diff options
Diffstat (limited to 'net/ipv6')
108 files changed, 38529 insertions, 18472 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ab7a9124f98..438a73aa777 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -3,17 +3,15 @@ # # IPv6 as module will cause a CRASH if you try to unload it -config IPV6 +menuconfig IPV6 tristate "The IPv6 protocol" default m - select CRYPTO if IPV6_PRIVACY - select CRYPTO_MD5 if IPV6_PRIVACY ---help--- This is complemental support for the IP version 6. You will still be able to do traditional IPv4 networking as well. For general information about IPv6, see - <http://playground.sun.com/pub/ipng/html/ipng-main.html>. + <https://en.wikipedia.org/wiki/IPv6>. For Linux IPv6 development information, see <http://www.linux-ipv6.org>. For specific information about IPv6 under Linux, read the HOWTO at <http://www.bieringer.de/linux/IPv6/>. @@ -21,26 +19,38 @@ config IPV6 To compile this protocol support as a module, choose M here: the module will be called ipv6. -config IPV6_PRIVACY - bool "IPv6: Privacy Extensions (RFC 3041) support" - depends on IPV6 +if IPV6 + +config IPV6_ROUTER_PREF + bool "IPv6: Router Preference (RFC 4191) support" + ---help--- + Router Preference is an optional extension to the Router + Advertisement message which improves the ability of hosts + to pick an appropriate router, especially when the hosts + are placed in a multi-homed network. + + If unsure, say N. + +config IPV6_ROUTE_INFO + bool "IPv6: Route Information (RFC 4191) support" + depends on IPV6_ROUTER_PREF ---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 + This is experimental support of Route Information. - See <file:Documentation/networking/ip-sysctl.txt> for details. + If unsure, say N. + +config IPV6_OPTIMISTIC_DAD + bool "IPv6: Enable RFC 4429 Optimistic DAD" + ---help--- + This is experimental support for optimistic Duplicate + Address Detection. It allows for autoconfigured addresses + to be used more quickly. + + If unsure, say N. config INET6_AH tristate "IPv6: AH transformation" - depends on IPV6 - select XFRM + select XFRM_ALGO select CRYPTO select CRYPTO_HMAC select CRYPTO_MD5 @@ -52,11 +62,12 @@ config INET6_AH config INET6_ESP tristate "IPv6: ESP transformation" - depends on IPV6 - select XFRM + select XFRM_ALGO select CRYPTO + select CRYPTO_AUTHENC select CRYPTO_HMAC select CRYPTO_MD5 + select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES ---help--- @@ -66,33 +77,185 @@ config INET6_ESP config INET6_IPCOMP tristate "IPv6: IPComp transformation" - depends on IPV6 - select XFRM - select INET6_TUNNEL - select CRYPTO - select CRYPTO_DEFLATE + select INET6_XFRM_TUNNEL + select XFRM_IPCOMP ---help--- Support for IP Payload Compression Protocol (IPComp) (RFC3173), typically needed for IPsec. If unsure, say Y. +config IPV6_MIP6 + tristate "IPv6: Mobility" + select XFRM + ---help--- + Support for IPv6 Mobility described in RFC 3775. + + If unsure, say N. + +config INET6_XFRM_TUNNEL + tristate + select INET6_TUNNEL + default n + config INET6_TUNNEL - tristate "IPv6: tunnel transformation" - depends on IPV6 + tristate + default n + +config INET6_XFRM_MODE_TRANSPORT + tristate "IPv6: IPsec transport mode" + default 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. - + Support for IPsec transport mode. + If unsure, say Y. +config INET6_XFRM_MODE_TUNNEL + tristate "IPv6: IPsec tunnel mode" + default IPV6 + select XFRM + ---help--- + Support for IPsec tunnel mode. + + If unsure, say Y. + +config INET6_XFRM_MODE_BEET + tristate "IPv6: IPsec BEET mode" + default IPV6 + select XFRM + ---help--- + Support for IPsec BEET mode. + + If unsure, say Y. + +config INET6_XFRM_MODE_ROUTEOPTIMIZATION + tristate "IPv6: MIPv6 route optimization mode" + select XFRM + ---help--- + Support for MIPv6 route optimization mode. + +config IPV6_VTI +tristate "Virtual (secure) IPv6: tunneling" + select IPV6_TUNNEL + select NET_IP_TUNNEL + depends on INET6_XFRM_MODE_TUNNEL + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This can be used with xfrm mode tunnel to give + the notion of a secure tunnel for IPSEC and then use routing protocol + on top. + +config IPV6_SIT + tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)" + select INET_TUNNEL + select NET_IP_TUNNEL + select IPV6_NDISC_NODETYPE + default y + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This driver implements encapsulation of IPv6 + into IPv4 packets. This is useful if you want to connect two IPv6 + networks over an IPv4-only path. + + Saying M here will produce a module called sit. If unsure, say Y. + +config IPV6_SIT_6RD + bool "IPv6: IPv6 Rapid Deployment (6RD)" + depends on IPV6_SIT + default n + ---help--- + IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon + mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly + deploy IPv6 unicast service to IPv4 sites to which it provides + customer premise equipment. Like 6to4, it utilizes stateless IPv6 in + IPv4 encapsulation in order to transit IPv4-only network + infrastructure. Unlike 6to4, a 6rd service provider uses an IPv6 + prefix of its own in place of the fixed 6to4 prefix. + + With this option enabled, the SIT driver offers 6rd functionality by + providing additional ioctl API to configure the IPv6 Prefix for in + stead of static 2002::/16 for 6to4. + + If unsure, say N. + +config IPV6_NDISC_NODETYPE + bool + config IPV6_TUNNEL - tristate "IPv6: IPv6-in-IPv6 tunnel" + tristate "IPv6: IP-in-IPv6 tunnel (RFC2473)" + select INET6_TUNNEL + ---help--- + Support for IPv6-in-IPv6 and IPv4-in-IPv6 tunnels described in + RFC 2473. + + If unsure, say N. + +config IPV6_GRE + tristate "IPv6: GRE tunnel" + select IPV6_TUNNEL + select NET_IP_TUNNEL + ---help--- + Tunneling means encapsulating data of one protocol type within + another protocol and sending it over a channel that understands the + encapsulating protocol. This particular tunneling driver implements + GRE (Generic Routing Encapsulation) and at this time allows + encapsulating of IPv4 or IPv6 over existing IPv6 infrastructure. + This driver is useful if the other endpoint is a Cisco router: Cisco + likes GRE much better than the other Linux tunneling driver ("IP + tunneling" above). In addition, GRE allows multicast redistribution + through the tunnel. + + Saying M here will produce a module called ip6_gre. If unsure, say N. + +config IPV6_MULTIPLE_TABLES + bool "IPv6: Multiple Routing Tables" + select FIB_RULES + ---help--- + Support multiple routing tables. + +config IPV6_SUBTREES + bool "IPv6: source address based routing" + depends on IPV6_MULTIPLE_TABLES + ---help--- + Enable routing by source address or prefix. + + The destination address is still the primary routing key, so mixing + normal and source prefix specific routes in the same routing table + may sometimes lead to unintended routing behavior. This can be + avoided by defining different routing tables for the normal and + source prefix specific routes. + + If unsure, say N. + +config IPV6_MROUTE + bool "IPv6: multicast routing" depends on IPV6 ---help--- - Support for IPv6-in-IPv6 tunnels described in RFC 2473. + Experimental support for IPv6 multicast forwarding. + If unsure, say N. +config IPV6_MROUTE_MULTIPLE_TABLES + bool "IPv6: multicast policy routing" + depends on IPV6_MROUTE + select FIB_RULES + help + Normally, a multicast router runs a userspace daemon and decides + what to do with a multicast packet based on the source and + destination addresses. If you say Y here, the multicast router + will also be able to take interfaces and packet marks into + account and run multiple instances of userspace daemons + simultaneously, each one handling a single table. + + If unsure, say N. + +config IPV6_PIMSM_V2 + bool "IPv6: PIM-SM version 2 support" + depends on IPV6_MROUTE + ---help--- + Support for IPv6 PIM multicast routing protocol PIM-SMv2. If unsure, say N. +endif # IPV6 diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 6460eec834b..2fe68364bb2 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -4,24 +4,44 @@ obj-$(CONFIG_IPV6) += ipv6.o -ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \ - route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o raw.o \ - protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ - exthdrs.o sysctl_net_ipv6.o datagram.o proc.o \ - ip6_flowlabel.o ipv6_syms.o netfilter.o +ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ + addrlabel.o \ + route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ + raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ + exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o + +ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o + +ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o +ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ - xfrm6_output.o + xfrm6_output.o xfrm6_protocol.o +ipv6-$(CONFIG_NETFILTER) += netfilter.o +ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o +ipv6-$(CONFIG_PROC_FS) += proc.o +ipv6-$(CONFIG_SYN_COOKIES) += syncookies.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_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o +obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o +obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o +obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o +obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o +obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o +obj-$(CONFIG_IPV6_MIP6) += mip6.o obj-$(CONFIG_NETFILTER) += netfilter/ +obj-$(CONFIG_IPV6_VTI) += ip6_vti.o +obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o +obj-$(CONFIG_IPV6_GRE) += ip6_gre.o -obj-y += exthdrs_core.o +obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o +obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2c5f57299d6..5667b3003af 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3,11 +3,9 @@ * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * 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 @@ -35,33 +33,44 @@ * YOSHIFUJI Hideaki @USAGI : ARCnet support * YOSHIFUJI Hideaki @USAGI : convert /proc/net/if_inet6 to * seq_file. + * YOSHIFUJI Hideaki @USAGI : improved source address + * selection; consider scope, + * status etc. */ -#include <linux/config.h> +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> +#include <linux/kernel.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_addr.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> +#include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif +#include <linux/capability.h> #include <linux/delay.h> #include <linux/notifier.h> #include <linux/string.h> +#include <linux/hash.h> +#include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> +#include <net/af_ieee802154.h> +#include <net/firewire.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> @@ -69,82 +78,94 @@ #include <net/addrconf.h> #include <net/tcp.h> #include <net/ip.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> - -#ifdef CONFIG_IPV6_PRIVACY +#include <linux/netconf.h> #include <linux/random.h> -#include <linux/crypto.h> -#include <linux/scatterlist.h> -#endif - -#include <asm/uaccess.h> +#include <linux/uaccess.h> +#include <asm/unaligned.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/export.h> /* Set to 3 to get tracing... */ #define ACONF_DEBUG 2 #if ACONF_DEBUG >= 3 -#define ADBG(x) printk x +#define ADBG(fmt, ...) printk(fmt, ##__VA_ARGS__) #else -#define ADBG(x) +#define ADBG(fmt, ...) do { if (0) printk(fmt, ##__VA_ARGS__); } while (0) #endif #define INFINITY_LIFE_TIME 0xFFFFFFFF -#define TIME_DELTA(a,b) ((unsigned long)((long)(a) - (long)(b))) + +static inline u32 cstamp_delta(unsigned long cstamp) +{ + return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; +} #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 -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(struct inet6_dev *idev); +static void __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_generate_eui64(u8 *eui, struct net_device *dev); 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 struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(addrconf_hash_lock); -static void addrconf_verify(unsigned long); +static void addrconf_verify(void); +static void addrconf_verify_rtnl(void); +static void addrconf_verify_work(struct work_struct *); -static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0); -static DEFINE_SPINLOCK(addrconf_verify_lock); +static struct workqueue_struct *addrconf_wq; +static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); +static void addrconf_type_change(struct net_device *dev, + unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); -static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); -static void addrconf_dad_timer(unsigned long data); +static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, + int plen, + const struct net_device *dev, + u32 flags, u32 noflags); + +static void addrconf_dad_start(struct inet6_ifaddr *ifp); +static void addrconf_dad_work(struct work_struct *w); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); +static void addrconf_dad_run(struct inet6_dev *idev); 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, +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 bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev); -static struct notifier_block *inet6addr_chain; - -struct ipv6_devconf ipv6_devconf = { +static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, @@ -152,167 +173,139 @@ struct ipv6_devconf ipv6_devconf = { .accept_redirects = 1, .autoconf = 1, .force_mld_version = 0, + .mldv1_unsolicited_report_interval = 10 * HZ, + .mldv2_unsolicited_report_interval = HZ, .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, + .accept_ra_defrtr = 1, + .accept_ra_pinfo = 1, +#ifdef CONFIG_IPV6_ROUTER_PREF + .accept_ra_rtr_pref = 1, + .rtr_probe_interval = 60 * HZ, +#ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_max_plen = 0, +#endif +#endif + .proxy_ndp = 0, + .accept_source_route = 0, /* we do not accept RH0 by default. */ + .disable_ipv6 = 0, + .accept_dad = 1, + .suppress_frag_ndisc = 1, }; -static struct ipv6_devconf ipv6_devconf_dflt = { +static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, .accept_ra = 1, .accept_redirects = 1, .autoconf = 1, + .force_mld_version = 0, + .mldv1_unsolicited_report_interval = 10 * HZ, + .mldv2_unsolicited_report_interval = HZ, .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; + .accept_ra_defrtr = 1, + .accept_ra_pinfo = 1, +#ifdef CONFIG_IPV6_ROUTER_PREF + .accept_ra_rtr_pref = 1, + .rtr_probe_interval = 60 * HZ, +#ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_max_plen = 0, +#endif #endif -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; + .proxy_ndp = 0, + .accept_source_route = 0, /* we do not accept RH0 by default. */ + .disable_ipv6 = 0, + .accept_dad = 1, + .suppress_frag_ndisc = 1, +}; -int ipv6_addr_type(const struct in6_addr *addr) +/* Check if a valid qdisc is available */ +static inline bool addrconf_qdisc_ok(const struct net_device *dev) { - 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; - } + return !qdisc_tx_is_noop(dev); +} - 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_rs_timer(struct inet6_dev *idev) +{ + if (del_timer(&idev->rs_timer)) + __in6_dev_put(idev); } -static void addrconf_del_timer(struct inet6_ifaddr *ifp) +static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) { - if (del_timer(&ifp->timer)) + if (cancel_delayed_work(&ifp->dad_work)) __in6_ifa_put(ifp); } -enum addrconf_timer_t +static void addrconf_mod_rs_timer(struct inet6_dev *idev, + unsigned long when) { - AC_NONE, - AC_DAD, - AC_RS, -}; + if (!timer_pending(&idev->rs_timer)) + in6_dev_hold(idev); + mod_timer(&idev->rs_timer, jiffies + when); +} -static void addrconf_mod_timer(struct inet6_ifaddr *ifp, - enum addrconf_timer_t what, - unsigned long when) +static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, + unsigned long delay) { - if (!del_timer(&ifp->timer)) + if (!delayed_work_pending(&ifp->dad_work)) 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); + mod_delayed_work(addrconf_wq, &ifp->dad_work, delay); } -/* Nobody refers to this device, we may destroy it. */ - -void in6_dev_finish_destroy(struct inet6_dev *idev) +static int snmp6_alloc_dev(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; + int i; + + idev->stats.ipv6 = alloc_percpu(struct ipstats_mib); + if (!idev->stats.ipv6) + goto err_ip; + + for_each_possible_cpu(i) { + struct ipstats_mib *addrconf_stats; + addrconf_stats = per_cpu_ptr(idev->stats.ipv6, i); + u64_stats_init(&addrconf_stats->syncp); } - snmp6_free_dev(idev); - kfree(idev); + + + idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device), + GFP_KERNEL); + if (!idev->stats.icmpv6dev) + goto err_icmp; + idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device), + GFP_KERNEL); + if (!idev->stats.icmpv6msgdev) + goto err_icmpmsg; + + return 0; + +err_icmpmsg: + kfree(idev->stats.icmpv6dev); +err_icmp: + free_percpu(idev->stats.ipv6); +err_ip: + return -ENOMEM; } -static struct inet6_dev * ipv6_add_dev(struct net_device *dev) +static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; @@ -321,223 +314,550 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) 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)); + ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); - 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 (ndev == NULL) + 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; - } + rwlock_init(&ndev->lock); + ndev->dev = dev; + INIT_LIST_HEAD(&ndev->addr_list); + setup_timer(&ndev->rs_timer, addrconf_rs_timer, + (unsigned long)ndev); + 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); + if (ndev->nd_parms == NULL) { + 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", + __func__, dev->name); + neigh_parms_release(&nd_tbl, ndev->nd_parms); + dev_put(dev); + kfree(ndev); + return NULL; + } - /* One reference from device. We must do this before - * we invoke __ipv6_regen_rndid(). - */ - in6_dev_hold(ndev); + if (snmp6_register_dev(ndev) < 0) { + ADBG(KERN_WARNING + "%s: cannot create /proc/net/dev_snmp6/%s\n", + __func__, dev->name); + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return NULL; + } -#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_NONE || - 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 + /* One reference from device. We must do this before + * we invoke __ipv6_regen_rndid(). + */ + in6_dev_hold(ndev); - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = ndev; - write_unlock_bh(&addrconf_lock); + if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) + ndev->cnf.accept_dad = -1; - 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); +#if IS_ENABLED(CONFIG_IPV6_SIT) + if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { + pr_info("%s: Disabled Multicast RS\n", dev->name); + ndev->cnf.rtr_solicits = 0; + } #endif + + INIT_LIST_HEAD(&ndev->tempaddr_list); + setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev); + if ((dev->flags&IFF_LOOPBACK) || + dev->type == ARPHRD_TUNNEL || + dev->type == ARPHRD_TUNNEL6 || + dev->type == ARPHRD_SIT || + dev->type == ARPHRD_NONE) { + ndev->cnf.use_tempaddr = -1; + } else { + in6_dev_hold(ndev); + ipv6_regen_rndid((unsigned long) ndev); } + + ndev->token = in6addr_any; + + if (netif_running(dev) && addrconf_qdisc_ok(dev)) + ndev->if_flags |= IF_READY; + + ipv6_mc_init_dev(ndev); + ndev->tstamp = jiffies; + addrconf_sysctl_register(ndev); + /* protected by rtnl_lock */ + rcu_assign_pointer(dev->ip6_ptr, ndev); + + /* Join interface-local all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); + + /* Join