X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv6%2Faddrconf.c;h=30184e0dd74c82146970b63e27c413748a85f9d7;hb=0388b0042624714e6f8db8cc7994101a0a02d392;hp=c0720e4659bcc91dfa29d06245383a407ed0d5eb;hpb=b24b8a247ff65c01b252025926fe564209fae4fc;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c0720e4..30184e0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6,8 +6,6 @@ * Pedro Roque * Alexey Kuznetsov * - * $Id: addrconf.c,v 1.69 2001/10/31 21:55:54 davem Exp $ - * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -101,8 +99,16 @@ #define TIME_DELTA(a,b) ((unsigned long)((long)(a) - (long)(b))) #ifdef CONFIG_SYSCTL -static void addrconf_sysctl_register(struct inet6_dev *idev, struct ipv6_devconf *p); -static void addrconf_sysctl_unregister(struct ipv6_devconf *p); +static void addrconf_sysctl_register(struct inet6_dev *idev); +static void addrconf_sysctl_unregister(struct inet6_dev *idev); +#else +static inline void addrconf_sysctl_register(struct inet6_dev *idev) +{ +} + +static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) +{ +} #endif #ifdef CONFIG_IPV6_PRIVACY @@ -113,6 +119,7 @@ static void ipv6_regen_rndid(unsigned long data); static int desync_factor = MAX_DESYNC_FACTOR * HZ; #endif +static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); /* @@ -141,7 +148,8 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo); -static int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *dev); +static int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); @@ -176,6 +184,8 @@ struct ipv6_devconf ipv6_devconf __read_mostly = { #endif .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ + .disable_ipv6 = 0, + .accept_dad = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -208,16 +218,26 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { #endif .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ + .disable_ipv6 = 0, + .accept_dad = 1, }; /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; /* Check if a valid qdisc is available */ -static inline int addrconf_qdisc_ok(struct net_device *dev) +static inline bool addrconf_qdisc_ok(const struct net_device *dev) { - return (dev->qdisc != &noop_qdisc); + return !qdisc_tx_is_noop(dev); +} + +/* Check if a route is valid prefix route */ +static inline int addrconf_is_prefix_route(const struct rt6_info *rt) +{ + return ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0); } static void addrconf_del_timer(struct inet6_ifaddr *ifp) @@ -256,16 +276,13 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp, static int snmp6_alloc_dev(struct inet6_dev *idev) { if (snmp_mib_init((void **)idev->stats.ipv6, - sizeof(struct ipstats_mib), - __alignof__(struct ipstats_mib)) < 0) + sizeof(struct ipstats_mib)) < 0) goto err_ip; if (snmp_mib_init((void **)idev->stats.icmpv6, - sizeof(struct icmpv6_mib), - __alignof__(struct icmpv6_mib)) < 0) + sizeof(struct icmpv6_mib)) < 0) goto err_icmp; if (snmp_mib_init((void **)idev->stats.icmpv6msg, - sizeof(struct icmpv6msg_mib), - __alignof__(struct icmpv6msg_mib)) < 0) + sizeof(struct icmpv6msg_mib)) < 0) goto err_icmpmsg; return 0; @@ -315,7 +332,6 @@ EXPORT_SYMBOL(in6_dev_finish_destroy); static struct inet6_dev * ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; - struct in6_addr maddr; ASSERT_RTNL(); @@ -329,7 +345,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) rwlock_init(&ndev->lock); ndev->dev = dev; - memcpy(&ndev->cnf, &ipv6_devconf_dflt, sizeof(ndev->cnf)); + memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); @@ -337,13 +353,15 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) kfree(ndev); return NULL; } + if (ndev->cnf.forwarding) + dev_disable_lro(dev); /* We refer to the device */ dev_hold(dev); if (snmp6_alloc_dev(ndev) < 0) { ADBG((KERN_WARNING "%s(): cannot allocate memory for statistics; dev=%s.\n", - __FUNCTION__, dev->name)); + __func__, dev->name)); neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; in6_dev_finish_destroy(ndev); @@ -353,7 +371,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) if (snmp6_register_dev(ndev) < 0) { ADBG((KERN_WARNING "%s(): cannot create /proc/net/dev_snmp6/%s\n", - __FUNCTION__, dev->name)); + __func__, dev->name)); neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; in6_dev_finish_destroy(ndev); @@ -365,13 +383,24 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) */ in6_dev_hold(ndev); + if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) + ndev->cnf.accept_dad = -1; + +#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) + if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { + printk(KERN_INFO + "%s: Disabled Multicast RS\n", + dev->name); + ndev->cnf.rtr_solicits = 0; + } +#endif + #ifdef CONFIG_IPV6_PRIVACY setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev); if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || -#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) + dev->type == ARPHRD_TUNNEL6 || dev->type == ARPHRD_SIT || -#endif dev->type == ARPHRD_NONE) { printk(KERN_INFO "%s: Disabled Privacy Extensions\n", @@ -388,19 +417,12 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; -#ifdef CONFIG_SYSCTL - neigh_sysctl_register(dev, ndev->nd_parms, NET_IPV6, - NET_IPV6_NEIGH, "ipv6", - &ndisc_ifinfo_sysctl_change, - NULL); - addrconf_sysctl_register(ndev, &ndev->cnf); -#endif + addrconf_sysctl_register(ndev); /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); /* Join all-node multicast group */ - ipv6_addr_all_nodes(&maddr); - ipv6_dev_mc_inc(dev, &maddr); + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); return ndev; } @@ -426,18 +448,17 @@ static void dev_forward_change(struct inet6_dev *idev) { struct net_device *dev; struct inet6_ifaddr *ifa; - struct in6_addr addr; if (!idev) return; dev = idev->dev; + if (idev->cnf.forwarding) + dev_disable_lro(dev); if (dev && (dev->flags & IFF_MULTICAST)) { - ipv6_addr_all_routers(&addr); - if (idev->cnf.forwarding) - ipv6_dev_mc_inc(dev, &addr); + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); else - ipv6_dev_mc_dec(dev, &addr); + ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); } for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) { if (ifa->flags&IFA_F_TENTATIVE) @@ -450,18 +471,18 @@ static void dev_forward_change(struct inet6_dev *idev) } -static void addrconf_forward_change(void) +static void addrconf_forward_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) { + for_each_netdev(net, dev) { rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - int changed = (!idev->cnf.forwarding) ^ (!ipv6_devconf.forwarding); - idev->cnf.forwarding = ipv6_devconf.forwarding; + int changed = (!idev->cnf.forwarding) ^ (!newf); + idev->cnf.forwarding = newf; if (changed) dev_forward_change(idev); } @@ -469,6 +490,27 @@ static void addrconf_forward_change(void) } read_unlock(&dev_base_lock); } + +static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) +{ + struct net *net; + + net = (struct net *)table->extra2; + if (p == &net->ipv6.devconf_dflt->forwarding) + return; + + rtnl_lock(); + if (p == &net->ipv6.devconf_all->forwarding) { + __s32 newf = net->ipv6.devconf_all->forwarding; + net->ipv6.devconf_dflt->forwarding = newf; + addrconf_forward_change(net, newf); + } else if ((!*p) ^ (!old)) + dev_forward_change((struct inet6_dev *)table->extra1); + rtnl_unlock(); + + if (*p) + rt6_purge_dflt_routers(net); +} #endif /* Nobody refers to this ifaddr, destroy it */ @@ -515,6 +557,25 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) *ifap = ifp; } +/* + * Hash function taken from net_alias.c + */ +static u8 ipv6_addr_hash(const struct in6_addr *addr) +{ + __u32 word; + + /* + * We perform the hash function over the last 64 bits of the address + * This will include the IEEE address token on links that support it. + */ + + word = (__force u32)(addr->s6_addr32[2] ^ addr->s6_addr32[3]); + word ^= (word >> 16); + word ^= (word >> 8); + + return ((word ^ (word >> 4)) & 0x0f); +} + /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * @@ -525,6 +586,13 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, struct rt6_info *rt; int hash; int err = 0; + int addr_type = ipv6_addr_type(addr); + + if (addr_type == IPV6_ADDR_ANY || + addr_type & IPV6_ADDR_MULTICAST || + (!