diff options
Diffstat (limited to 'net/ipv6')
44 files changed, 1170 insertions, 716 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 12368c5..a225d5e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -87,6 +87,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/export.h> /* Set to 3 to get tracing... */ #define ACONF_DEBUG 2 @@ -629,13 +630,13 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out; } - rt = addrconf_dst_alloc(idev, addr, 0); + rt = addrconf_dst_alloc(idev, addr, false); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto out; } - ipv6_addr_copy(&ifa->addr, addr); + ifa->addr = *addr; spin_lock_init(&ifa->lock); spin_lock_init(&ifa->state_lock); @@ -649,16 +650,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, ifa->rt = rt; - /* - * part one of RFC 4429, section 3.3 - * We should not configure an address as - * optimistic if we do not yet know the link - * layer address of our nexhop router - */ - - if (dst_get_neighbour_raw(&rt->dst) == NULL) - ifa->flags &= ~IFA_F_OPTIMISTIC; - ifa->idev = idev; in6_dev_hold(idev); /* For caller */ @@ -806,7 +797,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ip6_del_rt(rt); rt = NULL; } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { - rt->rt6i_expires = expires; + rt->dst.expires = expires; rt->rt6i_flags |= RTF_EXPIRES; } } @@ -824,12 +815,13 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i { struct inet6_dev *idev = ifp->idev; struct in6_addr addr, *tmpaddr; - unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_cstamp, tmp_tstamp, age; + unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_tstamp, age; unsigned long regen_advance; int tmp_plen; int ret = 0; int max_addresses; u32 addr_flags; + unsigned long now = jiffies; write_lock(&idev->lock); if (ift) { @@ -874,7 +866,7 @@ retry: goto out; } memcpy(&addr.s6_addr[8], idev->rndid, 8); - age = (jiffies - ifp->tstamp) / HZ; + age = (now - ifp->tstamp) / HZ; tmp_valid_lft = min_t(__u32, ifp->valid_lft, idev->cnf.temp_valid_lft + age); @@ -884,7 +876,6 @@ retry: idev->cnf.max_desync_factor); tmp_plen = ifp->prefix_len; max_addresses = idev->cnf.max_addresses; - tmp_cstamp = ifp->cstamp; tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); @@ -929,7 +920,7 @@ retry: ift->ifpub = ifp; ift->valid_lft = tmp_valid_lft; ift->prefered_lft = tmp_prefered_lft; - ift->cstamp = tmp_cstamp; + ift->cstamp = now; ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); @@ -1227,7 +1218,7 @@ try_nextdev: if (!hiscore->ifa) return -EADDRNOTAVAIL; - ipv6_addr_copy(saddr, &hiscore->ifa->addr); + *saddr = hiscore->ifa->addr; in6_ifa_put(hiscore->ifa); return 0; } @@ -1248,7 +1239,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { - ipv6_addr_copy(addr, &ifp->addr); + *addr = ifp->addr; err = 0; break; } @@ -1699,7 +1690,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, .fc_protocol = RTPROT_KERNEL, }; - ipv6_addr_copy(&cfg.fc_dst, pfx); + cfg.fc_dst = *pfx; /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole @@ -1713,6 +1704,40 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, ip6_route_add(&cfg); } + +static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, + int plen, + const struct net_device *dev, + u32 flags, u32 noflags) +{ + struct fib6_node *fn; + struct rt6_info *rt = NULL; + struct fib6_table *table; + + table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX); + if (table == NULL) + return NULL; + + write_lock_bh(&table->tb6_lock); + fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); + if (!fn) + goto out; + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (rt->dst.dev->ifindex != dev->ifindex) + continue; + if ((rt->rt6i_flags & flags) != flags) + continue; + if ((noflags != 0) && ((rt->rt6i_flags & flags) != 0)) + continue; + dst_hold(&rt->dst); + break; + } +out: + write_unlock_bh(&table->tb6_lock); + return rt; +} + + /* Create "default" multicast route to the interface */ static void addrconf_add_mroute(struct net_device *dev) @@ -1770,14 +1795,15 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) return ERR_PTR(-EACCES); /* Add default multicast route */ - addrconf_add_mroute(dev); + if (!(dev->flags & IFF_LOOPBACK)) + addrconf_add_mroute(dev); /* Add link local route */ addrconf_add_lroute(dev); return idev; } -void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) +void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; __u32 valid_lft; @@ -1842,21 +1868,24 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (addrconf_finite_timeout(rt_expires)) rt_expires *= HZ; - rt = rt6_lookup(net, &pinfo->prefix, NULL, - dev->ifindex, 1); + rt = addrconf_get_prefix_route(&pinfo->prefix, + pinfo->prefix_len, + dev, + RTF_ADDRCONF | RTF_PREFIX_RT, + RTF_GATEWAY | RTF_DEFAULT); - if (rt && addrconf_is_prefix_route(rt)) { + if (rt) { /* Autoconf prefix route */ if (valid_lft == 0) { ip6_del_rt(rt); rt = NULL; } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ - rt->rt6i_expires = jiffies + rt_expires; + rt->dst.expires = jiffies + rt_expires; rt->rt6i_flags |= RTF_EXPIRES; } else { rt->rt6i_flags &= ~RTF_EXPIRES; - rt->rt6i_expires = 0; + rt->dst.expires = 0; } } else if (valid_lft) { clock_t expires = 0; @@ -1905,7 +1934,7 @@ ok: #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && - !net->ipv6.devconf_all->forwarding) + !net->ipv6.devconf_all->forwarding && sllao) addr_flags = IFA_F_OPTIMISTIC; #endif @@ -1999,25 +2028,50 @@ ok: #ifdef CONFIG_IPV6_PRIVACY read_lock_bh(&in6_dev->lock); /* update all temporary addresses in the list */ - list_for_each_entry(ift, &in6_dev->tempaddr_list, tmp_list) { - /* - * When adjusting the lifetimes of an existing - * temporary address, only lower the lifetimes. - * Implementations must not increase the - * lifetimes of an existing temporary address - * when processing a Prefix Information Option. - */ + list_for_each_entry(ift, &in6_dev->tempaddr_list, + tmp_list) { + int age, max_valid, max_prefered; + if (ifp != ift->ifpub) continue; + /* + * RFC 4941 section 3.3: + * If a received option will extend the lifetime + * of a public address, the lifetimes of + * temporary addresses should be extended, + * subject to the overall constraint that no + * temporary addresses should ever remain + * "valid" or "preferred" for a time longer than + * (TEMP_VALID_LIFETIME) or + * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), + * respectively. + */ + age = (now - ift->cstamp) / HZ; + max_valid = in6_dev->cnf.temp_valid_lft - age; + if (max_valid < 0) + max_valid = 0; + + max_prefered = in6_dev->cnf.temp_prefered_lft - + in6_dev->cnf.max_desync_factor - + age; + if (max_prefered < 0) + max_prefered = 0; + + if (valid_lft > max_valid) + valid_lft = max_valid; + + if (prefered_lft > max_prefered) + prefered_lft = max_prefered; + spin_lock(&ift->lock); flags = ift->flags; - if (ift->valid_lft > valid_lft && - ift->valid_lft - valid_lft > (jiffies - ift->tstamp) / HZ) - ift->valid_lft = valid_lft + (jiffies - ift->tstamp) / HZ; - if (ift->prefered_lft > prefered_lft && - ift->prefered_lft - prefered_lft > (jiffies - ift->tstamp) / HZ) - ift->prefered_lft = prefered_lft + (jiffies - ift->tstamp) / HZ; + ift->valid_lft = valid_lft; + ift->prefered_lft = prefered_lft; + ift->tstamp = now; + if (prefered_lft > 0) + ift->flags &= ~IFA_F_DEPRECATED; + spin_unlock(&ift->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ift); @@ -2025,9 +2079,11 @@ ok: if ((create || list_empty(&in6_dev->tempaddr_list)) && in6_dev->cnf.use_tempaddr > 0) { /* - * When a new public address is created as described in [ADDRCONF], - * also create a new temporary address. Also create a temporary - * address if it's enabled but no temporary address currently exists. + * When a new public address is created as + * described in [ADDRCONF], also create a new + * temporary address. Also create a temporary + * address if it's enabled but no temporary + * address currently exists. */ read_unlock_bh(&in6_dev->lock); ipv6_create_tempaddr(ifp, NULL); @@ -2706,7 +2762,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) idev->dead = 1; /* protected by rtnl_lock */ - rcu_assign_pointer(dev->ip6_ptr, NULL); + RCU_INIT_POINTER(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); @@ -2969,12 +3025,12 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) ipv6_ifa_notify(RTM_NEWADDR, ifp); - /* If added prefix is link local and forwarding is off, - start sending router solicitations. + /* If added prefix is link local and we are prepared to process + router advertisements, start sending router solicitations. */ - if ((ifp->idev->cnf.forwarding == 0 || - ifp->idev->cnf.forwarding == 2) && + if (((ifp->idev->cnf.accept_ra == 1 && !ifp->idev->cnf.forwarding) || + ifp->idev->cnf.accept_ra == 2) && ifp->idev->cnf.rtr_solicits > 0 && (dev->flags&IFF_LOOPBACK) == 0 && (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { @@ -3012,20 +3068,39 @@ static void addrconf_dad_run(struct inet6_dev *idev) struct if6_iter_state { struct seq_net_private p; int bucket; + int offset; }; -static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) +static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) { struct inet6_ifaddr *ifa = NULL; struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + int p = 0; - for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { + /* initial bucket if pos is 0 */ + if (pos == 0) { + state->bucket = 0; + state->offset = 0; + } + + for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { struct hlist_node *n; hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], - addr_lst) + addr_lst) { + /* sync with offset */ + if (p < state->offset) { + p++; + continue; + } + state->offset++; if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; + } + + /* prepare for next bucket */ + state->offset = 0; + p = 0; } return NULL; } @@ -3037,13 +3112,17 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct hlist_node *n = &ifa->addr_lst; - hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) + hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) { + state->offset++; if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; + } while (++state->bucket < IN6_ADDR_HSIZE) { + state->offset = 0; hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) { + state->offset++; if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; } @@ -3052,21 +3131,11 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, return NULL; } -static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) -{ - struct inet6_ifaddr *ifa = if6_get_first(seq); - - if (ifa) - while (pos && (ifa = if6_get_next(seq, ifa)) != NULL) - --pos; - return pos ? NULL : ifa; -} - static void *if6_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu_bh) { rcu_read_lock_bh(); - return if6_get_idx(seq, *pos); + return if6_get_first(seq, *pos); } static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 6b03826..399287e 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -3,6 +3,7 @@ * not configured or static. */ +#include <linux/export.h> #include <net/ipv6.h> #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d27c797..273f48d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -347,7 +347,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!inet->transparent && + if (!(inet->freebind || inet->transparent) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; @@ -361,10 +361,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = v4addr; inet->inet_saddr = v4addr; - ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); + np->rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) - ipv6_addr_copy(&np->saddr, &addr->sin6_addr); + np->saddr = addr->sin6_addr; /* Make sure we are allowed to bind here. */ if (sk->sk_prot->get_port(sk, snum)) { @@ -458,14 +458,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, peer == 1) return -ENOTCONN; sin->sin6_port = inet->inet_dport; - ipv6_addr_copy(&sin->sin6_addr, &np->daddr); + sin->sin6_addr = np->daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; } else { if (ipv6_addr_any(&np->rcv_saddr)) - ipv6_addr_copy(&sin->sin6_addr, &np->saddr); + sin->sin6_addr = np->saddr; else - ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); + sin->sin6_addr = np->rcv_saddr; sin->sin6_port = inet->inet_sport; } @@ -660,8 +660,8 @@ int inet6_sk_rebuild_header(struct sock *sk) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; @@ -769,7 +769,8 @@ out: return err; } -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features) +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; @@ -985,9 +986,9 @@ static int __net_init ipv6_init_mibs(struct net *net) sizeof(struct icmpv6_mib), __alignof__(struct icmpv6_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void __percpu **)net->mib.icmpv6msg_statistics, - sizeof(struct icmpv6msg_mib), - __alignof__(struct icmpv6msg_mib)) < 0) + net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib), + GFP_KERNEL); + if (!net->mib.icmpv6msg_statistics) goto err_icmpmsg_mib; return 0; @@ -1008,7 +1009,7 @@ static void ipv6_cleanup_mibs(struct net *net) snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); - snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics); + kfree(net->mib.icmpv6msg_statistics); } static int __net_init inet6_net_init(struct net *net) @@ -1115,6 +1116,8 @@ static int __init inet6_init(void) if (err) goto static_sysctl_fail; #endif + tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; + /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2195ae6..2ae79db 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -193,9 +193,9 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length); goto bad; } - ipv6_addr_copy(&final_addr, &hao->addr); - ipv6_addr_copy(&hao->addr, &iph->saddr); - ipv6_addr_copy(&iph->saddr, &final_addr); + final_addr = hao->addr; + hao->addr = iph->saddr; + iph->saddr = final_addr; } break; } @@ -241,13 +241,13 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) segments = rthdr->hdrlen >> 1; addrs = ((struct rt0_hdr *)rthdr)->addr; - ipv6_addr_copy(&final_addr, addrs + segments - 1); + final_addr = addrs[segments - 1]; addrs += segments - segments_left; memmove(addrs + 1, addrs, (segments_left - 1) * sizeof(*addrs)); - ipv6_addr_copy(addrs, &iph->daddr); - ipv6_addr_copy(&iph->daddr, &final_addr); + addrs[0] = iph->daddr; + iph->daddr = final_addr; } static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) @@ -324,8 +324,6 @@ static void ah6_output_done(struct crypto_async_request *base, int err) #endif } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -466,12 +464,12 @@ static void ah6_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); __skb_pull(skb, ah_hlen + hdr_len); skb_set_transport_header(skb, -hdr_len); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -583,8 +581,6 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 674255f..59402b4 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -75,7 +75,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (pac == NULL) return -ENOMEM; pac->acl_next = NULL; - ipv6_addr_copy(&pac->acl_addr, addr); + pac->acl_addr = *addr; rcu_read_lock(); if (ifindex == 0) { @@ -83,7 +83,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; + dev = rt->dst.dev; dst_release(&rt->dst); } else if (ishost) { err = -EADDRNOTAVAIL; @@ -289,14 +289,14 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) goto out; } - rt = addrconf_dst_alloc(idev, addr, 1); + rt = addrconf_dst_alloc(idev, addr, true); if (IS_ERR(rt)) { kfree(aca); err = PTR_ERR(rt); goto out; } - ipv6_addr_copy(&aca->aca_addr, addr); + aca->aca_addr = *addr; aca->aca_idev = idev; aca->aca_rt = rt; aca->aca_users = 1; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b46e9f8..ae08aee 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -71,7 +71,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; } } @@ -143,7 +143,7 @@ ipv4_connected: } } - ipv6_addr_copy(&np->daddr, daddr); + np->daddr = *daddr; np->flow_label = fl6.flowlabel; inet->inet_dport = usin->sin6_port; @@ -154,8 +154,8 @@ ipv4_connected: */ fl6.flowi6_proto = sk->sk_protocol; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; @@ -179,10 +179,10 @@ ipv4_connected: /* source address lookup done in ip6_dst_lookup */ if (ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&np->saddr, &fl6.saddr); + np->saddr = fl6.saddr; if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_copy(&np->rcv_saddr, &fl6.saddr); + np->rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); @@ -257,7 +257,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); - ipv6_addr_copy(&iph->daddr, &fl6->daddr); + iph->daddr = fl6->daddr; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; @@ -294,20 +294,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); - ipv6_addr_copy(&iph->daddr, &fl6->daddr); + iph->daddr = fl6->daddr; mtu_info = IP6CBMTU(skb); - if (!mtu_info) { - kfree_skb(skb); - return; - } mtu_info->ip6m_mtu = mtu; mtu_info->ip6m_addr.sin6_family = AF_INET6; mtu_info->ip6m_addr.sin6_port = 0; mtu_info->ip6m_addr.sin6_flowinfo = 0; mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif; - ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr); + mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); @@ -358,8 +354,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = serr->port; sin->sin6_scope_id = 0; if (skb->protocol == htons(ETH_P_IPV6)) { - ipv6_addr_copy(&sin->sin6_addr, - (struct in6_addr *)(nh + serr->addr_offset)); + sin->sin6_addr = + *(struct in6_addr *)(nh + serr->addr_offset); if (np->sndflow) sin->sin6_flowinfo = (*(__be32 *)(nh + serr->addr_offset - 24) & @@ -380,7 +376,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (skb->protocol == htons(ETH_P_IPV6)) { - ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr); + sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) datagram_recv_ctl(sk, msg, skb); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) @@ -455,7 +451,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_flowinfo = 0; sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; - ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr); + sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); @@ -479,7 +475,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; - ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr); + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } @@ -554,7 +550,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; - ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr); + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { @@ -588,7 +584,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) */ sin6.sin6_family = AF_INET6; - ipv6_addr_copy(&sin6.sin6_addr, &ipv6_hdr(skb)->daddr); + sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; sin6.sin6_flowinfo = 0; sin6.sin6_scope_id = 0; @@ -658,12 +654,12 @@ int datagram_send_ctl(struct net *net, struct sock *sk, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; - if (!inet_sk(sk)->transparent && + if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && !ipv6_chk_addr(net, &src_info->ipi6_addr, strict ? dev : NULL, 0)) err = -EINVAL; else - ipv6_addr_copy(&fl6->saddr, &src_info->ipi6_addr); + fl6->saddr = src_info->ipi6_addr; } rcu_read_unlock(); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 79a485e..3d641b6 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -30,6 +30,7 @@ #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/slab.h> +#include <linux/export.h> #include <net/dst.h> #include <net/sock.h> @@ -242,9 +243,9 @@ static int ipv6_dest_hao(struct sk_buff *skb, int optoff) if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; - ipv6_addr_copy(&tmp_addr, &ipv6h->saddr); - ipv6_addr_copy(&ipv6h->saddr, &hao->addr); - ipv6_addr_copy(&hao->addr, &tmp_addr); + tmp_addr = ipv6h->saddr; + ipv6h->saddr = hao->addr; + hao->addr = tmp_addr; if (skb->tstamp.tv64 == 0) __net_timestamp(skb); @@ -273,12 +274,12 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dstbuf; #endif - struct dst_entry *dst; + struct dst_entry *dst = skb_dst(skb); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; @@ -289,9 +290,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) dstbuf = opt->dst1; #endif - dst = dst_clone(skb_dst(skb)); if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { - dst_release(dst); skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) @@ -304,7 +303,6 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); - dst_release(dst); return -1; } @@ -463,9 +461,9 @@ looped_back: return -1; } - ipv6_addr_copy(&daddr, addr); - ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr); - ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr); + daddr = *addr; + *addr = ipv6_hdr(skb)->daddr; + ipv6_hdr(skb)->daddr = daddr; skb_dst_drop(skb); ip6_route_input(skb); @@ -692,7 +690,7 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, memcpy(phdr->addr, ihdr->addr + 1, (hops - 1) * sizeof(struct in6_addr)); - ipv6_addr_copy(phdr->addr + (hops - 1), *addr_p); + phdr->addr[hops - 1] = **addr_p; *addr_p = ihdr->addr; phdr->rt_hdr.nexthdr = *proto; @@ -890,8 +888,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, if (!opt || !opt->srcrt) return NULL; - ipv6_addr_copy(orig, &fl6->daddr); - ipv6_addr_copy(&fl6->daddr, ((struct rt0_hdr *)opt->srcrt)->addr); + *orig = fl6->daddr; + fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; return orig; } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 14ed0a9..72957f4 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -2,6 +2,7 @@ * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. */ +#include <linux/export.h> #include <net/ipv6.h> /* @@ -56,6 +57,9 @@ int ipv6_ext_hdr(u8 nexthdr) * it returns NULL. * - First fragment header is skipped, not-first ones * are considered as unparsable. + * - Reports the offset field of the final fragment header so it is + * possible to tell whether this is a first fragment, later fragment, + * or not fragmented. * - ESP is unparsable for now and considered like * normal payload protocol. * - Note also special handling of AUTH header. Thanks to IPsec wizards. @@ -63,10 +67,13 @@ int ipv6_ext_hdr(u8 nexthdr) * --ANK (980726) */ -int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp) +int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, + __be16 *frag_offp) { u8 nexthdr = *nexthdrp; + *frag_offp = 0; + while (ipv6_ext_hdr(nexthdr)) { struct ipv6_opt_hdr _hdr, *hp; int hdrlen; @@ -86,7 +93,8 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp) if (fp == NULL) return -1; - if (ntohs(*fp) & ~0x7) + *frag_offp = *fp; + if (ntohs(*frag_offp) & ~0x7) break; hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 34d244d..b6c5731 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -14,6 +14,7 @@ */ #include <linux/netdevice.h> +#include <linux/export.h> #include <net/fib_rules.h> #include <net/ipv6.h> @@ -95,7 +96,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) goto again; - ipv6_addr_copy(&flp6->saddr, &saddr); + flp6->saddr = saddr; } goto out; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 1190041..01d46bf 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -135,11 +135,12 @@ static int is_ineligible(struct sk_buff *skb) int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; int len = skb->len - ptr; __u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; if (len < 0) return 1; - ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr); + ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off); if (ptr < 0) return 0; if (nexthdr == IPPROTO_ICMPV6) { @@ -290,9 +291,9 @@ static void mip6_addr_swap(struct sk_buff *skb) if (likely(off >= 0)) { hao = (struct ipv6_destopt_hao *) (skb_network_header(skb) + off); - ipv6_addr_copy(&tmp, &iph->saddr); - ipv6_addr_copy(&iph->saddr, &hao->addr); - ipv6_addr_copy(&hao->addr, &tmp); + tmp = iph->saddr; + iph->saddr = hao->addr; + hao->addr = tmp; } } } @@ -444,9 +445,9 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl6.daddr, &hdr->saddr); + fl6.daddr = hdr->saddr; if (saddr) - ipv6_addr_copy(&fl6.saddr, saddr); + fl6.saddr = *saddr; fl6.flowi6_oif = iif; fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; @@ -490,7 +491,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) goto out_dst_release; } - idev = in6_dev_get(skb->dev); + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), @@ -500,19 +502,16 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); - goto out_put; + } else { + err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + len + sizeof(struct icmp6hdr)); } - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); - -out_put: - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); out_dst_release: dst_release(dst); out: icmpv6_xmit_unlock(sk); } - EXPORT_SYMBOL(icmpv6_send); static void icmpv6_echo_reply(struct sk_buff *skb) @@ -540,9 +539,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); + fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) - ipv6_addr_copy(&fl6.saddr, saddr); + fl6.saddr = *saddr; fl6.flowi6_oif = skb->dev->ifindex; fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); @@ -569,7 +568,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - idev = in6_dev_get(skb->dev); + idev = __in6_dev_get(skb->dev); msg.skb = skb; msg.offset = 0; @@ -583,13 +582,10 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); - goto out_put; + } else { + err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + skb->len + sizeof(struct icmp6hdr)); } - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); - -out_put: - if (likely(idev != NULL)) - in6_dev_put(idev); dst_release(dst); out: icmpv6_xmit_unlock(sk); @@ -601,6 +597,7 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) int inner_offset; int hash; u8 nexthdr; + __be16 frag_off; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return; @@ -608,7 +605,8 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { /* now skip over extension headers */ - inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr); + inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); if (inner_offset<0) return; } else { @@ -791,8 +789,8 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, int oif) { memset(fl6, 0, sizeof(*fl6)); - ipv6_addr_copy(&fl6->saddr, saddr); - ipv6_addr_copy(&fl6->daddr, daddr); + fl6->saddr = *saddr; + fl6->daddr = *daddr; fl6->flowi6_proto = IPPROTO_ICMPV6; fl6->fl6_icmp_type = type; fl6->fl6_icmp_code = 0; @@ -840,8 +838,7 @@ static int __net_init icmpv6_sk_init(struct net *net) /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ - sk->sk_sndbuf = - (2 * ((64 * 1024) + sizeof(struct sk_buff))); + sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } return 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 8a58e8c..02dd203 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -65,9 +65,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + fl6.daddr = treq->rmt_addr; final_p = fl6_update_dst(&fl6, np->opt, &final); - ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.saddr = treq->loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet_rsk(req)->rmt_port; @@ -85,7 +85,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, * request_sock (formerly open request) hash tables. */ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, - const u32 rnd, const u16 synq_hsize) + const u32 rnd, const u32 synq_hsize) { u32 c; @@ -157,7 +157,7 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; sin6->sin6_family = AF_INET6; - ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); + sin6->sin6_addr = np->daddr; sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; @@ -211,11 +211,12 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) struct flowi6 fl6; struct dst_entry *dst; struct in6_addr *final_p, final; + int res; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl6.flowlabel); fl6.flowi6_oif = sk->sk_bound_dev_if; @@ -241,12 +242,14 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) __inet6_csk_dst_store(sk, dst, NULL, NULL); } - skb_dst_set(skb, dst_clone(dst)); + rcu_read_lock(); + skb_dst_set_noref(skb, dst); /* Restore final destination back after routing done */ - ipv6_addr_copy(&fl6.daddr, &np->daddr); + fl6.daddr = np->daddr; - return ip6_xmit(sk, skb, &fl6, np->opt); + res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + rcu_read_unlock(); + return res; } - EXPORT_SYMBOL_GPL(inet6_csk_xmit); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 320d91d..b82bcde 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -28,10 +28,6 @@ #include <linux/list.h> #include <linux/slab.h> -#ifdef CONFIG_PROC_FS -#include <linux/proc_fs.h> -#endif - #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> @@ -194,7 +190,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) struct fib6_table *table; table = kzalloc(sizeof(*table), GFP_ATOMIC); - if (table != NULL) { + if (table) { table->tb6_id = id; table->tb6_root.leaf = net->ipv6.ip6_null_entry; table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; @@ -214,7 +210,7 @@ struct fib6_table *fib6_new_table(struct net *net, u32 id) return tb; tb = fib6_alloc_table(net, id); - if (tb != NULL) + if (tb) fib6_link_table(net, tb); return tb; @@ -371,7 +367,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) s_e = cb->args[1]; w = (void *)cb->args[2]; - if (w == NULL) { + if (!w) { /* New dump: * * 1. hook callback destructor. @@ -383,7 +379,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) * 2. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); - if (w == NULL) + if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; @@ -429,7 +425,8 @@ out: static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, int addrlen, int plen, - int offset) + int offset, int allow_create, + int replace_required) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -451,8 +448,18 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, * Prefix match */ if (plen < fn->fn_bit || - !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) + !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { + if (!allow_create) { + if (replace_required) { + pr_warn("IPv6: Can't replace route, " + "no match found\n"); + return ERR_PTR(-ENOENT); + } + pr_warn("IPv6: NLM_F_CREATE should be set " + "when creating new route\n"); + } goto insert_above; + } /* * Exact match ? @@ -460,7 +467,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, if (plen == fn->fn_bit) { /* clean up an intermediate node */ - if ((fn->fn_flags & RTN_RTINFO) == 0) { + if (!(fn->fn_flags & RTN_RTINFO)) { rt6_release(fn->leaf); fn->leaf = NULL; } @@ -481,6 +488,23 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, fn = dir ? fn->right: fn->left; } while (fn); + if (!allow_create) { + /* We should not create new node because + * NLM_F_REPLACE was specified without NLM_F_CREATE + * I assume it is safe to require NLM_F_CREATE when + * REPLACE flag is used! Later we may want to remove the + * check for replace_required, because according + * to netlink specification, NLM_F_CREATE + * MUST be specified if new route is created. + * That would keep IPv6 consistent with IPv4 + */ + if (replace_required) { + pr_warn("IPv6: Can't replace route, no match found\n"); + return ERR_PTR(-ENOENT); + } + pr_warn("IPv6: NLM_F_CREATE should be set " + "when creating new route\n"); + } /* * We walked to the bottom of tree. * Create new leaf node without children. @@ -488,7 +512,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, ln = node_alloc(); - if (ln == NULL) + if (!ln) return NULL; ln->fn_bit = plen; @@ -531,7 +555,7 @@ insert_above: in = node_alloc(); ln = node_alloc(); - if (in == NULL || ln == NULL) { + if (!in || !ln) { if (in) node_free(in); if (ln) @@ -585,7 +609,7 @@ insert_above: ln = node_alloc(); - if (ln == NULL) + if (!ln) return NULL; ln->fn_bit = plen; @@ -618,10 +642,15 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, { struct rt6_info *iter = NULL; struct rt6_info **ins; + int replace = (info->nlh && + (info->nlh->nlmsg_flags & NLM_F_REPLACE)); + int add = (!info->nlh || + (info->nlh->nlmsg_flags & NLM_F_CREATE)); + int found = 0; ins = &fn->leaf; - for (iter = fn->leaf; iter; iter=iter->dst.rt6_next) { + for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) { /* * Search for duplicates */ @@ -630,17 +659,24 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* * Same priority level */ + if (info->nlh && + (info->nlh->nlmsg_flags & NLM_F_EXCL)) + return -EEXIST; + if (replace) { + found++; + break; + } - if (iter->rt6i_dev == rt->rt6i_dev && + if (iter->dst.dev == rt->dst.dev && iter->rt6i_idev == rt->rt6i_idev && ipv6_addr_equal(&iter->rt6i_gateway, &rt->rt6i_gateway)) { - if (!