all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); + + /* Join all-router multicast group if forwarding is set */ + if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + return ndev; } -static struct inet6_dev * ipv6_find_idev(struct net_device *dev) +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) + idev = __in6_dev_get(dev); + if (!idev) { + idev = ipv6_add_dev(dev); + if (!idev) return NULL; } + if (dev->flags&IFF_UP) ipv6_mc_up(idev); return idev; } +static int inet6_netconf_msgsize_devconf(int type) +{ + int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + + nla_total_size(4); /* NETCONFA_IFINDEX */ + + /* type -1 is used for ALL */ + if (type == -1 || type == NETCONFA_FORWARDING) + size += nla_total_size(4); +#ifdef CONFIG_IPV6_MROUTE + if (type == -1 || type == NETCONFA_MC_FORWARDING) + size += nla_total_size(4); +#endif + if (type == -1 || type == NETCONFA_PROXY_NEIGH) + size += nla_total_size(4); + + return size; +} + +static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, + struct ipv6_devconf *devconf, u32 portid, + u32 seq, int event, unsigned int flags, + int type) +{ + struct nlmsghdr *nlh; + struct netconfmsg *ncm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), + flags); + if (nlh == NULL) + return -EMSGSIZE; + + ncm = nlmsg_data(nlh); + ncm->ncm_family = AF_INET6; + + if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) + goto nla_put_failure; + + /* type -1 is used for ALL */ + if ((type == -1 || type == NETCONFA_FORWARDING) && + nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) + goto nla_put_failure; +#ifdef CONFIG_IPV6_MROUTE + if ((type == -1 || type == NETCONFA_MC_FORWARDING) && + nla_put_s32(skb, NETCONFA_MC_FORWARDING, + devconf->mc_forwarding) < 0) + goto nla_put_failure; +#endif + if ((type == -1 || type == NETCONFA_PROXY_NEIGH) && + nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, + struct ipv6_devconf *devconf) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, + RTM_NEWNETCONF, 0, type); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err); +} + +static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { + [NETCONFA_IFINDEX] = { .len = sizeof(int) }, + [NETCONFA_FORWARDING] = { .len = sizeof(int) }, + [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, +}; + +static int inet6_netconf_get_devconf(struct sk_buff *in_skb, + struct nlmsghdr *nlh) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NETCONFA_MAX+1]; + struct netconfmsg *ncm; + struct sk_buff *skb; + struct ipv6_devconf *devconf; + struct inet6_dev *in6_dev; + struct net_device *dev; + int ifindex; + int err; + + err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, + devconf_ipv6_policy); + if (err < 0) + goto errout; + + err = EINVAL; + if (!tb[NETCONFA_IFINDEX]) + goto errout; + + ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); + switch (ifindex) { + case NETCONFA_IFINDEX_ALL: + devconf = net->ipv6.devconf_all; + break; + case NETCONFA_IFINDEX_DEFAULT: + devconf = net->ipv6.devconf_dflt; + break; + default: + dev = __dev_get_by_index(net, ifindex); + if (dev == NULL) + goto errout; + in6_dev = __in6_dev_get(dev); + if (in6_dev == NULL) + goto errout; + devconf = &in6_dev->cnf; + break; + } + + err = -ENOBUFS; + skb = nlmsg_new(inet6_netconf_msgsize_devconf(-1), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_netconf_fill_devconf(skb, ifindex, devconf, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWNETCONF, 0, + -1); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + +static int inet6_netconf_dump_devconf(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx, s_idx; + struct net_device *dev; + struct inet6_dev *idev; + struct hlist_head *head; + + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + rcu_read_lock(); + cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ + net->dev_base_seq; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + idev = __in6_dev_get(dev); + if (!idev) + goto cont; + + if (inet6_netconf_fill_devconf(skb, dev->ifindex, + &idev->cnf, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + -1) <= 0) { + rcu_read_unlock(); + goto done; + } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + rcu_read_unlock(); + } + if (h == NETDEV_HASHENTRIES) { + if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + -1) <= 0) + goto done; + else + h++; + } + if (h == NETDEV_HASHENTRIES + 1) { + if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + -1) <= 0) + goto done; + else + h++; + } +done: + cb->args[0] = h; + cb->args[1] = idx; + + return skb->len; +} + #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); + if (idev->cnf.forwarding) + dev_disable_lro(dev); + if (dev->flags & IFF_MULTICAST) { + if (idev->cnf.forwarding) { + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allrouters); + ipv6_dev_mc_inc(dev, &in6addr_sitelocal_allrouters); + } else { + ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); + ipv6_dev_mc_dec(dev, &in6addr_interfacelocal_allrouters); + ipv6_dev_mc_dec(dev, &in6addr_sitelocal_allrouters); + } } - for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) { + + list_for_each_entry(ifa, &idev->addr_list, if_list) { + if (ifa->flags&IFA_F_TENTATIVE) + continue; if (idev->cnf.forwarding) addrconf_join_anycast(ifa); else addrconf_leave_anycast(ifa); } + inet6_netconf_notify_devconf(dev_net(dev), NETCONFA_FORWARDING, + dev->ifindex, &idev->cnf); } -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 (dev=dev_base; dev; dev=dev->next) { - read_lock(&addrconf_lock); + for_each_netdev(net, dev) { 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); } - read_unlock(&addrconf_lock); } - read_unlock(&dev_base_lock); +} + +static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) +{ + struct net *net; + int old; + + if (!rtnl_trylock()) + return restart_syscall(); + + net = (struct net *)table->extra2; + old = *p; + *p = newf; + + if (p == &net->ipv6.devconf_dflt->forwarding) { + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + rtnl_unlock(); + return 0; + } + + if (p == &net->ipv6.devconf_all->forwarding) { + net->ipv6.devconf_dflt->forwarding = newf; + addrconf_forward_change(net, newf); + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + } else if ((!newf) ^ (!old)) + dev_forward_change((struct inet6_dev *)table->extra1); + rtnl_unlock(); + + if (newf) + rt6_purge_dflt_routers(net); + return 1; } #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); + WARN_ON(!hlist_unhashed(&ifp->addr_lst)); + #ifdef NET_REFCNT_DEBUG - printk(KERN_DEBUG "inet6_ifa_finish_destroy\n"); + pr_debug("%s\n", __func__); #endif in6_dev_put(ifp->idev); - if (del_timer(&ifp->timer)) - printk("Timer is still running, when freeing ifa=%p\n", ifp); + if (cancel_delayed_work(&ifp->dad_work)) + pr_notice("delayed DAD work was pending while freeing ifa=%p\n", + ifp); - if (!ifp->dead) { - printk("Freeing alive inet6 address %p\n", ifp); + if (ifp->state != INET6_IFADDR_STATE_DEAD) { + pr_warn("Freeing alive inet6 address %p\n", ifp); return; } - dst_release(&ifp->rt->u.dst); + ip6_rt_put(ifp->rt); - kfree(ifp); + kfree_rcu(ifp, rcu); +} + +static void +ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) +{ + struct list_head *p; + int ifp_scope = ipv6_addr_src_scope(&ifp->addr); + + /* + * Each device address list is sorted in order of scope - + * global before linklocal. + */ + list_for_each(p, &idev->addr_list) { + struct inet6_ifaddr *ifa + = list_entry(p, struct inet6_ifaddr, if_list); + if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr)) + break; + } + + list_add_tail(&ifp->if_list, p); +} + +static u32 inet6_addr_hash(const struct in6_addr *addr) +{ + return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT); } /* 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, u32 flags) +ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, + const struct in6_addr *peer_addr, int pfxlen, + int scope, u32 flags, u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; - int hash; + unsigned 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); - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); if (idev->dead) { err = -ENODEV; /*XXX*/ goto out2; } - write_lock(&addrconf_hash_lock); + if (idev->cnf.disable_ipv6) { + err = -EACCES; + goto out2; + } + + spin_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")); + if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { + ADBG("ipv6_add_addr: already assigned\n"); err = -EEXIST; goto out; } - ifa = kmalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); + ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); if (ifa == NULL) { - ADBG(("ipv6_add_addr: malloc failed\n")); + ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; 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; } - memset(ifa, 0, sizeof(struct inet6_ifaddr)); - ipv6_addr_copy(&ifa->addr, addr); + neigh_parms_data_state_setall(idev->nd_parms); + + ifa->addr = *addr; + if (peer_addr) + ifa->peer_addr = *peer_addr; spin_lock_init(&ifa->lock); - init_timer(&ifa->timer); - ifa->timer.data = (unsigned long) ifa; + spin_lock_init(&ifa->state_lock); + INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); + INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = scope; ifa->prefix_len = pfxlen; ifa->flags = flags | IFA_F_TENTATIVE; + ifa->valid_lft = valid_lft; + ifa->prefered_lft = prefered_lft; ifa->cstamp = ifa->tstamp = jiffies; + ifa->tokenized = false; + + ifa->rt = rt; ifa->idev = idev; in6_dev_hold(idev); @@ -545,35 +865,27 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, in6_ifa_hold(ifa); /* Add to big hash table */ - hash = ipv6_addr_hash(addr); + hash = inet6_addr_hash(addr); - ifa->lst_next = inet6_addr_lst[hash]; - inet6_addr_lst[hash] = ifa; - in6_ifa_hold(ifa); - write_unlock(&addrconf_hash_lock); + hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + spin_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; + ipv6_link_dev_addr(idev, ifa); -#ifdef CONFIG_IPV6_PRIVACY if (ifa->flags&IFA_F_TEMPORARY) { - ifa->tmp_next = idev->tempaddr_list; - idev->tempaddr_list = ifa; + list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } -#endif - - ifa->rt = rt; in6_ifa_hold(ifa); write_unlock(&idev->lock); out2: - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); if (likely(err == 0)) - notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); ifa = ERR_PTR(err); @@ -581,144 +893,162 @@ out2: return ifa; out: - write_unlock(&addrconf_hash_lock); + spin_unlock(&addrconf_hash_lock); goto out2; } -/* This function wants to get referenced ifp and releases it before return */ +enum cleanup_prefix_rt_t { + CLEANUP_PREFIX_RT_NOP, /* no cleanup action for prefix route */ + CLEANUP_PREFIX_RT_DEL, /* delete the prefix route */ + CLEANUP_PREFIX_RT_EXPIRE, /* update the lifetime of the prefix route */ +}; -static void ipv6_del_addr(struct inet6_ifaddr *ifp) +/* + * Check, whether the prefix for ifp would still need a prefix route + * after deleting ifp. The function returns one of the CLEANUP_PREFIX_RT_* + * constants. + * + * 1) we don't purge prefix if address was not permanent. + * prefix is managed by its own lifetime. + * 2) we also don't purge, if the address was IFA_F_NOPREFIXROUTE. + * 3) if there are no addresses, delete prefix. + * 4) if there are still other permanent address(es), + * corresponding prefix is still permanent. + * 5) if there are still other addresses with IFA_F_NOPREFIXROUTE, + * don't purge the prefix, assume user space is managing it. + * 6) otherwise, update prefix lifetime to the + * longest valid lifetime among the corresponding + * addresses on the device. + * Note: subsequent RA will update lifetime. + **/ +static enum cleanup_prefix_rt_t +check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) { - struct inet6_ifaddr *ifa, **ifap; + struct inet6_ifaddr *ifa; struct inet6_dev *idev = ifp->idev; - int hash; - int deleted = 0, onlink = 0; - unsigned long expires = jiffies; + unsigned long lifetime; + enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_DEL; + + *expires = jiffies; - hash = ipv6_addr_hash(&ifp->addr); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + if (ifa == ifp) + continue; + if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + ifp->prefix_len)) + continue; + if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) + return CLEANUP_PREFIX_RT_NOP; - ifp->dead = 1; + action = CLEANUP_PREFIX_RT_EXPIRE; - 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; - } + spin_lock(&ifa->lock); + + 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; + spin_unlock(&ifa->lock); } - 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_list; (ifa=*ifap) != NULL; - ifap = &ifa->tmp_next) { - if (ifa == ifp) { - *ifap = ifa->tmp_next; - if (ifp->ifpub) { - in6_ifa_put(ifp->ifpub); - ifp->ifpub = NULL; - } - __in6_ifa_put(ifp); - ifa->tmp_next = NULL; - break; - } + return action; +} + +static void +cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) +{ + struct rt6_info *rt; + + rt = addrconf_get_prefix_route(&ifp->addr, + ifp->prefix_len, + ifp->idev->dev, + 0, RTF_GATEWAY | RTF_DEFAULT); + if (rt) { + if (del_rt) + ip6_del_rt(rt); + else { + if (!(rt->rt6i_flags & RTF_EXPIRES)) + rt6_set_expires(rt, expires); + ip6_rt_put(rt); } } -#endif +} - for (ifap = &idev->addr_list; (ifa=*ifap) != NULL; - ifap = &ifa->if_next) { - if (ifa == ifp) { - *ifap = ifa->if_next; - __in6_ifa_put(ifp); - ifa->if_next = NULL; - if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0) - break; - deleted = 1; - } else if (ifp->flags & IFA_F_PERMANENT) { - if (ipv6_prefix_equal(&ifa->addr, &ifp->addr, - ifp->prefix_len)) { - if (ifa->flags & IFA_F_PERMANENT) { - onlink = 1; - if (deleted) - break; - } else { - unsigned long lifetime; - - if (!onlink) - onlink = -1; - - spin_lock(&ifa->lock); - lifetime = min_t(unsigned long, - ifa->valid_lft, 0x7fffffffUL/HZ); - if (time_before(expires, - ifa->tstamp + lifetime * HZ)) - expires = ifa->tstamp + lifetime * HZ; - spin_unlock(&ifa->lock); - } - } + +/* This function wants to get referenced ifp and releases it before return */ + +static void ipv6_del_addr(struct inet6_ifaddr *ifp) +{ + int state; + enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; + unsigned long expires; + + ASSERT_RTNL(); + + spin_lock_bh(&ifp->state_lock); + state = ifp->state; + ifp->state = INET6_IFADDR_STATE_DEAD; + spin_unlock_bh(&ifp->state_lock); + + if (state == INET6_IFADDR_STATE_DEAD) + goto out; + + spin_lock_bh(&addrconf_hash_lock); + hlist_del_init_rcu(&ifp->addr_lst); + spin_unlock_bh(&addrconf_hash_lock); + + write_lock_bh(&ifp->idev->lock); + + if (ifp->flags&IFA_F_TEMPORARY) { + list_del(&ifp->tmp_list); + if (ifp->ifpub) { + in6_ifa_put(ifp->ifpub); + ifp->ifpub = NULL; } + __in6_ifa_put(ifp); } - write_unlock_bh(&idev->lock); - ipv6_ifa_notify(RTM_DELADDR, ifp); + if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) + action = check_cleanup_prefix_route(ifp, &expires); - notifier_call_chain(&inet6addr_chain,NETDEV_DOWN,ifp); + list_del_init(&ifp->if_list); + __in6_ifa_put(ifp); - addrconf_del_timer(ifp); + write_unlock_bh(&ifp->idev->lock); - /* - * Purge or update corresponding prefix - * - * 1) we don't purge prefix here if address was not permanent. - * prefix is managed by its own lifetime. - * 2) if there're no addresses, delete prefix. - * 3) if there're still other permanent address(es), - * corresponding prefix is still permanent. - * 4) otherwise, update prefix lifetime to the - * longest valid lifetime among the corresponding - * addresses on the device. - * Note: subsequent RA will update lifetime. - * - * --yoshfuji - */ - if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) { - struct in6_addr prefix; - struct rt6_info *rt; + addrconf_del_dad_work(ifp); - ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); - rt = rt6_lookup(&prefix, NULL, ifp->idev->dev->ifindex, 1); + ipv6_ifa_notify(RTM_DELADDR, ifp); - if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { - if (onlink == 0) { - ip6_del_rt(rt, NULL, NULL, NULL); - rt = NULL; - } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { - rt->rt6i_expires = expires; - rt->rt6i_flags |= RTF_EXPIRES; - } - } - dst_release(&rt->u.dst); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); + + if (action != CLEANUP_PREFIX_RT_NOP) { + cleanup_prefix_route(ifp, expires, + action == CLEANUP_PREFIX_RT_DEL); } + /* clean up prefsrc entries */ + rt6_remove_prefsrc(ifp); +out: in6_ifa_put(ifp); } -#ifdef CONFIG_IPV6_PRIVACY static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift) { 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 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); + write_lock_bh(&idev->lock); if (ift) { spin_lock_bh(&ift->lock); memcpy(&addr.s6_addr[8], &ift->addr.s6_addr[8], 8); @@ -730,9 +1060,8 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i retry: in6_dev_hold(idev); if (idev->cnf.use_tempaddr <= 0) { - write_unlock(&idev->lock); - printk(KERN_INFO - "ipv6_create_tempaddr(): use_tempaddr is disabled.\n"); + write_unlock_bh(&idev->lock); + pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); ret = -1; goto out; @@ -741,232 +1070,402 @@ retry: if (ifp->regen_count++ >= idev->cnf.regen_max_retry) { idev->cnf.use_tempaddr = -1; /*XXX*/ spin_unlock_bh(&ifp->lock); - write_unlock(&idev->lock); - printk(KERN_WARNING - "ipv6_create_tempaddr(): regeneration time exceeded. disabled temporary address support.\n"); + write_unlock_bh(&idev->lock); + pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", + __func__); in6_dev_put(idev); ret = -1; goto out; } in6_ifa_hold(ifp); memcpy(addr.s6_addr, ifp->addr.s6_addr, 8); - if (__ipv6_try_regen_rndid(idev, tmpaddr) < 0) { - spin_unlock_bh(&ifp->lock); - write_unlock(&idev->lock); - printk(KERN_WARNING - "ipv6_create_tempaddr(): regeneration of randomized interface id failed.\n"); - in6_ifa_put(ifp); - in6_dev_put(idev); - ret = -1; - goto out; - } + __ipv6_try_regen_rndid(idev, tmpaddr); memcpy(&addr.s6_addr[8], idev->rndid, 8); + age = (now - ifp->tstamp) / HZ; tmp_valid_lft = min_t(__u32, ifp->valid_lft, - idev->cnf.temp_valid_lft); - tmp_prefered_lft = min_t(__u32, - ifp->prefered_lft, - idev->cnf.temp_prefered_lft - desync_factor / HZ); + idev->cnf.temp_valid_lft + age); + tmp_prefered_lft = min_t(__u32, + ifp->prefered_lft, + idev->cnf.temp_prefered_lft + age - + 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); - write_unlock(&idev->lock); - ift = !max_addresses || - ipv6_count_addresses(idev) < max_addresses ? - ipv6_add_addr(idev, &addr, tmp_plen, - ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, IFA_F_TEMPORARY) : NULL; - if (!ift || IS_ERR(ift)) { + regen_advance = idev->cnf.regen_max_retry * + idev->cnf.dad_transmits * + NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ; + write_unlock_bh(&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. + * Use age calculation as in addrconf_verify to avoid unnecessary + * temporary addresses being generated. + */ + age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + if (tmp_prefered_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); - printk(KERN_INFO - "ipv6_create_tempaddr(): retry temporary address regeneration.