(idev->dev->flags & IFF_LOOPBACK) && + addr_type & IPV6_ADDR_LOOPBACK)) + return ERR_PTR(-EADDRNOTAVAIL); rcu_read_lock_bh(); if (idev->dead) { @@ -535,7 +603,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, write_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(addr, idev->dev)) { + if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { ADBG(("ipv6_add_addr: already assigned\n")); err = -EEXIST; goto out; @@ -688,8 +756,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) onlink = -1; spin_lock(&ifa->lock); - lifetime = min_t(unsigned long, - ifa->valid_lft, 0x7fffffffUL/HZ); + + lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); + /* + * Note: Because this address is + * not permanent, lifetime < + * LONG_MAX / HZ here. + */ if (time_before(expires, ifa->tstamp + lifetime * HZ)) expires = ifa->tstamp + lifetime * HZ; @@ -701,12 +774,12 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } write_unlock_bh(&idev->lock); + addrconf_del_timer(ifp); + ipv6_ifa_notify(RTM_DELADDR, ifp); atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp); - addrconf_del_timer(ifp); - /* * Purge or update corresponding prefix * @@ -725,11 +798,11 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) { struct in6_addr prefix; struct rt6_info *rt; - + struct net *net = dev_net(ifp->idev->dev); ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); - rt = rt6_lookup(&prefix, NULL, ifp->idev->dev->ifindex, 1); + rt = rt6_lookup(net, &prefix, NULL, ifp->idev->dev->ifindex, 1); - if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { + if (rt && addrconf_is_prefix_route(rt)) { if (onlink == 0) { ip6_del_rt(rt); rt = NULL; @@ -750,6 +823,7 @@ 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; + unsigned long regen_advance; int tmp_plen; int ret = 0; int max_addresses; @@ -810,8 +884,23 @@ retry: tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); + regen_advance = idev->cnf.regen_max_retry * + idev->cnf.dad_transmits * + idev->nd_parms->retrans_time / HZ; write_unlock(&idev->lock); + /* A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In particular, + * an implementation must not create a temporary address with a zero + * Preferred Lifetime. + */ + if (tmp_prefered_lft <= regen_advance) { + in6_ifa_put(ifp); + in6_dev_put(idev); + ret = -1; + goto out; + } + addr_flags = IFA_F_TEMPORARY; /* set in addrconf_prefix_rcv() */ if (ifp->flags & IFA_F_OPTIMISTIC) @@ -851,20 +940,40 @@ out: /* * Choose an appropriate source address (RFC3484) */ +enum { + IPV6_SADDR_RULE_INIT = 0, + IPV6_SADDR_RULE_LOCAL, + IPV6_SADDR_RULE_SCOPE, + IPV6_SADDR_RULE_PREFERRED, +#ifdef CONFIG_IPV6_MIP6 + IPV6_SADDR_RULE_HOA, +#endif + IPV6_SADDR_RULE_OIF, + IPV6_SADDR_RULE_LABEL, +#ifdef CONFIG_IPV6_PRIVACY + IPV6_SADDR_RULE_PRIVACY, +#endif + IPV6_SADDR_RULE_ORCHID, + IPV6_SADDR_RULE_PREFIX, + IPV6_SADDR_RULE_MAX +}; + struct ipv6_saddr_score { - int addr_type; - unsigned int attrs; - int matchlen; - int scope; - unsigned int rule; + int rule; + int addr_type; + struct inet6_ifaddr *ifa; + DECLARE_BITMAP(scorebits, IPV6_SADDR_RULE_MAX); + int scopedist; + int matchlen; }; -#define IPV6_SADDR_SCORE_LOCAL 0x0001 -#define IPV6_SADDR_SCORE_PREFERRED 0x0004 -#define IPV6_SADDR_SCORE_HOA 0x0008 -#define IPV6_SADDR_SCORE_OIF 0x0010 -#define IPV6_SADDR_SCORE_LABEL 0x0020 -#define IPV6_SADDR_SCORE_PRIVACY 0x0040 +struct ipv6_saddr_dst { + const struct in6_addr *addr; + int ifindex; + int scope; + int label; + unsigned int prefs; +}; static inline int ipv6_saddr_preferred(int type) { @@ -874,55 +983,154 @@ static inline int ipv6_saddr_preferred(int type) return 0; } -/* static matching label */ -static inline int ipv6_saddr_label(const struct in6_addr *addr, int type) -{ - /* - * prefix (longest match) label - * ----------------------------- - * ::1/128 0 - * ::/0 1 - * 2002::/16 2 - * ::/96 3 - * ::ffff:0:0/96 4 - * fc00::/7 5 - * 2001::/32 6 - */ - if (type & IPV6_ADDR_LOOPBACK) - return 0; - else if (type & IPV6_ADDR_COMPATv4) - return 3; - else if (type & IPV6_ADDR_MAPPED) - return 4; - else if (addr->s6_addr32[0] == htonl(0x20010000)) - return 6; - else if (addr->s6_addr16[0] == htons(0x2002)) - return 2; - else if ((addr->s6_addr[0] & 0xfe) == 0xfc) - return 5; - return 1; +static int ipv6_get_saddr_eval(struct net *net, + struct ipv6_saddr_score *score, + struct ipv6_saddr_dst *dst, + int i) +{ + int ret; + + if (i <= score->rule) { + switch (i) { + case IPV6_SADDR_RULE_SCOPE: + ret = score->scopedist; + break; + case IPV6_SADDR_RULE_PREFIX: + ret = score->matchlen; + break; + default: + ret = !!test_bit(i, score->scorebits); + } + goto out; + } + + switch (i) { + case IPV6_SADDR_RULE_INIT: + /* Rule 0: remember if hiscore is not ready yet */ + ret = !!score->ifa; + break; + case IPV6_SADDR_RULE_LOCAL: + /* Rule 1: Prefer same address */ + ret = ipv6_addr_equal(&score->ifa->addr, dst->addr); + break; + case IPV6_SADDR_RULE_SCOPE: + /* Rule 2: Prefer appropriate scope + * + * ret + * ^ + * -1 | d 15 + * ---+--+-+---> scope + * | + * | d is scope of the destination. + * B-d | \ + * | \ <- smaller scope is better if + * B-15 | \ if scope is enough for destinaion. + * | ret = B - scope (-1 <= scope >= d <= 15). + * d-C-1 | / + * |/ <- greater is better + * -C / if scope is not enough for destination. + * /| ret = scope - C (-1 <= d < scope <= 15). + * + * d - C - 1 < B -15 (for all -1 <= d <= 15). + * C > d + 14 - B >= 15 + 14 - B = 29 - B. + * Assume B = 0 and we get C > 29. + */ + ret = __ipv6_addr_src_scope(score->addr_type); + if (ret >= dst->scope) + ret = -ret; + else + ret -= 128; /* 30 is enough */ + score->scopedist = ret; + break; + case IPV6_SADDR_RULE_PREFERRED: + /* Rule 3: Avoid deprecated and optimistic addresses */ + ret = ipv6_saddr_preferred(score->addr_type) || + !(score->ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)); + break; +#ifdef CONFIG_IPV6_MIP6 + case IPV6_SADDR_RULE_HOA: + { + /* Rule 4: Prefer home address */ + int prefhome = !(dst->prefs & IPV6_PREFER_SRC_COA); + ret = !(score->ifa->flags & IFA_F_HOMEADDRESS) ^ prefhome; + break; + } +#endif + case IPV6_SADDR_RULE_OIF: + /* Rule 5: Prefer outgoing interface */ + ret = (!dst->ifindex || + dst->ifindex == score->ifa->idev->dev->ifindex); + break; + case IPV6_SADDR_RULE_LABEL: + /* Rule 6: Prefer matching label */ + ret = ipv6_addr_label(net, + &score->ifa->addr, score->addr_type, + score->ifa->idev->dev->ifindex) == dst->label; + break; +#ifdef CONFIG_IPV6_PRIVACY + case IPV6_SADDR_RULE_PRIVACY: + { + /* Rule 7: Prefer public address + * Note: prefer temprary address if use_tempaddr >= 2 + */ + int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? + !!(dst->prefs & IPV6_PREFER_SRC_TMP) : + score->ifa->idev->cnf.use_tempaddr >= 2; + ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; + break; + } +#endif + case IPV6_SADDR_RULE_ORCHID: + /* Rule 8-: Prefer ORCHID vs ORCHID or + * non-ORCHID vs non-ORCHID + */ + ret = !