(iter->rt6i_flags&RTF_EXPIRES)) + if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; - iter->rt6i_expires = rt->rt6i_expires; - if (!(rt->rt6i_flags&RTF_EXPIRES)) { + iter->dst.expires = rt->dst.expires; + if (!(rt->rt6i_flags & RTF_EXPIRES)) { iter->rt6i_flags &= ~RTF_EXPIRES; - iter->rt6i_expires = 0; + iter->dst.expires = 0; } return -EEXIST; } @@ -659,17 +695,40 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* * insert node */ + if (!replace) { + if (!add) + pr_warn("IPv6: NLM_F_CREATE should be set when creating new route\n"); + +add: + rt->dst.rt6_next = iter; + *ins = rt; + rt->rt6i_node = fn; + atomic_inc(&rt->rt6i_ref); + inet6_rt_notify(RTM_NEWROUTE, rt, info); + info->nl_net->ipv6.rt6_stats->fib_rt_entries++; + + if (!(fn->fn_flags & RTN_RTINFO)) { + info->nl_net->ipv6.rt6_stats->fib_route_nodes++; + fn->fn_flags |= RTN_RTINFO; + } - rt->dst.rt6_next = iter; - *ins = rt; - rt->rt6i_node = fn; - atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); - info->nl_net->ipv6.rt6_stats->fib_rt_entries++; - - if ((fn->fn_flags & RTN_RTINFO) == 0) { - info->nl_net->ipv6.rt6_stats->fib_route_nodes++; - fn->fn_flags |= RTN_RTINFO; + } else { + if (!found) { + if (add) + goto add; + pr_warn("IPv6: NLM_F_REPLACE set, but no existing node found!\n"); + return -ENOENT; + } + *ins = rt; + rt->rt6i_node = fn; + rt->dst.rt6_next = iter->dst.rt6_next; + atomic_inc(&rt->rt6i_ref); + inet6_rt_notify(RTM_NEWROUTE, rt, info); + rt6_release(iter); + if (!(fn->fn_flags & RTN_RTINFO)) { + info->nl_net->ipv6.rt6_stats->fib_route_nodes++; + fn->fn_flags |= RTN_RTINFO; + } } return 0; @@ -678,7 +737,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && - (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE))) + (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE))) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } @@ -700,11 +759,28 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; + int allow_create = 1; + int replace_required = 0; + + if (info->nlh) { + if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) + allow_create = 0; + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) + replace_required = 1; + } + if (!allow_create && !replace_required) + pr_warn("IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst)); + rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), + allow_create, replace_required); - if (fn == NULL) + if (IS_ERR(fn)) { + err = PTR_ERR(fn); + fn = NULL; + } + + if (!fn) goto out; pn = fn; @@ -713,7 +789,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) if (rt->rt6i_src.plen) { struct fib6_node *sn; - if (fn->subtree == NULL) { + if (!fn->subtree) { struct fib6_node *sfn; /* @@ -728,7 +804,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) /* Create subtree root node */ sfn = node_alloc(); - if (sfn == NULL) + if (!sfn) goto st_failure; sfn->leaf = info->nl_net->ipv6.ip6_null_entry; @@ -740,9 +816,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) sn = fib6_add_1(sfn, &rt->rt6i_src.addr, sizeof(struct in6_addr), rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src)); + offsetof(struct rt6_info, rt6i_src), + allow_create, replace_required); - if (sn == NULL) { + if (!sn) { /* If it is failed, discard just allocated root, and then (in st_failure) stale node in main tree. @@ -757,13 +834,18 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, sizeof(struct in6_addr), rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src)); + offsetof(struct rt6_info, rt6i_src), + allow_create, replace_required); - if (sn == NULL) + if (IS_ERR(sn)) { + err = PTR_ERR(sn); + sn = NULL; + } + if (!sn) goto st_failure; } - if (fn->leaf == NULL) { + if (!fn->leaf) { fn->leaf = rt; atomic_inc(&rt->rt6i_ref); } @@ -772,10 +854,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) #endif err = fib6_add_rt2node(fn, rt, info); - - if (err == 0) { + if (!err) { fib6_start_gc(info->nl_net, rt); - if (!(rt->rt6i_flags&RTF_CACHE)) + if (!(rt->rt6i_flags & RTF_CACHE)) fib6_prune_clones(info->nl_net, pn, rt); } @@ -823,7 +904,7 @@ st_failure: */ struct lookup_args { - int offset; /* key offset on rt6_info */ + int offset; /* key offset on rt6_info */ const struct in6_addr *addr; /* search key */ }; @@ -853,11 +934,10 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, fn = next; continue; } - break; } - while(fn) { + while (fn) { if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { struct rt6key *key; @@ -904,8 +984,7 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *da }; fn = fib6_lookup_1(root, daddr ? args : args + 1); - - if (fn == NULL || fn->fn_flags & RTN_TL_ROOT) + if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; @@ -965,7 +1044,7 @@ struct fib6_node * fib6_locate(struct fib6_node *root, } #endif - if (fn && fn->fn_flags&RTN_RTINFO) + if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; @@ -979,14 +1058,13 @@ struct fib6_node * fib6_locate(struct fib6_node *root, static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) { - if (fn->fn_flags&RTN_ROOT) + if (fn->fn_flags & RTN_ROOT) return net->ipv6.ip6_null_entry; - while(fn) { - if(fn->left) + while (fn) { + if (fn->left) return fn->left->leaf; - - if(fn->right) + if (fn->right) return fn->right->leaf; fn = FIB6_SUBTREE(fn); @@ -1024,12 +1102,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ - || (children && fn->fn_flags&RTN_ROOT) + || (children && fn->fn_flags & RTN_ROOT) #endif ) { fn->leaf = fib6_find_prefix(net, fn); #if RT6_DEBUG >= 2 - if (fn->leaf==NULL) { + if (!fn->leaf) { WARN_ON(!fn->leaf); fn->leaf = net->ipv6.ip6_null_entry; } @@ -1062,7 +1140,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, read_lock(&fib6_walker_lock); FOR_WALKERS(w) { - if (child == NULL) { + if (!child) { if (w->root == fn) { w->root = w->node = NULL; RT6_TRACE("W %p adjusted by delroot 1\n", w); @@ -1091,7 +1169,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, read_unlock(&fib6_walker_lock); node_free(fn); - if (pn->fn_flags&RTN_RTINFO || FIB6_SUBTREE(pn)) + if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; rt6_release(pn->leaf); @@ -1125,7 +1203,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); w->leaf = rt->dst.rt6_next; - if (w->leaf == NULL) + if (!w->leaf) w->state = FWS_U; } } @@ -1134,7 +1212,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, rt->dst.rt6_next = NULL; /* If it was last route, expunge its radix tree node */ - if (fn->leaf == NULL) { + if (!fn->leaf) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; fn = fib6_repair_tree(net, fn); @@ -1148,7 +1226,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, * to still alive ones. */ while (fn) { - if (!(fn->fn_flags&RTN_RTINFO) && fn->leaf == rt) { + if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { fn->leaf = fib6_find_prefix(net, fn); atomic_inc(&fn->leaf->rt6i_ref); rt6_release(rt); @@ -1175,17 +1253,17 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) return -ENOENT; } #endif - if (fn == NULL || rt == net->ipv6.ip6_null_entry) + if (!fn || rt == net->ipv6.ip6_null_entry) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - if (!(rt->rt6i_flags&RTF_CACHE)) { + if (!(rt->rt6i_flags & RTF_CACHE)) { struct fib6_node *pn = fn; #ifdef CONFIG_IPV6_SUBTREES /* clones of this route might be in another subtree */ if (rt->rt6i_src.plen) { - while (!(pn->fn_flags&RTN_ROOT)) + while (!(pn->fn_flags & RTN_ROOT)) pn = pn->parent; pn = pn->parent; } @@ -1236,11 +1314,11 @@ static int fib6_walk_continue(struct fib6_walker_t *w) for (;;) { fn = w->node; - if (fn == NULL) + if (!fn) return 0; if (w->prune && fn != w->root && - fn->fn_flags&RTN_RTINFO && w->state < FWS_C) { + fn->fn_flags & RTN_RTINFO && w->state < FWS_C) { w->state = FWS_C; w->leaf = fn->leaf; } @@ -1269,7 +1347,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->state = FWS_C; w->leaf = fn->leaf; case FWS_C: - if (w->leaf && fn->fn_flags&RTN_RTINFO) { + if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; if (w->count < w->skip) { @@ -1384,6 +1462,26 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, fib6_walk(&c.w); } +void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg), + int prune, void *arg) +{ + struct fib6_table *table; + struct hlist_node *node; + struct hlist_head *head; + unsigned int h; + + rcu_read_lock(); + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { + read_lock_bh(&table->tb6_lock); + fib6_clean_tree(net, &table->tb6_root, + func, prune, arg); + read_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), int prune, void *arg) { @@ -1443,8 +1541,8 @@ static int fib6_age(struct rt6_info *rt, void *arg) * only if they are not in use now. */ - if (rt->rt6i_flags&RTF_EXPIRES && rt->rt6i_expires) { - if (time_after(now, rt->rt6i_expires)) { + if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { + if (time_after(now, rt->dst.expires)) { RT6_TRACE("expiring %p\n", rt); return -1; } @@ -1455,7 +1553,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) RT6_TRACE("aging clone %p\n", rt); return -1; } else if ((rt->rt6i_flags & RTF_GATEWAY) && - (!(dst_get_neighbour_raw(&rt->dst)->flags & NTF_ROUTER))) { + (!(dst_get_neighbour_noref_raw(&rt->dst)->flags & NTF_ROUTER))) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); return -1; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 5430394..b7867a1 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -21,6 +21,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/export.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -385,7 +386,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, err = -EINVAL; goto done; } - ipv6_addr_copy(&fl->dst, &freq->flr_dst); + fl->dst = freq->flr_dst; atomic_set(&fl->users, 1); switch (fl->share) { case IPV6_FL_S_EXCL: diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 027c7ff..1ca5d45 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -111,6 +111,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt ipv6_addr_loopback(&hdr->daddr)) goto err; + /* + * RFC4291 2.7 + * Multicast addresses must not be used as source addresses in IPv6 + * packets or appear in any Routing header. + */ + if (ipv6_addr_is_multicast(&hdr->saddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); @@ -272,6 +280,7 @@ int ip6_mc_input(struct sk_buff *skb) u8 *ptr = skb_network_header(skb) + opt->ra; struct icmp6hdr *icmp6; u8 nexthdr = hdr->nexthdr; + __be16 frag_off; int offset; /* Check if the value of Router Alert @@ -285,7 +294,7 @@ int ip6_mc_input(struct sk_buff *skb) goto out; } offset = ipv6_skip_exthdr(skb, sizeof(*hdr), - &nexthdr); + &nexthdr, &frag_off); if (offset < 0) goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4c882cf..d97e071 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -136,7 +136,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh) { int res = neigh_output(neigh, skb); @@ -180,7 +180,7 @@ int ip6_output(struct sk_buff *skb) */ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt) + struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -190,7 +190,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; - int tclass = 0; u32 mtu; if (opt) { @@ -228,10 +227,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, /* * Fill in the IPv6 header */ - if (np) { - tclass = np->tclass; + if (np) hlimit = np->hop_limit; - } if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); @@ -241,8 +238,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hdr->nexthdr = proto; hdr->hop_limit = hlimit; - ipv6_addr_copy(&hdr->saddr, &fl6->saddr); - ipv6_addr_copy(&hdr->daddr, first_hop); + hdr->saddr = fl6->saddr; + hdr->daddr = *first_hop; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -293,8 +290,8 @@ int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, hdr->nexthdr = proto; hdr->hop_limit = np->hop_limit; - ipv6_addr_copy(&hdr->saddr, saddr); - ipv6_addr_copy(&hdr->daddr, daddr); + hdr->saddr = *saddr; + hdr->daddr = *daddr; return 0; } @@ -332,10 +329,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) { struct ipv6hdr *hdr = ipv6_hdr(skb); u8 nexthdr = hdr->nexthdr; + __be16 frag_off; int offset; if (ipv6_ext_hdr(nexthdr)) { - offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr); + offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) return 0; } else @@ -465,7 +463,7 @@ int ip6_forward(struct sk_buff *skb) send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct rt6_info *rt; @@ -606,7 +604,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) static atomic_t ipv6_fragmentation_id; int old, new; - if (rt) { + if (rt && !(rt->dst.flags & DST_NOPEER)) { struct inet_peer *peer; if (!rt->rt6i_peer) @@ -634,6 +632,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; + int hroom, troom; __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; @@ -800,6 +799,8 @@ slow_path: */ *prevhdr = NEXTHDR_FRAGMENT; + hroom = LL_RESERVED_SPACE(rt->dst.dev); + troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. @@ -818,7 +819,8 @@ slow_path: * Allocate buffer. */ - if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) { + if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + + hroom + troom, GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); @@ -831,7 +833,7 @@ slow_path: */ ip6_copy_metadata(frag, skb); - skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(frag, hroom); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); @@ -981,7 +983,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry of the nexthop router */ rcu_read_lock(); - n = dst_get_neighbour(*dst); + n = dst_get_neighbour_noref(*dst); if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; @@ -1062,7 +1064,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (err) return ERR_PTR(err); if (final_dst) - ipv6_addr_copy(&fl6->daddr, final_dst); + fl6->daddr = *final_dst; if (can_sleep) fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; @@ -1098,7 +1100,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (err) return ERR_PTR(err); if (final_dst) - ipv6_addr_copy(&fl6->daddr, final_dst); + fl6->daddr = *final_dst; if (can_sleep) fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; @@ -1126,7 +1128,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); if (skb == NULL) - return -ENOMEM; + return err; /* reserve space for Hardware header */ skb_reserve(skb, hh_len); @@ -1193,6 +1195,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct sk_buff *skb; unsigned int maxfraglen, fragheaderlen; int exthdrlen; + int dst_exthdrlen; int hh_len; int mtu; int copy; @@ -1248,7 +1251,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, np->cork.hop_limit = hlimit; np->cork.tclass = tclass; mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + rt->dst.dev->mtu : dst_mtu(&rt->dst); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; @@ -1259,16 +1262,17 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, cork->length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) - - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; length += exthdrlen; transhdrlen += exthdrlen; + dst_exthdrlen = rt->dst.header_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; + dst_exthdrlen = 0; mtu = cork->fragsize; } @@ -1368,6 +1372,8 @@ alloc_new_skb: else alloclen = datalen + fragheaderlen; + alloclen += dst_exthdrlen; + /* * The last fragment gets additional space at tail. * Note: we overallocate on fragments with MSG_MODE @@ -1419,9 +1425,9 @@ alloc_new_skb: /* * Find where to start putting bytes */ - data = skb_put(skb, fraglen); - skb_set_network_header(skb, exthdrlen); - data += fragheaderlen; + data = skb_put(skb, fraglen + dst_exthdrlen); + skb_set_network_header(skb, exthdrlen + dst_exthdrlen); + data += fragheaderlen + dst_exthdrlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { @@ -1434,6 +1440,7 @@ alloc_new_skb: pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap; + if (copy < 0) { err = -EINVAL; kfree_skb(skb); @@ -1448,6 +1455,7 @@ alloc_new_skb: length -= datalen - fraggap; transhdrlen = 0; exthdrlen = 0; + dst_exthdrlen = 0; csummode = CHECKSUM_NONE; /* @@ -1480,13 +1488,13 @@ alloc_new_skb: if (page && (left = PAGE_SIZE - off) > 0) { if (copy >= left) copy = left; - if (page != frag->page) { + if (page != skb_frag_page(frag)) { if (i == MAX_SKB_FRAGS) { err = -EMSGSIZE; goto error; } - get_page(page); skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); + skb_frag_ref(skb, i); frag = &skb_shinfo(skb)->frags[i]; } } else if(i < MAX_SKB_FRAGS) { @@ -1506,12 +1514,14 @@ alloc_new_skb: err = -EMSGSIZE; goto error; } - if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) { + if (getfrag(from, + skb_frag_address(frag) + skb_frag_size(frag), + offset, copy, skb->len, skb) < 0) { err = -EFAULT; goto error; } sk->sk_sndmsg_off += copy; - frag->size += copy; + skb_frag_size_add(frag, copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -1583,7 +1593,7 @@ int ip6_push_pending_frames(struct sock *sk) if (np->pmtudisc < IPV6_PMTUDISC_DO) skb->local_df = 1; - ipv6_addr_copy(final_dst, &fl6->daddr); + *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -1599,8 +1609,8 @@ int ip6_push_pending_frames(struct sock *sk) hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; - ipv6_addr_copy(&hdr->saddr, &fl6->saddr); - ipv6_addr_copy(&hdr->daddr, final_dst); + hdr->saddr = fl6->saddr; + hdr->daddr = *final_dst; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0bc9888..aa21da6 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -93,7 +93,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ip6_get_stats(struct net_device *dev) { @@ -289,6 +289,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) if ((err = register_netdevice(dev)) < 0) goto failed_free; + strcpy(t->parms.name, dev->name); + dev_hold(dev); ip6_tnl_link(ip6n, t); return t; @@ -350,7 +352,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) - rcu_assign_pointer(ip6n->tnls_wc[0], NULL); + RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); ip6_tnl_dst_reset(t); @@ -651,8 +653,8 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); - if (rt && rt->rt6i_dev) - skb2->dev = rt->rt6i_dev; + if (rt && rt->dst.dev) + skb2->dev = rt->dst.dev; icmpv6_send(skb2, rel_type, rel_code, rel_info); @@ -889,7 +891,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ipv6_tel_txoption opt; - struct dst_entry *dst; + struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; unsigned int max_headroom = sizeof(struct ipv6hdr); @@ -897,19 +899,20 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, int err = -1; int pkt_len; - if ((dst = ip6_tnl_dst_check(t)) != NULL) - dst_hold(dst); - else { - dst = ip6_route_output(net, NULL, fl6); + if (!fl6->flowi6_mark) + dst = ip6_tnl_dst_check(t); + if (!dst) { + ndst = ip6_route_output(net, NULL, fl6); - if (dst->error) + if (ndst->error) goto tx_err_link_failure; - dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(dst)) { - err = PTR_ERR(dst); - dst = NULL; + ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); + ndst = NULL; goto tx_err_link_failure; } + dst = ndst; } tdev = dst->dev; @@ -955,8 +958,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb = new_skb; } skb_dst_drop(skb); - skb_dst_set(skb, dst_clone(dst)); - + if (fl6->flowi6_mark) { + skb_dst_set(skb, dst); + ndst = NULL; + } else { + skb_dst_set_noref(skb, dst); + } skb->transport_header = skb->network_header; proto = fl6->flowi6_proto; @@ -972,8 +979,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; - ipv6_addr_copy(&ipv6h->saddr, &fl6->saddr); - ipv6_addr_copy(&ipv6h->daddr, &fl6->daddr); + ipv6h->saddr = fl6->saddr; + ipv6h->daddr = fl6->daddr; nf_reset(skb); pkt_len = skb->len; err = ip6_local_out(skb); @@ -987,13 +994,14 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, stats->tx_errors++; stats->tx_aborted_errors++; } - ip6_tnl_dst_store(t, dst); + if (ndst) + ip6_tnl_dst_store(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(dst); + dst_release(ndst); return err; } @@ -1020,9 +1028,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) dsfield = ipv4_get_dsfield(iph); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) & IPV6_TCLASS_MASK; + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { @@ -1069,10 +1079,12 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) fl6.flowi6_proto = IPPROTO_IPV6; dsfield = ipv6_get_dsfield(ipv6h); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) + if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)) + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { @@ -1143,8 +1155,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ - ipv6_addr_copy(&fl6->saddr, &p->laddr); - ipv6_addr_copy(&fl6->daddr, &p->raddr); + fl6->saddr = p->laddr; + fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; @@ -1173,11 +1185,11 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) if (rt == NULL) return; - if (rt->rt6i_dev) { - dev->hard_header_len = rt->rt6i_dev->hard_header_len + + if (rt->dst.dev) { + dev->hard_header_len = rt->dst.dev->hard_header_len + sizeof (struct ipv6hdr); - dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr); + dev->mtu = rt->dst.dev->mtu - sizeof (struct ipv6hdr); if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu-=8; @@ -1200,8 +1212,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) static int ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) { - ipv6_addr_copy(&t->parms.laddr, &p->laddr); - ipv6_addr_copy(&t->parms.raddr, &p->raddr); + t->parms.laddr = p->laddr; + t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; @@ -1397,7 +1409,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; - strcpy(t->parms.name, dev->name); dev->tstats = alloc_percpu(struct pcpu_tstats); if (!dev->tstats) return -ENOMEM; @@ -1477,6 +1488,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; @@ -1497,6 +1509,10 @@ static int __net_init ip6_tnl_init_net(struct net *net) err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; + + t = netdev_priv(ip6n->fb_tnl_dev); + + strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index def0538..c7e95c8 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -51,6 +51,7 @@ #include <linux/pim.h> #include <net/addrconf.h> #include <linux/netfilter_ipv6.h> +#include <linux/export.h> #include <net/ip6_checksum.h> struct mr6_table { @@ -1104,8 +1105,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, msg->im6_msgtype = MRT6MSG_WHOLEPKT; msg->im6_mif = mrt->mroute_reg_vif_num; msg->im6_pad = 0; - ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); - ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); + msg->im6_src = ipv6_hdr(pkt)->saddr; + msg->im6_dst = ipv6_hdr(pkt)->daddr; skb->ip_summed = CHECKSUM_UNNECESSARY; } else @@ -1130,8 +1131,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, msg->im6_msgtype = assert; msg->im6_mif = mifi; msg->im6_pad = 0; - ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); - ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); + msg->im6_src = ipv6_hdr(pkt)->saddr; + msg->im6_dst = ipv6_hdr(pkt)->daddr; skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -2180,8 +2181,8 @@ int ip6mr_get_route(struct net *net, iph->payload_len = 0; iph->nexthdr = IPPROTO_NONE; iph->hop_limit = 0; - ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); - ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); + iph->saddr = rt->rt6i_src.addr; + iph->daddr = rt->rt6i_dst.addr; err = ip6mr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2fbda5f..18a2719 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -343,7 +343,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (!capable(CAP_NET_ADMIN)) { + if (valbool && !capable(CAP_NET_ADMIN) && !capable(CAP_NET_RAW)) { retv = -EPERM; break; } @@ -435,7 +435,7 @@ sticky_done: goto e_inval; np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex; - ipv6_addr_copy(&np->sticky_pktinfo.ipi6_addr, &pkt.ipi6_addr); + np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr; retv = 0; break; } @@ -503,7 +503,7 @@ done: goto e_inval; if (val > 255 || val < -1) goto e_inval; - np->mcast_hops = val; + np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val); retv = 0; break; @@ -980,8 +980,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) : - ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr)); + src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { @@ -992,8 +991,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) : - ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr)); + src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index ee7839f..b853f06 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -155,14 +155,14 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return -ENOMEM; mc_lst->next = NULL; - ipv6_addr_copy(&mc_lst->addr, addr); + mc_lst->addr = *addr; rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; + dev = rt->dst.dev; dst_release(&rt->dst); } } else @@ -256,7 +256,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; + dev = rt->dst.dev; dev_hold(dev); dst_release(&rt->dst); } @@ -858,7 +858,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc); - ipv6_addr_copy(&mc->mca_addr, addr); + mc->mca_addr = *addr; mc->idev = idev; /* (reference taken) */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ @@ -1343,13 +1343,15 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) struct mld2_report *pmr; struct in6_addr addr_buf; const struct in6_addr *saddr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; int err; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - size += LL_ALLOCATED_SPACE(dev); + size += hlen + tlen; /* limit our allocations to order-0 page */ size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); @@ -1357,7 +1359,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) if (!skb) return NULL; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: @@ -1408,18 +1410,11 @@ static void mld_sendpack(struct sk_buff *skb) csum_partial(skb_transport_header(skb), mldlen, 0)); - dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); - - if (!dst) { - err = -ENOMEM; - goto err_out; - } - icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); + dst = icmp6_dst_alloc(skb->dev, NULL, &fl6); - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); @@ -1723,6 +1718,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, @@ -1744,7 +1741,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) IPSTATS_MIB_OUT, full_len); rcu_read_unlock(); - skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + full_len, 1, &err); + skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (skb == NULL) { rcu_read_lock(); @@ -1754,7 +1751,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) return; } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: @@ -1772,7 +1769,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); memset(hdr, 0, sizeof(struct mld_msg)); hdr->mld_type = type; - ipv6_addr_copy(&hdr->mld_mca, addr); + hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, @@ -1781,17 +1778,10 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) rcu_read_lock(); idev = __in6_dev_get(skb->dev); - dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); - if (!dst) { - err = -ENOMEM; - goto err_out; - } - icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + dst = icmp6_dst_alloc(skb->dev, NULL, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; @@ -1914,7 +1904,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, * Add multicast single-source filter to the interface list */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, - const struct in6_addr *psfsrc, int delta) + const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; @@ -2045,7 +2035,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, pmc->mca_sfcount[sfmode]++; err = 0; for (i=0; i<sfcount; i++) { - err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i], delta); + err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 43242e6..7e1e0fb 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -195,8 +195,8 @@ static inline int mip6_report_rl_allow(struct timeval *stamp, mip6_report_rl.stamp.tv_sec = stamp->tv_sec; mip6_report_rl.stamp.tv_usec = stamp->tv_usec; mip6_report_rl.iif = iif; - ipv6_addr_copy(&mip6_report_rl.src, src); - ipv6_addr_copy(&mip6_report_rl.dst, dst); + mip6_report_rl.src = *src; + mip6_report_rl.dst = *dst; allow = 1; } spin_unlock_bh(&mip6_report_rl.lock); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9da6e02..d8f02ef 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -93,7 +93,7 @@ static u32 ndisc_hash(const void *pkey, const struct net_device *dev, - __u32 rnd); + __u32 *hash_rnd); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -126,7 +126,6 @@ static const struct neigh_ops ndisc_direct_ops = { struct neigh_table nd_tbl = { .family = AF_INET6, - .entry_size = sizeof(struct neighbour) + sizeof(struct in6_addr), .key_len = sizeof(struct in6_addr), .hash = ndisc_hash, .constructor = ndisc_constructor, @@ -141,7 +140,7 @@ struct neigh_table nd_tbl = { .gc_staletime = 60 * HZ, .reachable_time = ND_REACHABLE_TIME, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 3, .mcast_probes = 3, .anycast_delay = 1 * HZ, @@ -350,16 +349,9 @@ EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, - __u32 hash_rnd) + __u32 *hash_rnd) { - const u32 *p32 = pkey; - u32 addr_hash, i; - - addr_hash = 0; - for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++) - addr_hash ^= *p32++; - - return jhash_2words(addr_hash, dev->ifindex, hash_rnd); + return ndisc_hashfn(pkey, dev, hash_rnd); } static int ndisc_constructor(struct neighbour *neigh) @@ -370,17 +362,14 @@ static int ndisc_constructor(struct neighbour *neigh) struct neigh_parms *parms; int is_multicast = ipv6_addr_is_multicast(addr); - rcu_read_lock(); in6_dev = in6_dev_get(dev); if (in6_dev == NULL) { - rcu_read_unlock(); return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); - rcu_read_unlock(); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { @@ -449,6 +438,8 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; int len; int err; u8 *opt; @@ -462,7 +453,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, skb = sock_alloc_send_skb(sk, (MAX_HEADER + sizeof(struct ipv6hdr) + - len + LL_ALLOCATED_SPACE(dev)), + len + hlen + tlen), 1, &err); if (!skb) { ND_PRINTK0(KERN_ERR @@ -471,7 +462,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, return NULL; } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); skb->transport_header = skb->tail; @@ -482,7 +473,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); if (target) { - ipv6_addr_copy((struct in6_addr *)opt, target); + *(struct in6_addr *)opt = *target; opt += sizeof(*target); } @@ -518,14 +509,7 @@ void ndisc_send_skb(struct sk_buff *skb, type = icmp6h->icmp6_type; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex); - - dst = icmp6_dst_alloc(dev, neigh, daddr); - if (!dst) { - kfree_skb(skb); - return; - } - - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + dst = icmp6_dst_alloc(dev, neigh, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); return; @@ -533,7 +517,8 @@ void ndisc_send_skb(struct sk_buff *skb, skb_dst_set(skb, dst); - idev = in6_dev_get(dst->dev); + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, @@ -543,8 +528,7 @@ void ndisc_send_skb(struct sk_buff *skb, ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); } EXPORT_SYMBOL(ndisc_send_skb); @@ -1039,7 +1023,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) if (skb->len < sizeof(*rs_msg)) return; - idev = in6_dev_get(skb->dev); + idev = __in6_dev_get(skb->dev); if (!idev) { if (net_ratelimit()) ND_PRINTK1("ICMP6 RS: can't find in6 device\n"); @@ -1080,7 +1064,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) neigh_release(neigh); } out: - in6_dev_put(idev); + return; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) @@ -1179,7 +1163,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) * set the RA_RECV flag in the interface */ - in6_dev = in6_dev_get(skb->dev); + in6_dev = __in6_dev_get(skb->dev); if (in6_dev == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: can't find inet6 device for %s.