *)(nh + offset); switch (nexthdr) { + case NEXTHDR_FRAGMENT: + onlyproto = 1; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: @@ -299,17 +177,18 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: - if (pskb_may_pull(skb, nh + offset + 4 - skb->data)) { + if (!onlyproto && (nh + offset + 4 < skb->data || + pskb_may_pull(skb, nh + offset + 4 - skb->data))) { __be16 *ports = (__be16 *)exthdr; - fl->fl_ip_sport = ports[0]; - fl->fl_ip_dport = ports[1]; + fl->fl_ip_sport = ports[!!reverse]; + fl->fl_ip_dport = ports[!reverse]; } fl->proto = nexthdr; return; case IPPROTO_ICMPV6: - if (pskb_may_pull(skb, nh + offset + 2 - skb->data)) { + if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { u8 *icmp = (u8 *)exthdr; fl->fl_icmp_type = icmp[0]; @@ -320,7 +199,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) case IPPROTO_MH: - if (pskb_may_pull(skb, nh + offset + 3 - skb->data)) { + if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { struct ip6_mh *mh; mh = (struct ip6_mh *)exthdr; @@ -342,10 +221,12 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) } } -static inline int xfrm6_garbage_collect(void) +static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - xfrm6_policy_afinfo.garbage_collect(); - return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); + + xfrm6_policy_afinfo.garbage_collect(net); + return (atomic_read(&ops->entries) > ops->gc_thresh * 2); } static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -375,7 +256,8 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xdst = (struct xfrm_dst *)dst; if (xdst->u.rt6.rt6i_idev->dev == dev) { - struct inet6_dev *loopback_idev = in6_dev_get(init_net.loopback_dev); + struct inet6_dev *loopback_idev = + in6_dev_get(dev_net(dev)->loopback_dev); BUG_ON(!loopback_idev); do { @@ -393,13 +275,14 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static struct dst_ops xfrm6_dst_ops = { .family = AF_INET6, - .protocol = __constant_htons(ETH_P_IPV6), + .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, + .local_out = __ip6_local_out, .gc_thresh = 1024, - .entry_size = sizeof(struct xfrm_dst), + .entries = ATOMIC_INIT(0), }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { @@ -408,13 +291,15 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, .find_bundle = __xfrm6_find_bundle, - .bundle_create = __xfrm6_bundle_create, .decode_session = _decode_session6, + .get_tos = xfrm6_get_tos, + .init_path = xfrm6_init_path, + .fill_dst = xfrm6_fill_dst, }; -static void __init xfrm6_policy_init(void) +static int __init xfrm6_policy_init(void) { - xfrm_policy_register_afinfo(&xfrm6_policy_afinfo); + return xfrm_policy_register_afinfo(&xfrm6_policy_afinfo); } static void xfrm6_policy_fini(void) @@ -422,14 +307,65 @@ static void xfrm6_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo); } -void __init xfrm6_init(void) +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm6_policy_table[] = { + { + .procname = "xfrm6_gc_thresh", + .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static struct ctl_table_header *sysctl_hdr; +#endif + +int __init xfrm6_init(void) { - xfrm6_policy_init(); - xfrm6_state_init(); + int ret; + unsigned int gc_thresh; + + /* + * We need a good default value for the xfrm6 gc threshold. + * In ipv4 we set it to the route hash table size * 8, which + * is half the size of the maximaum route cache for ipv4. It + * would be good to do the same thing for v6, except the table is + * constructed differently here. Here each table for a net namespace + * can have FIB_TABLE_HASHSZ entries, so lets go with the same + * computation that we used for ipv4 here. Also, lets keep the initial + * gc_thresh to a minimum of 1024, since, the ipv6 route cache defaults + * to that as a minimum as well + */ + gc_thresh = FIB6_TABLE_HASHSZ * 8; + xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + + ret = xfrm6_policy_init(); + if (ret) + goto out; + + ret = xfrm6_state_init(); + if (ret) + goto out_policy; + +#ifdef CONFIG_SYSCTL + sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, + xfrm6_policy_table); +#endif +out: + return ret; +out_policy: + xfrm6_policy_fini(); + goto out; } void xfrm6_fini(void) { +#ifdef CONFIG_SYSCTL + if (sysctl_hdr) + unregister_net_sysctl_table(sysctl_hdr); +#endif //xfrm6_input_fini(); xfrm6_policy_fini(); xfrm6_state_fini();