(ipv6_addr_orchid(&score->ifa->addr) ^ + ipv6_addr_orchid(dst->addr)); + break; + case IPV6_SADDR_RULE_PREFIX: + /* Rule 8: Use longest matching prefix */ + score->matchlen = ret = ipv6_addr_diff(&score->ifa->addr, + dst->addr); + break; + default: + ret = 0; + } + + if (ret) + __set_bit(i, score->scorebits); + score->rule = i; +out: + return ret; } -int ipv6_dev_get_saddr(struct net_device *daddr_dev, - struct in6_addr *daddr, struct in6_addr *saddr) +int ipv6_dev_get_saddr(struct net_device *dst_dev, + const struct in6_addr *daddr, unsigned int prefs, + struct in6_addr *saddr) { - struct ipv6_saddr_score hiscore; - struct inet6_ifaddr *ifa_result = NULL; - int daddr_type = __ipv6_addr_type(daddr); - int daddr_scope = __ipv6_addr_src_scope(daddr_type); - u32 daddr_label = ipv6_saddr_label(daddr, daddr_type); + struct ipv6_saddr_score scores[2], + *score = &scores[0], *hiscore = &scores[1]; + struct net *net = dev_net(dst_dev); + struct ipv6_saddr_dst dst; struct net_device *dev; + int dst_type; + + dst_type = __ipv6_addr_type(daddr); + dst.addr = daddr; + dst.ifindex = dst_dev ? dst_dev->ifindex : 0; + dst.scope = __ipv6_addr_src_scope(dst_type); + dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex); + dst.prefs = prefs; - memset(&hiscore, 0, sizeof(hiscore)); + hiscore->rule = -1; + hiscore->ifa = NULL; read_lock(&dev_base_lock); rcu_read_lock(); - for_each_netdev(&init_net, dev) { + for_each_netdev(net, dev) { struct inet6_dev *idev; - struct inet6_ifaddr *ifa; - /* Rule 0: Candidate Source Address (section 4) + /* Candidate Source Address (section 4) * - multicast and link-local destination address, * the set of candidate source address MUST only * include addresses assigned to interfaces @@ -934,9 +1142,9 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, * belonging to the same site as the outgoing * interface.) */ - if ((daddr_type & IPV6_ADDR_MULTICAST || - daddr_scope <= IPV6_ADDR_SCOPE_LINKLOCAL) && - daddr_dev && dev != daddr_dev) + if (((dst_type & IPV6_ADDR_MULTICAST) || + dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) && + dst.ifindex && dev->ifindex != dst.ifindex) continue; idev = __in6_dev_get(dev); @@ -944,12 +1152,10 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, continue; read_lock_bh(&idev->lock); - for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) { - struct ipv6_saddr_score score; - - score.addr_type = __ipv6_addr_type(&ifa->addr); + for (score->ifa = idev->addr_list; score->ifa; score->ifa = score->ifa->if_next) { + int i; - /* Rule 0: + /* * - Tentative Address (RFC2462 section 5.4) * - A tentative address is not considered * "assigned to an interface" in the traditional @@ -959,11 +1165,14 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, * addresses, and the unspecified address MUST * NOT be included in a candidate set. */ - if ((ifa->flags & IFA_F_TENTATIVE) && - (!(ifa->flags & IFA_F_OPTIMISTIC))) + if ((score->ifa->flags & IFA_F_TENTATIVE) && + (!(score->ifa->flags & IFA_F_OPTIMISTIC))) continue; - if (unlikely(score.addr_type == IPV6_ADDR_ANY || - score.addr_type & IPV6_ADDR_MULTICAST)) { + + score->addr_type = __ipv6_addr_type(&score->ifa->addr); + + if (unlikely(score->addr_type == IPV6_ADDR_ANY || + score->addr_type & IPV6_ADDR_MULTICAST)) { LIMIT_NETDEBUG(KERN_DEBUG "ADDRCONF: unspecified / multicast address " "assigned as unicast address on %s", @@ -971,203 +1180,63 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, continue; } - score.attrs = 0; - score.matchlen = 0; - score.scope = 0; - score.rule = 0; - - if (ifa_result == NULL) { - /* record it if the first available entry */ - goto record_it; - } - - /* Rule 1: Prefer same address */ - if (hiscore.rule < 1) { - if (ipv6_addr_equal(&ifa_result->addr, daddr)) - hiscore.attrs |= IPV6_SADDR_SCORE_LOCAL; - hiscore.rule++; - } - if (ipv6_addr_equal(&ifa->addr, daddr)) { - score.attrs |= IPV6_SADDR_SCORE_LOCAL; - if (!(hiscore.attrs & IPV6_SADDR_SCORE_LOCAL)) { - score.rule = 1; - goto record_it; - } - } else { - if (hiscore.attrs & IPV6_SADDR_SCORE_LOCAL) - continue; - } - - /* Rule 2: Prefer appropriate scope */ - if (hiscore.rule < 2) { - hiscore.scope = __ipv6_addr_src_scope(hiscore.addr_type); - hiscore.rule++; - } - score.scope = __ipv6_addr_src_scope(score.addr_type); - if (hiscore.scope < score.scope) { - if (hiscore.scope < daddr_scope) { - score.rule = 2; - goto record_it; - } else - continue; - } else if (score.scope < hiscore.scope) { - if (score.scope < daddr_scope) - break; /* addresses sorted by scope */ - else { - score.rule = 2; - goto record_it; - } - } + score->rule = -1; + bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); + + for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { + int minihiscore, miniscore; + + minihiscore = ipv6_get_saddr_eval(net, hiscore, &dst, i); + miniscore = ipv6_get_saddr_eval(net, score, &dst, i); + + if (minihiscore > miniscore) { + if (i == IPV6_SADDR_RULE_SCOPE && + score->scopedist > 0) { + /* + * special case: + * each remaining entry + * has too small (not enough) + * scope, because ifa entries + * are sorted by their scope + * values. + */ + goto try_nextdev; + } + break; + } else if (minihiscore < miniscore) { + struct ipv6_saddr_score *tmp; - /* Rule 3: Avoid deprecated and optimistic addresses */ - if (hiscore.rule < 3) { - if (ipv6_saddr_preferred(hiscore.addr_type) || - (((ifa_result->flags & - (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) - hiscore.attrs |= IPV6_SADDR_SCORE_PREFERRED; - hiscore.rule++; - } - if (ipv6_saddr_preferred(score.addr_type) || - (((ifa->flags & - (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) { - score.attrs |= IPV6_SADDR_SCORE_PREFERRED; - if (!(hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)) { - score.rule = 3; - goto record_it; - } - } else { - if (hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED) - continue; - } + if (hiscore->ifa) + in6_ifa_put(hiscore->ifa); - /* Rule 4: Prefer home address */ -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - if (hiscore.rule < 4) { - if (ifa_result->flags & IFA_F_HOMEADDRESS) - hiscore.attrs |= IPV6_SADDR_SCORE_HOA; - hiscore.rule++; - } - if (ifa->flags & IFA_F_HOMEADDRESS) { - score.attrs |= IPV6_SADDR_SCORE_HOA; - if (!(ifa_result->flags & IFA_F_HOMEADDRESS)) { - score.rule = 4; - goto record_it; - } - } else { - if (hiscore.attrs & IPV6_SADDR_SCORE_HOA) - continue; - } -#else - if (hiscore.rule < 4) - hiscore.rule++; -#endif + in6_ifa_hold(score->ifa); - /* Rule 5: Prefer outgoing interface */ - if (hiscore.rule < 5) { - if (daddr_dev == NULL || - daddr_dev == ifa_result->idev->dev) - hiscore.attrs |= IPV6_SADDR_SCORE_OIF; - hiscore.rule++; - } - if (daddr_dev == NULL || - daddr_dev == ifa->idev->dev) { - score.attrs |= IPV6_SADDR_SCORE_OIF; - if (!(hiscore.attrs & IPV6_SADDR_SCORE_OIF)) { - score.rule = 5; - goto record_it; - } - } else { - if (hiscore.attrs & IPV6_SADDR_SCORE_OIF) - continue; - } + tmp = hiscore; + hiscore = score; + score = tmp; - /* Rule 6: Prefer matching label */ - if (hiscore.rule < 6) { - if (ipv6_saddr_label(&ifa_result->addr, hiscore.addr_type) == daddr_label) - hiscore.attrs |= IPV6_SADDR_SCORE_LABEL; - hiscore.rule++; - } - if (ipv6_saddr_label(&ifa->addr, score.addr_type) == daddr_label) { - score.attrs |= IPV6_SADDR_SCORE_LABEL; - if (!(hiscore.attrs & IPV6_SADDR_SCORE_LABEL)) { - score.rule = 6; - goto record_it; - } - } else { - if (hiscore.attrs & IPV6_SADDR_SCORE_LABEL) - continue; - } + /* restore our iterator */ + score->ifa = hiscore->ifa; -#ifdef CONFIG_IPV6_PRIVACY - /* Rule 7: Prefer public address - * Note: prefer temprary address if use_tempaddr >= 2 - */ - if (hiscore.rule < 7) { - if ((!(ifa_result->flags & IFA_F_TEMPORARY)) ^ - (ifa_result->idev->cnf.use_tempaddr >= 2)) - hiscore.attrs |= IPV6_SADDR_SCORE_PRIVACY; - hiscore.rule++; - } - if ((!(ifa->flags & IFA_F_TEMPORARY)) ^ - (ifa->idev->cnf.use_tempaddr >= 2)) { - score.attrs |= IPV6_SADDR_SCORE_PRIVACY; - if (!