\n"); + ret = -1; + goto out; + } + + addr_flags = IFA_F_TEMPORARY; + /* set in addrconf_prefix_rcv() */ + if (ifp->flags & IFA_F_OPTIMISTIC) + addr_flags |= IFA_F_OPTIMISTIC; + + ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen, + ipv6_addr_scope(&addr), addr_flags, + tmp_valid_lft, tmp_prefered_lft); + if (IS_ERR(ift)) { + in6_ifa_put(ifp); + in6_dev_put(idev); + pr_info("%s: retry temporary address regeneration\n", __func__); tmpaddr = &addr; - write_lock(&idev->lock); + write_lock_bh(&idev->lock); goto retry; } spin_lock_bh(&ift->lock); 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); - addrconf_dad_start(ift, 0); + addrconf_dad_start(ift); in6_ifa_put(ift); in6_dev_put(idev); out: return ret; } -#endif /* - * Choose an appropriate source address - * should do: - * i) get an address with an appropriate scope - * ii) see if there is a specific route for the destination and use - * an address of the attached interface - * iii) don't use deprecated addresses + * Choose an appropriate source address (RFC3484) */ -static int inline ipv6_saddr_pref(const struct inet6_ifaddr *ifp, u8 invpref) -{ - int pref; - pref = ifp->flags&IFA_F_DEPRECATED ? 0 : 2; -#ifdef CONFIG_IPV6_PRIVACY - pref |= (ifp->flags^invpref)&IFA_F_TEMPORARY ? 0 : 1; +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 - return pref; -} + IPV6_SADDR_RULE_OIF, + IPV6_SADDR_RULE_LABEL, + IPV6_SADDR_RULE_PRIVACY, + IPV6_SADDR_RULE_ORCHID, + IPV6_SADDR_RULE_PREFIX, + IPV6_SADDR_RULE_MAX +}; -#ifdef CONFIG_IPV6_PRIVACY -#define IPV6_GET_SADDR_MAXSCORE(score) ((score) == 3) -#else -#define IPV6_GET_SADDR_MAXSCORE(score) (score) -#endif +struct ipv6_saddr_score { + int rule; + int addr_type; + struct inet6_ifaddr *ifa; + DECLARE_BITMAP(scorebits, IPV6_SADDR_RULE_MAX); + int scopedist; + int matchlen; +}; -int ipv6_dev_get_saddr(struct net_device *dev, - struct in6_addr *daddr, struct in6_addr *saddr) -{ - struct inet6_ifaddr *ifp = NULL; - struct inet6_ifaddr *match = NULL; - struct inet6_dev *idev; +struct ipv6_saddr_dst { + const struct in6_addr *addr; + int ifindex; int scope; - int err; - int hiscore = -1, score; + int label; + unsigned int prefs; +}; - scope = ipv6_addr_scope(daddr); +static inline int ipv6_saddr_preferred(int type) +{ + if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|IPV6_ADDR_LOOPBACK)) + return 1; + return 0; +} - /* - * known dev - * search dev and walk through dev addresses - */ +static int ipv6_get_saddr_eval(struct net *net, + struct ipv6_saddr_score *score, + struct ipv6_saddr_dst *dst, + int i) +{ + int ret; - if (dev) { - if (dev->flags & IFF_LOOPBACK) - scope = IFA_HOST; + 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; + } - read_lock(&addrconf_lock); - idev = __in6_dev_get(dev); - if (idev) { - read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == scope) { - if (ifp->flags&IFA_F_TENTATIVE) - continue; -#ifdef CONFIG_IPV6_PRIVACY - score = ipv6_saddr_pref(ifp, idev->cnf.use_tempaddr > 1 ? IFA_F_TEMPORARY : 0); -#else - score = ipv6_saddr_pref(ifp, 0); + 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 destination. + * | 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 - if (score <= hiscore) - continue; - - if (match) - in6_ifa_put(match); - match = ifp; - hiscore = score; - in6_ifa_hold(ifp); - - if (IPV6_GET_SADDR_MAXSCORE(score)) { - read_unlock_bh(&idev->lock); - read_unlock(&addrconf_lock); - goto out; - } - } - } - read_unlock_bh(&idev->lock); - } - read_unlock(&addrconf_lock); + 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; + case IPV6_SADDR_RULE_PRIVACY: + { + /* Rule 7: Prefer public address + * Note: prefer temporary 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; + } + 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 */ + ret = ipv6_addr_diff(&score->ifa->addr, dst->addr); + if (ret > score->ifa->prefix_len) + ret = score->ifa->prefix_len; + score->matchlen = ret; + break; + default: + ret = 0; } - if (scope == IFA_LINK) - goto out; + if (ret) + __set_bit(i, score->scorebits); + score->rule = i; +out: + return ret; +} - /* - * dev == NULL or search failed for specified dev - */ +int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, + const struct in6_addr *daddr, unsigned int prefs, + struct in6_addr *saddr) +{ + struct ipv6_saddr_score scores[2], + *score = &scores[0], *hiscore = &scores[1]; + 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; + + hiscore->rule = -1; + hiscore->ifa = NULL; + + rcu_read_lock(); + + for_each_netdev_rcu(net, dev) { + struct inet6_dev *idev; + + /* Candidate Source Address (section 4) + * - multicast and link-local destination address, + * the set of candidate source address MUST only + * include addresses assigned to interfaces + * belonging to the same link as the outgoing + * interface. + * (- For site-local destination addresses, the + * set of candidate source addresses MUST only + * include addresses assigned to interfaces + * belonging to the same site as the outgoing + * interface.) + */ + if (((dst_type & IPV6_ADDR_MULTICAST) || + dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) && + dst.ifindex && dev->ifindex != dst.ifindex) + continue; - read_lock(&dev_base_lock); - read_lock(&addrconf_lock); - for (dev = dev_base; dev; dev=dev->next) { idev = __in6_dev_get(dev); - if (idev) { - read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == scope) { - if (ifp->flags&IFA_F_TENTATIVE) - continue; -#ifdef CONFIG_IPV6_PRIVACY - score = ipv6_saddr_pref(ifp, idev->cnf.use_tempaddr > 1 ? IFA_F_TEMPORARY : 0); -#else - score = ipv6_saddr_pref(ifp, 0); -#endif - if (score <= hiscore) - continue; + if (!idev) + continue; - if (match) - in6_ifa_put(match); - match = ifp; - hiscore = score; - in6_ifa_hold(ifp); + read_lock_bh(&idev->lock); + list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + int i; + + /* + * - Tentative Address (RFC2462 section 5.4) + * - A tentative address is not considered + * "assigned to an interface" in the traditional + * sense, unless it is also flagged as optimistic. + * - Candidate Source Address (section 4) + * - In any case, anycast addresses, multicast + * addresses, and the unspecified address MUST + * NOT be included in a candidate set. + */ + if ((score->ifa->flags & IFA_F_TENTATIVE) && + (!(score->ifa->flags & IFA_F_OPTIMISTIC))) + continue; + + 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", + dev->name); + continue; + } - if (IPV6_GET_SADDR_MAXSCORE(score)) { - read_unlock_bh(&idev->lock); - goto out_unlock_base; + 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) { + if (hiscore->ifa) + in6_ifa_put(hiscore->ifa); + + in6_ifa_hold(score->ifa); + + swap(hiscore, score); + + /* restore our iterator */ + score->ifa = hiscore->ifa; + + break; } } - read_unlock_bh(&idev->lock); } +try_nextdev: + read_unlock_bh(&idev->lock); } + rcu_read_unlock(); -out_unlock_base: - read_unlock(&addrconf_lock); - read_unlock(&dev_base_lock); + if (!hiscore->ifa) + return -EADDRNOTAVAIL; -out: - err = -EADDRNOTAVAIL; - if (match) { - ipv6_addr_copy(saddr, &match->addr); - err = 0; - in6_ifa_put(match); - } - - return err; + *saddr = hiscore->ifa->addr; + in6_ifa_put(hiscore->ifa); + return 0; } +EXPORT_SYMBOL(ipv6_dev_get_saddr); - -int ipv6_get_saddr(struct dst_entry *dst, - struct in6_addr *daddr, struct in6_addr *saddr) +int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, + u32 banned_flags) { - return ipv6_dev_get_saddr(dst ? ((struct rt6_info *)dst)->rt6i_idev->dev : NULL, daddr, saddr); -} + struct inet6_ifaddr *ifp; + int err = -EADDRNOTAVAIL; + list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { + if (ifp->scope > IFA_LINK) + break; + if (ifp->scope == IFA_LINK && + !(ifp->flags & banned_flags)) { + *addr = ifp->addr; + err = 0; + break; + } + } + return err; +} -int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr) +int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, + u32 banned_flags) { struct inet6_dev *idev; int err = -EADDRNOTAVAIL; - read_lock(&addrconf_lock); - if ((idev = __in6_dev_get(dev)) != NULL) { - struct inet6_ifaddr *ifp; - + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { - ipv6_addr_copy(addr, &ifp->addr); - err = 0; - break; - } - } + err = __ipv6_get_lladdr(idev, addr, banned_flags); read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); return err; } @@ -976,112 +1475,142 @@ static int ipv6_count_addresses(struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) + list_for_each_entry(ifp, &idev->addr_list, if_list) cnt++; read_unlock_bh(&idev->lock); return cnt; } -int ipv6_chk_addr(struct in6_addr *addr, struct net_device *dev, int strict) +int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) { - struct inet6_ifaddr * ifp; - u8 hash = ipv6_addr_hash(addr); + struct inet6_ifaddr *ifp; + unsigned int hash = inet6_addr_hash(addr); - read_lock_bh(&addrconf_hash_lock); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + rcu_read_lock_bh(); + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { + 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 || - !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) - break; + !(ifp->flags&IFA_F_TENTATIVE) && + (dev == NULL || ifp->idev->dev == dev || + !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { + rcu_read_unlock_bh(); + return 1; } } - read_unlock_bh(&addrconf_hash_lock); - return ifp != NULL; + + rcu_read_unlock_bh(); + return 0; } +EXPORT_SYMBOL(ipv6_chk_addr); -static -int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *dev) +static bool 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); + unsigned int hash = inet6_addr_hash(addr); + struct inet6_ifaddr *ifp; - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { + 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; + return true; } } - return ifp != NULL; + return false; } -struct inet6_ifaddr * ipv6_get_ifaddr(struct in6_addr *addr, struct net_device *dev, int strict) +/* Compares an address/prefix_len with addresses on device @dev. + * If one is found it returns true. + */ +bool ipv6_chk_custom_prefix(const struct in6_addr *addr, + const unsigned int prefix_len, struct net_device *dev) { - struct inet6_ifaddr * ifp; - u8 hash = ipv6_addr_hash(addr); + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool ret = false; - read_lock_bh(&addrconf_hash_lock); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { - if (ipv6_addr_equal(&ifp->addr, addr)) { - if (dev == NULL || ifp->idev->dev == dev || - !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { - in6_ifa_hold(ifp); + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); + if (ret) break; - } } + read_unlock_bh(&idev->lock); } - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock(); - return ifp; + return ret; } +EXPORT_SYMBOL(ipv6_chk_custom_prefix); -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) +int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { - const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; - const struct in6_addr *sk2_rcv_saddr6 = tcp_v6_rcv_saddr(sk2); - u32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; - u32 sk2_rcv_saddr = inet_rcv_saddr(sk2); - int sk_ipv6only = ipv6_only_sock(sk); - int sk2_ipv6only = inet_v6_ipv6only(sk2); - int addr_type = ipv6_addr_type(sk_rcv_saddr6); - int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; - - if (!sk2_rcv_saddr && !sk_ipv6only) - return 1; - - if (addr_type2 == IPV6_ADDR_ANY && - !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) - return 1; + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + int onlink; - if (addr_type == IPV6_ADDR_ANY && - !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) - return 1; + onlink = 0; + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + 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); - if (sk2_rcv_saddr6 && - ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6)) - return 1; +struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, + struct net_device *dev, int strict) +{ + struct inet6_ifaddr *ifp, *result = NULL; + unsigned int hash = inet6_addr_hash(addr); - if (addr_type == IPV6_ADDR_MAPPED && - !sk2_ipv6only && - (!sk2_rcv_saddr || !sk_rcv_saddr || sk_rcv_saddr == sk2_rcv_saddr)) - return 1; + rcu_read_lock_bh(); + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { + 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)) { + result = ifp; + in6_ifa_hold(ifp); + break; + } + } + } + rcu_read_unlock_bh(); - return 0; + return result; } /* Gets referenced address, destroys ifaddr */ -void addrconf_dad_failure(struct inet6_ifaddr *ifp) +static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { - if (net_ratelimit()) - printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name); if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); - addrconf_del_timer(ifp); + addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; + if (dad_failed) + ifp->flags |= IFA_F_DADFAILED; spin_unlock_bh(&ifp->lock); + if (dad_failed) + ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); -#ifdef CONFIG_IPV6_PRIVACY } else if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); @@ -1095,18 +1624,69 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); -#endif - } else + } else { ipv6_del_addr(ifp); + } +} + +static int addrconf_dad_end(struct inet6_ifaddr *ifp) +{ + int err = -ENOENT; + + spin_lock_bh(&ifp->state_lock); + if (ifp->state == INET6_IFADDR_STATE_DAD) { + ifp->state = INET6_IFADDR_STATE_POSTDAD; + err = 0; + } + spin_unlock_bh(&ifp->state_lock); + + return err; } +void addrconf_dad_failure(struct inet6_ifaddr *ifp) +{ + struct inet6_dev *idev = ifp->idev; + + if (addrconf_dad_end(ifp)) { + in6_ifa_put(ifp); + return; + } + + net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", + ifp->idev->dev->name, &ifp->addr); + + 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; + + pr_info("%s: IPv6 being disabled!\n", + ifp->idev->dev->name); + } + } + + spin_lock_bh(&ifp->state_lock); + /* transition from _POSTDAD to _ERRDAD */ + ifp->state = INET6_IFADDR_STATE_ERRDAD; + spin_unlock_bh(&ifp->state_lock); + + addrconf_mod_dad_work(ifp, 0); +} /* Join to solicited addr multicast group. */ -void addrconf_join_solict(struct net_device *dev, struct in6_addr *addr) +void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; + ASSERT_RTNL(); + if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1114,10 +1694,12 @@ void addrconf_join_solict(struct net_device *dev, struct in6_addr *addr) ipv6_dev_mc_inc(dev, &maddr); } -void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr) +void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; + ASSERT_RTNL(); + if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; @@ -1128,6 +1710,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr) static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + + ASSERT_RTNL(); + + if (ifp->prefix_len >= 127) /* RFC 6164 */ + return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; @@ -1137,58 +1724,150 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + + ASSERT_RTNL(); + + if (ifp->prefix_len >= 127) /* RFC 6164 */ + return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; __ipv6_dev_ac_dec(ifp->idev, &addr); } +static int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) +{ + if (dev->addr_len != ETH_ALEN) + return -1; + memcpy(eui, dev->dev_addr, 3); + memcpy(eui + 5, dev->dev_addr + 3, 3); + + /* + * The zSeries OSA network cards can be shared among various + * OS instances, but the OSA cards have only one MAC address. + * This leads to duplicate address conflicts in conjunction + * with IPv6 if more than one instance uses the same card. + * + * The driver for these cards can deliver a unique 16-bit + * identifier for each instance sharing the same card. It is + * placed instead of 0xFFFE in the interface identifier. The + * "u" bit of the interface identifier is not inverted in this + * case. Hence the resulting interface identifier has local + * scope according to RFC2373. + */ + if (dev->dev_id) { + eui[3] = (dev->dev_id >> 8) & 0xFF; + eui[4] = dev->dev_id & 0xFF; + } else { + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[0] ^= 2; + } + return 0; +} + +static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) +{ + if (dev->addr_len != IEEE802154_ADDR_LEN) + return -1; + memcpy(eui, dev->dev_addr, 8); + eui[0] ^= 2; + return 0; +} + +static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev) +{ + union fwnet_hwaddr *ha; + + if (dev->addr_len != FWNET_ALEN) + return -1; + + ha = (union fwnet_hwaddr *)dev->dev_addr; + + memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id)); + eui[0] ^= 2; + return 0; +} + +static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev) +{ + /* XXX: inherit EUI-64 from other interface -- yoshfuji */ + if (dev->addr_len != ARCNET_ALEN) + return -1; + memset(eui, 0, 7); + eui[7] = *(u8 *)dev->dev_addr; + return 0; +} + +static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) +{ + if (dev->addr_len != INFINIBAND_ALEN) + return -1; + memcpy(eui, dev->dev_addr + 12, 8); + eui[0] |= 2; + return 0; +} + +static int __ipv6_isatap_ifid(u8 *eui, __be32 addr) +{ + if (addr == 0) + return -1; + 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; +} + +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 addrconf_ifid_gre(u8 *eui, struct net_device *dev) +{ + return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); +} + +static int addrconf_ifid_ip6tnl(u8 *eui, struct net_device *dev) +{ + memcpy(eui, dev->perm_addr, 3); + memcpy(eui + 5, dev->perm_addr + 3, 3); + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[0] ^= 2; + return 0; +} + static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: - case ARPHRD_IEEE802_TR: - if (dev->addr_len != ETH_ALEN) - return -1; - memcpy(eui, dev->dev_addr, 3); - memcpy(eui + 5, dev->dev_addr + 3, 3); - - /* - * The zSeries OSA network cards can be shared among various - * OS instances, but the OSA cards have only one MAC address. - * This leads to duplicate address conflicts in conjunction - * with IPv6 if more than one instance uses the same card. - * - * The driver for these cards can deliver a unique 16-bit - * identifier for each instance sharing the same card. It is - * placed instead of 0xFFFE in the interface identifier. The - * "u" bit of the interface identifier is not inverted in this - * case. Hence the resulting interface identifier has local - * scope according to RFC2373. - */ - if (dev->dev_id) { - eui[3] = (dev->dev_id >> 8) & 0xFF; - eui[4] = dev->dev_id & 0xFF; - } else { - eui[3] = 0xFF; - eui[4] = 0xFE; - eui[0] ^= 2; - } - return 0; + return addrconf_ifid_eui48(eui, dev); case ARPHRD_ARCNET: - /* XXX: inherit EUI-64 from other interface -- yoshfuji */ - if (dev->addr_len != ARCNET_ALEN) - return -1; - memset(eui, 0, 7); - eui[7] = *(u8*)dev->dev_addr; - return 0; + return addrconf_ifid_arcnet(eui, dev); case ARPHRD_INFINIBAND: - if (dev->addr_len != INFINIBAND_ALEN) - return -1; - memcpy(eui, dev->dev_addr + 12, 8); - eui[0] |= 2; - return 0; + return addrconf_ifid_infiniband(eui, dev); + case ARPHRD_SIT: + return addrconf_ifid_sit(eui, dev); + case ARPHRD_IPGRE: + return addrconf_ifid_gre(eui, dev); + case ARPHRD_6LOWPAN: + case ARPHRD_IEEE802154: + return addrconf_ifid_eui64(eui, dev); + case ARPHRD_IEEE1394: + return addrconf_ifid_ieee1394(eui, dev); + case ARPHRD_TUNNEL6: + return addrconf_ifid_ip6tnl(eui, dev); } return -1; } @@ -1199,7 +1878,9 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { + list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { + if (ifp->scope > IFA_LINK) + break; if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { memcpy(eui, ifp->addr.s6_addr+8, 8); err = 0; @@ -1210,38 +1891,12 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) return err; } -#ifdef CONFIG_IPV6_PRIVACY /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */ -static int __ipv6_regen_rndid(struct inet6_dev *idev) +static void __ipv6_regen_rndid(struct inet6_dev *idev) { - struct net_device *dev; - struct scatterlist sg[2]; - - sg_set_buf(&sg[0], idev->entropy, 8); - sg_set_buf(&sg[1], idev->work_eui64, 8); - - dev = idev->dev; - - if (ipv6_generate_eui64(idev->work_eui64, dev)) { - printk(KERN_INFO - "__ipv6_regen_rndid(idev=%p): cannot get EUI64 identifier; use random bytes.