diff options
Diffstat (limited to 'net/ipv6')
60 files changed, 35124 insertions, 0 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig new file mode 100644 index 00000000000..e66ca9381cf --- /dev/null +++ b/net/ipv6/Kconfig @@ -0,0 +1,79 @@ +# +# IPv6 configuration +# +config IPV6_PRIVACY + bool "IPv6: Privacy Extensions (RFC 3041) support" + depends on IPV6 + ---help--- + Privacy Extensions for Stateless Address Autoconfiguration in IPv6 + support. With this option, additional periodically-alter + pseudo-random global-scope unicast address(es) will assigned to + your interface(s). + + By default, kernel do not generate temporary addresses. + To use temporary addresses, do + + echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr + + See <file:Documentation/networking/ip-sysctl.txt> for details. + +config INET6_AH + tristate "IPv6: AH transformation" + depends on IPV6 + select XFRM + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_MD5 + select CRYPTO_SHA1 + ---help--- + Support for IPsec AH. + + If unsure, say Y. + +config INET6_ESP + tristate "IPv6: ESP transformation" + depends on IPV6 + select XFRM + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_MD5 + select CRYPTO_SHA1 + select CRYPTO_DES + ---help--- + Support for IPsec ESP. + + If unsure, say Y. + +config INET6_IPCOMP + tristate "IPv6: IPComp transformation" + depends on IPV6 + select XFRM + select INET6_TUNNEL + select CRYPTO + select CRYPTO_DEFLATE + ---help--- + Support for IP Payload Compression Protocol (IPComp) (RFC3173), + typically needed for IPsec. + + If unsure, say Y. + +config INET6_TUNNEL + tristate "IPv6: tunnel transformation" + depends on IPV6 + select XFRM + ---help--- + Support for generic IPv6-in-IPv6 tunnel transformation, which is + required by the IPv6-in-IPv6 tunneling module as well as tunnel mode + IPComp. + + If unsure, say Y. + +config IPV6_TUNNEL + tristate "IPv6: IPv6-in-IPv6 tunnel" + depends on IPV6 + select INET6_TUNNEL + ---help--- + Support for IPv6-in-IPv6 tunnels described in RFC 2473. + + If unsure, say N. + diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile new file mode 100644 index 00000000000..b39e0494059 --- /dev/null +++ b/net/ipv6/Makefile @@ -0,0 +1,25 @@ +# +# Makefile for the Linux TCP/IP (INET6) layer. +# + +obj-$(CONFIG_IPV6) += ipv6.o + +ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \ + route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o raw.o \ + protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ + exthdrs.o sysctl_net_ipv6.o datagram.o proc.o \ + ip6_flowlabel.o ipv6_syms.o + +ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ + xfrm6_output.o +ipv6-objs += $(ipv6-y) + +obj-$(CONFIG_INET6_AH) += ah6.o +obj-$(CONFIG_INET6_ESP) += esp6.o +obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o +obj-$(CONFIG_INET6_TUNNEL) += xfrm6_tunnel.o +obj-$(CONFIG_NETFILTER) += netfilter/ + +obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o + +obj-y += exthdrs_core.