(hiscore.attrs & IPV6_SADDR_SCORE_PRIVACY)) { - score.rule = 7; - goto record_it; + break; } - } else { - if (hiscore.attrs & IPV6_SADDR_SCORE_PRIVACY) - continue; } -#else - if (hiscore.rule < 7) - hiscore.rule++; -#endif - /* Rule 8: Use longest matching prefix */ - if (hiscore.rule < 8) { - hiscore.matchlen = ipv6_addr_diff(&ifa_result->addr, daddr); - hiscore.rule++; - } - score.matchlen = ipv6_addr_diff(&ifa->addr, daddr); - if (score.matchlen > hiscore.matchlen) { - score.rule = 8; - goto record_it; - } -#if 0 - else if (score.matchlen < hiscore.matchlen) - continue; -#endif - - /* Final Rule: choose first available one */ - continue; -record_it: - if (ifa_result) - in6_ifa_put(ifa_result); - in6_ifa_hold(ifa); - ifa_result = ifa; - hiscore = score; } +try_nextdev: read_unlock_bh(&idev->lock); } rcu_read_unlock(); read_unlock(&dev_base_lock); - if (!ifa_result) + if (!hiscore->ifa) return -EADDRNOTAVAIL; - ipv6_addr_copy(saddr, &ifa_result->addr); - in6_ifa_put(ifa_result); + ipv6_addr_copy(saddr, &hiscore->ifa->addr); + in6_ifa_put(hiscore->ifa); return 0; } - -int ipv6_get_saddr(struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) -{ - return ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, daddr, saddr); -} - -EXPORT_SYMBOL(ipv6_get_saddr); +EXPORT_SYMBOL(ipv6_dev_get_saddr); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, unsigned char banned_flags) @@ -1205,13 +1274,16 @@ static int ipv6_count_addresses(struct inet6_dev *idev) return cnt; } -int ipv6_chk_addr(struct in6_addr *addr, struct net_device *dev, int strict) +int ipv6_chk_addr(struct net *net, struct in6_addr *addr, + struct net_device *dev, int strict) { struct inet6_ifaddr * ifp; u8 hash = ipv6_addr_hash(addr); read_lock_bh(&addrconf_hash_lock); for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp->flags&IFA_F_TENTATIVE)) { if (dev == NULL || ifp->idev->dev == dev || @@ -1222,16 +1294,18 @@ int ipv6_chk_addr(struct in6_addr *addr, struct net_device *dev, int strict) read_unlock_bh(&addrconf_hash_lock); return ifp != NULL; } - EXPORT_SYMBOL(ipv6_chk_addr); static -int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *dev) +int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev) { struct inet6_ifaddr * ifp; u8 hash = ipv6_addr_hash(addr); for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; if (ipv6_addr_equal(&ifp->addr, addr)) { if (dev == NULL || ifp->idev->dev == dev) break; @@ -1240,13 +1314,41 @@ int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *dev) return ifp != NULL; } -struct inet6_ifaddr * ipv6_get_ifaddr(struct in6_addr *addr, struct net_device *dev, int strict) +int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + int onlink; + + onlink = 0; + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) { + onlink = ipv6_prefix_equal(addr, &ifa->addr, + ifa->prefix_len); + if (onlink) + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + return onlink; +} + +EXPORT_SYMBOL(ipv6_chk_prefix); + +struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, + struct net_device *dev, int strict) { struct inet6_ifaddr * ifp; u8 hash = ipv6_addr_hash(addr); read_lock_bh(&addrconf_hash_lock); for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; if (ipv6_addr_equal(&ifp->addr, addr)) { if (dev == NULL || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { @@ -1325,6 +1427,20 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct inet6_ifaddr *ifp) { + struct inet6_dev *idev = ifp->idev; + if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { + struct in6_addr addr; + + addr.s6_addr32[0] = htonl(0xfe800000); + addr.s6_addr32[1] = 0; + + if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && + ipv6_addr_equal(&ifp->addr, &addr)) { + /* DAD failed for link-local based on MAC address */ + idev->cnf.disable_ipv6 = 1; + } + } + if (net_ratelimit()) printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name); addrconf_dad_stop(ifp); @@ -1422,6 +1538,29 @@ static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) return 0; } +int __ipv6_isatap_ifid(u8 *eui, __be32 addr) +{ + eui[0] = (ipv4_is_zeronet(addr) || ipv4_is_private_10(addr) || + ipv4_is_loopback(addr) || ipv4_is_linklocal_169(addr) || + ipv4_is_private_172(addr) || ipv4_is_test_192(addr) || + ipv4_is_anycast_6to4(addr) || ipv4_is_private_192(addr) || + ipv4_is_test_198(addr) || ipv4_is_multicast(addr) || + ipv4_is_lbcast(addr)) ? 0x00 : 0x02; + eui[1] = 0; + eui[2] = 0x5E; + eui[3] = 0xFE; + memcpy(eui + 4, &addr, 4); + return 0; +} +EXPORT_SYMBOL(__ipv6_isatap_ifid); + +static int addrconf_ifid_sit(u8 *eui, struct net_device *dev) +{ + if (dev->priv_flags & IFF_ISATAP) + return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); + return -1; +} + static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { @@ -1433,6 +1572,8 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_arcnet(eui, dev); case ARPHRD_INFINIBAND: return addrconf_ifid_infiniband(eui, dev); + case ARPHRD_SIT: + return addrconf_ifid_sit(eui, dev); } return -1; } @@ -1468,7 +1609,7 @@ regen: * * - Reserved subnet anycast (RFC 2526) * 11111101 11....11 1xxxxxxx - * - ISATAP (draft-ietf-ngtrans-isatap-13.txt) 5.1 + * - ISATAP (RFC4214) 6.1 * 00-00-5E-FE-xx-xx-xx-xx * - value 0 * - XXX: already assigned to an address on the device @@ -1544,6 +1685,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, .fc_expires = expires, .fc_dst_len = plen, .fc_flags = RTF_UP | flags, + .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_copy(&cfg.fc_dst, pfx); @@ -1570,6 +1712,7 @@ static void addrconf_add_mroute(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, + .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); @@ -1586,6 +1729,7 @@ static void sit_route_add(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 96, .fc_flags = RTF_UP | RTF_NONEXTHOP, + .fc_nlinfo.nl_net = dev_net(dev), }; /* prefix length - 96 bits "::d.d.d.d" */ @@ -1624,7 +1768,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) __u32 valid_lft; __u32 prefered_lft; int addr_type; - unsigned long rt_expires; struct inet6_dev *in6_dev; pinfo = (struct prefix_info *) opt; @@ -1666,40 +1809,49 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) * 2) Configure prefixes with the auto flag set */ - /* Avoid arithmetic overflow. Really, we could - save rt_expires in seconds, likely valid_lft, - but it would require division in fib gc, that it - not good. - */ - if (valid_lft >= 0x7FFFFFFF/HZ) - rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ); - else - rt_expires = valid_lft * HZ; - - /* - * We convert this (in jiffies) to clock_t later. - * Avoid arithmetic overflow there as well. - * Overflow can happen only if HZ < USER_HZ. - */ - if (HZ < USER_HZ && rt_expires > 0x7FFFFFFF / USER_HZ) - rt_expires = 0x7FFFFFFF / USER_HZ; - if (pinfo->onlink) { struct rt6_info *rt; - rt = rt6_lookup(&pinfo->prefix, NULL, dev->ifindex, 1); + unsigned long rt_expires; - if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { - if (rt->rt6i_flags&RTF_EXPIRES) { - if (valid_lft == 0) { - ip6_del_rt(rt); - rt = NULL; - } else { - rt->rt6i_expires = jiffies + rt_expires; - } + /* Avoid arithmetic overflow. Really, we could + * save rt_expires in seconds, likely valid_lft, + * but it would require division in fib gc, that it + * not good. + */ + if (HZ > USER_HZ) + rt_expires = addrconf_timeout_fixup(valid_lft, HZ); + else + rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); + + if (addrconf_finite_timeout(rt_expires)) + rt_expires *= HZ; + + rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, + dev->ifindex, 1); + + if (rt && addrconf_is_prefix_route(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->rt6i_flags |= RTF_EXPIRES; + } else { + rt->rt6i_flags &= ~RTF_EXPIRES; + rt->rt6i_expires = 0; } } else if (valid_lft) { + clock_t expires = 0; + int flags = RTF_ADDRCONF | RTF_PREFIX_RT; + if (addrconf_finite_timeout(rt_expires)) { + /* not infinity */ + flags |= RTF_EXPIRES; + expires = jiffies_to_clock_t(rt_expires); + } addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, - dev, jiffies_to_clock_t(rt_expires), RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT); + dev, expires, flags); } if (rt) dst_release(&rt->u.dst); @@ -1729,7 +1881,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) ok: - ifp = ipv6_get_ifaddr(&addr, dev, 1); + ifp = ipv6_get_ifaddr(dev_net(dev), &addr, dev, 1); if (ifp == NULL && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; @@ -1815,6 +1967,9 @@ ok: * lifetimes of an existing temporary address * when processing a Prefix Information Option. */ + if (ifp != ift->ifpub) + continue; + spin_lock(&ift->lock); flags = ift->flags; if (ift->valid_lft > valid_lft && @@ -1852,7 +2007,7 @@ ok: * Special case for SIT interfaces where we create a new "virtual" * device. */ -int addrconf_set_dstaddr(void __user *arg) +int addrconf_set_dstaddr(struct net *net, void __user *arg) { struct in6_ifreq ireq; struct net_device *dev; @@ -1864,7 +2019,7 @@ int addrconf_set_dstaddr(void __user *arg) if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) goto err_exit; - dev = __dev_get_by_index(&init_net, ireq.ifr6_ifindex); + dev = __dev_get_by_index(net, ireq.ifr6_ifindex); err = -ENODEV; if (dev == NULL) @@ -1887,7 +2042,7 @@ int addrconf_set_dstaddr(void __user *arg) p.iph.ihl = 5; p.iph.protocol = IPPROTO_IPV6; p.iph.ttl = 64; - ifr.ifr_ifru.ifru_data = (void __user *)&p; + ifr.ifr_ifru.ifru_data = (__force void __user *)&p; oldfs = get_fs(); set_fs(KERNEL_DS); err = dev->do_ioctl(dev, &ifr, SIOCADDTUNNEL); @@ -1895,7 +2050,8 @@ int addrconf_set_dstaddr(void __user *arg) if (err == 0) { err = -ENOBUFS; - if ((dev = __dev_get_by_name(&init_net, p.name)) == NULL) + dev = __dev_get_by_name(net, p.name); + if (!dev) goto err_exit; err = dev_open(dev); } @@ -1910,22 +2066,29 @@ err_exit: /* * Manual configuration of address on an interface */ -static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, - __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) +static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, + unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, + __u32 valid_lft) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; int scope; - u32 flags = RTF_EXPIRES; + u32 flags; + clock_t expires; + unsigned long timeout; ASSERT_RTNL(); + if (plen > 128) + return -EINVAL; + /* check the lifetime */ if (!valid_lft || prefered_lft > valid_lft) return -EINVAL; - if ((dev = __dev_get_by_index(&init_net, ifindex)) == NULL) + dev = __dev_get_by_index(net, ifindex); + if (!dev) return -ENODEV; if ((idev = addrconf_add_dev(dev)) == NULL) @@ -1933,17 +2096,23 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, scope = ipv6_addr_scope(pfx); - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; + flags = RTF_EXPIRES; + } else { + expires = 0; flags = 0; - } else if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + ifa_flags |= IFA_F_PERMANENT; + } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); @@ -1955,7 +2124,7 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, spin_unlock_bh(&ifp->lock); addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, - jiffies_to_clock_t(valid_lft * HZ), flags); + expires, flags); /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for @@ -1970,13 +2139,18 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, return PTR_ERR(ifp); } -static int inet6_addr_del(int ifindex, struct in6_addr *pfx, int plen) +static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, + unsigned int plen) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; - if ((dev = __dev_get_by_index(&init_net, ifindex)) == NULL) + if (plen > 128) + return -EINVAL; + + dev = __dev_get_by_index(net, ifindex); + if (!dev) return -ENODEV; if ((idev = __in6_dev_get(dev)) == NULL) @@ -2004,7 +2178,7 @@ static int inet6_addr_del(int ifindex, struct in6_addr *pfx, int plen) } -int addrconf_add_ifaddr(void __user *arg) +int addrconf_add_ifaddr(struct net *net, void __user *arg) { struct in6_ifreq ireq; int err; @@ -2016,13 +2190,14 @@ int addrconf_add_ifaddr(void __user *arg) return -EFAULT; rtnl_lock(); - err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen, - IFA_F_PERMANENT, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, + ireq.ifr6_prefixlen, IFA_F_PERMANENT, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); rtnl_unlock(); return err; } -int addrconf_del_ifaddr(void __user *arg) +int addrconf_del_ifaddr(struct net *net, void __user *arg) { struct in6_ifreq ireq; int err; @@ -2034,7 +2209,8 @@ int addrconf_del_ifaddr(void __user *arg) return -EFAULT; rtnl_lock(); - err = inet6_addr_del(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen); + err = inet6_addr_del(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, + ireq.ifr6_prefixlen); rtnl_unlock(); return err; } @@ -2045,6 +2221,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) struct inet6_ifaddr * ifp; struct in6_addr addr; struct net_device *dev; + struct net *net = dev_net(idev->dev); int scope; ASSERT_RTNL(); @@ -2071,7 +2248,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) return; } - for_each_netdev(&init_net, dev) { + for_each_netdev(net, dev) { struct in_device * in_dev = __in_dev_get_rtnl(dev); if (in_dev && (dev->flags & IFF_UP)) { struct in_ifaddr * ifa; @@ -2199,6 +2376,16 @@ static void addrconf_sit_config(struct net_device *dev) return; } + if (dev->priv_flags & IFF_ISATAP) { + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + addrconf_prefix_route(&addr, 64, dev, 0, 0); + if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) + addrconf_add_linklocal(idev, &addr); + return; + } + sit_add_v4_addrs(idev); if (dev->flags&IFF_POINTOPOINT) { @@ -2224,15 +2411,16 @@ ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) static void ip6_tnl_add_linklocal(struct inet6_dev *idev) { struct net_device *link_dev; + struct net *net = dev_net(idev->dev); /* first try to inherit the link-local address from the link device */ if (idev->dev->iflink && - (link_dev = __dev_get_by_index(&init_net, idev->dev->iflink))) { + (link_dev = __dev_get_by_index(net, idev->dev->iflink))) { if (!ipv6_inherit_linklocal(idev, link_dev)) return; } /* then try to inherit it from any device */ - for_each_netdev(&init_net, link_dev) { + for_each_netdev(net, link_dev) { if (!ipv6_inherit_linklocal(idev, link_dev)) return; } @@ -2265,9 +2453,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, int run_pending = 0; int err; - if (dev->nd_net != &init_net) - return NOTIFY_DONE; - switch(event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { @@ -2383,15 +2568,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGENAME: if (idev) { snmp6_unregister_dev(idev); -#ifdef CONFIG_SYSCTL - addrconf_sysctl_unregister(&idev->cnf); - neigh_sysctl_unregister(idev->nd_parms); - neigh_sysctl_register(dev, idev->nd_parms, - NET_IPV6, NET_IPV6_NEIGH, "ipv6", - &ndisc_ifinfo_sysctl_change, - NULL); - addrconf_sysctl_register(idev, &idev->cnf); -#endif + addrconf_sysctl_unregister(idev); + addrconf_sysctl_register(idev); err = snmp6_register_dev(idev); if (err) return notifier_from_errno(err); @@ -2414,14 +2592,15 @@ static int addrconf_ifdown(struct net_device *dev, int how) { struct inet6_dev *idev; struct inet6_ifaddr *ifa, **bifa; + struct net *net = dev_net(dev); int i; ASSERT_RTNL(); - if (dev == init_net.loopback_dev && how == 1) + if ((dev->flags & IFF_LOOPBACK) && how == 1) how = 0; - rt6_ifdown(dev); + rt6_ifdown(net, dev); neigh_ifdown(&nd_tbl, dev); idev = __in6_dev_get(dev); @@ -2431,7 +2610,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Step 1: remove reference to ipv6 device from parent device. Do not dev_put! */ - if (how == 1) { + if (how) { idev->dead = 1; /* protected by rtnl_lock */ @@ -2463,12 +2642,12 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&idev->lock); /* Step 3: clear flags for stateless addrconf */ - if (how != 1) + if (!how) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); /* Step 4: clear address list */ #ifdef CONFIG_IPV6_PRIVACY - if (how == 1 && del_timer(&idev->regen_timer)) + if (how && del_timer(&idev->regen_timer)) in6_dev_put(idev); /* clear tempaddr list */ @@ -2505,7 +2684,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Step 5: Discard multicast list */ - if (how == 1) + if (how) ipv6_mc_destroy_dev(idev); else