\n", @@ -1188,7 +1172,6 @@ static void ndisc_router_discovery(struct sk_buff *skb) } if (!ndisc_parse_options(opt, optlen, &ndopts)) { - in6_dev_put(in6_dev); ND_PRINTK2(KERN_WARNING "ICMP6 RA: invalid ND options\n"); return; @@ -1225,6 +1208,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (!in6_dev->cnf.accept_ra_defrtr) goto skip_defrtr; + if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + goto skip_defrtr; + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); #ifdef CONFIG_IPV6_ROUTER_PREF @@ -1238,7 +1224,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); if (rt) - neigh = dst_get_neighbour(&rt->dst); + neigh = dst_get_neighbour_noref(&rt->dst); if (rt && lifetime == 0) { neigh_clone(neigh); @@ -1255,17 +1241,15 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() failed to add default route.\n", __func__); - in6_dev_put(in6_dev); return; } - neigh = dst_get_neighbour(&rt->dst); + neigh = dst_get_neighbour_noref(&rt->dst); if (neigh == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() got default router without neighbour.\n", __func__); dst_release(&rt->dst); - in6_dev_put(in6_dev); return; } neigh->flags |= NTF_ROUTER; @@ -1274,7 +1258,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) } if (rt) - rt->rt6i_expires = jiffies + (HZ * lifetime); + rt->dst.expires = jiffies + (HZ * lifetime); if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; @@ -1349,6 +1333,9 @@ skip_linkparms: goto out; #ifdef CONFIG_IPV6_ROUTE_INFO + if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0)) + goto skip_routeinfo; + if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; @@ -1366,6 +1353,8 @@ skip_linkparms: &ipv6_hdr(skb)->saddr); } } + +skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE @@ -1379,7 +1368,9 @@ skip_linkparms: for (p = ndopts.nd_opts_pi; p; p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) { - addrconf_prefix_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3); + addrconf_prefix_rcv(skb->dev, (u8 *)p, + (p->nd_opt_len) << 3, + ndopts.nd_opts_src_lladdr != NULL); } } @@ -1422,7 +1413,6 @@ out: dst_release(&rt->dst); else if (neigh) neigh_release(neigh); - in6_dev_put(in6_dev); } static void ndisc_redirect_rcv(struct sk_buff *skb) @@ -1481,13 +1471,11 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) return; } - in6_dev = in6_dev_get(skb->dev); + in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) { - in6_dev_put(in6_dev); + 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 @@ -1497,7 +1485,6 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { ND_PRINTK2(KERN_WARNING "ICMPv6 Redirect: invalid ND options\n"); - in6_dev_put(in6_dev); return; } if (ndopts.nd_opts_tgt_lladdr) { @@ -1506,7 +1493,6 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) if (!lladdr) { ND_PRINTK2(KERN_WARNING "ICMPv6 Redirect: invalid link-layer address length\n"); - in6_dev_put(in6_dev); return; } } @@ -1518,7 +1504,6 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) on_link); neigh_release(neigh); } - in6_dev_put(in6_dev); } void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, @@ -1537,6 +1522,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, struct inet6_dev *idev; struct flowi6 fl6; u8 *opt; + int hlen, tlen; int rd_len; int err; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; @@ -1575,7 +1561,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, } if (!rt->rt6i_peer) rt6_bind_peer(rt, 1); - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { @@ -1594,9 +1580,11 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, rd_len &= ~0x7; len += rd_len; + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; buff = sock_alloc_send_skb(sk, (MAX_HEADER + sizeof(struct ipv6hdr) + - len + LL_ALLOCATED_SPACE(dev)), + len + hlen + tlen), 1, &err); if (buff == NULL) { ND_PRINTK0(KERN_ERR @@ -1605,7 +1593,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, goto release; } - skb_reserve(buff, LL_RESERVED_SPACE(dev)); + skb_reserve(buff, hlen); ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr, IPPROTO_ICMPV6, len); @@ -1621,9 +1609,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, */ addrp = (struct in6_addr *)(icmph + 1); - ipv6_addr_copy(addrp, target); + *addrp = *target; addrp++; - ipv6_addr_copy(addrp, &ipv6_hdr(skb)->daddr); + *addrp = ipv6_hdr(skb)->daddr; opt = (u8*) (addrp + 1); @@ -1651,7 +1639,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, csum_partial(icmph, len, 0)); skb_dst_set(buff, dst); - idev = in6_dev_get(dst->dev); + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, dst_output); @@ -1660,8 +1649,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); return; release: diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 30fcee4..db31561 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -3,6 +3,7 @@ #include <linux/ipv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> +#include <linux/export.h> #include <net/dst.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -100,9 +101,16 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst, .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, }; const void *sk = strict ? &fake_sk : NULL; - - *dst = ip6_route_output(net, sk, &fl->u.ip6); - return (*dst)->error; + struct dst_entry *result; + int err; + + result = ip6_route_output(net, sk, &fl->u.ip6); + err = result->error; + if (err) + dst_release(result); + else + *dst = result; + return err; } __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4484648..9a68fb5 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -125,6 +125,16 @@ config IP6_NF_MATCH_MH To compile it as a module, choose M here. If unsure, say N. +config IP6_NF_MATCH_RPFILTER + tristate '"rpfilter" reverse path filter match support' + depends on NETFILTER_ADVANCED + ---help--- + This option allows you to match packets whose replies would + go out via the interface the packet came in. + + To compile it as a module, choose M here. If unsure, say N. + The module will be called ip6t_rpfilter. + config IP6_NF_MATCH_RT tristate '"rt" Routing header match support' depends on NETFILTER_ADVANCED @@ -186,7 +196,6 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index abfee91..2eaed96 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o +obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 5e5ce77..a34c9e4 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -405,6 +405,7 @@ __ipq_rcv_skb(struct sk_buff *skb) int status, type, pid, flags; unsigned int nlmsglen, skblen; struct nlmsghdr *nlh; + bool enable_timestamp = false; skblen = skb->len; if (skblen < sizeof(*nlh)) @@ -442,11 +443,13 @@ __ipq_rcv_skb(struct sk_buff *skb) RCV_SKB_FAIL(-EBUSY); } } else { - net_enable_timestamp(); + enable_timestamp = true; peer_pid = pid; } spin_unlock_bh(&queue_lock); + if (enable_timestamp) + net_enable_timestamp(); status = ipq_receive_peer(NLMSG_DATA(nlh), type, nlmsglen - NLMSG_LENGTH(0)); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index a5a4c5d..aad2fa4 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -49,6 +49,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) const __u8 tclass = DEFAULT_TOS_VALUE; struct dst_entry *dst = NULL; u8 proto; + __be16 frag_off; struct flowi6 fl6; if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || @@ -58,7 +59,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) } proto = oip6h->nexthdr; - tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto); + tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off); if ((tcphoff < 0) || (tcphoff > oldskb->len)) { pr_debug("Cannot get TCP header.\n"); @@ -93,8 +94,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.saddr, &oip6h->daddr); - ipv6_addr_copy(&fl6.daddr, &oip6h->saddr); + fl6.saddr = oip6h->daddr; + fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph.dest; fl6.fl6_dport = otcph.source; security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); @@ -129,8 +130,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; - ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); - ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr); + ip6h->saddr = oip6h->daddr; + ip6h->daddr = oip6h->saddr; tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c new file mode 100644 index 0000000..5d1d8b0 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -0,0 +1,133 @@ +/* + * Copyright (c) 2011 Florian Westphal <fw@strlen.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/route.h> +#include <net/ip6_fib.h> +#include <net/ip6_route.h> + +#include <linux/netfilter/xt_rpfilter.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("Xtables: IPv6 reverse path filter match"); + +static bool rpfilter_addr_unicast(const struct in6_addr *addr) +{ + int addr_type = ipv6_addr_type(addr); + return addr_type & IPV6_ADDR_UNICAST; +} + +static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, + const struct net_device *dev, u8 flags) +{ + struct rt6_info *rt; + struct ipv6hdr *iph = ipv6_hdr(skb); + bool ret = false; + struct flowi6 fl6 = { + .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, + .flowi6_proto = iph->nexthdr, + .daddr = iph->saddr, + }; + int lookup_flags; + + if (rpfilter_addr_unicast(&iph->daddr)) { + memcpy(&fl6.saddr, &iph->daddr, sizeof(struct in6_addr)); + lookup_flags = RT6_LOOKUP_F_HAS_SADDR; + } else { + lookup_flags = 0; + } + + fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; + if ((flags & XT_RPFILTER_LOOSE) == 0) { + fl6.flowi6_oif = dev->ifindex; + lookup_flags |= RT6_LOOKUP_F_IFACE; + } + + rt = (void *) ip6_route_lookup(dev_net(dev), &fl6, lookup_flags); + if (rt->dst.error) + goto out; + + if (rt->rt6i_flags & (RTF_REJECT|RTF_ANYCAST)) + goto out; + + if (rt->rt6i_flags & RTF_LOCAL) { + ret = flags & XT_RPFILTER_ACCEPT_LOCAL; + goto out; + } + + if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) + ret = true; + out: + dst_release(&rt->dst); + return ret; +} + +static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_rpfilter_info *info = par->matchinfo; + int saddrtype; + struct ipv6hdr *iph; + bool invert = info->flags & XT_RPFILTER_INVERT; + + if (par->in->flags & IFF_LOOPBACK) + return true ^ invert; + + iph = ipv6_hdr(skb); + saddrtype = ipv6_addr_type(&iph->saddr); + if (unlikely(saddrtype == IPV6_ADDR_ANY)) + return true ^ invert; /* not routable: forward path will drop it */ + + return rpfilter_lookup_reverse6(skb, par->in, info->flags) ^ invert; +} + +static int rpfilter_check(const struct xt_mtchk_param *par) +{ + const struct xt_rpfilter_info *info = par->matchinfo; + unsigned int options = ~XT_RPFILTER_OPTION_MASK; + + if (info->flags & options) { + pr_info("unknown options encountered"); + return -EINVAL; + } + + if (strcmp(par->table, "mangle") != 0 && + strcmp(par->table, "raw") != 0) { + pr_info("match only valid in the \'raw\' " + "or \'mangle\' tables, not \'%s\'.\n", par->table); + return -EINVAL; + } + + return 0; +} + +static struct xt_match rpfilter_mt_reg __read_mostly = { + .name = "rpfilter", + .family = NFPROTO_IPV6, + .checkentry = rpfilter_check, + .match = rpfilter_mt, + .matchsize = sizeof(struct xt_rpfilter_info), + .hooks = (1 << NF_INET_PRE_ROUTING), + .me = THIS_MODULE +}; + +static int __init rpfilter_mt_init(void) +{ + return xt_register_match(&rpfilter_mt_reg); +} + +static void __exit rpfilter_mt_exit(void) +{ + xt_unregister_match(&rpfilter_mt_reg); +} + +module_init(rpfilter_mt_init); +module_exit(rpfilter_mt_exit); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index c9e37c8..a8f6da9 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -44,7 +44,7 @@ ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ -static int forward = NF_ACCEPT; +static bool forward = NF_ACCEPT; module_param(forward, bool, 0000); static int __net_init ip6table_filter_net_init(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0857272..38f00b0 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -182,7 +182,6 @@ fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst) return container_of(q, struct nf_ct_frag6_queue, q); oom: - pr_debug("Can't alloc new queue\n"); return NULL; } @@ -370,16 +369,16 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) struct sk_buff *clone; int i, plen = 0; - if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) { - pr_debug("Can't alloc skb\n"); + clone = alloc_skb(0, GFP_ATOMIC); + if (clone == NULL) goto out_oom; - } + clone->next = head->next; head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); - for (i=0; i<skb_shinfo(head)->nr_frags; i++) - plen += skb_shinfo(head)->frags[i].size; + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; head->data_len -= clone->len; head->len -= clone->len; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 18ff5df..fdeb6d0 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -21,6 +21,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stddef.h> +#include <linux/export.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> @@ -141,11 +142,7 @@ static const struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_SENTINEL }; -/* can be called either with percpu mib (pcpumib != NULL), - * or shared one (smib != NULL) - */ -static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpumib, - atomic_long_t *smib) +static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib) { char name[32]; int i; @@ -162,14 +159,14 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpum snprintf(name, sizeof(name), "Icmp6%s%s", i & 0x100 ? "Out" : "In", p); seq_printf(seq, "%-32s\t%lu\n", name, - pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i)); + atomic_long_read(smib + i)); } /* print by number (nonzero only) - ICMPMsgStat format */ for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { unsigned long val; - val = pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i); + val = atomic_long_read(smib + i); if (!val) continue; snprintf(name, sizeof(name), "Icmp6%sType%u", @@ -214,8 +211,7 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics, NULL, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, - (void __percpu **)net->mib.icmpv6msg_statistics, NULL); + snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs); snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6, NULL, snmp6_udp6_list); snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6, @@ -245,7 +241,7 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v) snmp6_ipstats_list); snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, NULL, idev->stats.icmpv6msgdev->mibs); + snmp6_seq_show_icmpv6msg(seq, idev->stats.icmpv6msgdev->mibs); return 0; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 343852e..d02f7e4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -61,6 +61,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/export.h> static struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), @@ -137,7 +138,7 @@ EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { - rcu_assign_pointer(mh_filter, NULL); + RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } @@ -298,9 +299,9 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; - ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); + np->rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) - ipv6_addr_copy(&np->saddr, &addr->sin6_addr); + np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); @@ -372,9 +373,9 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, read_unlock(&raw_v6_hashinfo.lock); } -static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) +static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { - if ((raw6_sk(sk)->checksum || rcu_dereference_raw(sk->sk_filter)) && + if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); @@ -382,7 +383,8 @@ static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) } /* Charge it to the socket. */ - if (ip_queue_rcv_skb(sk, skb) < 0) { + skb_dst_drop(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -493,7 +495,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; - ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr); + sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) @@ -542,8 +544,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, goto out; offset = rp->offset; - total_len = inet_sk(sk)->cork.base.length - (skb_network_header(skb) - - skb->data); + total_len = inet_sk(sk)->cork.base.length; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); @@ -610,6 +611,8 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; + int hlen = LL_RESERVED_SPACE(rt->dst.dev); + int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); @@ -619,11 +622,11 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, goto out; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, + length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -843,11 +846,11 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, goto out; if (!ipv6_addr_any(daddr)) - ipv6_addr_copy(&fl6.daddr, daddr); + fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 7b954e2..b69fae7 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -42,6 +42,7 @@ #include <linux/jhash.h> #include <linux/skbuff.h> #include <linux/slab.h> +#include <linux/export.h> #include <net/sock.h> #include <net/snmp.h> @@ -152,8 +153,8 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) fq->id = arg->id; fq->user = arg->user; - ipv6_addr_copy(&fq->saddr, arg->src); - ipv6_addr_copy(&fq->daddr, arg->dst); + fq->saddr = *arg->src; + fq->daddr = *arg->dst; } EXPORT_SYMBOL(ip6_frag_init); @@ -464,8 +465,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); - for (i=0; i<skb_shinfo(head)->nr_frags; i++) - plen += skb_shinfo(head)->frags[i].size; + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->len = clone->data_len = head->data_len - plen; head->data_len -= clone->len; head->len -= clone->len; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fb545ed..07361df 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -26,6 +26,7 @@ #include <linux/capability.h> #include <linux/errno.h> +#include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> @@ -61,22 +62,11 @@ #include <linux/sysctl.h> #endif -/* Set to 3 to get tracing. */ -#define RT6_DEBUG 2 - -#if RT6_DEBUG >= 3 -#define RDBG(x) printk x -#define RT6_TRACE(x...) printk(KERN_DEBUG x) -#else -#define RDBG(x) -#define RT6_TRACE(x...) do { ; } while (0) -#endif - static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_default_mtu(const struct dst_entry *dst); +static unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -133,7 +123,23 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr) { - return __neigh_lookup_errno(&nd_tbl, daddr, dst->dev); + struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); + if (n) + return n; + return neigh_create(&nd_tbl, daddr, dst->dev); +} + +static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev) +{ + struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway); + if (!n) { + n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev); + if (IS_ERR(n)) + return PTR_ERR(n); + } + dst_set_neighbour(&rt->dst, n); + + return 0; } static struct dst_ops ip6_dst_ops_template = { @@ -143,7 +149,7 @@ static struct dst_ops ip6_dst_ops_template = { .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, - .default_mtu = ip6_default_mtu, + .mtu = ip6_mtu, .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, @@ -154,9 +160,11 @@ static struct dst_ops ip6_dst_ops_template = { .neigh_lookup = ip6_neigh_lookup, }; -static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -174,7 +182,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, - .default_mtu = ip6_blackhole_default_mtu, + .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .cow_metrics = ip6_rt_blackhole_cow_metrics, @@ -244,9 +252,9 @@ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, { struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags); - if (rt != NULL) + if (rt) memset(&rt->rt6i_table, 0, - sizeof(*rt) - sizeof(struct dst_entry)); + sizeof(*rt) - sizeof(struct dst_entry)); return rt; } @@ -260,7 +268,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); - if (idev != NULL) { + if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); } @@ -296,10 +304,10 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, struct net_device *loopback_dev = dev_net(dev)->loopback_dev; - if (dev != loopback_dev && idev != NULL && idev->dev == dev) { + if (dev != loopback_dev && idev && idev->dev == dev) { struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev); - if (loopback_idev != NULL) { + if (loopback_idev) { rt->rt6i_idev = loopback_idev; in6_dev_put(idev); } @@ -309,7 +317,7 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static __inline__ int rt6_check_expired(const struct rt6_info *rt) { return (rt->rt6i_flags & RTF_EXPIRES) && - time_after(jiffies, rt->rt6i_expires); + time_after(jiffies, rt->dst.expires); } static inline int rt6_need_strict(const struct in6_addr *daddr) @@ -335,13 +343,13 @@ static inline struct rt6_info *rt6_device_match(struct net *net, goto out; for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { - struct net_device *dev = sprt->rt6i_dev; + struct net_device *dev = sprt->dst.dev; if (oif) { if (dev->ifindex == oif) return sprt; if (dev->flags & IFF_LOOPBACK) { - if (sprt->rt6i_idev == NULL || + if (!sprt->rt6i_idev || sprt->rt6i_idev->dev->ifindex != oif) { if (flags & RT6_LOOKUP_F_IFACE && oif) continue; @@ -382,7 +390,7 @@ static void rt6_probe(struct rt6_info *rt) * to no more than one per minute. */ rcu_read_lock(); - neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; + neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) goto out; read_lock_bh(&neigh->lock); @@ -396,7 +404,7 @@ static void rt6_probe(struct rt6_info *rt) target = (struct in6_addr *)&neigh->primary_key; addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL); + ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); } else { read_unlock_bh(&neigh->lock); } @@ -414,7 +422,7 @@ static inline void rt6_probe(struct rt6_info *rt) */ static inline int rt6_check_dev(struct rt6_info *rt, int oif) { - struct net_device *dev = rt->rt6i_dev; + struct net_device *dev = rt->dst.dev; if (!oif || dev->ifindex == oif) return 2; if ((dev->flags & IFF_LOOPBACK) && @@ -429,7 +437,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt) int m; rcu_read_lock(); - neigh = dst_get_neighbour(&rt->dst); + neigh = dst_get_neighbour_noref(&rt->dst); if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) m = 1; @@ -515,9 +523,6 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) struct rt6_info *match, *rt0; struct net *net; - RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n", - __func__, fn->leaf, oif); - rt0 = fn->rr_ptr; if (!rt0) fn->rr_ptr = rt0 = fn->leaf; @@ -536,10 +541,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) fn->rr_ptr = next; } - RT6_TRACE("%s() => %p\n", - __func__, match); - - net = dev_net(rt0->rt6i_dev); + net = dev_net(rt0->dst.dev); return match ? match : net->ipv6.ip6_null_entry; } @@ -608,7 +610,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (!addrconf_finite_timeout(lifetime)) { rt->rt6i_flags &= ~RTF_EXPIRES; } else { - rt->rt6i_expires = jiffies + HZ * lifetime; + rt->dst.expires = jiffies + HZ * lifetime; rt->rt6i_flags |= RTF_EXPIRES; } dst_release(&rt->dst); @@ -633,7 +635,7 @@ do { \ goto restart; \ } \ } \ -} while(0) +} while (0) static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, @@ -655,6 +657,13 @@ out: } +struct dst_entry * ip6_route_lookup(struct net *net, struct flowi6 *fl6, + int flags) +{ + return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup); +} +EXPORT_SYMBOL_GPL(ip6_route_lookup); + struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, int strict) { @@ -703,7 +712,7 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) int ip6_ins_rt(struct rt6_info *rt) { struct nl_info info = { - .nl_net = dev_net(rt->rt6i_dev), + .nl_net = dev_net(rt->dst.dev), }; return __ip6_ins_rt(rt, &info); } @@ -721,29 +730,27 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, rt = ip6_rt_copy(ort, daddr); if (rt) { - struct neighbour *neigh; int attempts = !in_softirq(); - if (!(rt->rt6i_flags&RTF_GATEWAY)) { - if (rt->rt6i_dst.plen != 128 && + if (!(rt->rt6i_flags & RTF_GATEWAY)) { + if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - ipv6_addr_copy(&rt->rt6i_gateway, daddr); + rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { - ipv6_addr_copy(&rt->rt6i_src.addr, saddr); + rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif retry: - neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); - if (IS_ERR(neigh)) { - struct net *net = dev_net(rt->rt6i_dev); + if (rt6_bind_neighbour(rt, rt->dst.dev)) { + struct net *net = dev_net(rt->dst.dev); int saved_rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int saved_rt_elasticity = @@ -768,8 +775,6 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, dst_free(&rt->dst); return NULL; } - dst_set_neighbour(&rt->dst, neigh); - } return rt; @@ -782,7 +787,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, if (rt) { rt->rt6i_flags |= RTF_CACHE; - dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst))); + dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst))); } return rt; } @@ -816,7 +821,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -872,7 +877,7 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, - .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, + .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; @@ -929,9 +934,9 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); - rt->rt6i_expires = 0; + rt->dst.expires = 0; - ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); + rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; rt->rt6i_metric = 0; @@ -994,7 +999,7 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags&RTF_CACHE) { + if (rt->rt6i_flags & RTF_CACHE) { dst_set_expires(&rt->dst, 0); rt->rt6i_flags |= RTF_EXPIRES; } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) @@ -1040,10 +1045,15 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_mtu(const struct dst_entry *dst) { - unsigned int mtu = IPV6_MIN_MTU; struct inet6_dev *idev; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu) + return mtu; + + mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); @@ -1059,38 +1069,41 @@ static DEFINE_SPINLOCK(icmp6_dst_lock); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *addr) + struct flowi6 *fl6) { + struct dst_entry *dst; struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); struct net *net = dev_net(dev); - if (unlikely(idev == NULL)) + if (unlikely(!idev)) return NULL; rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); - if (unlikely(rt == NULL)) { + if (unlikely(!rt)) { in6_dev_put(idev); + dst = ERR_PTR(-ENOMEM); goto out; } if (neigh) neigh_hold(neigh); else { - neigh = ndisc_get_neigh(dev, addr); - if (IS_ERR(neigh)) - neigh = NULL; + neigh = ip6_neigh_lookup(&rt->dst, &fl6->daddr); + if (IS_ERR(neigh)) { + dst_free(&rt->dst); + return ERR_CAST(neigh); + } } rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; dst_set_neighbour(&rt->dst, neigh); atomic_set(&rt->dst.__refcnt, 1); - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); - - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); + rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; @@ -1099,8 +1112,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, fib6_force_start_gc(net); + dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); + out: - return &rt->dst; + return dst; } int icmp6_dst_gc(void) @@ -1230,21 +1245,30 @@ int ip6_route_add(struct fib6_config *cfg) if (cfg->fc_metric == 0) cfg->fc_metric = IP6_RT_PRIO_USER; - table = fib6_new_table(net, cfg->fc_table); - if (table == NULL) { - err = -ENOBUFS; - goto out; + err = -ENOBUFS; + if (cfg->fc_nlinfo.nlh && + !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { + table = fib6_get_table(net, cfg->fc_table); + if (!table) { + printk(KERN_WARNING "IPv6: NLM_F_CREATE should be specified when creating new route\n"); + table = fib6_new_table(net, cfg->fc_table); + } + } else { + table = fib6_new_table(net, cfg->fc_table); } + if (!table) + goto out; + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT); - if (rt == NULL) { + if (!rt) { err = -ENOMEM; goto out; } rt->dst.obsolete = -1; - rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ? + rt->dst.expires = (cfg->fc_flags & RTF_EXPIRES) ? jiffies + clock_t_to_jiffies(cfg->fc_expires) : 0; @@ -1287,8 +1311,9 @@ int ip6_route_add(struct fib6_config *cfg) they would result in kernel looping; promote them to reject routes */ if ((cfg->fc_flags & RTF_REJECT) || - (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK) - && !(cfg->fc_flags&RTF_LOCAL))) { + (dev && (dev->flags & IFF_LOOPBACK) && + !(addr_type & IPV6_ADDR_LOOPBACK) && + !(cfg->fc_flags & RTF_LOCAL))) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { @@ -1315,7 +1340,7 @@ int ip6_route_add(struct fib6_config *cfg) int gwa_type; gw_addr = &cfg->fc_gateway; - ipv6_addr_copy(&rt->rt6i_gateway, gw_addr); + rt->rt6i_gateway = *gw_addr; gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -1329,26 +1354,26 @@ int ip6_route_add(struct fib6_config *cfg) some exceptions. --ANK */ err = -EINVAL; - if (!(gwa_type&IPV6_ADDR_UNICAST)) + if (!(gwa_type & IPV6_ADDR_UNICAST)) goto out; grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1); err = -EHOSTUNREACH; - if (grt == NULL) + if (!grt) goto out; if (dev) { - if (dev != grt->rt6i_dev) { + if (dev != grt->dst.dev) { dst_release(&grt->dst); goto out; } } else { - dev = grt->rt6i_dev; + dev = grt->dst.dev; idev = grt->rt6i_idev; dev_hold(dev); in6_dev_hold(grt->rt6i_idev); } - if (!(grt->rt6i_flags&RTF_GATEWAY)) + if (!(grt->rt6i_flags & RTF_GATEWAY)) err = 0; dst_release(&grt->dst); @@ -1356,12 +1381,12 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } err = -EINVAL; - if (dev == NULL || (dev->flags&IFF_LOOPBACK)) + if (!dev || (dev->flags & IFF_LOOPBACK)) goto out; } err = -ENODEV; - if (dev == NULL) + if (!dev) goto out; if (!ipv6_addr_any(&cfg->fc_prefsrc)) { @@ -1369,18 +1394,15 @@ int ip6_route_add(struct fib6_config *cfg) err = -EINVAL; goto out; } - ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc); + rt->rt6i_prefsrc.addr = cfg->fc_prefsrc; rt->rt6i_prefsrc.plen = 128; } else rt->rt6i_prefsrc.plen = 0; if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { - struct neighbour *n = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); - if (IS_ERR(n)) { - err = PTR_ERR(n); + err = rt6_bind_neighbour(rt, dev); + if (err) goto out; - } - dst_set_neighbour(&rt->dst, n); } rt->rt6i_flags = cfg->fc_flags; @@ -1426,7 +1448,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) { int err; struct fib6_table *table; - struct net *net = dev_net(rt->rt6i_dev); + struct net *net = dev_net(rt->dst.dev); if (rt == net->ipv6.ip6_null_entry) return -ENOENT; @@ -1445,7 +1467,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) int ip6_del_rt(struct rt6_info *rt) { struct nl_info info = { - .nl_net = dev_net(rt->rt6i_dev), + .nl_net = dev_net(rt->dst.dev), }; return __ip6_del_rt(rt, &info); } @@ -1458,7 +1480,7 @@ static int ip6_route_del(struct fib6_config *cfg) int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); - if (table == NULL) + if (!table) return err; read_lock_bh(&table->tb6_lock); @@ -1470,8 +1492,8 @@ static int ip6_route_del(struct fib6_config *cfg) if (fn) { for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { if (cfg->fc_ifindex && - (rt->rt6i_dev == NULL || - rt->rt6i_dev->ifindex != cfg->fc_ifindex)) + (!rt->dst.dev || + rt->dst.dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) @@ -1533,7 +1555,7 @@ restart: continue; if (!