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c new file mode 100644 index 00000000000..5ffde14ddc0 --- /dev/null +++ b/net/ipv6/addrconf.c @@ -0,0 +1,3615 @@ +/* + * IPv6 Address [auto]configuration + * Linux INET6 implementation + * + * Authors: + * Pedro Roque <roque@di.fc.ul.pt> + * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> + * + * $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 + * 2 of the License, or (at your option) any later version. + */ + +/* + * Changes: + * + * Janos Farkas : delete timer on ifdown + * <chexum@bankinf.banki.hu> + * Andi Kleen : kill double kfree on module + * unload. + * Maciej W. Rozycki : FDDI support + * sekiya@USAGI : Don't send too many RS + * packets. + * yoshfuji@USAGI : Fixed interval between DAD + * packets. + * YOSHIFUJI Hideaki @USAGI : improved accuracy of + * address validation timer. + * YOSHIFUJI Hideaki @USAGI : Privacy Extensions (RFC3041) + * support. + * Yuji SEKIYA @USAGI : Don't assign a same IPv6 + * address on a same interface. + * YOSHIFUJI Hideaki @USAGI : ARCnet support + * YOSHIFUJI Hideaki @USAGI : convert /proc/net/if_inet6 to + * seq_file. + */ + +#include <linux/config.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <linux/sched.h> +#include <linux/net.h> +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/if_arcnet.h> +#include <linux/if_infiniband.h> +#include <linux/route.h> +#include <linux/inetdevice.h> +#include <linux/init.h> +#ifdef CONFIG_SYSCTL +#include <linux/sysctl.h> +#endif +#include <linux/delay.h> +#include <linux/notifier.h> + +#include <net/sock.h> +#include <net/snmp.h> + +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/ndisc.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> +#include <net/tcp.h> +#include <net/ip.h> +#include <linux/if_tunnel.h> +#include <linux/rtnetlink.h> + +#ifdef CONFIG_IPV6_PRIVACY +#include <linux/random.h> +#include <linux/crypto.h> +#include <asm/scatterlist.h> +#endif + +#include <asm/uaccess.h> + +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +/* Set to 3 to get tracing... */ +#define ACONF_DEBUG 2 + +#if ACONF_DEBUG >= 3 +#define ADBG(x) printk x +#else +#define ADBG(x) +#endif + +#define INFINITY_LIFE_TIME 0xFFFFFFFF +#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); +#endif + +#ifdef CONFIG_IPV6_PRIVACY +static int __ipv6_regen_rndid(struct inet6_dev *idev); +static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); +static void ipv6_regen_rndid(unsigned long data); + +static int desync_factor = MAX_DESYNC_FACTOR * HZ; +static struct crypto_tfm *md5_tfm; +static DEFINE_SPINLOCK(md5_tfm_lock); +#endif + +static int ipv6_count_addresses(struct inet6_dev *idev); + +/* + * Configured unicast address hash table + */ +static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE]; +static DEFINE_RWLOCK(addrconf_hash_lock); + +/* Protects inet6 devices */ +DEFINE_RWLOCK(addrconf_lock); + +static void addrconf_verify(unsigned long); + +static struct timer_list addr_chk_timer = + TIMER_INITIALIZER(addrconf_verify, 0, 0); +static DEFINE_SPINLOCK(addrconf_verify_lock); + +static void addrconf_join_anycast(struct inet6_ifaddr *ifp); +static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); + +static int addrconf_ifdown(struct net_device *dev, int how); + +static void addrconf_dad_start(struct inet6_ifaddr *ifp, int flags); +static void addrconf_dad_timer(unsigned long data); +static void addrconf_dad_completed(struct inet6_ifaddr *ifp); +static void addrconf_rs_timer(unsigned long data); +static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); +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 struct notifier_block *inet6addr_chain; + +struct ipv6_devconf ipv6_devconf = { + .forwarding = 0, + .hop_limit = IPV6_DEFAULT_HOPLIMIT, + .mtu6 = IPV6_MIN_MTU, + .accept_ra = 1, + .accept_redirects = 1, + .autoconf = 1, + .force_mld_version = 0, + .dad_transmits = 1, + .rtr_solicits = MAX_RTR_SOLICITATIONS, + .