ipv6_mc_down(idev); @@ -2514,11 +2693,8 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Shot the device (if unregistered) */ - if (how == 1) { -#ifdef CONFIG_SYSCTL - addrconf_sysctl_unregister(&idev->cnf); - neigh_sysctl_unregister(idev->nd_parms); -#endif + if (how) { + addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); neigh_ifdown(&nd_tbl, dev); in6_dev_put(idev); @@ -2543,8 +2719,6 @@ static void addrconf_rs_timer(unsigned long data) spin_lock(&ifp->lock); if (ifp->probes++ < ifp->idev->cnf.rtr_solicits) { - struct in6_addr all_routers; - /* The wait after the last probe can be shorter */ addrconf_mod_timer(ifp, AC_RS, (ifp->probes == ifp->idev->cnf.rtr_solicits) ? @@ -2552,9 +2726,7 @@ static void addrconf_rs_timer(unsigned long data) ifp->idev->cnf.rtr_solicit_interval); spin_unlock(&ifp->lock); - ipv6_addr_all_routers(&all_routers); - - ndisc_send_rs(ifp->idev->dev, &ifp->addr, &all_routers); + ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters); } else { spin_unlock(&ifp->lock); /* @@ -2601,6 +2773,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) spin_lock_bh(&ifp->lock); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || + idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC); @@ -2641,7 +2814,6 @@ static void addrconf_dad_timer(unsigned long data) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; struct inet6_dev *idev = ifp->idev; - struct in6_addr unspec; struct in6_addr mcaddr; read_lock_bh(&idev->lock); @@ -2649,6 +2821,11 @@ static void addrconf_dad_timer(unsigned long data) read_unlock_bh(&idev->lock); goto out; } + if (idev->cnf.accept_dad > 1 && idev->cnf.disable_ipv6) { + read_unlock_bh(&idev->lock); + addrconf_dad_failure(ifp); + return; + } spin_lock_bh(&ifp->lock); if (ifp->probes == 0) { /* @@ -2670,9 +2847,8 @@ static void addrconf_dad_timer(unsigned long data) read_unlock_bh(&idev->lock); /* send a neighbour solicitation for our addr */ - memset(&unspec, 0, sizeof(unspec)); addrconf_addr_solict_mult(&ifp->addr, &mcaddr); - ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &unspec); + ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any); out: in6_ifa_put(ifp); } @@ -2695,16 +2871,12 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp) ifp->idev->cnf.rtr_solicits > 0 && (dev->flags&IFF_LOOPBACK) == 0 && (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { - struct in6_addr all_routers; - - ipv6_addr_all_routers(&all_routers); - /* * If a host as already performed a random delay * [...] as part of DAD [...] there is no need * to delay again before sending the first RS */ - ndisc_send_rs(ifp->idev->dev, &ifp->addr, &all_routers); + ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters); spin_lock_bh(&ifp->lock); ifp->probes = 1; @@ -2732,6 +2904,7 @@ static void addrconf_dad_run(struct inet6_dev *idev) { #ifdef CONFIG_PROC_FS struct if6_iter_state { + struct seq_net_private p; int bucket; }; @@ -2739,9 +2912,13 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) { struct inet6_ifaddr *ifa = NULL; struct if6_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { ifa = inet6_addr_lst[state->bucket]; + + while (ifa && !net_eq(dev_net(ifa->idev->dev), net)) + ifa = ifa->lst_next; if (ifa) break; } @@ -2751,13 +2928,22 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa) { struct if6_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); ifa = ifa->lst_next; try_again: + if (ifa) { + if (!net_eq(dev_net(ifa->idev->dev), net)) { + ifa = ifa->lst_next; + goto try_again; + } + } + if (!ifa && ++state->bucket < IN6_ADDR_HSIZE) { ifa = inet6_addr_lst[state->bucket]; goto try_again; } + return ifa; } @@ -2772,6 +2958,7 @@ static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(addrconf_hash_lock) { read_lock_bh(&addrconf_hash_lock); return if6_get_idx(seq, *pos); @@ -2787,6 +2974,7 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void if6_seq_stop(struct seq_file *seq, void *v) + __releases(addrconf_hash_lock) { read_unlock_bh(&addrconf_hash_lock); } @@ -2814,8 +3002,8 @@ static const struct seq_operations if6_seq_ops = { static int if6_seq_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &if6_seq_ops, - sizeof(struct if6_iter_state)); + return seq_open_net(inode, file, &if6_seq_ops, + sizeof(struct if6_iter_state)); } static const struct file_operations if6_fops = { @@ -2823,32 +3011,49 @@ static const struct file_operations if6_fops = { .open = if6_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; -int __init if6_proc_init(void) +static int if6_proc_net_init(struct net *net) { - if (!proc_net_fops_create(&init_net, "if_inet6", S_IRUGO, &if6_fops)) + if (!proc_net_fops_create(net, "if_inet6", S_IRUGO, &if6_fops)) return -ENOMEM; return 0; } +static void if6_proc_net_exit(struct net *net) +{ + proc_net_remove(net, "if_inet6"); +} + +static struct pernet_operations if6_proc_net_ops = { + .init = if6_proc_net_init, + .exit = if6_proc_net_exit, +}; + +int __init if6_proc_init(void) +{ + return register_pernet_subsys(&if6_proc_net_ops); +} + void if6_proc_exit(void) { - proc_net_remove(&init_net, "if_inet6"); + unregister_pernet_subsys(&if6_proc_net_ops); } #endif /* CONFIG_PROC_FS */ #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) /* Check if address is a home address configured on any interface. */ -int ipv6_chk_home_addr(struct in6_addr *addr) +int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) { int ret = 0; struct inet6_ifaddr * ifp; u8 hash = ipv6_addr_hash(addr); read_lock_bh(&addrconf_hash_lock); for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) { - if (ipv6_addr_cmp(&ifp->addr, addr) == 0 && + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; + if (ipv6_addr_equal(&ifp->addr, addr) && (ifp->flags & IFA_F_HOMEADDRESS)) { ret = 1; break; @@ -2995,6 +3200,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { static int inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { + struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx; @@ -3009,28 +3215,36 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (pfx == NULL) return -EINVAL; - return inet6_addr_del(ifm->ifa_index, pfx, ifm->ifa_prefixlen); + return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen); } static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, u32 prefered_lft, u32 valid_lft) { - u32 flags = RTF_EXPIRES; + u32 flags; + clock_t expires; + unsigned long timeout; if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; + flags = RTF_EXPIRES; + } else { + expires = 0; flags = 0; - } else if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + ifa_flags |= IFA_F_PERMANENT; + } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } spin_lock_bh(&ifp->lock); ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; @@ -3043,7 +3257,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, ipv6_ifa_notify(0, ifp); addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, - jiffies_to_clock_t(valid_lft * HZ), flags); + expires, flags); addrconf_verify(0); return 0; @@ -3052,6 +3266,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, static int inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { + struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx; @@ -3081,21 +3296,22 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) valid_lft = INFINITY_LIFE_TIME; } - dev = __dev_get_by_index(&init_net, ifm->ifa_index); + dev = __dev_get_by_index(net, ifm->ifa_index); if (dev == NULL) return -ENODEV; /* We ignore other flags so far. */ ifa_flags = ifm->ifa_flags & (IFA_F_NODAD | IFA_F_HOMEADDRESS); - ifa = ipv6_get_ifaddr(pfx, dev, 1); + ifa = ipv6_get_ifaddr(net, pfx, dev, 1); if (ifa == NULL) { /* * It would be best to check for !NLM_F_CREATE here but * userspace alreay relies on not having to provide this. */ - return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen, - ifa_flags, preferred_lft, valid_lft); + return