(rt->rt6i_flags & RTF_GATEWAY)) continue; - if (fl6->flowi6_oif != rt->rt6i_dev->ifindex) + if (fl6->flowi6_oif != rt->dst.dev->ifindex) continue; if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) continue; @@ -1566,7 +1588,7 @@ static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest, }, }; - ipv6_addr_copy(&rdfl.gateway, gateway); + rdfl.gateway = *gateway; if (rt6_need_strict(dest)) flags |= RT6_LOOKUP_F_IFACE; @@ -1611,18 +1633,18 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, dst_confirm(&rt->dst); /* Duplicate redirect: silently ignore. */ - if (neigh == dst_get_neighbour_raw(&rt->dst)) + if (neigh == dst_get_neighbour_noref_raw(&rt->dst)) goto out; nrt = ip6_rt_copy(rt, dest); - if (nrt == NULL) + if (!nrt) goto out; nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE; if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; - ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); + nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; dst_set_neighbour(&nrt->dst, neigh_clone(neigh)); if (ip6_ins_rt(nrt)) @@ -1632,7 +1654,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, netevent.new = &nrt->dst; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); - if (rt->rt6i_flags&RTF_CACHE) { + if (rt->rt6i_flags & RTF_CACHE) { ip6_del_rt(rt); return; } @@ -1653,7 +1675,7 @@ static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr int allfrag = 0; again: rt = rt6_lookup(net, daddr, saddr, ifindex, 0); - if (rt == NULL) + if (!rt) return; if (rt6_check_expired(rt)) { @@ -1703,7 +1725,7 @@ again: 1. It is connected route. Action: COW 2. It is gatewayed route or NONEXTHOP route. Action: clone it. */ - if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, daddr, saddr); else nrt = rt6_alloc_clone(rt, daddr); @@ -1759,7 +1781,7 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, const struct in6_addr *dest) { - struct net *net = dev_net(ort->rt6i_dev); + struct net *net = dev_net(ort->dst.dev); struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, ort->dst.dev, 0); @@ -1768,7 +1790,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, rt->dst.output = ort->dst.output; rt->dst.flags |= DST_HOST; - ipv6_addr_copy(&rt->rt6i_dst.addr, dest); + rt->rt6i_dst.addr = *dest; rt->rt6i_dst.plen = 128; dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; @@ -1776,9 +1798,9 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_expires = 0; + rt->dst.expires = 0; - ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); + rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; rt->rt6i_metric = 0; @@ -1801,7 +1823,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, struct fib6_table *table; table = fib6_get_table(net, RT6_TABLE_INFO); - if (table == NULL) + if (!table) return NULL; write_lock_bh(&table->tb6_lock); @@ -1810,7 +1832,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, goto out; for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - if (rt->rt6i_dev->ifindex != ifindex) + if (rt->dst.dev->ifindex != ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; @@ -1841,8 +1863,8 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; - ipv6_addr_copy(&cfg.fc_dst, prefix); - ipv6_addr_copy(&cfg.fc_gateway, gwaddr); + cfg.fc_dst = *prefix; + cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) @@ -1860,12 +1882,12 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev struct fib6_table *table; table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT); - if (table == NULL) + if (!table) return NULL; write_lock_bh(&table->tb6_lock); for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) { - if (dev == rt->rt6i_dev && + if (dev == rt->dst.dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; @@ -1891,7 +1913,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_nlinfo.nl_net = dev_net(dev), }; - ipv6_addr_copy(&cfg.fc_gateway, gwaddr); + cfg.fc_gateway = *gwaddr; ip6_route_add(&cfg); @@ -1905,7 +1927,7 @@ void rt6_purge_dflt_routers(struct net *net) /* NOTE: Keep consistent with rt6_get_dflt_router */ table = fib6_get_table(net, RT6_TABLE_DFLT); - if (table == NULL) + if (!table) return; restart: @@ -1937,9 +1959,9 @@ static void rtmsg_to_fib6_config(struct net *net, cfg->fc_nlinfo.nl_net = net; - ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst); - ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src); - ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway); + cfg->fc_dst = rtmsg->rtmsg_dst; + cfg->fc_src = rtmsg->rtmsg_src; + cfg->fc_gateway = rtmsg->rtmsg_gateway; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) @@ -2038,14 +2060,14 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb) struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, - int anycast) + bool anycast) { struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, net->loopback_dev, 0); - struct neighbour *neigh; + int err; - if (rt == NULL) { + if (!rt) { if (net_ratelimit()) pr_warning("IPv6: Maximum number of routes reached," " consider increasing route/max_size.\n"); @@ -2065,15 +2087,13 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_flags |= RTF_ANYCAST; else rt->rt6i_flags |= RTF_LOCAL; - neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); - if (IS_ERR(neigh)) { + err = rt6_bind_neighbour(rt, rt->dst.dev); + if (err) { dst_free(&rt->dst); - - return ERR_CAST(neigh); + return ERR_PTR(err); } - dst_set_neighbour(&rt->dst, neigh); - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); + rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); @@ -2091,7 +2111,7 @@ int ip6_route_get_saddr(struct net *net, struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt); int err = 0; if (rt->rt6i_prefsrc.plen) - ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr); + *saddr = rt->rt6i_prefsrc.addr; else err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, daddr, prefs, saddr); @@ -2111,7 +2131,7 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; - if (((void *)rt->rt6i_dev == dev || dev == NULL) && + if (((void *)rt->dst.dev == dev || !dev) && rt != net->ipv6.ip6_null_entry && ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { /* remove prefsrc entry */ @@ -2141,11 +2161,10 @@ static int fib6_ifdown(struct rt6_info *rt, void *arg) const struct arg_dev_net *adn = arg; const struct net_device *dev = adn->dev; - if ((rt->rt6i_dev == dev || dev == NULL) && - rt != adn->net->ipv6.ip6_null_entry) { - RT6_TRACE("deleted by ifdown %p\n", rt); + if ((rt->dst.dev == dev || !dev) && + rt != adn->net->ipv6.ip6_null_entry) return -1; - } + return 0; } @@ -2178,7 +2197,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) */ idev = __in6_dev_get(arg->dev); - if (idev == NULL) + if (!idev) return 0; /* For administrative MTU increase, there is no way to discover @@ -2195,7 +2214,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) also have the lowest MTU, TOO BIG MESSAGE will be lead to PMTU discouvery. */ - if (rt->rt6i_dev == arg->dev && + if (rt->dst.dev == arg->dev && !dst_metric_locked(&rt->dst, RTAX_MTU) && (dst_mtu(&rt->dst) >= arg->mtu || (dst_mtu(&rt->dst) < arg->mtu && @@ -2344,11 +2363,13 @@ static int rt6_fill_node(struct net *net, int iif, int type, u32 pid, u32 seq, int prefix, int nowait, unsigned int flags) { + const struct inet_peer *peer; struct rtmsg *rtm; struct nlmsghdr *nlh; long expires; u32 table; struct neighbour *n; + u32 ts, tsage; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2358,7 +2379,7 @@ static int rt6_fill_node(struct net *net, } nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); @@ -2372,25 +2393,25 @@ static int rt6_fill_node(struct net *net, table = RT6_TABLE_UNSPEC; rtm->rtm_table = table; NLA_PUT_U32(skb, RTA_TABLE, table); - if (rt->rt6i_flags&RTF_REJECT) + if (rt->rt6i_flags & RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; - else if (rt->rt6i_flags&RTF_LOCAL) + else if (rt->rt6i_flags & RTF_LOCAL) rtm->rtm_type = RTN_LOCAL; - else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) + else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) rtm->rtm_type = RTN_LOCAL; else rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->rt6i_protocol; - if (rt->rt6i_flags&RTF_DYNAMIC) + if (rt->rt6i_flags & RTF_DYNAMIC) rtm->rtm_protocol = RTPROT_REDIRECT; else if (rt->rt6i_flags & RTF_ADDRCONF) rtm->rtm_protocol = RTPROT_KERNEL; - else if (rt->rt6i_flags&RTF_DEFAULT) + else if (rt->rt6i_flags & RTF_DEFAULT) rtm->rtm_protocol = RTPROT_RA; - if (rt->rt6i_flags&RTF_CACHE) + if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dst) { @@ -2430,7 +2451,7 @@ static int rt6_fill_node(struct net *net, if (rt->rt6i_prefsrc.plen) { struct in6_addr saddr_buf; - ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr); + saddr_buf = rt->rt6i_prefsrc.addr; NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } @@ -2438,24 +2459,31 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; rcu_read_lock(); - n = dst_get_neighbour(&rt->dst); + n = dst_get_neighbour_noref(&rt->dst); if (n) NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key); rcu_read_unlock(); if (rt->dst.dev) - NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); + NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); if (!(rt->rt6i_flags & RTF_EXPIRES)) expires = 0; - else if (rt->rt6i_expires - jiffies < INT_MAX) - expires = rt->rt6i_expires - jiffies; + else if (rt->dst.expires - jiffies < INT_MAX) + expires = rt->dst.expires - jiffies; else expires = INT_MAX; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, + peer = rt->rt6i_peer; + ts = tsage = 0; + if (peer && peer->tcp_ts_stamp) { + ts = peer->tcp_ts; + tsage = get_seconds() - peer->tcp_ts_stamp; + } + + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, ts, tsage, expires, rt->dst.error) < 0) goto nla_put_failure; @@ -2504,14 +2532,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; - ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC])); + fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; - ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST])); + fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) @@ -2530,7 +2558,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (skb == NULL) { + if (!skb) { err = -ENOBUFS; goto errout; } @@ -2565,10 +2593,10 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) int err; err = -ENOBUFS; - seq = info->nlh != NULL ? info->nlh->nlmsg_seq : 0; + seq = info->nlh ? info->nlh->nlmsg_seq : 0; skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); - if (skb == NULL) + if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, @@ -2635,7 +2663,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) seq_puts(m, "00000000000000000000000000000000 00 "); #endif rcu_read_lock(); - n = dst_get_neighbour(&rt->dst); + n = dst_get_neighbour_noref(&rt->dst); if (n) { seq_printf(m, "%pi6", n->primary_key); } else { @@ -2645,14 +2673,14 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) seq_printf(m, " %08x %08x %08x %08x %8s\n", rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), rt->dst.__use, rt->rt6i_flags, - rt->rt6i_dev ? rt->rt6i_dev->name : ""); + rt->dst.dev ? rt->dst.dev->name : ""); return 0; } static int ipv6_route_show(struct seq_file *m, void *v) { struct net *net = (struct net *)m->private; - fib6_clean_all(net, rt6_info_route, 0, m); + fib6_clean_all_ro(net, rt6_info_route, 0, m); return 0; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 00b15ac..133768e 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -91,7 +91,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipip6_get_stats(struct net_device *dev) { @@ -263,6 +263,8 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip6_tunnel_link(sitn, nt); @@ -474,7 +476,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - rcu_assign_pointer(sitn->tunnels_wc[0], NULL); + RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); ipip6_tunnel_del_prl(netdev_priv(dev), NULL); @@ -680,7 +682,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct neighbour *neigh = NULL; if (skb_dst(skb)) - neigh = dst_get_neighbour(skb_dst(skb)); + neigh = dst_get_neighbour_noref(skb_dst(skb)); if (neigh == NULL) { if (net_ratelimit()) @@ -705,7 +707,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct neighbour *neigh = NULL; if (skb_dst(skb)) - neigh = dst_get_neighbour(skb_dst(skb)); + neigh = dst_get_neighbour_noref(skb_dst(skb)); if (neigh == NULL) { if (net_ratelimit()) @@ -914,7 +916,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; #ifdef CONFIG_IPV6_SIT_6RD } else { - ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix); + ip6rd.prefix = t->ip6rd.prefix; ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; @@ -1082,7 +1084,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) if (relay_prefix != ip6rd.relay_prefix) goto done; - ipv6_addr_copy(&t->ip6rd.prefix, &prefix); + t->ip6rd.prefix = prefix; t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd.prefixlen; t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; @@ -1144,7 +1146,6 @@ static int ipip6_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -1207,6 +1208,7 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); + struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; @@ -1231,6 +1233,9 @@ static int __net_init sit_init_net(struct net *net) if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(sitn->fb_tunnel_dev); + + strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index ac83896..8e951d8 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -115,7 +115,7 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, & COOKIEMASK; } -__u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) +__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); @@ -137,7 +137,7 @@ __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp) jiffies / (HZ * 60), mssind); } -static inline int cookie_check(struct sk_buff *skb, __u32 cookie) +static inline int cookie_check(const struct sk_buff *skb, __u32 cookie) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); @@ -152,7 +152,7 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tcp_opt; - u8 *hash_location; + const u8 *hash_location; struct inet_request_sock *ireq; struct inet6_request_sock *ireq6; struct tcp_request_sock *treq; @@ -200,8 +200,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->mss = mss; ireq->rmt_port = th->source; ireq->loc_port = th->dest; - ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); + ireq6->rmt_addr = ipv6_hdr(skb)->saddr; + ireq6->loc_addr = ipv6_hdr(skb)->daddr; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { @@ -237,9 +237,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); + fl6.daddr = ireq6->rmt_addr; final_p = fl6_update_dst(&fl6, np->opt, &final); - ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr); + fl6.saddr = ireq6->loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet_rsk(req)->rmt_port; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 6dcf5e7..166a57c 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -10,6 +10,7 @@ #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/slab.h> +#include <linux/export.h> #include <net/ndisc.h> #include <net/ipv6.h> #include <net/addrconf.h> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7b8fc57..906c7ca 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -62,6 +62,7 @@ #include <net/netdma.h> #include <net/inet_common.h> #include <net/secure_seq.h> +#include <net/tcp_memcontrol.h> #include <asm/uaccess.h> @@ -114,7 +115,7 @@ static __inline__ __sum16 tcp_v6_check(int len, return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); } -static __u32 tcp_v6_init_sequence(struct sk_buff *skb) +static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, @@ -153,7 +154,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } @@ -195,7 +196,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->write_seq = 0; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); + np->daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -244,9 +245,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, saddr = &np->rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, - (saddr ? saddr : &np->saddr)); + fl6.daddr = np->daddr; + fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; @@ -264,11 +264,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - ipv6_addr_copy(&np->rcv_saddr, saddr); + np->rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); + np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; @@ -398,8 +398,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; @@ -489,8 +489,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); - ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.daddr = treq->rmt_addr; + fl6.saddr = treq->loc_addr; fl6.flowlabel = 0; fl6.flowi6_oif = treq->iif; fl6.flowi6_mark = sk->sk_mark; @@ -512,8 +512,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl6, opt); + fl6.daddr = treq->rmt_addr; + err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -617,8 +617,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, tp->md5sig_info->alloced6++; } - ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr, - peer); + tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer; tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey; tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen; @@ -750,8 +749,8 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, bp = &hp->md5_blk.ip6; /* 1. TCP pseudo-header (RFC2460) */ - ipv6_addr_copy(&bp->saddr, saddr); - ipv6_addr_copy(&bp->daddr, daddr); + bp->saddr = *saddr; + bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); @@ -761,7 +760,7 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, const struct in6_addr *daddr, struct in6_addr *saddr, - struct tcphdr *th) + const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct hash_desc *desc; @@ -793,13 +792,14 @@ clear_hash_noput: } static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - struct sock *sk, struct request_sock *req, - struct sk_buff *skb) + const struct sock *sk, + const struct request_sock *req, + const struct sk_buff *skb) { const struct in6_addr *saddr, *daddr; struct tcp_md5sig_pool *hp; struct hash_desc *desc; - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); if (sk) { saddr = &inet6_sk(sk)->saddr; @@ -842,12 +842,12 @@ clear_hash_noput: return 1; } -static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) +static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) { - __u8 *hash_location = NULL; + const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); int genhash; u8 newhash[16]; @@ -978,9 +978,10 @@ static int tcp6_gro_complete(struct sk_buff *skb) } static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 ts, struct tcp_md5sig_key *key, int rst) + u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass) { - struct tcphdr *th = tcp_hdr(skb), *t1; + const struct tcphdr *th = tcp_hdr(skb); + struct tcphdr *t1; struct sk_buff *buff; struct flowi6 fl6; struct net *net = dev_net(skb_dst(skb)->dev); @@ -1037,8 +1038,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, #endif memset(&fl6, 0, sizeof(fl6)); - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr); + fl6.daddr = ipv6_hdr(skb)->saddr; + fl6.saddr = ipv6_hdr(skb)->daddr; buff->ip_summed = CHECKSUM_PARTIAL; buff->csum = 0; @@ -1058,7 +1059,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl6, NULL); + ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); @@ -1070,7 +1071,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; struct tcp_md5sig_key *key = NULL; @@ -1091,13 +1092,13 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1); + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1, 0); } static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, - struct tcp_md5sig_key *key) + struct tcp_md5sig_key *key, u8 tclass) { - tcp_v6_send_response(skb, seq, ack, win, ts, key, 0); + tcp_v6_send_response(skb, seq, ack, win, ts, key, 0, tclass); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -1107,7 +1108,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw)); + tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), + tw->tw_tclass); inet_twsk_put(tw); } @@ -1116,7 +1118,7 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr)); + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0); } @@ -1160,7 +1162,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; struct tcp_options_received tmp_opt; - u8 *hash_location; + const u8 *hash_location; struct request_sock *req; struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); @@ -1247,11 +1249,18 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); treq = inet6_rsk(req); - ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); + treq->rmt_addr = ipv6_hdr(skb)->saddr; + treq->loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, tcp_hdr(skb)); + treq->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = inet6_iif(skb); + if (!isn) { struct inet_peer *peer = NULL; @@ -1261,12 +1270,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) atomic_inc(&skb->users); treq->pktopts = skb; } - treq->iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); if (want_cookie) { isn = cookie_v6_init_sequence(sk, skb, &req->mss); @@ -1377,7 +1380,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newnp->rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1441,9 +1444,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr); - ipv6_addr_copy(&newnp->saddr, &treq->loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr); + newnp->daddr = treq->rmt_addr; + newnp->saddr = treq->loc_addr; + newnp->rcv_saddr = treq->loc_addr; newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... @@ -1608,7 +1611,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) opt_skb = skb_clone(skb, GFP_ATOMIC); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) goto reset; if (opt_skb) @@ -1630,7 +1633,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * the new socket.. */ if(nsk != sk) { - sock_rps_save_rxhash(nsk, skb->rxhash); + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) @@ -1638,7 +1641,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } } else - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; @@ -1688,7 +1691,7 @@ ipv6_pktoptions: static int tcp_v6_rcv(struct sk_buff *skb) { - struct tcphdr *th; + const struct tcphdr *th; const struct ipv6hdr *hdr; struct sock *sk; int ret; @@ -1722,7 +1725,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->when = 0; - TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(hdr); + TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); @@ -1856,8 +1859,8 @@ static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) static void *tcp_v6_tw_get_peer(struct sock *sk) { - struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - struct inet_timewait_sock *tw = inet_twsk(sk); + const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); + const struct inet_timewait_sock *tw = inet_twsk(sk); if (tw->tw_family == AF_INET) return tcp_v4_tw_get_peer(sk); @@ -1992,7 +1995,8 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); + sock_update_memcg(sk); + sk_sockets_allocated_inc(sk); local_bh_enable(); return 0; @@ -2012,7 +2016,7 @@ static void tcp_v6_destroy_sock(struct sock *sk) #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - struct sock *sk, struct request_sock *req, int i, int uid) + const struct sock *sk, struct request_sock *req, int i, int uid) { int ttd = req->expires - jiffies; const struct in6_addr *src = &inet6_rsk(req)->loc_addr; @@ -2048,10 +2052,10 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) __u16 destp, srcp; int timer_active; unsigned long timer_expires; - struct inet_sock *inet = inet_sk(sp); - struct tcp_sock *tp = tcp_sk(sp); + const struct inet_sock *inet = inet_sk(sp); + const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); + const struct ipv6_pinfo *np = inet6_sk(sp); dest = &np->daddr; src = &np->rcv_saddr; @@ -2103,7 +2107,7 @@ static void get_timewait6_sock(struct seq_file *seq, { const struct in6_addr *dest, *src; __u16 destp, srcp; - struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); + const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); int ttd = tw->tw_ttd - jiffies; if (ttd < 0) @@ -2158,12 +2162,18 @@ out: return 0; } +static const struct file_operations tcp6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = tcp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct tcp_seq_afinfo tcp6_seq_afinfo = { .name = "tcp6", .family = AF_INET6, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &tcp6_afinfo_seq_fops, .seq_ops = { .show = tcp6_seq_show, }, @@ -2205,7 +2215,6 @@ struct proto tcpv6_prot = { .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, - .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, @@ -2219,6 +2228,9 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + .proto_cgroup = tcp_proto_cgroup, +#endif }; static const struct inet6_protocol tcpv6_protocol = { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index bb95e8e..4f96b5c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -238,7 +238,7 @@ exact_match: return result; } -static struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, struct udp_table *udptable) @@ -305,6 +305,7 @@ begin: rcu_read_unlock(); return result; } +EXPORT_SYMBOL_GPL(__udp6_lib_lookup); static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, @@ -340,7 +341,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -363,9 +364,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); @@ -376,14 +378,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov,len); + msg->msg_iov, copied ); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) @@ -417,8 +419,7 @@ try_again: ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin6->sin6_addr); else { - ipv6_addr_copy(&sin6->sin6_addr, - &ipv6_hdr(skb)->saddr); + sin6->sin6_addr = ipv6_hdr(skb)->saddr; if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6->sin6_scope_id = IP6CB(skb)->iif; } @@ -432,7 +433,7 @@ try_again: datagram_recv_ctl(sk, msg, skb); } - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; @@ -509,7 +510,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) int is_udplite = IS_UDPLITE(sk); if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) - sock_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; @@ -533,12 +534,14 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) } } - if (rcu_dereference_raw(sk->sk_filter)) { + if (rcu_access_pointer(sk->sk_filter)) { if (udp_lib_checksum_complete(skb)) goto drop; } - if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) { + skb_dst_drop(skb); + rc = sock_queue_rcv_skb(sk, skb); + if (rc < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), @@ -1113,11 +1116,11 @@ do_udp_sendmsg: fl6.flowi6_proto = sk->sk_protocol; if (!ipv6_addr_any(daddr)) - ipv6_addr_copy(&fl6.daddr, daddr); + fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; final_p = fl6_update_dst(&fl6, opt, &final); @@ -1298,7 +1301,8 @@ static int udp6_ufo_send_check(struct sk_buff *skb) return 0; } -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; @@ -1424,13 +1428,19 @@ int udp6_seq_show(struct seq_file *seq, void *v) return 0; } +static const struct file_operations udp6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct udp_seq_afinfo udp6_seq_afinfo = { .name = "udp6", .family = AF_INET6, .udp_table = &udp_table, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &udp6_afinfo_seq_fops, .seq_ops = { .show = udp6_seq_show, }, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 986c4de..1d08e21 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -11,6 +11,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include <linux/export.h> #include "udp_impl.h" static int udplitev6_rcv(struct sk_buff *skb) @@ -93,13 +94,20 @@ void udplitev6_exit(void) } #ifdef CONFIG_PROC_FS + +static const struct file_operations udplite6_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + static struct udp_seq_afinfo udplite6_seq_afinfo = { .name = "udplite6", .family = AF_INET6, .udp_table = &udplite_table, - .seq_fops = { - .owner = THIS_MODULE, - }, + .seq_fops = &udplite6_afinfo_seq_fops, .seq_ops = { .show = udp6_seq_show, }, diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 3437d7d..a81ce94 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -72,8 +72,8 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->nexthdr = IPPROTO_BEETPH; } - ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; return 0; } @@ -99,8 +99,8 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) ip6h = ipv6_hdr(skb); ip6h->payload_len = htons(skb->len - size); - ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6); - ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6); + ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6; + ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6; err = 0; out: return err; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 4d6edff..261e6e6 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -55,8 +55,8 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) dsfield &= ~INET_ECN_MASK; ipv6_change_dsfield(top_iph, 0, dsfield); top_iph->hop_limit = ip6_dst_hoplimit(dst->child); - ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr); + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 49a91c5f..4eeff89 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -28,6 +28,43 @@ int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, EXPORT_SYMBOL(xfrm6_find_1stfragopt); +static int xfrm6_local_dontfrag(struct sk_buff *skb) +{ + int proto; + struct sock *sk = skb->sk; + + if (sk) { + proto = sk->sk_protocol; + + if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) + return inet6_sk(sk)->dontfrag; + } + + return 0; +} + +static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu) +{ + struct flowi6 fl6; + struct sock *sk = skb->sk; + + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.daddr = ipv6_hdr(skb)->daddr; + + ipv6_local_rxpmtu(sk, &fl6, mtu); +} + +static void xfrm6_local_error(struct sk_buff *skb, u32 mtu) +{ + struct flowi6 fl6; + struct sock *sk = skb->sk; + + fl6.fl6_dport = inet_sk(sk)->inet_dport; + fl6.daddr = ipv6_hdr(skb)->daddr; + + ipv6_local_error(sk, EMSGSIZE, &fl6, mtu); +} + static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; @@ -39,7 +76,13 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (!skb->local_df && skb->len > mtu) { skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + + if (xfrm6_local_dontfrag(skb)) + xfrm6_local_rxpmtu(skb, mtu); + else if (skb->sk) + xfrm6_local_error(skb, mtu); + else + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; } @@ -93,9 +136,18 @@ static int __xfrm6_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; + int mtu = ip6_skb_dst_mtu(skb); + + if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { + xfrm6_local_rxpmtu(skb, mtu); + return -EMSGSIZE; + } else if (!skb->local_df && skb->len > mtu && skb->sk) { + xfrm6_local_error(skb, mtu); + return -EMSGSIZE; + } if ((x && x->props.mode == XFRM_MODE_TUNNEL) && - ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index d879f7e..8ea65e0 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -132,8 +132,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; - ipv6_addr_copy(&fl6->daddr, reverse ? &hdr->saddr : &hdr->daddr); - ipv6_addr_copy(&fl6->saddr, reverse ? &hdr->daddr : &hdr->saddr); + fl6->daddr = reverse ? hdr->saddr : hdr->daddr; + fl6->saddr = reverse ? hdr->daddr : hdr->saddr; while (nh + offset + 1 < skb->data || pskb_may_pull(skb, nh + offset + 1 - skb->data)) { diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 248f0b2..3f2f7c4 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -15,6 +15,7 @@ #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/netfilter_ipv6.h> +#include <linux/export.h> #include <net/dsfield.h> #include <net/ipv6.h> #include <net/addrconf.h> @@ -26,8 +27,8 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl6->daddr); - ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl6->saddr); + *(struct in6_addr *)&sel->daddr = fl6->daddr; + *(struct in6_addr *)&sel->saddr = fl6->saddr; sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl6->uli); |