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, + .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, +#ifdef CONFIG_IPV6_PRIVACY + .use_tempaddr = 0, + .temp_valid_lft = TEMP_VALID_LIFETIME, + .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_max_retry = REGEN_MAX_RETRY, + .max_desync_factor = MAX_DESYNC_FACTOR, +#endif + .max_addresses = IPV6_MAX_ADDRESSES, +}; + +static struct ipv6_devconf ipv6_devconf_dflt = { + .forwarding = 0, + .hop_limit = IPV6_DEFAULT_HOPLIMIT, + .mtu6 = IPV6_MIN_MTU, + .accept_ra = 1, + .accept_redirects = 1, + .autoconf = 1, + .dad_transmits = 1, + .rtr_solicits = MAX_RTR_SOLICITATIONS, + .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, + .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, +#ifdef CONFIG_IPV6_PRIVACY + .use_tempaddr = 0, + .temp_valid_lft = TEMP_VALID_LIFETIME, + .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_max_retry = REGEN_MAX_RETRY, + .max_desync_factor = MAX_DESYNC_FACTOR, +#endif + .max_addresses = IPV6_MAX_ADDRESSES, +}; + +/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ +#if 0 +const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +#endif +const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; + +int ipv6_addr_type(const struct in6_addr *addr) +{ + int type; + u32 st; + + st = addr->s6_addr32[0]; + + if ((st & htonl(0xFF000000)) == htonl(0xFF000000)) { + type = IPV6_ADDR_MULTICAST; + + switch((st & htonl(0x00FF0000))) { + case __constant_htonl(0x00010000): + type |= IPV6_ADDR_LOOPBACK; + break; + + case __constant_htonl(0x00020000): + type |= IPV6_ADDR_LINKLOCAL; + break; + + case __constant_htonl(0x00050000): + type |= IPV6_ADDR_SITELOCAL; + break; + }; + return type; + } + + type = IPV6_ADDR_UNICAST; + + /* Consider all addresses with the first three bits different of + 000 and 111 as finished. + */ + if ((st & htonl(0xE0000000)) != htonl(0x00000000) && + (st & htonl(0xE0000000)) != htonl(0xE0000000)) + return type; + + if ((st & htonl(0xFFC00000)) == htonl(0xFE800000)) + return (IPV6_ADDR_LINKLOCAL | type); + + if ((st & htonl(0xFFC00000)) == htonl(0xFEC00000)) + return (IPV6_ADDR_SITELOCAL | type); + + if ((addr->s6_addr32[0] | addr->s6_addr32[1]) == 0) { + if (addr->s6_addr32[2] == 0) { + if (addr->s6_addr32[3] == 0) + return IPV6_ADDR_ANY; + + if (addr->s6_addr32[3] == htonl(0x00000001)) + return (IPV6_ADDR_LOOPBACK | type); + + return (IPV6_ADDR_COMPATv4 | type); + } + + if (addr->s6_addr32[2] == htonl(0x0000ffff)) + return IPV6_ADDR_MAPPED; + } + + st &= htonl(0xFF000000); + if (st == 0) + return IPV6_ADDR_RESERVED; + st &= htonl(0xFE000000); + if (st == htonl(0x02000000)) + return IPV6_ADDR_RESERVED; /* for NSAP */ + if (st == htonl(0x04000000)) + return IPV6_ADDR_RESERVED; /* for IPX */ + return type; +} + +static void addrconf_del_timer(struct inet6_ifaddr *ifp) +{ + if (del_timer(&ifp->timer)) + __in6_ifa_put(ifp); +} + +enum addrconf_timer_t +{ + AC_NONE, + AC_DAD, + AC_RS, +}; + +static void addrconf_mod_timer(struct inet6_ifaddr *ifp, + enum addrconf_timer_t what, + unsigned long when) +{ + if (!del_timer(&ifp->timer)) + in6_ifa_hold(ifp); + + switch (what) { + case AC_DAD: + ifp->timer.function = addrconf_dad_timer; + break; + case AC_RS: + ifp->timer.function = addrconf_rs_timer; + break; + default:; + } + ifp->timer.expires = jiffies + when; + add_timer(&ifp->timer); +} + +/* Nobody refers to this device, we may destroy it. */ + +void in6_dev_finish_destroy(struct inet6_dev *idev) +{ + struct net_device *dev = idev->dev; + BUG_TRAP(idev->addr_list==NULL); + BUG_TRAP(idev->mc_list==NULL); +#ifdef NET_REFCNT_DEBUG + printk(KERN_DEBUG "in6_dev_finish_destroy: %s\n", dev ? dev->name : "NIL"); +#endif + dev_put(dev); + if (!idev->dead) { + printk("Freeing alive inet6 device %p\n", idev); + return; + } + snmp6_free_dev(idev); + kfree(idev); +} + +static struct inet6_dev * ipv6_add_dev(struct net_device *dev) +{ + struct inet6_dev *ndev; + + ASSERT_RTNL(); + + if (dev->mtu < IPV6_MIN_MTU) + return NULL; + + ndev = kmalloc(sizeof(struct inet6_dev), GFP_KERNEL); + + if (ndev) { + memset(ndev, 0, sizeof(struct inet6_dev)); + + rwlock_init(&ndev->lock); + ndev->dev = dev; + memcpy(&ndev->cnf, &ipv6_devconf_dflt, sizeof(ndev->cnf)); + ndev->cnf.mtu6 = dev->mtu; + ndev->cnf.sysctl = NULL; + ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); + if (ndev->nd_parms == NULL) { + kfree(ndev); + return NULL; + } + /* 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)); + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return NULL; + } + + if (snmp6_register_dev(ndev) < 0) { + ADBG((KERN_WARNING + "%s(): cannot create /proc/net/dev_snmp6/%s\n", + __FUNCTION__, dev->name)); + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return NULL; + } + + /* One reference from device. We must do this before + * we invoke __ipv6_regen_rndid(). + */ + in6_dev_hold(ndev); + +#ifdef CONFIG_IPV6_PRIVACY + get_random_bytes(ndev->rndid, sizeof(ndev->rndid)); + get_random_bytes(ndev->entropy, sizeof(ndev->entropy)); + init_timer(&ndev->regen_timer); + ndev->regen_timer.function = ipv6_regen_rndid; + ndev->regen_timer.data = (unsigned long) ndev; + if ((dev->flags&IFF_LOOPBACK) || + dev->type == ARPHRD_TUNNEL || + dev->type == ARPHRD_SIT) { + printk(KERN_INFO + "Disabled Privacy Extensions on device %p(%s)\n", + dev, dev->name); + ndev->cnf.use_tempaddr = -1; + } else { + in6_dev_hold(ndev); + ipv6_regen_rndid((unsigned long) ndev); + } +#endif + + write_lock_bh(&addrconf_lock); + dev->ip6_ptr = ndev; + write_unlock_bh(&addrconf_lock); + + 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 + } + return ndev; +} + +static struct inet6_dev * ipv6_find_idev(struct net_device *dev) +{ + struct inet6_dev *idev; + + ASSERT_RTNL(); + + if ((idev = __in6_dev_get(dev)) == NULL) { + if ((idev = ipv6_add_dev(dev)) == NULL) + return NULL; + } + if (dev->flags&IFF_UP) + ipv6_mc_up(idev); + return idev; +} + +#ifdef CONFIG_SYSCTL +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 (dev && (dev->flags & IFF_MULTICAST)) { + ipv6_addr_all_routers(&addr); + + if (idev->cnf.forwarding) + ipv6_dev_mc_inc(dev, &addr); + else + ipv6_dev_mc_dec(dev, &addr); + } + for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) { + if (idev->cnf.forwarding) + addrconf_join_anycast(ifa); + else + addrconf_leave_anycast(ifa); + } +} + + +static void addrconf_forward_change(void) +{ + struct net_device *dev; + struct inet6_dev *idev; + + read_lock(&dev_base_lock); + for (dev=dev_base; dev; dev=dev->next) { + read_lock(&addrconf_lock); + idev = __in6_dev_get(dev); + if (idev) { + int changed = (!idev->cnf.forwarding) ^ (!ipv6_devconf.forwarding); + idev->cnf.forwarding = ipv6_devconf.forwarding; + if (changed) + dev_forward_change(idev); + } + read_unlock(&addrconf_lock); + } + read_unlock(&dev_base_lock); +} +#endif + +/* Nobody refers to this ifaddr, destroy it */ + +void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) +{ + BUG_TRAP(ifp->if_next==NULL); + BUG_TRAP(ifp->lst_next==NULL); +#ifdef NET_REFCNT_DEBUG + printk(KERN_DEBUG "inet6_ifa_finish_destroy\n"); +#endif + + in6_dev_put(ifp->idev); + + if (del_timer(&ifp->timer)) + printk("Timer is still running, when freeing ifa=%p\n", ifp); + + if (!ifp->dead) { + printk("Freeing alive inet6 address %p\n", ifp); + return; + } + dst_release(&ifp->rt->u.dst); + + kfree(ifp); +} + +/* On success it returns ifp with increased reference count */ + +static struct inet6_ifaddr * +ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, + int scope, unsigned flags) +{ + struct inet6_ifaddr *ifa = NULL; + struct rt6_info *rt; + int hash; + int err = 0; + + read_lock_bh(&addrconf_lock); + if (idev->dead) { + err = -ENODEV; /*XXX*/ + goto out2; + } + + write_lock(&addrconf_hash_lock); + + /* Ignore adding duplicate addresses on an interface */ + if (ipv6_chk_same_addr(addr, idev->dev)) { + ADBG(("ipv6_add_addr: already assigned\n")); + err = -EEXIST; + goto out; + } + + ifa = kmalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); + + if (ifa == NULL) { + ADBG(("ipv6_add_addr: malloc failed\n")); + err = -ENOBUFS; + goto out; + } + + rt = addrconf_dst_alloc(idev, addr, 0); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + goto out; + } + + memset(ifa, 0, sizeof(struct inet6_ifaddr)); + ipv6_addr_copy(&ifa->addr, addr); + + spin_lock_init(&ifa->lock); + init_timer(&ifa->timer); + ifa->timer.data = (unsigned long) ifa; + ifa->scope = scope; + ifa->prefix_len = pfxlen; + ifa->flags = flags | IFA_F_TENTATIVE; + ifa->cstamp = ifa->tstamp = jiffies; + + ifa->idev = idev; + in6_dev_hold(idev); + /* For caller */ + in6_ifa_hold(ifa); + + /* Add to big hash table */ + hash = ipv6_addr_hash(addr); + + ifa->lst_next = inet6_addr_lst[hash]; + inet6_addr_lst[hash] = ifa; + in6_ifa_hold(ifa); + write_unlock(&addrconf_hash_lock); + + write_lock(&idev->lock); + /* Add to inet6_dev unicast addr list. */ + ifa->if_next = idev->addr_list; + idev->addr_list = ifa; + +#ifdef CONFIG_IPV6_PRIVACY + if (ifa->flags&IFA_F_TEMPORARY) { + ifa->tmp_next = idev->tempaddr_list; + idev->tempaddr_list = ifa; + in6_ifa_hold(ifa); + } +#endif + + ifa->rt = rt; + + in6_ifa_hold(ifa); + write_unlock(&idev->lock); +out2: + read_unlock_bh(&addrconf_lock); + + if (unlikely(err == 0)) + notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); + else { + kfree(ifa); + ifa = ERR_PTR(err); + } + + return ifa; +out: + write_unlock(&addrconf_hash_lock); + goto out2; +} + +/* This function wants to get referenced ifp and releases it before return */ + +static void ipv6_del_addr(struct inet6_ifaddr *ifp) +{ + struct inet6_ifaddr *ifa, **ifap; + struct inet6_dev *idev = ifp->idev; + int hash; + int deleted = 0, onlink = 0; + unsigned long expires = jiffies; + + hash = ipv6_addr_hash(&ifp->addr); + + ifp->dead = 1; + + write_lock_bh(&addrconf_hash_lock); + for (ifap = &inet6_addr_lst[hash]; (ifa=*ifap) != NULL; + ifap = &ifa->lst_next) { + if (ifa == ifp) { + *ifap = ifa->lst_next; + __in6_ifa_put(ifp); + ifa->lst_next = NULL; + break; + } + } + write_unlock_bh(&addrconf_hash_lock); + + write_lock_bh(&idev->lock); +#ifdef CONFIG_IPV6_PRIVACY + if (ifp->flags&IFA_F_TEMPORARY) { + for (ifap = &idev->tempaddr_li |