inet6_addr_add(net, ifm->ifa_index, pfx, + ifm->ifa_prefixlen, ifa_flags, + preferred_lft, valid_lft); } if (nlh->nlmsg_flags & NLM_F_EXCL || @@ -3260,12 +3476,13 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, struct inet6_ifaddr *ifa; struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; + struct net *net = sock_net(skb->sk); s_idx = cb->args[0]; s_ip_idx = ip_idx = cb->args[1]; idx = 0; - for_each_netdev(&init_net, dev) { + for_each_netdev(net, dev) { if (idx < s_idx) goto cont; if (idx > s_idx) @@ -3281,11 +3498,11 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, ifa = ifa->if_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - if ((err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWADDR, - NLM_F_MULTI)) <= 0) - goto done; + err = inet6_fill_ifaddr(skb, ifa, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWADDR, + NLM_F_MULTI); } break; case MULTICAST_ADDR: @@ -3294,11 +3511,11 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, ifmca = ifmca->next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - if ((err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_GETMULTICAST, - NLM_F_MULTI)) <= 0) - goto done; + err = inet6_fill_ifmcaddr(skb, ifmca, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_GETMULTICAST, + NLM_F_MULTI); } break; case ANYCAST_ADDR: @@ -3307,11 +3524,11 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, ifaca = ifaca->aca_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - if ((err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_GETANYCAST, - NLM_F_MULTI)) <= 0) - goto done; + err = inet6_fill_ifacaddr(skb, ifaca, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_GETANYCAST, + NLM_F_MULTI); } break; default: @@ -3319,14 +3536,12 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } read_unlock_bh(&idev->lock); in6_dev_put(idev); + + if (err <= 0) + break; cont: idx++; } -done: - if (err <= 0) { - read_unlock_bh(&idev->lock); - in6_dev_put(idev); - } cb->args[0] = idx; cb->args[1] = ip_idx; return skb->len; @@ -3335,12 +3550,14 @@ done: static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = UNICAST_ADDR; + return inet6_dump_addr(skb, cb, type); } static int inet6_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = MULTICAST_ADDR; + return inet6_dump_addr(skb, cb, type); } @@ -3348,12 +3565,14 @@ static int inet6_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = ANYCAST_ADDR; + return inet6_dump_addr(skb, cb, type); } static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { + struct net *net = sock_net(in_skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL; @@ -3374,9 +3593,9 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = __dev_get_by_index(&init_net, ifm->ifa_index); + dev = __dev_get_by_index(net, ifm->ifa_index); - if ((ifa = ipv6_get_ifaddr(addr, dev, 1)) == NULL) { + if ((ifa = ipv6_get_ifaddr(net, addr, dev, 1)) == NULL) { err = -EADDRNOTAVAIL; goto errout; } @@ -3394,7 +3613,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, kfree_skb(skb); goto errout_ifa; } - err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); errout_ifa: in6_ifa_put(ifa); errout: @@ -3404,6 +3623,7 @@ errout: static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; + struct net *net = dev_net(ifa->idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); @@ -3417,10 +3637,10 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); + err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); errout: if (err < 0) - rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, @@ -3462,6 +3682,11 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad; #endif +#ifdef CONFIG_IPV6_MROUTE + array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding; +#endif + array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; + array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; } static inline size_t inet6_if_nlmsg_size(void) @@ -3579,6 +3804,7 @@ nla_put_failure: static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); int idx, err; int s_idx = cb->args[0]; struct net_device *dev; @@ -3586,7 +3812,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) read_lock(&dev_base_lock); idx = 0; - for_each_netdev(&init_net, dev) { + for_each_netdev(net, dev) { if (idx < s_idx) goto cont; if ((idev = in6_dev_get(dev)) == NULL) @@ -3608,6 +3834,7 @@ cont: void inet6_ifinfo_notify(int event, struct inet6_dev *idev) { struct sk_buff *skb; + struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC); @@ -3621,10 +3848,10 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); + err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); errout: if (err < 0) - rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static inline size_t inet6_prefix_nlmsg_size(void) @@ -3677,6 +3904,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; + struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC); @@ -3690,10 +3918,10 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); + err = rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); errout: if (err < 0) - rtnl_set_sk_err(RTNLGRP_IPV6_PREFIX, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@ -3744,22 +3972,8 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp, ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - if (write && valp != &ipv6_devconf_dflt.forwarding) { - if (valp != &ipv6_devconf.forwarding) { - if ((!*valp) ^ (!val)) { - struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1; - if (idev == NULL) - return ret; - dev_forward_change(idev); - } - } else { - ipv6_devconf_dflt.forwarding = ipv6_devconf.forwarding; - addrconf_forward_change(); - } - if (*valp) - rt6_purge_dflt_routers(); - } - + if (write) + addrconf_fixup_forwarding(ctl, valp, val); return ret; } @@ -3770,6 +3984,7 @@ static int addrconf_sysctl_forward_strategy(ctl_table *table, void __user *newval, size_t newlen) { int *valp = table->data; + int val = *valp; int new; if (!newval || !newlen) @@ -3794,37 +4009,16 @@ static int addrconf_sysctl_forward_strategy(ctl_table *table, } } - if (valp != &ipv6_devconf_dflt.forwarding) { - if (valp != &ipv6_devconf.forwarding) { - struct inet6_dev *idev = (struct inet6_dev *)table->extra1; - int changed; - if (unlikely(idev == NULL)) - return -ENODEV; - changed = (!*valp) ^ (!new); - *valp = new; - if (changed) - dev_forward_change(idev); - } else { - *valp = new; - addrconf_forward_change(); - } - - if (*valp) - rt6_purge_dflt_routers(); - } else - *valp = new; - + *valp = new; + addrconf_fixup_forwarding(table, valp, val); return 1; } static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; - ctl_table addrconf_vars[__NET_IPV6_MAX]; - ctl_table addrconf_dev[2]; - ctl_table addrconf_conf_dir[2]; - ctl_table addrconf_proto_dir[2]; - ctl_table addrconf_root_dir[2]; + ctl_table addrconf_vars[DEVCONF_MAX+1]; + char *dev_name; } addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { @@ -4041,49 +4235,31 @@ static struct addrconf_sysctl_table }, #endif +#ifdef CONFIG_IPV6_MROUTE { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_dev = { - { - .ctl_name = NET_PROTO_CONF_ALL, - .procname = "all", - .mode = 0555, - .child = addrconf_sysctl.addrconf_vars, - }, - { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_conf_dir = { - { - .ctl_name = NET_IPV6_CONF, - .procname = "conf", - .mode = 0555, - .child = addrconf_sysctl.addrconf_dev, + .ctl_name = CTL_UNNUMBERED, + .procname = "mc_forwarding", + .data = &ipv6_devconf.mc_forwarding, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, }, +#endif { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_proto_dir = { - { - .ctl_name = NET_IPV6, - .procname = "ipv6", - .mode = 0555, - .child = addrconf_sysctl.addrconf_conf_dir, + .ctl_name = CTL_UNNUMBERED, + .procname = "disable_ipv6", + .data = &ipv6_devconf.disable_ipv6, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, }, { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_root_dir = { - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, - .child = addrconf_sysctl.addrconf_proto_dir, + .ctl_name = CTL_UNNUMBERED, + .procname = "accept_dad", + .data = &ipv6_devconf.accept_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, }, { .ctl_name = 0, /* sentinel */ @@ -4091,26 +4267,31 @@ static struct addrconf_sysctl_table }, }; -static void addrconf_sysctl_register(struct inet6_dev *idev, struct ipv6_devconf *p) +static int __addrconf_sysctl_register(struct net *net, char *dev_name, + int ctl_name, struct inet6_dev *idev, struct ipv6_devconf *p) { int i; - struct net_device *dev = idev ? idev->dev : NULL; struct addrconf_sysctl_table *t; - char *dev_name = NULL; + +#define ADDRCONF_CTL_PATH_DEV 3 + + struct ctl_path addrconf_ctl_path[] = { + { .procname = "net", .ctl_name = CTL_NET, }, + { .procname = "ipv6", .ctl_name = NET_IPV6, }, + { .procname = "conf", .ctl_name = NET_IPV6_CONF, }, + { /* to be set */ }, + { }, + }; + t = kmemdup(&addrconf_sysctl, sizeof(*t), GFP_KERNEL); if (t == NULL) - return; + goto out; + for (i=0; t->addrconf_vars[i].data; i++) { t->addrconf_vars[i].data += (char*)p - (char*)&ipv6_devconf; t->addrconf_vars[i].extra1 = idev; /* embedded; no ref */ - } - if (dev) { - dev_name = dev->name; - t->addrconf_dev[0].ctl_name = dev->ifindex; - } else { - dev_name = "default"; - t->addrconf_dev[0].ctl_name = NET_PROTO_CONF_DEFAULT; + t->addrconf_vars[i].extra2 = net; } /* @@ -4118,47 +4299,126 @@ static void addrconf_sysctl_register(struct inet6_dev *idev, struct ipv6_devconf * by sysctl and we wouldn't want anyone to change it under our feet * (see SIOCSIFNAME). */ - dev_name = kstrdup(dev_name, GFP_KERNEL); - if (!dev_name) - goto free; - - t->addrconf_dev[0].procname = dev_name; + t->dev_name = kstrdup(dev_name, GFP_KERNEL); + if (!t->dev_name) + goto free; - t->addrconf_dev[0].child = t->addrconf_vars; - t->addrconf_conf_dir[0].child = t->addrconf_dev; - t->addrconf_proto_dir[0].child = t->addrconf_conf_dir; - t->addrconf_root_dir[0].child = t->addrconf_proto_dir; + addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].procname = t->dev_name; + addrconf_ctl_path[ADDRCONF_CTL_PATH_DEV].ctl_name = ctl_name; - t->sysctl_header = register_sysctl_table(t->addrconf_root_dir); + t->sysctl_header = register_net_sysctl_table(net, addrconf_ctl_path, + t->addrconf_vars); if (t->sysctl_header == NULL) goto free_procname; - else - p->sysctl = t; - return; - /* error path */ - free_procname: - kfree(dev_name); - free: + p->sysctl = t; + return 0; + +free_procname: + kfree(t->dev_name); +free: + kfree(t); +out: + return -ENOBUFS; +} + +static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) +{ + struct addrconf_sysctl_table *t; + + if (p->sysctl == NULL) + return; + + t = p->sysctl; + p->sysctl = NULL; + unregister_sysctl_table(t->sysctl_header); + kfree(t->dev_name); kfree(t); +} - return; +static void addrconf_sysctl_register(struct inet6_dev *idev) +{ + neigh_sysctl_register(idev->dev, idev->nd_parms, NET_IPV6, + NET_IPV6_NEIGH, "ipv6", + &ndisc_ifinfo_sysctl_change, + ndisc_ifinfo_sysctl_strategy); + __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, + idev->dev->ifindex, idev, &idev->cnf); } -static void addrconf_sysctl_unregister(struct ipv6_devconf *p) +static void addrconf_sysctl_unregister(struct inet6_dev *idev) { - if (p->sysctl) { - struct addrconf_sysctl_table *t = p->sysctl; - p->sysctl = NULL; - unregister_sysctl_table(t->sysctl_header); - kfree(t->addrconf_dev[0].procname); - kfree(t); - } + __addrconf_sysctl_unregister(&idev->cnf); + neigh_sysctl_unregister(idev->nd_parms); } #endif +static int addrconf_init_net(struct net *net) +{ + int err; + struct ipv6_devconf *all, *dflt; + + err = -ENOMEM; + all = &ipv6_devconf; + dflt = &ipv6_devconf_dflt; + + if (net != &init_net) { + all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); + if (all == NULL) + goto err_alloc_all; + + dflt = kmemdup(dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); + if (dflt == NULL) + goto err_alloc_dflt; + } + + net->ipv6.devconf_all = all; + net->ipv6.devconf_dflt = dflt; + +#ifdef CONFIG_SYSCTL + err = __addrconf_sysctl_register(net, "all", NET_PROTO_CONF_ALL, + NULL, all); + if (err < 0) + goto err_reg_all; + + err = __addrconf_sysctl_register(net, "default", NET_PROTO_CONF_DEFAULT, + NULL, dflt); + if (err < 0) + goto err_reg_dflt; +#endif + return 0; + +#ifdef CONFIG_SYSCTL +err_reg_dflt: + __addrconf_sysctl_unregister(all); +err_reg_all: + kfree(dflt); +#endif +err_alloc_dflt: + kfree(all); +err_alloc_all: + return err; +} + +static void addrconf_exit_net(struct net *net) +{ +#ifdef CONFIG_SYSCTL + __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); + __addrconf_sysctl_unregister(net->ipv6.devconf_all); +#endif + if (net != &init_net) { + kfree(net->ipv6.devconf_dflt); + kfree(net->ipv6.devconf_all); + } +} + +static struct pernet_operations addrconf_ops = { + .init = addrconf_init_net, + .exit = addrconf_exit_net, +}; + /* * Device notifier */ @@ -4177,13 +4437,40 @@ int unregister_inet6addr_notifier(struct notifier_block *nb) EXPORT_SYMBOL(unregister_inet6addr_notifier); +static void addrconf_net_exit(struct net *net) +{ + struct net_device *dev; + + rtnl_lock(); + /* clean dev list */ + for_each_netdev(net, dev) { + if (__in6_dev_get(dev) == NULL) + continue; + addrconf_ifdown(dev, 1); + } + addrconf_ifdown(net->loopback_dev, 2); + rtnl_unlock(); +} + +static struct pernet_operations addrconf_net_ops = { + .exit = addrconf_net_exit, +}; + /* * Init / cleanup code */ int __init addrconf_init(void) { - int err = 0; + int err; + + if ((err = ipv6_addr_label_init()) < 0) { + printk(KERN_CRIT "IPv6 Addrconf: cannot initialize default policy table: %d.\n", + err); + return err; + } + + register_pernet_subsys(&addrconf_ops); /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup @@ -4208,16 +4495,11 @@ int __init addrconf_init(void) err = -ENOMEM; rtnl_unlock(); if (err) - return err; + goto errlo; - ip6_null_entry.u.dst.dev = init_net.loopback_dev; - ip6_null_entry.rt6i_idev = in6_dev_get(init_net.loopback_dev); -#ifdef CONFIG_IPV6_MULTIPLE_TABLES - ip6_prohibit_entry.u.dst.dev = init_net.loopback_dev; - ip6_prohibit_entry.rt6i_idev = in6_dev_get(init_net.loopback_dev); - ip6_blk_hole_entry.u.dst.dev = init_net.loopback_dev; - ip6_blk_hole_entry.rt6i_idev = in6_dev_get(init_net.loopback_dev); -#endif + err = register_pernet_device(&addrconf_net_ops); + if (err) + return err; register_netdevice_notifier(&ipv6_dev_notf); @@ -4234,49 +4516,32 @@ int __init addrconf_init(void) __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr); -#ifdef CONFIG_SYSCTL - addrconf_sysctl.sysctl_header = - register_sysctl_table(addrconf_sysctl.addrconf_root_dir); - addrconf_sysctl_register(NULL, &ipv6_devconf_dflt); -#endif + ipv6_addr_label_rtnl_register(); return 0; errout: unregister_netdevice_notifier(&ipv6_dev_notf); +errlo: + unregister_pernet_subsys(&addrconf_ops); return err; } -void __exit addrconf_cleanup(void) +void addrconf_cleanup(void) { - struct net_device *dev; struct inet6_ifaddr *ifa; int i; unregister_netdevice_notifier(&ipv6_dev_notf); + unregister_pernet_device(&addrconf_net_ops); -#ifdef CONFIG_SYSCTL - addrconf_sysctl_unregister(&ipv6_devconf_dflt); - addrconf_sysctl_unregister(&ipv6_devconf); -#endif + unregister_pernet_subsys(&addrconf_ops); rtnl_lock(); /* - * clean dev list. - */ - - for_each_netdev(&init_net, dev) { - if (__in6_dev_get(dev) == NULL) - continue; - addrconf_ifdown(dev, 1); - } - addrconf_ifdown(init_net.loopback_dev, 2); - - /* * Check hash table. */ - write_lock_bh(&addrconf_hash_lock); for (i=0; i < IN6_ADDR_HSIZE; i++) { for (ifa=inet6_addr_lst[i]; ifa; ) { @@ -4293,6 +4558,7 @@ void __exit addrconf_cleanup(void) write_unlock_bh(&addrconf_hash_lock); del_timer(&addr_chk_timer); - rtnl_unlock(); + + unregister_pernet_subsys(&addrconf_net_ops); }