\n", - idev); - get_random_bytes(idev->work_eui64, sizeof(idev->work_eui64)); - } regen: - spin_lock(&md5_tfm_lock); - if (unlikely(md5_tfm == NULL)) { - spin_unlock(&md5_tfm_lock); - return -1; - } - crypto_digest_init(md5_tfm); - crypto_digest_update(md5_tfm, sg, 2); - crypto_digest_final(md5_tfm, idev->work_digest); - spin_unlock(&md5_tfm_lock); - - memcpy(idev->rndid, &idev->work_digest[0], 8); + get_random_bytes(idev->rndid, sizeof(idev->rndid)); idev->rndid[0] &= ~0x02; - memcpy(idev->entropy, &idev->work_digest[8], 8); /* * <draft-ietf-ipngwg-temp-addresses-v2-00.txt>: @@ -1249,12 +1904,12 @@ 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 */ - if (idev->rndid[0] == 0xfd && + if (idev->rndid[0] == 0xfd && (idev->rndid[1]&idev->rndid[2]&idev->rndid[3]&idev->rndid[4]&idev->rndid[5]&idev->rndid[6]) == 0xff && (idev->rndid[7]&0x80)) goto regen; @@ -1264,8 +1919,6 @@ regen: if ((idev->rndid[2]|idev->rndid[3]|idev->rndid[4]|idev->rndid[5]|idev->rndid[6]|idev->rndid[7]) == 0x00) goto regen; } - - return 0; } static void ipv6_regen_rndid(unsigned long data) @@ -1273,22 +1926,22 @@ static void ipv6_regen_rndid(unsigned long data) struct inet6_dev *idev = (struct inet6_dev *) data; unsigned long expires; - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); write_lock_bh(&idev->lock); if (idev->dead) goto out; - if (__ipv6_regen_rndid(idev) < 0) - goto out; - + __ipv6_regen_rndid(idev); + expires = jiffies + - idev->cnf.temp_prefered_lft * HZ - - idev->cnf.regen_max_retry * idev->cnf.dad_transmits * idev->nd_parms->retrans_time - desync_factor; + idev->cnf.temp_prefered_lft * HZ - + idev->cnf.regen_max_retry * idev->cnf.dad_transmits * + NEIGH_VAR(idev->nd_parms, RETRANS_TIME) - + idev->cnf.max_desync_factor * HZ; if (time_before(expires, jiffies)) { - printk(KERN_WARNING - "ipv6_regen_rndid(): too short regeneration interval; timer disabled for %s.\n", - idev->dev->name); + pr_warn("%s: too short regeneration interval; timer disabled for %s\n", + __func__, idev->dev->name); goto out; } @@ -1297,18 +1950,15 @@ static void ipv6_regen_rndid(unsigned long data) out: write_unlock_bh(&idev->lock); - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); in6_dev_put(idev); } -static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) { - int ret = 0; - +static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr) +{ if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0) - ret = __ipv6_regen_rndid(idev); - return ret; + __ipv6_regen_rndid(idev); } -#endif /* * Add prefix route. @@ -1318,67 +1968,81 @@ static void addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, unsigned long expires, u32 flags) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_PREFIX, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_expires = expires, + .fc_dst_len = plen, + .fc_flags = RTF_UP | flags, + .fc_nlinfo.nl_net = dev_net(dev), + .fc_protocol = RTPROT_KERNEL, + }; - memset(&rtmsg, 0, sizeof(rtmsg)); - ipv6_addr_copy(&rtmsg.rtmsg_dst, pfx); - rtmsg.rtmsg_dst_len = plen; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; - rtmsg.rtmsg_ifindex = dev->ifindex; - rtmsg.rtmsg_info = expires; - rtmsg.rtmsg_flags = RTF_UP|flags; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; + cfg.fc_dst = *pfx; /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ - if (dev->type == ARPHRD_SIT && (dev->flags&IFF_POINTOPOINT)) - rtmsg.rtmsg_flags |= RTF_NONEXTHOP; +#if IS_ENABLED(CONFIG_IPV6_SIT) + if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) + cfg.fc_flags |= RTF_NONEXTHOP; +#endif - ip6_route_add(&rtmsg, NULL, NULL, NULL); + ip6_route_add(&cfg); } -/* Create "default" multicast route to the interface */ - -static void addrconf_add_mroute(struct net_device *dev) -{ - struct in6_rtmsg rtmsg; - - memset(&rtmsg, 0, sizeof(rtmsg)); - ipv6_addr_set(&rtmsg.rtmsg_dst, - htonl(0xFF000000), 0, 0, 0); - rtmsg.rtmsg_dst_len = 8; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; - rtmsg.rtmsg_ifindex = dev->ifindex; - rtmsg.rtmsg_flags = RTF_UP; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ip6_route_add(&rtmsg, NULL, NULL, NULL); -} -static void sit_route_add(struct net_device *dev) +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 in6_rtmsg rtmsg; + struct fib6_node *fn; + struct rt6_info *rt = NULL; + struct fib6_table *table; - memset(&rtmsg, 0, sizeof(rtmsg)); + table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX); + if (table == NULL) + return NULL; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; + read_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 ((rt->rt6i_flags & noflags) != 0) + continue; + dst_hold(&rt->dst); + break; + } +out: + read_unlock_bh(&table->tb6_lock); + return rt; +} - /* prefix length - 96 bits "::d.d.d.d" */ - rtmsg.rtmsg_dst_len = 96; - rtmsg.rtmsg_flags = RTF_UP|RTF_NONEXTHOP; - rtmsg.rtmsg_ifindex = dev->ifindex; - ip6_route_add(&rtmsg, NULL, NULL, NULL); -} +/* Create "default" multicast route to the interface */ -static void addrconf_add_lroute(struct net_device *dev) +static void addrconf_add_mroute(struct net_device *dev) { - struct in6_addr addr; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_LOCAL, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_dst_len = 8, + .fc_flags = RTF_UP, + .fc_nlinfo.nl_net = dev_net(dev), + }; - ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - addrconf_prefix_route(&addr, 64, dev, 0, 0); + ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); + + ip6_route_add(&cfg); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -1387,33 +2051,103 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) ASSERT_RTNL(); - if ((idev = ipv6_find_idev(dev)) == NULL) - return NULL; + idev = ipv6_find_idev(dev); + if (!idev) + return ERR_PTR(-ENOBUFS); + + if (idev->cnf.disable_ipv6) + 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) +static void manage_tempaddrs(struct inet6_dev *idev, + struct inet6_ifaddr *ifp, + __u32 valid_lft, __u32 prefered_lft, + bool create, unsigned long now) +{ + u32 flags; + struct inet6_ifaddr *ift; + + read_lock_bh(&idev->lock); + /* update all temporary addresses in the list */ + list_for_each_entry(ift, &idev->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 = idev->cnf.temp_valid_lft - age; + if (max_valid < 0) + max_valid = 0; + + max_prefered = idev->cnf.temp_prefered_lft - + idev->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; + 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); + } + + if ((create || list_empty(&idev->tempaddr_list)) && + idev->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. + */ + read_unlock_bh(&idev->lock); + ipv6_create_tempaddr(ifp, NULL); + } else { + read_unlock_bh(&idev->lock); + } +} + +void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; __u32 valid_lft; __u32 prefered_lft; int addr_type; - unsigned long rt_expires; struct inet6_dev *in6_dev; + struct net *net = dev_net(dev); pinfo = (struct prefix_info *) opt; - + if (len < sizeof(struct prefix_info)) { - ADBG(("addrconf: prefix option too short\n")); + ADBG("addrconf: prefix option too short\n"); return; } - + /* * Validation checks ([ADDRCONF], page 19) */ @@ -1427,16 +2161,15 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) prefered_lft = ntohl(pinfo->prefered); if (prefered_lft > valid_lft) { - if (net_ratelimit()) - printk(KERN_WARNING "addrconf: prefix option has invalid lifetime\n"); + net_warn_ratelimited("addrconf: prefix option has invalid lifetime\n"); return; } in6_dev = in6_dev_get(dev); if (in6_dev == NULL) { - if (net_ratelimit()) - printk(KERN_DEBUG "addrconf: device %s not configured\n", dev->name); + net_dbg_ratelimited("addrconf: device %s not configured\n", + dev->name); return; } @@ -1446,90 +2179,126 @@ 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 = 0; - else - rt_expires = jiffies + valid_lft * 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, NULL, NULL, NULL); - rt = NULL; - } else { - rt->rt6i_expires = 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 = addrconf_get_prefix_route(&pinfo->prefix, + pinfo->prefix_len, + dev, + RTF_ADDRCONF | RTF_PREFIX_RT, + RTF_GATEWAY | RTF_DEFAULT); + + if (rt) { + /* Autoconf prefix route */ + if (valid_lft == 0) { + ip6_del_rt(rt); + rt = NULL; + } else if (addrconf_finite_timeout(rt_expires)) { + /* not infinity */ + rt6_set_expires(rt, jiffies + rt_expires); + } else { + rt6_clean_expires(rt); } } 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, rt_expires, RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT); + dev, expires, flags); } - if (rt) - dst_release(&rt->u.dst); + ip6_rt_put(rt); } /* Try to figure out our local address for this prefix */ if (pinfo->autoconf && in6_dev->cnf.autoconf) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp; struct in6_addr addr; int create = 0, update_lft = 0; + bool tokenized = false; if (pinfo->prefix_len == 64) { memcpy(&addr, &pinfo->prefix, 8); - if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && - ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { + + if (!ipv6_addr_any(&in6_dev->token)) { + read_lock_bh(&in6_dev->lock); + memcpy(addr.s6_addr + 8, + in6_dev->token.s6_addr + 8, 8); + read_unlock_bh(&in6_dev->lock); + tokenized = true; + } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && + ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { in6_dev_put(in6_dev); return; } goto ok; } - if (net_ratelimit()) - printk(KERN_DEBUG "IPv6 addrconf: prefix with wrong length %d\n", - pinfo->prefix_len); + net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n", + pinfo->prefix_len); in6_dev_put(in6_dev); return; ok: - ifp = ipv6_get_ifaddr(&addr, dev, 1); + ifp = ipv6_get_ifaddr(net, &addr, dev, 1); if (ifp == NULL && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; + u32 addr_flags = 0; + +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + if (in6_dev->cnf.optimistic_dad && + !net->ipv6.devconf_all->forwarding && sllao) + addr_flags = IFA_F_OPTIMISTIC; +#endif /* Do not allow to create too much of autoconfigured * addresses; this would be too easy way to crash kernel. */ if (!max_addresses || ipv6_count_addresses(in6_dev) < max_addresses) - ifp = ipv6_add_addr(in6_dev, &addr, pinfo->prefix_len, - addr_type&IPV6_ADDR_SCOPE_MASK, 0); + ifp = ipv6_add_addr(in6_dev, &addr, NULL, + pinfo->prefix_len, + addr_type&IPV6_ADDR_SCOPE_MASK, + addr_flags, valid_lft, + prefered_lft); - if (!ifp || IS_ERR(ifp)) { + if (IS_ERR_OR_NULL(ifp)) { in6_dev_put(in6_dev); return; } - update_lft = create = 1; + update_lft = 0; + create = 1; + spin_lock_bh(&ifp->lock); + ifp->flags |= IFA_F_MANAGETEMPADDR; ifp->cstamp = jiffies; - addrconf_dad_start(ifp, RTF_ADDRCONF|RTF_PREFIX_RT); + ifp->tokenized = tokenized; + spin_unlock_bh(&ifp->lock); + addrconf_dad_start(ifp); } if (ifp) { - int flags; + u32 flags; unsigned long now; -#ifdef CONFIG_IPV6_PRIVACY - struct inet6_ifaddr *ift; -#endif u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ @@ -1539,20 +2308,22 @@ ok: stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!update_lft && stored_lft) { - if (valid_lft > MIN_VALID_LIFETIME || - valid_lft > stored_lft) - update_lft = 1; - else if (stored_lft <= MIN_VALID_LIFETIME) { - /* valid_lft <= stored_lft is always true */ - /* XXX: IPsec */ - update_lft = 0; - } else { - valid_lft = MIN_VALID_LIFETIME; - if (valid_lft < prefered_lft) - prefered_lft = valid_lft; - update_lft = 1; - } + if (!update_lft && !create && stored_lft) { + const u32 minimum_lft = min( + stored_lft, (u32)MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; } if (update_lft) { @@ -1568,43 +2339,11 @@ ok: } else spin_unlock(&ifp->lock); -#ifdef CONFIG_IPV6_PRIVACY - read_lock_bh(&in6_dev->lock); - /* update all temporary addresses in the list */ - for (ift=in6_dev->tempaddr_list; ift; ift=ift->tmp_next) { - /* - * 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. - */ - 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; - spin_unlock(&ift->lock); - if (!(flags&IFA_F_TENTATIVE)) - ipv6_ifa_notify(0, ift); - } + manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, + create, now); - if (create && in6_dev->cnf.use_tempaddr > 0) { - /* - * When a new public address is created as described in [ADDRCONF], - * also create a new temporary address. - */ - read_unlock_bh(&in6_dev->lock); - ipv6_create_tempaddr(ifp, NULL); - } else { - read_unlock_bh(&in6_dev->lock); - } -#endif in6_ifa_put(ifp); - addrconf_verify(0); + addrconf_verify(); } } inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo); @@ -1616,7 +2355,7 @@ 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; @@ -1628,15 +2367,16 @@ 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(ireq.ifr6_ifindex); + dev = __dev_get_by_index(net, ireq.ifr6_ifindex); err = -ENODEV; if (dev == NULL) goto err_exit; +#if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT) { + const struct net_device_ops *ops = dev->netdev_ops; struct ifreq ifr; - mm_segment_t oldfs; struct ip_tunnel_parm p; err = -EADDRNOTAVAIL; @@ -1650,19 +2390,26 @@ 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; + + if (ops->ndo_do_ioctl) { + mm_segment_t oldfs = get_fs(); - oldfs = get_fs(); set_fs(KERNEL_DS); - err = dev->do_ioctl(dev, &ifr, SIOCADDTUNNEL); - set_fs(oldfs); + set_fs(KERNEL_DS); + err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); + set_fs(oldfs); + } else + err = -EOPNOTSUPP; if (err == 0) { err = -ENOBUFS; - if ((dev = __dev_get_by_name(p.name)) == NULL) + dev = __dev_get_by_name(net, p.name); + if (!dev) goto err_exit; err = dev_open(dev); } } +#endif err_exit: rtnl_unlock(); @@ -1672,62 +2419,116 @@ err_exit: /* * Manual configuration of address on an interface */ -static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen) +static int inet6_addr_add(struct net *net, int ifindex, + const struct in6_addr *pfx, + const struct in6_addr *peer_pfx, + unsigned int plen, __u32 ifa_flags, + __u32 prefered_lft, __u32 valid_lft) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; int scope; + u32 flags; + clock_t expires; + unsigned long timeout; ASSERT_RTNL(); - - if ((dev = __dev_get_by_index(ifindex)) == NULL) + + if (plen > 128) + return -EINVAL; + + /* check the lifetime */ + if (!valid_lft || prefered_lft > valid_lft) + return -EINVAL; + + if (ifa_flags & IFA_F_MANAGETEMPADDR && plen != 64) + return -EINVAL; + + dev = __dev_get_by_index(net, ifindex); + if (!dev) return -ENODEV; - - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - if ((idev = addrconf_add_dev(dev)) == NULL) - return -ENOBUFS; + idev = addrconf_add_dev(dev); + if (IS_ERR(idev)) + return PTR_ERR(idev); scope = ipv6_addr_scope(pfx); - ifp = ipv6_add_addr(idev, pfx, plen, scope, 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; + ifa_flags |= IFA_F_PERMANENT; + } + + 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, peer_pfx, plen, scope, ifa_flags, + valid_lft, prefered_lft); + if (!IS_ERR(ifp)) { - addrconf_dad_start(ifp, 0); + if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, + expires, flags); + } + + /* + * Note that section 3.1 of RFC 4429 indicates + * that the Optimistic flag should not be set for + * manually configured addresses + */ + addrconf_dad_start(ifp); + if (ifa_flags & IFA_F_MANAGETEMPADDR) + manage_tempaddrs(idev, ifp, valid_lft, prefered_lft, + true, jiffies); in6_ifa_put(ifp); + addrconf_verify_rtnl(); return 0; } 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, u32 ifa_flags, + const 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(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) return -ENXIO; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; ifp=ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->prefix_len == plen && ipv6_addr_equal(pfx, &ifp->addr)) { in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); - - ipv6_del_addr(ifp); - /* If the last address is deleted administratively, - disable IPv6 on this interface. - */ - if (idev->addr_list == NULL) - addrconf_ifdown(idev->dev, 1); + if (!(ifp->flags & IFA_F_TEMPORARY) && + (ifa_flags & IFA_F_MANAGETEMPADDR)) + manage_tempaddrs(idev, ifp, 0, 0, false, + jiffies); + ipv6_del_addr(ifp); + addrconf_verify_rtnl(); return 0; } } @@ -1736,46 +2537,68 @@ 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; - - if (!capable(CAP_NET_ADMIN)) + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - + if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; rtnl_lock(); - err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen); + err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, + 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; - - if (!capable(CAP_NET_ADMIN)) + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) 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, 0, &ireq.ifr6_addr, + ireq.ifr6_prefixlen); rtnl_unlock(); return err; } +static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, + int plen, int scope) +{ + struct inet6_ifaddr *ifp; + + ifp = ipv6_add_addr(idev, addr, NULL, plen, + scope, IFA_F_PERMANENT, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + if (!IS_ERR(ifp)) { + spin_lock_bh(&ifp->lock); + ifp->flags &= ~IFA_F_TENTATIVE; + spin_unlock_bh(&ifp->lock); + ipv6_ifa_notify(RTM_NEWADDR, ifp); + in6_ifa_put(ifp); + } +} + +#if IS_ENABLED(CONFIG_IPV6_SIT) static void sit_add_v4_addrs(struct inet6_dev *idev) { - struct inet6_ifaddr * ifp; struct in6_addr addr; struct net_device *dev; - int scope; + struct net *net = dev_net(idev->dev); + int scope, plen; + u32 pflags = 0; ASSERT_RTNL(); @@ -1785,31 +2608,27 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (idev->dev->flags&IFF_POINTOPOINT) { addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; + plen = 64; } else { scope = IPV6_ADDR_COMPATv4; + plen = 96; + pflags |= RTF_NONEXTHOP; } if (addr.s6_addr32[3]) { - ifp = ipv6_add_addr(idev, &addr, 128, scope, IFA_F_PERMANENT); - if (!IS_ERR(ifp)) { - spin_lock_bh(&ifp->lock); - ifp->flags &= ~IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); - ipv6_ifa_notify(RTM_NEWADDR, ifp); - in6_ifa_put(ifp); - } + add_addr(idev, &addr, plen, scope); + addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags); return; } - for (dev = dev_base; dev != NULL; dev = dev->next) { - struct in_device * in_dev = __in_dev_get_rtnl(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; + struct in_ifaddr *ifa; int flag = scope; for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { - int plen; addr.s6_addr32[3] = ifa->ifa_local; @@ -1820,56 +2639,91 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) continue; flag |= IFA_HOST; } - if (idev->dev->flags&IFF_POINTOPOINT) - plen = 64; - else - plen = 96; - - ifp = ipv6_add_addr(idev, &addr, plen, flag, - IFA_F_PERMANENT); - if (!IS_ERR(ifp)) { - spin_lock_bh(&ifp->lock); - ifp->flags &= ~IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); - ipv6_ifa_notify(RTM_NEWADDR, ifp); - in6_ifa_put(ifp); - } + + add_addr(idev, &addr, plen, flag); + addrconf_prefix_route(&addr, plen, idev->dev, 0, + pflags); } } - } + } } +#endif static void init_loopback(struct net_device *dev) { struct inet6_dev *idev; - struct inet6_ifaddr * ifp; + struct net_device *sp_dev; + struct inet6_ifaddr *sp_ifa; + struct rt6_info *sp_rt; /* ::1 */ ASSERT_RTNL(); if ((idev = ipv6_find_idev(dev)) == NULL) { - printk(KERN_DEBUG "init loopback: add_dev failed\n"); + pr_debug("%s: add_dev failed\n", __func__); return; } - ifp = ipv6_add_addr(idev, &in6addr_loopback, 128, IFA_HOST, IFA_F_PERMANENT); - if (!IS_ERR(ifp)) { - spin_lock_bh(&ifp->lock); - ifp->flags &= ~IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); - ipv6_ifa_notify(RTM_NEWADDR, ifp); - in6_ifa_put(ifp); + add_addr(idev, &in6addr_loopback, 128, IFA_HOST); + + /* Add routes to other interface's IPv6 addresses */ + for_each_netdev(dev_net(dev), sp_dev) { + if (!strcmp(sp_dev->name, dev->name)) + continue; + + idev = __in6_dev_get(sp_dev); + if (!idev) + continue; + + read_lock_bh(&idev->lock); + list_for_each_entry(sp_ifa, &idev->addr_list, if_list) { + + if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE)) + continue; + + if (sp_ifa->rt) { + /* This dst has been added to garbage list when + * lo device down, release this obsolete dst and + * reallocate a new router for ifa. + */ + if (sp_ifa->rt->dst.obsolete > 0) { + ip6_rt_put(sp_ifa->rt); + sp_ifa->rt = NULL; + } else { + continue; + } + } + + sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, false); + + /* Failure cases are ignored */ + if (!IS_ERR(sp_rt)) { + sp_ifa->rt = sp_rt; + ip6_ins_rt(sp_rt); + } + } + read_unlock_bh(&idev->lock); } } -static void addrconf_add_linklocal(struct inet6_dev *idev, struct in6_addr *addr) +static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp; + u32 addr_flags = IFA_F_PERMANENT; + +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + if (idev->cnf.optimistic_dad && + !dev_net(idev->dev)->ipv6.devconf_all->forwarding) + addr_flags |= IFA_F_OPTIMISTIC; +#endif - ifp = ipv6_add_addr(idev, addr, 64, IFA_LINK, IFA_F_PERMANENT); + + ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); if (!IS_ERR(ifp)) { - addrconf_dad_start(ifp, 0); + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); + addrconf_dad_start(ifp); in6_ifa_put(ifp); } } @@ -1877,21 +2731,24 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, struct in6_addr *addr static void addrconf_dev_config(struct net_device *dev) { struct in6_addr addr; - struct inet6_dev * idev; + struct inet6_dev *idev; ASSERT_RTNL(); - if ((dev->type != ARPHRD_ETHER) && + if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_FDDI) && - (dev->type != ARPHRD_IEEE802_TR) && (dev->type != ARPHRD_ARCNET) && - (dev->type != ARPHRD_INFINIBAND)) { + (dev->type != ARPHRD_INFINIBAND) && + (dev->type != ARPHRD_IEEE802154) && + (dev->type != ARPHRD_IEEE1394) && + (dev->type != ARPHRD_TUNNEL6) && + (dev->type != ARPHRD_6LOWPAN)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } idev = addrconf_add_dev(dev); - if (idev == NULL) + if (IS_ERR(idev)) return; memset(&addr, 0, sizeof(struct in6_addr)); @@ -1901,96 +2758,128 @@ static void addrconf_dev_config(struct net_device *dev) addrconf_add_linklocal(idev, &addr); } +#if IS_ENABLED(CONFIG_IPV6_SIT) static void addrconf_sit_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); - /* - * Configure the tunnel with one of our IPv4 - * addresses... we should configure all of + /* + * Configure the tunnel with one of our IPv4 + * addresses... we should configure all of * our v4 addrs in the tunnel */ if ((idev = ipv6_find_idev(dev)) == NULL) { - printk(KERN_DEBUG "init sit: add_dev failed\n"); + pr_debug("%s: add_dev failed\n", __func__); return; } - sit_add_v4_addrs(idev); - - if (dev->flags&IFF_POINTOPOINT) { - addrconf_add_mroute(dev); - addrconf_add_lroute(dev); - } else - sit_route_add(dev); -} - -static inline int -ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) -{ - struct in6_addr lladdr; + if (dev->priv_flags & IFF_ISATAP) { + struct in6_addr addr; - if (!ipv6_get_lladdr(link_dev, &lladdr)) { - addrconf_add_linklocal(idev, &lladdr); - return 0; + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) + addrconf_add_linklocal(idev, &addr); + return; } - return -1; -} -static void ip6_tnl_add_linklocal(struct inet6_dev *idev) -{ - struct net_device *link_dev; + sit_add_v4_addrs(idev); - /* first try to inherit the link-local address from the link device */ - if (idev->dev->iflink && - (link_dev = __dev_get_by_index(idev->dev->iflink))) { - if (!ipv6_inherit_linklocal(idev, link_dev)) - return; - } - /* then try to inherit it from any device */ - for (link_dev = dev_base; link_dev; link_dev = link_dev->next) { - if (!ipv6_inherit_linklocal(idev, link_dev)) - return; - } - printk(KERN_DEBUG "init ip6-ip6: add_linklocal failed\n"); + if (dev->flags&IFF_POINTOPOINT) + addrconf_add_mroute(dev); } +#endif -/* - * Autoconfigure tunnel with a link-local address so routing protocols, - * DHCPv6, MLD etc. can be run over the virtual link - */ - -static void addrconf_ip6_tnl_config(struct net_device *dev) +#if IS_ENABLED(CONFIG_NET_IPGRE) +static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; + struct in6_addr addr; ASSERT_RTNL(); - if ((idev = addrconf_add_dev(dev)) == NULL) { - printk(KERN_DEBUG "init ip6-ip6: add_dev failed\n"); + if ((idev = ipv6_find_idev(dev)) == NULL) { + pr_debug("%s: add_dev failed\n", __func__); return; } - ip6_tnl_add_linklocal(idev); - addrconf_add_mroute(dev); + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) + addrconf_add_linklocal(idev, &addr); + else + addrconf_prefix_route(&addr, 64, dev, 0, 0); } +#endif -static int addrconf_notify(struct notifier_block *this, unsigned long event, - void * data) +static int addrconf_notify(struct notifier_block *this, unsigned long event, + void *ptr) { - struct net_device *dev = (struct net_device *) data; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); + int run_pending = 0; + int err; + + switch (event) { + case NETDEV_REGISTER: + if (!idev && dev->mtu >= IPV6_MIN_MTU) { + idev = ipv6_add_dev(dev); + if (!idev) + return notifier_from_errno(-ENOMEM); + } + break; - switch(event) { case NETDEV_UP: - switch(dev->type) { + case NETDEV_CHANGE: + if (dev->flags & IFF_SLAVE) + break; + + if (event == NETDEV_UP) { + if (!addrconf_qdisc_ok(dev)) { + /* device is not ready yet. */ + pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", + dev->name); + break; + } + + if (!idev && dev->mtu >= IPV6_MIN_MTU) + idev = ipv6_add_dev(dev); + + if (idev) { + idev->if_flags |= IF_READY; + run_pending = 1; + } + } else { + if (!addrconf_qdisc_ok(dev)) { + /* device is still not ready. */ + break; + } + + if (idev) { + if (idev->if_flags & IF_READY) + /* device is already configured. */ + break; + idev->if_flags |= IF_READY; + } + + pr_info("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n", + dev->name); + + run_pending = 1; + } + + switch (dev->type) { +#if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: addrconf_sit_config(dev); break; - case ARPHRD_TUNNEL6: - addrconf_ip6_tnl_config(dev); +#endif +#if IS_ENABLED(CONFIG_NET_IPGRE) + case ARPHRD_IPGRE: + addrconf_gre_config(dev); break; +#endif case ARPHRD_LOOPBACK: init_loopback(dev); break; @@ -1998,34 +2887,51 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, default: addrconf_dev_config(dev); break; - }; + } + if (idev) { - /* If the MTU changed during the interface down, when the - interface up, the changed MTU must be reflected in the - idev as well as routers. + if (run_pending) + addrconf_dad_run(idev); + + /* + * If the MTU changed during the interface down, + * when the interface up, the changed MTU must be + * reflected in the idev as well as routers. */ - if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) { + if (idev->cnf.mtu6 != dev->mtu && + dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); idev->cnf.mtu6 = dev->mtu; } idev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, idev); - /* If the changed mtu during down is lower than IPV6_MIN_MTU - stop IPv6 on this interface. + + /* + * If the changed mtu during down is lower than + * IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) - addrconf_ifdown(dev, event != NETDEV_DOWN); + addrconf_ifdown(dev, 1); } break; case NETDEV_CHANGEMTU: - if ( idev && dev->mtu >= IPV6_MIN_MTU) { + if (idev && dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); idev->cnf.mtu6 = dev->mtu; break; } - /* MTU falled under IPV6_MIN_MTU. Stop IPv6 on this interface. */ + if (!idev && dev->mtu >= IPV6_MIN_MTU) { + idev = ipv6_add_dev(dev); + if (idev) + break; + } + + /* + * if MTU under IPV6_MIN_MTU. + * Stop IPv6 on this interface. + */ case NETDEV_DOWN: case NETDEV_UNREGISTER: @@ -2034,22 +2940,23 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ addrconf_ifdown(dev, event != NETDEV_DOWN); break; - case NETDEV_CHANGE: - break; + case NETDEV_CHANGENAME: -#ifdef CONFIG_SYSCTL if (idev) { - 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); + snmp6_unregister_dev(idev); + addrconf_sysctl_unregister(idev); + addrconf_sysctl_register(idev); + err = snmp6_register_dev(idev); + if (err) + return notifier_from_errno(err); } -#endif break; - }; + + case NETDEV_PRE_TYPE_CHANGE: + case NETDEV_POST_TYPE_CHANGE: + addrconf_type_change(dev, event); + break; + } return NOTIFY_OK; } @@ -2059,35 +2966,46 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, - .priority = 0 }; +static void addrconf_type_change(struct net_device *dev, unsigned long event) +{ + struct inet6_dev *idev; + ASSERT_RTNL(); + + idev = __in6_dev_get(dev); + + if (event == NETDEV_POST_TYPE_CHANGE) + ipv6_mc_remap(idev); + else if (event == NETDEV_PRE_TYPE_CHANGE) + ipv6_mc_unmap(idev); +} + static int addrconf_ifdown(struct net_device *dev, int how) { + struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa, **bifa; - int i; + struct inet6_ifaddr *ifa; + int state, i; ASSERT_RTNL(); - if (dev == &loopback_dev && how == 1) - how = 0; - - rt6_ifdown(dev); + rt6_ifdown(net, dev); neigh_ifdown(&nd_tbl, dev); idev = __in6_dev_get(dev); if (idev == NULL) return -ENODEV; - /* Step 1: remove reference to ipv6 device from parent device. - Do not dev_put! + /* + * Step 1: remove reference to ipv6 device from parent device. + * Do not dev_put! */ - if (how == 1) { - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = NULL; + if (how) { idev->dead = 1; - write_unlock_bh(&addrconf_lock); + + /* protected by rtnl_lock */ + RCU_INIT_POINTER(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); @@ -2095,39 +3013,37 @@ static int addrconf_ifdown(struct net_device *dev, int how) } /* Step 2: clear hash table */ - for (i=0; i<IN6_ADDR_HSIZE; i++) { - bifa = &inet6_addr_lst[i]; + for (i = 0; i < IN6_ADDR_HSIZE; i++) { + struct hlist_head *h = &inet6_addr_lst[i]; - write_lock_bh(&addrconf_hash_lock); - while ((ifa = *bifa) != NULL) { + spin_lock_bh(&addrconf_hash_lock); + restart: + hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { - *bifa = ifa->lst_next; - ifa->lst_next = NULL; - addrconf_del_timer(ifa); - in6_ifa_put(ifa); - continue; + hlist_del_init_rcu(&ifa->addr_lst); + addrconf_del_dad_work(ifa); + goto restart; } - bifa = &ifa->lst_next; } - write_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&addrconf_hash_lock); } write_lock_bh(&idev->lock); - /* Step 3: clear flags for stateless addrconf */ - if (how != 1) - idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD); + addrconf_del_rs_timer(idev); + + /* Step 2: clear flags for stateless addrconf */ + 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 */ - while ((ifa = idev->tempaddr_list) != NULL) { - idev->tempaddr_list = ifa->tmp_next; - ifa->tmp_next = NULL; - ifa->dead = 1; + /* Step 3: clear tempaddr list */ + while (!list_empty(&idev->tempaddr_list)) { + ifa = list_first_entry(&idev->tempaddr_list, + struct inet6_ifaddr, tmp_list); + list_del(&ifa->tmp_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -2139,39 +3055,43 @@ static int addrconf_ifdown(struct net_device *dev, int how) in6_ifa_put(ifa); write_lock_bh(&idev->lock); } -#endif - while ((ifa = idev->addr_list) != NULL) { - idev->addr_list = ifa->if_next; - ifa->if_next = NULL; - ifa->dead = 1; - addrconf_del_timer(ifa); + + while (!list_empty(&idev->addr_list)) { + ifa = list_first_entry(&idev->addr_list, + struct inet6_ifaddr, if_list); + addrconf_del_dad_work(ifa); + + list_del(&ifa->if_list); + write_unlock_bh(&idev->lock); - __ipv6_ifa_notify(RTM_DELADDR, ifa); + spin_lock_bh(&ifa->state_lock); + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + spin_unlock_bh(&ifa->state_lock); + + if (state != INET6_IFADDR_STATE_DEAD) { + __ipv6_ifa_notify(RTM_DELADDR, ifa); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); + } in6_ifa_put(ifa); write_lock_bh(&idev->lock); } + write_unlock_bh(&idev->lock); /* Step 5: Discard multicast list */ - - if (how == 1) + if (how) ipv6_mc_destroy_dev(idev); else ipv6_mc_down(idev); - /* Step 5: netlink notification of this interface */ idev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_DELLINK, idev); - - /* Shot the device (if unregistered) */ - if (how == 1) { -#ifdef CONFIG_SYSCTL - addrconf_sysctl_unregister(&idev->cnf); - neigh_sysctl_unregister(idev->nd_parms); -#endif + /* Last: Shot the device (if unregistered) */ + if (how) { + addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); neigh_ifdown(&nd_tbl, dev); in6_dev_put(idev); @@ -2181,131 +3101,236 @@ static int addrconf_ifdown(struct net_device *dev, int how) static void addrconf_rs_timer(unsigned long data) { - struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; + struct inet6_dev *idev = (struct inet6_dev *)data; + struct net_device *dev = idev->dev; + struct in6_addr lladdr; - if (ifp->idev->cnf.forwarding) + write_lock(&idev->lock); + if (idev->dead || !(idev->if_flags & IF_READY)) goto out; - if (ifp->idev->if_flags & IF_RA_RCVD) { - /* - * Announcement received after solicitation - * was sent - */ + if (!ipv6_accept_ra(idev)) goto out; - } - - 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) ? - ifp->idev->cnf.rtr_solicit_delay : - ifp->idev->cnf.rtr_solicit_interval); - spin_unlock(&ifp->lock); + /* Announcement received after solicitation was sent */ + if (idev->if_flags & IF_RA_RCVD) + goto out; - ipv6_addr_all_routers(&all_routers); + if (idev->rs_probes++ < idev->cnf.rtr_solicits) { + write_unlock(&idev->lock); + if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) + ndisc_send_rs(dev, &lladdr, + &in6addr_linklocal_allrouters); + else + goto put; - ndisc_send_rs(ifp->idev->dev, &ifp->addr, &all_routers); + write_lock(&idev->lock); + /* The wait after the last probe can be shorter */ + addrconf_mod_rs_timer(idev, (idev->rs_probes == + idev->cnf.rtr_solicits) ? + idev->cnf.rtr_solicit_delay : + idev->cnf.rtr_solicit_interval); } else { - spin_unlock(&ifp->lock); /* * Note: we do not support deprecated "all on-link" * assumption any longer. */ - printk(KERN_DEBUG "%s: no IPv6 routers present\n", - ifp->idev->dev->name); + pr_debug("%s: no IPv6 routers present\n", idev->dev->name); } out: - in6_ifa_put(ifp); + write_unlock(&idev->lock); +put: + in6_dev_put(idev); } /* * Duplicate Address Detection */ -static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) +static void addrconf_dad_kick(struct inet6_ifaddr *ifp) +{ + unsigned long rand_num; + struct inet6_dev *idev = ifp->idev; + + if (ifp->flags & IFA_F_OPTIMISTIC) + rand_num = 0; + else + rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); + + ifp->dad_probes = idev->cnf.dad_transmits; + addrconf_mod_dad_work(ifp, rand_num); +} + +static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; - unsigned long rand_num; addrconf_join_solict(dev, &ifp->addr); - if (ifp->prefix_len != 128 && (ifp->flags&IFA_F_PERMANENT)) - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, 0, - flags); - - net_srandom(ifp->addr.s6_addr32[3]); - rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); + prandom_seed((__force u32) ifp->addr.s6_addr32[3]); read_lock_bh(&idev->lock); - if (ifp->dead) + spin_lock(&ifp->lock); + if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; - spin_lock_bh(&ifp->lock); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - !(ifp->flags&IFA_F_TENTATIVE)) { - ifp->flags &= ~IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); + idev->cnf.accept_dad < 1 || + !(ifp->flags&IFA_F_TENTATIVE) || + ifp->flags & IFA_F_NODAD) { + ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); + spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); addrconf_dad_completed(ifp); return; } - ifp->probes = idev->cnf.dad_transmits; - addrconf_mod_timer(ifp, AC_DAD, rand_num); + if (!(idev->if_flags & IF_READY)) { + spin_unlock(&ifp->lock); + read_unlock_bh(&idev->lock); + /* + * If the device is not ready: + * - keep it tentative if it is a permanent address. + * - otherwise, kill it. + */ + in6_ifa_hold(ifp); + addrconf_dad_stop(ifp, 0); + return; + } - spin_unlock_bh(&ifp->lock); + /* + * Optimistic nodes can start receiving + * Frames right away + */ + if (ifp->flags & IFA_F_OPTIMISTIC) + ip6_ins_rt(ifp->rt); + + addrconf_dad_kick(ifp); out: + spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); } -static void addrconf_dad_timer(unsigned long data) +static void addrconf_dad_start(struct inet6_ifaddr *ifp) +{ + bool begin_dad = false; + + spin_lock_bh(&ifp->state_lock); + if (ifp->state != INET6_IFADDR_STATE_DEAD) { + ifp->state = INET6_IFADDR_STATE_PREDAD; + begin_dad = true; + } + spin_unlock_bh(&ifp->state_lock); + + if (begin_dad) + addrconf_mod_dad_work(ifp, 0); +} + +static void addrconf_dad_work(struct work_struct *w) { - struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data; + struct inet6_ifaddr *ifp = container_of(to_delayed_work(w), + struct inet6_ifaddr, + dad_work); struct inet6_dev *idev = ifp->idev; - struct in6_addr unspec; struct in6_addr mcaddr; - read_lock_bh(&idev->lock); - if (idev->dead) { - read_unlock_bh(&idev->lock); + enum { + DAD_PROCESS, + DAD_BEGIN, + DAD_ABORT, + } action = DAD_PROCESS; + + rtnl_lock(); + + spin_lock_bh(&ifp->state_lock); + if (ifp->state == INET6_IFADDR_STATE_PREDAD) { + action = DAD_BEGIN; + ifp->state = INET6_IFADDR_STATE_DAD; + } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { + action = DAD_ABORT; + ifp->state = INET6_IFADDR_STATE_POSTDAD; + } + spin_unlock_bh(&ifp->state_lock); + + if (action == DAD_BEGIN) { + addrconf_dad_begin(ifp); + goto out; + } else if (action == DAD_ABORT) { + addrconf_dad_stop(ifp, 1); goto out; } - spin_lock_bh(&ifp->lock); - if (ifp->probes == 0) { + + if (!ifp->dad_probes && addrconf_dad_end(ifp)) + goto out; + + write_lock_bh(&idev->lock); + if (idev->dead || !(idev->if_flags & IF_READY)) { + write_unlock_bh(&idev->lock); + goto out; + } + + spin_lock(&ifp->lock); + if (ifp->state == INET6_IFADDR_STATE_DEAD) { + spin_unlock(&ifp->lock); + write_unlock_bh(&idev->lock); + goto out; + } + + if (ifp->dad_probes == 0) { /* * DAD was successful */ - ifp->flags &= ~IFA_F_TENTATIVE; - spin_unlock_bh(&ifp->lock); - read_unlock_bh(&idev->lock); + ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); + spin_unlock(&ifp->lock); + write_unlock_bh(&idev->lock); addrconf_dad_completed(ifp); goto out; } - ifp->probes--; - addrconf_mod_timer(ifp, AC_DAD, ifp->idev->nd_parms->retrans_time); - spin_unlock_bh(&ifp->lock); - read_unlock_bh(&idev->lock); + ifp->dad_probes--; + addrconf_mod_dad_work(ifp, + NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME)); + spin_unlock(&ifp->lock); + write_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); + rtnl_unlock(); +} + +/* ifp->idev must be at least read locked */ +static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) +{ + struct inet6_ifaddr *ifpiter; + struct inet6_dev *idev = ifp->idev; + + list_for_each_entry_reverse(ifpiter, &idev->addr_list, if_list) { + if (ifpiter->scope > IFA_LINK) + break; + if (ifp != ifpiter && ifpiter->scope == IFA_LINK && + (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE| + IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) == + IFA_F_PERMANENT) + return false; + } + return true; } static void addrconf_dad_completed(struct inet6_ifaddr *ifp) { - struct net_device * dev = ifp->idev->dev; + struct net_device *dev = ifp->idev->dev; + struct in6_addr lladdr; + bool send_rs, send_mld; + + addrconf_del_dad_work(ifp); /* * Configure the address for reception. Now it is valid. @@ -2313,78 +3338,133 @@ 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.rtr_solicits > 0 && - (dev->flags&IFF_LOOPBACK) == 0 && - (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) { - struct in6_addr all_routers; + read_lock_bh(&ifp->idev->lock); + send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); + send_rs = send_mld && + ipv6_accept_ra(ifp->idev) && + ifp->idev->cnf.rtr_solicits > 0 && + (dev->flags&IFF_LOOPBACK) == 0; + read_unlock_bh(&ifp->idev->lock); - ipv6_addr_all_routers(&all_routers); + /* While dad is in progress mld report's source address is in6_addrany. + * Resend with proper ll now. + */ + if (send_mld) + ipv6_mc_dad_complete(ifp->idev); + if (send_rs) { /* * 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); + if (ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) + return; + ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters); - spin_lock_bh(&ifp->lock); - ifp->probes = 1; + write_lock_bh(&ifp->idev->lock); + spin_lock(&ifp->lock); + ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; - addrconf_mod_timer(ifp, AC_RS, ifp->idev->cnf.rtr_solicit_interval); - spin_unlock_bh(&ifp->lock); + addrconf_mod_rs_timer(ifp->idev, + ifp->idev->cnf.rtr_solicit_interval); + spin_unlock(&ifp->lock); + write_unlock_bh(&ifp->idev->lock); } } +static void addrconf_dad_run(struct inet6_dev *idev) +{ + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + spin_lock(&ifp->lock); + if (ifp->flags & IFA_F_TENTATIVE && + ifp->state == INET6_IFADDR_STATE_DAD) + addrconf_dad_kick(ifp); + spin_unlock(&ifp->lock); + } + read_unlock_bh(&idev->lock); +} + #ifdef CONFIG_PROC_FS 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) { - ifa = inet6_addr_lst[state->bucket]; - if (ifa) - break; + /* initial bucket if pos is 0 */ + if (pos == 0) { + state->bucket = 0; + state->offset = 0; } - return ifa; + + for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { + hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], + addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; + /* sync with offset */ + if (p < state->offset) { + p++; + continue; + } + state->offset++; + return ifa; + } + + /* prepare for next bucket */ + state->offset = 0; + p = 0; + } + return NULL; } -static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa) +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 && ++state->bucket < IN6_ADDR_HSIZE) { - ifa = inet6_addr_lst[state->bucket]; - goto try_again; + hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; + state->offset++; + return ifa; } - return ifa; -} -static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) -{ - struct inet6_ifaddr *ifa = if6_get_first(seq); + while (++state->bucket < IN6_ADDR_HSIZE) { + state->offset = 0; + hlist_for_each_entry_rcu_bh(ifa, + &inet6_addr_lst[state->bucket], addr_lst) { + if (!net_eq(dev_net(ifa->idev->dev), net)) + continue; + state->offset++; + return ifa; + } + } - if (ifa) - while(pos && (ifa = if6_get_next(seq, ifa)) != NULL) - --pos; - return pos ? NULL : ifa; + return NULL; } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu_bh) { - read_lock_bh(&addrconf_hash_lock); - return if6_get_idx(seq, *pos); + rcu_read_lock_bh(); + return if6_get_first(seq, *pos); } static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -2397,25 +3477,25 @@ 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(rcu_bh) { - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); } static int if6_seq_show(struct seq_file *seq, void *v) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v; - seq_printf(seq, - "%04x%04x%04x%04x%04x%04x%04x%04x %02x %02x %02x %02x %8s\n", - NIP6(ifp->addr), + seq_printf(seq, "%pi6 %02x %02x %02x %02x %8s\n", + &ifp->addr, ifp->idev->dev->ifindex, ifp->prefix_len, ifp->scope, - ifp->flags, + (u8) ifp->flags, ifp->idev->dev->name); return 0; } -static struct seq_operations if6_seq_ops = { +static const struct seq_operations if6_seq_ops = { .start = if6_seq_start, .next = if6_seq_next, .show = if6_seq_show, @@ -2424,94 +3504,115 @@ static struct seq_operations if6_seq_ops = { static int if6_seq_open(struct inode *inode, struct file *file) { - struct seq_file *seq; - int rc = -ENOMEM; - struct if6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); - - if (!s) - goto out; - memset(s, 0, sizeof(*s)); - - rc = seq_open(file, &if6_seq_ops); - if (rc) - goto out_kfree; - - seq = file->private_data; - seq->private = s; -out: - return rc; -out_kfree: - kfree(s); - goto out; + return seq_open_net(inode, file, &if6_seq_ops, + sizeof(struct if6_iter_state)); } -static struct file_operations if6_fops = { +static const struct file_operations if6_fops = { .owner = THIS_MODULE, .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 __net_init if6_proc_net_init(struct net *net) { - if (!proc_net_fops_create("if_inet6", S_IRUGO, &if6_fops)) + if (!proc_create("if_inet6", S_IRUGO, net->proc_net, &if6_fops)) return -ENOMEM; return 0; } +static void __net_exit if6_proc_net_exit(struct net *net) +{ + remove_proc_entry("if_inet6", net->proc_net); +} + +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("if_inet6"); + unregister_pernet_subsys(&if6_proc_net_ops); } #endif /* CONFIG_PROC_FS */ +#if IS_ENABLED(CONFIG_IPV6_MIP6) +/* Check if address is a home address configured on any interface. */ +int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) +{ + int ret = 0; + struct inet6_ifaddr *ifp = NULL; + unsigned int hash = inet6_addr_hash(addr); + + rcu_read_lock_bh(); + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { + 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; + } + } + rcu_read_unlock_bh(); + return ret; +} +#endif + /* * Periodic address status verification */ -static void addrconf_verify(unsigned long foo) +static void addrconf_verify_rtnl(void) { + unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; - unsigned long now, next; int i; - spin_lock_bh(&addrconf_verify_lock); - now = jiffies; - next = now + ADDR_CHECK_FREQUENCY; + ASSERT_RTNL(); - del_timer(&addr_chk_timer); + rcu_read_lock_bh(); + now = jiffies; + next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - for (i=0; i < IN6_ADDR_HSIZE; i++) { + cancel_delayed_work(&addr_chk_work); + for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - write_lock(&addrconf_hash_lock); - for (ifp=inet6_addr_lst[i]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { unsigned long age; -#ifdef CONFIG_IPV6_PRIVACY - unsigned long regen_advance; -#endif - if (ifp->flags & IFA_F_PERMANENT) + /* When setting preferred_lft to a value not zero or + * infinity, while valid_lft is infinity + * IFA_F_PERMANENT has a non-infinity life time. + */ + if ((ifp->flags & IFA_F_PERMANENT) && + (ifp->prefered_lft == INFINITY_LIFE_TIME)) continue; spin_lock(&ifp->lock); - age = (now - ifp->tstamp) / HZ; - -#ifdef CONFIG_IPV6_PRIVACY - regen_advance = ifp->idev->cnf.regen_max_retry * - ifp->idev->cnf.dad_transmits * - ifp->idev->nd_parms->retrans_time / HZ; -#endif + /* We try to batch several events at once. */ + age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (age >= ifp->valid_lft) { + if (ifp->valid_lft != INFINITY_LIFE_TIME && + age >= ifp->valid_lft) { spin_unlock(&ifp->lock); in6_ifa_hold(ifp); - write_unlock(&addrconf_hash_lock); ipv6_del_addr(ifp); goto restart; + } else if (ifp->prefered_lft == INFINITY_LIFE_TIME) { + spin_unlock(&ifp->lock); + continue; } else if (age >= ifp->prefered_lft) { - /* jiffies - ifp->tsamp > age >= ifp->prefered_lft */ + /* jiffies - ifp->tstamp > age >= ifp->prefered_lft */ int deprecate = 0; if (!(ifp->flags&IFA_F_DEPRECATED)) { @@ -2519,22 +3620,25 @@ restart: ifp->flags |= IFA_F_DEPRECATED; } - if (time_before(ifp->tstamp + ifp->valid_lft * HZ, next)) + if ((ifp->valid_lft != INFINITY_LIFE_TIME) && + (time_before(ifp->tstamp + ifp->valid_lft * HZ, next))) next = ifp->tstamp + ifp->valid_lft * HZ; spin_unlock(&ifp->lock); if (deprecate) { in6_ifa_hold(ifp); - write_unlock(&addrconf_hash_lock); ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); goto restart; } -#ifdef CONFIG_IPV6_PRIVACY } else if ((ifp->flags&IFA_F_TEMPORARY) && !(ifp->flags&IFA_F_TENTATIVE)) { + unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * + ifp->idev->cnf.dad_transmits * + NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME) / HZ; + if (age >= ifp->prefered_lft - regen_advance) { struct inet6_ifaddr *ifpub = ifp->ifpub; if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) @@ -2544,7 +3648,10 @@ restart: in6_ifa_hold(ifp); in6_ifa_hold(ifpub); spin_unlock(&ifp->lock); - write_unlock(&addrconf_hash_lock); + + spin_lock(&ifpub->lock); + ifpub->regen_count = 0; + spin_unlock(&ifpub->lock); ipv6_create_tempaddr(ifpub, ifp); in6_ifa_put(ifpub); in6_ifa_put(ifp); @@ -2553,7 +3660,6 @@ restart: } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; spin_unlock(&ifp->lock); -#endif } else { /* ifp->prefered_lft <= ifp->valid_lft */ if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) @@ -2561,281 +3667,521 @@ restart: spin_unlock(&ifp->lock); } } - write_unlock(&addrconf_hash_lock); } - addr_chk_timer.expires = time_before(next, jiffies + HZ) ? jiffies + HZ : next; - add_timer(&addr_chk_timer); - spin_unlock_bh(&addrconf_verify_lock); + next_sec = round_jiffies_up(next); + next_sched = next; + + /* If rounded timeout is accurate enough, accept it. */ + if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) + next_sched = next_sec; + + /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ + if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) + next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; + + ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", + now, next, next_sec, next_sched); + mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now); + rcu_read_unlock_bh(); } -static int -inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static void addrconf_verify_work(struct work_struct *w) { - struct rtattr **rta = arg; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); - struct in6_addr *pfx; + rtnl_lock(); + addrconf_verify_rtnl(); + rtnl_unlock(); +} - pfx = NULL; - if (rta[IFA_ADDRESS-1]) { - if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*pfx)) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_ADDRESS-1]); - } - if (rta[IFA_LOCAL-1]) { - if (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx))) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_LOCAL-1]); +static void addrconf_verify(void) +{ + mod_delayed_work(addrconf_wq, &addr_chk_work, 0); +} + +static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, + struct in6_addr **peer_pfx) +{ + struct in6_addr *pfx = NULL; + + *peer_pfx = NULL; + + if (addr) + pfx = nla_data(addr); + + if (local) { + if (pfx && nla_memcmp(local, pfx, sizeof(*pfx))) + *peer_pfx = pfx; + pfx = nla_data(local); } + + return pfx; +} + +static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { + [IFA_ADDRESS] = { .len = sizeof(struct in6_addr) }, + [IFA_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, + [IFA_FLAGS] = { .len = sizeof(u32) }, +}; + +static int +inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifaddrmsg *ifm; + struct nlattr *tb[IFA_MAX+1]; + struct in6_addr *pfx, *peer_pfx; + u32 ifa_flags; + int err; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); + if (err < 0) + return err; + + ifm = nlmsg_data(nlh); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (pfx == NULL) return -EINVAL; - return inet6_addr_del(ifm->ifa_index, pfx, ifm->ifa_prefixlen); + ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; + + /* We ignore other flags so far. */ + ifa_flags &= IFA_F_MANAGETEMPADDR; + + return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, + ifm->ifa_prefixlen); } -static int -inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, + u32 prefered_lft, u32 valid_lft) { - struct rtattr **rta = arg; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); - struct in6_addr *pfx; + u32 flags; + clock_t expires; + unsigned long timeout; + bool was_managetempaddr; + bool had_prefixroute; - pfx = NULL; - if (rta[IFA_ADDRESS-1]) { - if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*pfx)) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_ADDRESS-1]); + ASSERT_RTNL(); + + if (!valid_lft || (prefered_lft > valid_lft)) + return -EINVAL; + + if (ifa_flags & IFA_F_MANAGETEMPADDR && + (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) + return -EINVAL; + + 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; + ifa_flags |= IFA_F_PERMANENT; + } + + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; } - if (rta[IFA_LOCAL-1]) { - if (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx))) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_LOCAL-1]); + + spin_lock_bh(&ifp->lock); + was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; + had_prefixroute = ifp->flags & IFA_F_PERMANENT && + !(ifp->flags & IFA_F_NOPREFIXROUTE); + ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | + IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | + IFA_F_NOPREFIXROUTE); + ifp->flags |= ifa_flags; + ifp->tstamp = jiffies; + ifp->valid_lft = valid_lft; + ifp->prefered_lft = prefered_lft; + + spin_unlock_bh(&ifp->lock); + if (!(ifp->flags&IFA_F_TENTATIVE)) + ipv6_ifa_notify(0, ifp); + + if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, + expires, flags); + } else if (had_prefixroute) { + enum cleanup_prefix_rt_t action; + unsigned long rt_expires; + + write_lock_bh(&ifp->idev->lock); + action = check_cleanup_prefix_route(ifp, &rt_expires); + write_unlock_bh(&ifp->idev->lock); + + if (action != CLEANUP_PREFIX_RT_NOP) { + cleanup_prefix_route(ifp, rt_expires, + action == CLEANUP_PREFIX_RT_DEL); + } } + + if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) { + if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR)) + valid_lft = prefered_lft = 0; + manage_tempaddrs(ifp->idev, ifp, valid_lft, prefered_lft, + !was_managetempaddr, jiffies); + } + + addrconf_verify_rtnl(); + + return 0; +} + +static int +inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifaddrmsg *ifm; + struct nlattr *tb[IFA_MAX+1]; + struct in6_addr *pfx, *peer_pfx; + struct inet6_ifaddr *ifa; + struct net_device *dev; + u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; + u32 ifa_flags; + int err; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); + if (err < 0) + return err; + + ifm = nlmsg_data(nlh); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (pfx == NULL) return -EINVAL; - return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen); + if (tb[IFA_CACHEINFO]) { + struct ifa_cacheinfo *ci; + + ci = nla_data(tb[IFA_CACHEINFO]); + valid_lft = ci->ifa_valid; + preferred_lft = ci->ifa_prefered; + } else { + preferred_lft = INFINITY_LIFE_TIME; + valid_lft = INFINITY_LIFE_TIME; + } + + dev = __dev_get_by_index(net, ifm->ifa_index); + if (dev == NULL) + return -ENODEV; + + ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; + + /* We ignore other flags so far. */ + ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | + IFA_F_NOPREFIXROUTE; + + ifa = ipv6_get_ifaddr(net, pfx, dev, 1); + if (ifa == NULL) { + /* + * It would be best to check for !NLM_F_CREATE here but + * userspace already relies on not having to provide this. + */ + return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, + ifm->ifa_prefixlen, ifa_flags, + preferred_lft, valid_lft); + } + + if (nlh->nlmsg_flags & NLM_F_EXCL || + !(nlh->nlmsg_flags & NLM_F_REPLACE)) + err = -EEXIST; + else + err = inet6_addr_modify(ifa, ifa_flags, preferred_lft, valid_lft); + + in6_ifa_put(ifa); + + return err; } -static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 pid, u32 seq, int event, unsigned int flags) +static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u32 flags, + u8 scope, int ifindex) { struct ifaddrmsg *ifm; - struct nlmsghdr *nlh; - struct ifa_cacheinfo ci; - unsigned char *b = skb->tail; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); + ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET6; - ifm->ifa_prefixlen = ifa->prefix_len; - ifm->ifa_flags = ifa->flags; - ifm->ifa_scope = RT_SCOPE_UNIVERSE; - if (ifa->scope&IFA_HOST) - ifm->ifa_scope = RT_SCOPE_HOST; - else if (ifa->scope&IFA_LINK) - ifm->ifa_scope = RT_SCOPE_LINK; - else if (ifa->scope&IFA_SITE) - ifm->ifa_scope = RT_SCOPE_SITE; - ifm->ifa_index = ifa->idev->dev->ifindex; - RTA_PUT(skb, IFA_ADDRESS, 16, &ifa->addr); - if (!(ifa->flags&IFA_F_PERMANENT)) { - ci.ifa_prefered = ifa->prefered_lft; - ci.ifa_valid = ifa->valid_lft; - if (ci.ifa_prefered != INFINITY_LIFE_TIME) { + ifm->ifa_prefixlen = prefixlen; + ifm->ifa_flags = flags; + ifm->ifa_scope = scope; + ifm->ifa_index = ifindex; +} + +static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, + unsigned long tstamp, u32 preferred, u32 valid) +{ + struct ifa_cacheinfo ci; + + ci.cstamp = cstamp_delta(cstamp); + ci.tstamp = cstamp_delta(tstamp); + ci.ifa_prefered = preferred; + ci.ifa_valid = valid; + + return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); +} + +static inline int rt_scope(int ifa_scope) +{ + if (ifa_scope & IFA_HOST) + return RT_SCOPE_HOST; + else if (ifa_scope & IFA_LINK) + return RT_SCOPE_LINK; + else if (ifa_scope & IFA_SITE) + return RT_SCOPE_SITE; + else + return RT_SCOPE_UNIVERSE; +} + +static inline int inet6_ifaddr_msgsize(void) +{ + return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(16) /* IFA_LOCAL */ + + nla_total_size(16) /* IFA_ADDRESS */ + + nla_total_size(sizeof(struct ifa_cacheinfo)) + + nla_total_size(4) /* IFA_FLAGS */; +} + +static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, + u32 portid, u32 seq, int event, unsigned int flags) +{ + struct nlmsghdr *nlh; + u32 preferred, valid; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + if (nlh == NULL) + return -EMSGSIZE; + + put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), + ifa->idev->dev->ifindex); + + if (!((ifa->flags&IFA_F_PERMANENT) && + (ifa->prefered_lft == INFINITY_LIFE_TIME))) { + preferred = ifa->prefered_lft; + valid = ifa->valid_lft; + if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->tstamp)/HZ; - ci.ifa_prefered -= tval; - if (ci.ifa_valid != INFINITY_LIFE_TIME) - ci.ifa_valid -= tval; + if (preferred > tval) + preferred -= tval; + else + preferred = 0; + if (valid != INFINITY_LIFE_TIME) { + if (valid > tval) + valid -= tval; + else + valid = 0; + } } } else { - ci.ifa_prefered = INFINITY_LIFE_TIME; - ci.ifa_valid = INFINITY_LIFE_TIME; - } - ci.cstamp = (__u32)(TIME_DELTA(ifa->cstamp, INITIAL_JIFFIES) / HZ * 100 - + TIME_DELTA(ifa->cstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); - ci.tstamp = (__u32)(TIME_DELTA(ifa->tstamp, INITIAL_JIFFIES) / HZ * 100 - + TIME_DELTA(ifa->tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); - RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + preferred = INFINITY_LIFE_TIME; + valid = INFINITY_LIFE_TIME; + } -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (!ipv6_addr_any(&ifa->peer_addr)) { + if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 || + nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0) + goto error; + } else + if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0) + goto error; + + if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + goto error; + + if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) + goto error; + + return nlmsg_end(skb, nlh); + +error: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 pid, u32 seq, int event, u16 flags) + u32 portid, u32 seq, int event, u16 flags) { - struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - struct ifa_cacheinfo ci; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); - ifm->ifa_family = AF_INET6; - ifm->ifa_prefixlen = 128; - ifm->ifa_flags = IFA_F_PERMANENT; - ifm->ifa_scope = RT_SCOPE_UNIVERSE; - if (ipv6_addr_scope(&ifmca->mca_addr)&IFA_SITE) - ifm->ifa_scope = RT_SCOPE_SITE; - ifm->ifa_index = ifmca->idev->dev->ifindex; - RTA_PUT(skb, IFA_MULTICAST, 16, &ifmca->mca_addr); - ci.cstamp = (__u32)(TIME_DELTA(ifmca->mca_cstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifmca->mca_cstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.tstamp = (__u32)(TIME_DELTA(ifmca->mca_tstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifmca->mca_tstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.ifa_prefered = INFINITY_LIFE_TIME; - ci.ifa_valid = INFINITY_LIFE_TIME; - RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + u8 scope = RT_SCOPE_UNIVERSE; + int ifindex = ifmca->idev->dev->ifindex; + + if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) + scope = RT_SCOPE_SITE; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + if (nlh == NULL) + return -EMSGSIZE; + + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); + if (nla_put(skb, IFA_MULTICAST, 16, &ifmca->mca_addr) < 0 || + put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + return nlmsg_end(skb, nlh); } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { - struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - struct ifa_cacheinfo ci; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); - ifm->ifa_family = AF_INET6; - ifm->ifa_prefixlen = 128; - ifm->ifa_flags = IFA_F_PERMANENT; - ifm->ifa_scope = RT_SCOPE_UNIVERSE; - if (ipv6_addr_scope(&ifaca->aca_addr)&IFA_SITE) - ifm->ifa_scope = RT_SCOPE_SITE; - ifm->ifa_index = ifaca->aca_idev->dev->ifindex; - RTA_PUT(skb, IFA_ANYCAST, 16, &ifaca->aca_addr); - ci.cstamp = (__u32)(TIME_DELTA(ifaca->aca_cstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifaca->aca_cstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.tstamp = (__u32)(TIME_DELTA(ifaca->aca_tstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifaca->aca_tstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.ifa_prefered = INFINITY_LIFE_TIME; - ci.ifa_valid = INFINITY_LIFE_TIME; - RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + u8 scope = RT_SCOPE_UNIVERSE; + int ifindex = ifaca->aca_idev->dev->ifindex; + + if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) + scope = RT_SCOPE_SITE; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + if (nlh == NULL) + return -EMSGSIZE; + + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); + if (nla_put(skb, IFA_ANYCAST, 16, &ifaca->aca_addr) < 0 || + put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + return nlmsg_end(skb, nlh); } -enum addr_type_t -{ +enum addr_type_t { UNICAST_ADDR, MULTICAST_ADDR, ANYCAST_ADDR, }; +/* called with rcu_read_lock() */ +static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, enum addr_type_t type, + int s_ip_idx, int *p_ip_idx) +{ + struct ifmcaddr6 *ifmca; + struct ifacaddr6 *ifaca; + int err = 1; + int ip_idx = *p_ip_idx; + + read_lock_bh(&idev->lock); + switch (type) { + case UNICAST_ADDR: { + struct inet6_ifaddr *ifa; + + /* unicast address incl. temp addr */ + list_for_each_entry(ifa, &idev->addr_list, if_list) { + if (++ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifaddr(skb, ifa, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWADDR, + NLM_F_MULTI); + if (err <= 0) + break; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + } + break; + } + case MULTICAST_ADDR: + /* multicast address */ + for (ifmca = idev->mc_list; ifmca; + ifmca = ifmca->next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifmcaddr(skb, ifmca, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_GETMULTICAST, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + case ANYCAST_ADDR: + /* anycast address */ + for (ifaca = idev->ac_list; ifaca; + ifaca = ifaca->aca_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifacaddr(skb, ifaca, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_GETANYCAST, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + default: + break; + } + read_unlock_bh(&idev->lock); + *p_ip_idx = ip_idx; + return err; +} + static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *net = sock_net(skb->sk); + int h, s_h; int idx, ip_idx; int s_idx, s_ip_idx; - int err = 1; struct net_device *dev; - struct inet6_dev *idev = NULL; - struct inet6_ifaddr *ifa; - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; - - s_idx = cb->args[0]; - s_ip_idx = ip_idx = cb->args[1]; - read_lock(&dev_base_lock); - - for (dev = dev_base, idx = 0; dev; dev = dev->next, idx++) { - if (idx < s_idx) - continue; - if (idx > s_idx) - s_ip_idx = 0; - ip_idx = 0; - if ((idev = in6_dev_get(dev)) == NULL) - continue; - read_lock_bh(&idev->lock); - switch (type) { - case UNICAST_ADDR: - /* unicast address incl. temp addr */ - for (ifa = idev->addr_list; ifa; - 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; - } - break; - case MULTICAST_ADDR: - /* multicast address */ - for (ifmca = idev->mc_list; ifmca; - 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; - } - break; - case ANYCAST_ADDR: - /* anycast address */ - for (ifaca = idev->ac_list; ifaca; - 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; - } - break; - default: - break; + struct inet6_dev *idev; + struct hlist_head *head; + + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + s_ip_idx = ip_idx = cb->args[2]; + + rcu_read_lock(); + cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq; + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (h > s_h || idx > s_idx) + s_ip_idx = 0; + ip_idx = 0; + idev = __in6_dev_get(dev); + if (!idev) + goto cont; + + if (in6_dump_addrs(idev, skb, cb, type, + s_ip_idx, &ip_idx) <= 0) + goto done; +cont: + idx++; } - read_unlock_bh(&idev->lock); - in6_dev_put(idev); } done: - if (err <= 0) { - read_unlock_bh(&idev->lock); - in6_dev_put(idev); - } - read_unlock(&dev_base_lock); - cb->args[0] = idx; - cb->args[1] = ip_idx; + rcu_read_unlock(); + cb->args[0] = h; + cb->args[1] = idx; + cb->args[2] = ip_idx; + return skb->len; } 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); } @@ -2843,31 +4189,91 @@ 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 void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) +static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(in_skb->sk); + struct ifaddrmsg *ifm; + struct nlattr *tb[IFA_MAX+1]; + struct in6_addr *addr = NULL, *peer; + struct net_device *dev = NULL; + struct inet6_ifaddr *ifa; struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifaddrmsg)+128); + int err; - skb = alloc_skb(size, GFP_ATOMIC); + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); + if (err < 0) + goto errout; + + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); + if (addr == NULL) { + err = -EINVAL; + goto errout; + } + + ifm = nlmsg_data(nlh); + if (ifm->ifa_index) + dev = __dev_get_by_index(net, ifm->ifa_index); + + ifa = ipv6_get_ifaddr(net, addr, dev, 1); + if (!ifa) { + err = -EADDRNOTAVAIL; + goto errout; + } + + skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL); if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, ENOBUFS); - return; + err = -ENOBUFS; + goto errout_ifa; } - if (inet6_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { + + err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWADDR, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ + WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, EINVAL); - return; + goto errout_ifa; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout_ifa: + in6_ifa_put(ifa); +errout: + return err; +} + +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); + if (skb == NULL) + goto errout; + + err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFADDR; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFADDR, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } -static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, +static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, __s32 *array, int bytes) { + BUG_ON(bytes < (DEVCONF_MAX * 4)); + memset(array, 0, bytes); array[DEVCONF_FORWARDING] = cnf->forwarding; array[DEVCONF_HOPLIMIT] = cnf->hop_limit; @@ -2877,106 +4283,330 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_AUTOCONF] = cnf->autoconf; array[DEVCONF_DAD_TRANSMITS] = cnf->dad_transmits; array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits; - array[DEVCONF_RTR_SOLICIT_INTERVAL] = cnf->rtr_solicit_interval; - array[DEVCONF_RTR_SOLICIT_DELAY] = cnf->rtr_solicit_delay; + array[DEVCONF_RTR_SOLICIT_INTERVAL] = + jiffies_to_msecs(cnf->rtr_solicit_interval); + array[DEVCONF_RTR_SOLICIT_DELAY] = + jiffies_to_msecs(cnf->rtr_solicit_delay); array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; -#ifdef CONFIG_IPV6_PRIVACY + array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] = + jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval); + array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = + jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval); array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr; array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft; array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft; array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry; array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; -#endif array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; + array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; +#ifdef CONFIG_IPV6_ROUTER_PREF + array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; + array[DEVCONF_RTR_PROBE_INTERVAL] = + jiffies_to_msecs(cnf->rtr_probe_interval); +#ifdef CONFIG_IPV6_ROUTE_INFO + array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; +#endif +#endif + array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; + array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route; +#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; + array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; + array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; + array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; } -static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, - u32 pid, u32 seq, int event, unsigned int flags) +static inline size_t inet6_ifla6_size(void) { - struct net_device *dev = idev->dev; - __s32 *array = NULL; - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - struct rtattr *subattr; - __u32 mtu = dev->mtu; - struct ifla_cacheinfo ci; + return nla_total_size(4) /* IFLA_INET6_FLAGS */ + + nla_total_size(sizeof(struct ifla_cacheinfo)) + + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ + + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */ + + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */ + + nla_total_size(sizeof(struct in6_addr)); /* IFLA_INET6_TOKEN */ +} - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_INET6; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = 0; +static inline size_t inet6_if_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(4) /* IFLA_MTU */ + + nla_total_size(4) /* IFLA_LINK */ + + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */ +} - RTA_PUT(skb, IFLA_IFNAME, strlen(dev->name)+1, dev->name); +static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib, + int items, int bytes) +{ + int i; + int pad = bytes - sizeof(u64) * items; + BUG_ON(pad < 0); - if (dev->addr_len) - RTA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); + /* Use put_unaligned() because stats may not be aligned for u64. */ + put_unaligned(items, &stats[0]); + for (i = 1; i < items; i++) + put_unaligned(atomic_long_read(&mib[i]), &stats[i]); - RTA_PUT(skb, IFLA_MTU, sizeof(mtu), &mtu); - if (dev->ifindex != dev->iflink) - RTA_PUT(skb, IFLA_LINK, sizeof(int), &dev->iflink); - - subattr = (struct rtattr*)skb->tail; + memset(&stats[items], 0, pad); +} - RTA_PUT(skb, IFLA_PROTINFO, 0, NULL); +static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib, + int items, int bytes, size_t syncpoff) +{ + int i; + int pad = bytes - sizeof(u64) * items; + BUG_ON(pad < 0); - /* return the device flags */ - RTA_PUT(skb, IFLA_INET6_FLAGS, sizeof(__u32), &idev->if_flags); + /* Use put_unaligned() because stats may not be aligned for u64. */ + put_unaligned(items, &stats[0]); + for (i = 1; i < items; i++) + put_unaligned(snmp_fold_field64(mib, i, syncpoff), &stats[i]); - /* return interface cacheinfo */ + memset(&stats[items], 0, pad); +} + +static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, + int bytes) +{ + switch (attrtype) { + case IFLA_INET6_STATS: + __snmp6_fill_stats64(stats, idev->stats.ipv6, + IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp)); + break; + case IFLA_INET6_ICMP6STATS: + __snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, ICMP6_MIB_MAX, bytes); + break; + } +} + +static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) +{ + struct nlattr *nla; + struct ifla_cacheinfo ci; + + if (nla_put_u32(skb, IFLA_INET6_FLAGS, idev->if_flags)) + goto nla_put_failure; ci.max_reasm_len = IPV6_MAXPLEN; - ci.tstamp = (__u32)(TIME_DELTA(idev->tstamp, INITIAL_JIFFIES) / HZ * 100 - + TIME_DELTA(idev->tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); - ci.reachable_time = idev->nd_parms->reachable_time; - ci.retrans_time = idev->nd_parms->retrans_time; - RTA_PUT(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci); - - /* return the device sysctl params */ - if ((array = kmalloc(DEVCONF_MAX * sizeof(*array), GFP_ATOMIC)) == NULL) - goto rtattr_failure; - ipv6_store_devconf(&idev->cnf, array, DEVCONF_MAX * sizeof(*array)); - RTA_PUT(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(*array), array); - - /* XXX - Statistics/MC not implemented */ - subattr->rta_len = skb->tail - (u8*)subattr; - - nlh->nlmsg_len = skb->tail - b; - kfree(array); - return skb->len; + ci.tstamp = cstamp_delta(idev->tstamp); + ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); + ci.retrans_time = jiffies_to_msecs(NEIGH_VAR(idev->nd_parms, RETRANS_TIME)); + if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; + nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); + if (nla == NULL) + goto nla_put_failure; + ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla)); + + /* XXX - MC not implemented */ + + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); + if (nla == NULL) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); + + nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); + if (nla == NULL) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + + nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); + if (nla == NULL) + goto nla_put_failure; + read_lock_bh(&idev->lock); + memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); + read_unlock_bh(&idev->lock); -nlmsg_failure: -rtattr_failure: - if (array) - kfree(array); - skb_trim(skb, b - skb->data); - return -1; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static size_t inet6_get_link_af_size(const struct net_device *dev) +{ + if (!__in6_dev_get(dev)) + return 0; + + return inet6_ifla6_size(); +} + +static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +{ + struct inet6_dev *idev = __in6_dev_get(dev); + + if (!idev) + return -ENODATA; + + if (inet6_fill_ifla6_attrs(skb, idev) < 0) + return -EMSGSIZE; + + return 0; +} + +static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) +{ + struct inet6_ifaddr *ifp; + struct net_device *dev = idev->dev; + bool update_rs = false; + struct in6_addr ll_addr; + + ASSERT_RTNL(); + + if (token == NULL) + return -EINVAL; + if (ipv6_addr_any(token)) + return -EINVAL; + if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) + return -EINVAL; + if (!ipv6_accept_ra(idev)) + return -EINVAL; + if (idev->cnf.rtr_solicits <= 0) + return -EINVAL; + + write_lock_bh(&idev->lock); + + BUILD_BUG_ON(sizeof(token->s6_addr) != 16); + memcpy(idev->token.s6_addr + 8, token->s6_addr + 8, 8); + + write_unlock_bh(&idev->lock); + + if (!idev->dead && (idev->if_flags & IF_READY) && + !ipv6_get_lladdr(dev, &ll_addr, IFA_F_TENTATIVE | + IFA_F_OPTIMISTIC)) { + + /* If we're not ready, then normal ifup will take care + * of this. Otherwise, we need to request our rs here. + */ + ndisc_send_rs(dev, &ll_addr, &in6addr_linklocal_allrouters); + update_rs = true; + } + + write_lock_bh(&idev->lock); + + if (update_rs) { + idev->if_flags |= IF_RS_SENT; + idev->rs_probes = 1; + addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval); + } + + /* Well, that's kinda nasty ... */ + list_for_each_entry(ifp, &idev->addr_list, if_list) { + spin_lock(&ifp->lock); + if (ifp->tokenized) { + ifp->valid_lft = 0; + ifp->prefered_lft = 0; + } + spin_unlock(&ifp->lock); + } + + write_unlock_bh(&idev->lock); + addrconf_verify_rtnl(); + return 0; +} + +static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) +{ + int err = -EINVAL; + struct inet6_dev *idev = __in6_dev_get(dev); + struct nlattr *tb[IFLA_INET6_MAX + 1]; + + if (!idev) + return -EAFNOSUPPORT; + + if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL) < 0) + BUG(); + + if (tb[IFLA_INET6_TOKEN]) + err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); + + return err; +} + +static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, + u32 portid, u32 seq, int event, unsigned int flags) +{ + struct net_device *dev = idev->dev; + struct ifinfomsg *hdr; + struct nlmsghdr *nlh; + void *protoinfo; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); + if (nlh == NULL) + return -EMSGSIZE; + + hdr = nlmsg_data(nlh); + hdr->ifi_family = AF_INET6; + hdr->__ifi_pad = 0; + hdr->ifi_type = dev->type; + hdr->ifi_index = dev->ifindex; + hdr->ifi_flags = dev_get_flags(dev); + hdr->ifi_change = 0; + + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink))) + goto nla_put_failure; + protoinfo = nla_nest_start(skb, IFLA_PROTINFO); + if (protoinfo == NULL) + goto nla_put_failure; + + if (inet6_fill_ifla6_attrs(skb, idev) < 0) + goto nla_put_failure; + + nla_nest_end(skb, protoinfo); + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { - int idx, err; - int s_idx = cb->args[0]; + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx = 0, s_idx; struct net_device *dev; struct inet6_dev *idev; - - read_lock(&dev_base_lock); - for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { - if (idx < s_idx) - continue; - if ((idev = in6_dev_get(dev)) == NULL) - continue; - err = inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); - in6_dev_put(idev); - if (err <= 0) - break; + struct hlist_head *head; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + idev = __in6_dev_get(dev); + if (!idev) + goto cont; + if (inet6_fill_ifinfo(skb, idev, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWLINK, NLM_F_MULTI) <= 0) + goto out; +cont: + idx++; + } } - read_unlock(&dev_base_lock); - cb->args[0] = idx; +out: + rcu_read_unlock(); + cb->args[1] = idx; + cb->args[0] = h; return skb->len; } @@ -2984,34 +4614,47 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) void inet6_ifinfo_notify(int event, struct inet6_dev *idev) { struct sk_buff *skb; - /* 128 bytes ?? */ - int size = NLMSG_SPACE(sizeof(struct ifinfomsg)+128); - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, ENOBUFS); - return; - } - if (inet6_fill_ifinfo(skb, idev, current->pid, 0, event, 0) < 0) { + struct net *net = dev_net(idev->dev); + int err = -ENOBUFS; + + skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_if_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFINFO; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFINFO, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); +} + +static inline size_t inet6_prefix_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct prefixmsg)) + + nla_total_size(sizeof(struct in6_addr)) + + nla_total_size(sizeof(struct prefix_cacheinfo)); } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, - struct prefix_info *pinfo, u32 pid, u32 seq, - int event, unsigned int flags) + struct prefix_info *pinfo, u32 portid, u32 seq, + int event, unsigned int flags) { - struct prefixmsg *pmsg; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; + struct prefixmsg *pmsg; + struct nlmsghdr *nlh; struct prefix_cacheinfo ci; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*pmsg), flags); - pmsg = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags); + if (nlh == NULL) + return -EMSGSIZE; + + pmsg = nlmsg_data(nlh); pmsg->prefix_family = AF_INET6; pmsg->prefix_pad1 = 0; pmsg->prefix_pad2 = 0; @@ -3019,477 +4662,670 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; - pmsg->prefix_flags = 0; if (pinfo->onlink) pmsg->prefix_flags |= IF_PREFIX_ONLINK; if (pinfo->autoconf) pmsg->prefix_flags |= IF_PREFIX_AUTOCONF; - RTA_PUT(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix); - + if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) + goto nla_put_failure; ci.preferred_time = ntohl(pinfo->prefered); ci.valid_time = ntohl(pinfo->valid); - RTA_PUT(skb, PREFIX_CACHEINFO, sizeof(ci), &ci); - - nlh->nlmsg_len = skb->tail - b; - return skb->len; + if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } -static void inet6_prefix_notify(int event, struct inet6_dev *idev, +static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct prefixmsg)+128); + struct net *net = dev_net(idev->dev); + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, ENOBUFS); - return; - } - if (inet6_fill_prefix(skb, idev, pinfo, current->pid, 0, event, 0) < 0) { + skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet6_prefix_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_PREFIX; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_PREFIX, GFP_ATOMIC); -} - -static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { - [RTM_GETLINK - RTM_BASE] = { .dumpit = inet6_dump_ifinfo, }, - [RTM_NEWADDR - RTM_BASE] = { .doit = inet6_rtm_newaddr, }, - [RTM_DELADDR - RTM_BASE] = { .doit = inet6_rtm_deladdr, }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = inet6_dump_ifaddr, }, - [RTM_GETMULTICAST - RTM_BASE] = { .dumpit = inet6_dump_ifmcaddr, }, - [RTM_GETANYCAST - RTM_BASE] = { .dumpit = inet6_dump_ifacaddr, }, - [RTM_NEWROUTE - RTM_BASE] = { .doit = inet6_rtm_newroute, }, - [RTM_DELROUTE - RTM_BASE] = { .doit = inet6_rtm_delroute, }, - [RTM_GETROUTE - RTM_BASE] = { .doit = inet6_rtm_getroute, - .dumpit = inet6_dump_fib, }, -}; + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); +} static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { + struct net *net = dev_net(ifp->idev->dev); + + if (event) + ASSERT_RTNL(); + inet6_ifa_notify(event ? : RTM_NEWADDR, ifp); switch (event) { case RTM_NEWADDR: - dst_hold(&ifp->rt->u.dst); - if (ip6_ins_rt(ifp->rt, NULL, NULL, NULL)) - dst_release(&ifp->rt->u.dst); + /* + * If the address was optimistic + * we inserted the route at the start of + * our DAD process, so we don't need + * to do it again + */ + if (!(ifp->rt->rt6i_node)) + ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); + if (!ipv6_addr_any(&ifp->peer_addr)) + addrconf_prefix_route(&ifp->peer_addr, 128, + ifp->idev->dev, 0, 0); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); - dst_hold(&ifp->rt->u.dst); - if (ip6_del_rt(ifp->rt, NULL, NULL, NULL)) - dst_free(&ifp->rt->u.dst); - else - dst_release(&ifp->rt->u.dst); + if (!ipv6_addr_any(&ifp->peer_addr)) { + struct rt6_info *rt; + struct net_device *dev = ifp->idev->dev; + + rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL, + dev->ifindex, 1); + if (rt) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } + } + dst_hold(&ifp->rt->dst); + + if (ip6_del_rt(ifp->rt)) + dst_free(&ifp->rt->dst); break; } + atomic_inc(&net->ipv6.dev_addr_genid); + rt_genid_bump_ipv6(net); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); if (likely(ifp->idev->dead == 0)) __ipv6_ifa_notify(event, ifp); - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); } #ifdef CONFIG_SYSCTL static -int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp, +int addrconf_sysctl_forward(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; int ret; - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + /* + * ctl->data points to idev->cnf.forwarding, we should + * not modify it until we get the rtnl lock. + */ + lctl = *ctl; + lctl.data = &val; - 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(); + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write) + ret = addrconf_fixup_forwarding(ctl, valp, val); + if (ret) + *ppos = pos; + return ret; +} + +static void dev_disable_change(struct inet6_dev *idev) +{ + struct netdev_notifier_info info; + + if (!idev || !idev->dev) + return; + + netdev_notifier_info_init(&info, idev->dev); + if (idev->cnf.disable_ipv6) + addrconf_notify(NULL, NETDEV_DOWN, &info); + else + addrconf_notify(NULL, NETDEV_UP, &info); +} + +static void addrconf_disable_change(struct net *net, __s32 newf) +{ + struct net_device *dev; + struct inet6_dev *idev; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + idev = __in6_dev_get(dev); + if (idev) { + int changed = (!idev->cnf.disable_ipv6) ^ (!newf); + idev->cnf.disable_ipv6 = newf; + if (changed) + dev_disable_change(idev); } - if (*valp) - rt6_purge_dflt_routers(); } - - return ret; + rcu_read_unlock(); } -static int addrconf_sysctl_forward_strategy(ctl_table *table, - int __user *name, int nlen, - void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen, - void **context) +static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) { - int *valp = table->data; - int new; + struct net *net; + int old; - if (!newval || !newlen) - return 0; - if (newlen != sizeof(int)) - return -EINVAL; - if (get_user(new, (int __user *)newval)) - return -EFAULT; - if (new == *valp) + if (!rtnl_trylock()) + return restart_syscall(); + + net = (struct net *)table->extra2; + old = *p; + *p = newf; + + if (p == &net->ipv6.devconf_dflt->disable_ipv6) { + rtnl_unlock(); return 0; - if (oldval && oldlenp) { - size_t len; - if (get_user(len, oldlenp)) - return -EFAULT; - if (len) { - if (len > table->maxlen) - len = table->maxlen; - if (copy_to_user(oldval, valp, len)) - return -EFAULT; - if (put_user(len, oldlenp)) - return -EFAULT; - } } - 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 (p == &net->ipv6.devconf_all->disable_ipv6) { + net->ipv6.devconf_dflt->disable_ipv6 = newf; + addrconf_disable_change(net, newf); + } else if ((!newf) ^ (!old)) + dev_disable_change((struct inet6_dev *)table->extra1); - if (*valp) - rt6_purge_dflt_routers(); - } else - *valp = new; + rtnl_unlock(); + return 0; +} - return 1; +static +int addrconf_sysctl_disable(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; + int ret; + + /* + * ctl->data points to idev->cnf.disable_ipv6, we should + * not modify it until we get the rtnl lock. + */ + lctl = *ctl; + lctl.data = &val; + + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write) + ret = addrconf_disable_ipv6(ctl, valp, val); + if (ret) + *ppos = pos; + return ret; } +static +int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = ctl->data; + int ret; + int old, new; + + old = *valp; + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + new = *valp; + + if (write && old != new) { + struct net *net = ctl->extra2; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (valp == &net->ipv6.devconf_dflt->proxy_ndp) + inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + else if (valp == &net->ipv6.devconf_all->proxy_ndp) + inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + else { + struct inet6_dev *idev = ctl->extra1; + + inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + idev->dev->ifindex, + &idev->cnf); + } + rtnl_unlock(); + } + + return ret; +} + + 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]; -} addrconf_sysctl = { + struct ctl_table addrconf_vars[DEVCONF_MAX+1]; +} addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { - { - .ctl_name = NET_IPV6_FORWARDING, - .procname = "forwarding", - .data = &ipv6_devconf.forwarding, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &addrconf_sysctl_forward, - .strategy = &addrconf_sysctl_forward_strategy, + { + .procname = "forwarding", + .data = &ipv6_devconf.forwarding, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_forward, + }, + { + .procname = "hop_limit", + .data = &ipv6_devconf.hop_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "mtu", + .data = &ipv6_devconf.mtu6, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "accept_ra", + .data = &ipv6_devconf.accept_ra, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_HOP_LIMIT, - .procname = "hop_limit", - .data = &ipv6_devconf.hop_limit, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, + .procname = "accept_redirects", + .data = &ipv6_devconf.accept_redirects, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_MTU, - .procname = "mtu", - .data = &ipv6_devconf.mtu6, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "autoconf", + .data = &ipv6_devconf.autoconf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_RA, - .procname = "accept_ra", - .data = &ipv6_devconf.accept_ra, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "dad_transmits", + .data = &ipv6_devconf.dad_transmits, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ACCEPT_REDIRECTS, - .procname = "accept_redirects", - .data = &ipv6_devconf.accept_redirects, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "router_solicitations", + .data = &ipv6_devconf.rtr_solicits, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_AUTOCONF, - .procname = "autoconf", - .data = &ipv6_devconf.autoconf, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "router_solicitation_interval", + .data = &ipv6_devconf.rtr_solicit_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_DAD_TRANSMITS, - .procname = "dad_transmits", - .data = &ipv6_devconf.dad_transmits, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "router_solicitation_delay", + .data = &ipv6_devconf.rtr_solicit_delay, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_RTR_SOLICITS, - .procname = "router_solicitations", - .data = &ipv6_devconf.rtr_solicits, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "force_mld_version", + .data = &ipv6_devconf.force_mld_version, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_RTR_SOLICIT_INTERVAL, - .procname = "router_solicitation_interval", - .data = &ipv6_devconf.rtr_solicit_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .procname = "mldv1_unsolicited_report_interval", + .data = + &ipv6_devconf.mldv1_unsolicited_report_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, }, { - .ctl_name = NET_IPV6_RTR_SOLICIT_DELAY, - .procname = "router_solicitation_delay", - .data = &ipv6_devconf.rtr_solicit_delay, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .procname = "mldv2_unsolicited_report_interval", + .data = + &ipv6_devconf.mldv2_unsolicited_report_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, }, { - .ctl_name = NET_IPV6_FORCE_MLD_VERSION, - .procname = "force_mld_version", - .data = &ipv6_devconf.force_mld_version, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "use_tempaddr", + .data = &ipv6_devconf.use_tempaddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, -#ifdef CONFIG_IPV6_PRIVACY { - .ctl_name = NET_IPV6_USE_TEMPADDR, - .procname = "use_tempaddr", - .data = &ipv6_devconf.use_tempaddr, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "temp_valid_lft", + .data = &ipv6_devconf.temp_valid_lft, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_TEMP_VALID_LFT, - .procname = "temp_valid_lft", - .data = &ipv6_devconf.temp_valid_lft, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "temp_prefered_lft", + .data = &ipv6_devconf.temp_prefered_lft, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_TEMP_PREFERED_LFT, - .procname = "temp_prefered_lft", - .data = &ipv6_devconf.temp_prefered_lft, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "regen_max_retry", + .data = &ipv6_devconf.regen_max_retry, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_REGEN_MAX_RETRY, - .procname = "regen_max_retry", - .data = &ipv6_devconf.regen_max_retry, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "max_desync_factor", + .data = &ipv6_devconf.max_desync_factor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_MAX_DESYNC_FACTOR, - .procname = "max_desync_factor", - .data = &ipv6_devconf.max_desync_factor, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "max_addresses", + .data = &ipv6_devconf.max_addresses, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, }, + { + .procname = "accept_ra_defrtr", + .data = &ipv6_devconf.accept_ra_defrtr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "accept_ra_pinfo", + .data = &ipv6_devconf.accept_ra_pinfo, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_IPV6_ROUTER_PREF + { + .procname = "accept_ra_rtr_pref", + .data = &ipv6_devconf.accept_ra_rtr_pref, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "router_probe_interval", + .data = &ipv6_devconf.rtr_probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#ifdef CONFIG_IPV6_ROUTE_INFO + { + .procname = "accept_ra_rt_info_max_plen", + .data = &ipv6_devconf.accept_ra_rt_info_max_plen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif #endif { - .ctl_name = NET_IPV6_MAX_ADDRESSES, - .procname = "max_addresses", - .data = &ipv6_devconf.max_addresses, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, + .procname = "proxy_ndp", + .data = &ipv6_devconf.proxy_ndp, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_proxy_ndp, }, { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_dev = { + .procname = "accept_source_route", + .data = &ipv6_devconf.accept_source_route, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD { - .ctl_name = NET_PROTO_CONF_ALL, - .procname = "all", - .mode = 0555, - .child = addrconf_sysctl.addrconf_vars, + .procname = "optimistic_dad", + .data = &ipv6_devconf.optimistic_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_IPV6_MROUTE { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_conf_dir = { + .procname = "mc_forwarding", + .data = &ipv6_devconf.mc_forwarding, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, +#endif { - .ctl_name = NET_IPV6_CONF, - .procname = "conf", - .mode = 0555, - .child = addrconf_sysctl.addrconf_dev, + .procname = "disable_ipv6", + .data = &ipv6_devconf.disable_ipv6, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_disable, }, { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_proto_dir = { + .procname = "accept_dad", + .data = &ipv6_devconf.accept_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { - .ctl_name = NET_IPV6, - .procname = "ipv6", - .mode = 0555, - .child = addrconf_sysctl.addrconf_conf_dir, + .procname = "force_tllao", + .data = &ipv6_devconf.force_tllao, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec }, { - .ctl_name = 0, /* sentinel */ - } - }, - .addrconf_root_dir = { + .procname = "ndisc_notify", + .data = &ipv6_devconf.ndisc_notify, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, - .child = addrconf_sysctl.addrconf_proto_dir, + .procname = "suppress_frag_ndisc", + .data = &ipv6_devconf.suppress_frag_ndisc, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec }, { - .ctl_name = 0, /* sentinel */ + /* sentinel */ } }, }; -static void addrconf_sysctl_register(struct inet6_dev *idev, struct ipv6_devconf *p) +static int __addrconf_sysctl_register(struct net *net, char *dev_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; + char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; - t = kmalloc(sizeof(*t), GFP_KERNEL); + t = kmemdup(&addrconf_sysctl, sizeof(*t), GFP_KERNEL); if (t == NULL) - return; - memcpy(t, &addrconf_sysctl, sizeof(*t)); - for (i=0; t->addrconf_vars[i].data; i++) { - t->addrconf_vars[i].data += (char*)p - (char*)&ipv6_devconf; - t->addrconf_vars[i].de = NULL; + 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 */ + t->addrconf_vars[i].extra2 = net; } - 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; - } - - /* - * Make a copy of dev_name, because '.procname' is regarded as const - * 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->addrconf_dev[0].child = t->addrconf_vars; - t->addrconf_dev[0].de = NULL; - t->addrconf_conf_dir[0].child = t->addrconf_dev; - t->addrconf_conf_dir[0].de = NULL; - t->addrconf_proto_dir[0].child = t->addrconf_conf_dir; - t->addrconf_proto_dir[0].de = NULL; - t->addrconf_root_dir[0].child = t->addrconf_proto_dir; - t->addrconf_root_dir[0].de = NULL; - - t->sysctl_header = register_sysctl_table(t->addrconf_root_dir, 0); + + snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name); + + t->sysctl_header = register_net_sysctl(net, path, t->addrconf_vars); if (t->sysctl_header == NULL) - goto free_procname; - else - p->sysctl = t; - return; + goto free; + + p->sysctl = t; + return 0; - /* error path */ - free_procname: - kfree(dev_name); - free: +free: kfree(t); +out: + return -ENOBUFS; +} - return; +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_net_sysctl_table(t->sysctl_header); + kfree(t); } -static void addrconf_sysctl_unregister(struct ipv6_devconf *p) +static void addrconf_sysctl_register(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); - } + neigh_sysctl_register(idev->dev, idev->nd_parms, + &ndisc_ifinfo_sysctl_change); + __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, + idev, &idev->cnf); } +static void addrconf_sysctl_unregister(struct inet6_dev *idev) +{ + __addrconf_sysctl_unregister(&idev->cnf); + neigh_sysctl_unregister(idev->nd_parms); +} -#endif -/* - * Device notifier - */ +#endif -int register_inet6addr_notifier(struct notifier_block *nb) +static int __net_init addrconf_init_net(struct net *net) { - return notifier_chain_register(&inet6addr_chain, nb); + int err = -ENOMEM; + struct ipv6_devconf *all, *dflt; + + all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); + if (all == NULL) + goto err_alloc_all; + + dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); + if (dflt == NULL) + goto err_alloc_dflt; + + /* these will be inherited by all namespaces */ + dflt->autoconf = ipv6_defaults.autoconf; + dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; + + net->ipv6.devconf_all = all; + net->ipv6.devconf_dflt = dflt; + +#ifdef CONFIG_SYSCTL + err = __addrconf_sysctl_register(net, "all", NULL, all); + if (err < 0) + goto err_reg_all; + + err = __addrconf_sysctl_register(net, "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; } -int unregister_inet6addr_notifier(struct notifier_block *nb) +static void __net_exit addrconf_exit_net(struct net *net) { - return notifier_chain_unregister(&inet6addr_chain,nb); +#ifdef CONFIG_SYSCTL + __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); + __addrconf_sysctl_unregister(net->ipv6.devconf_all); +#endif + if (!net_eq(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, +}; + +static struct rtnl_af_ops inet6_ops = { + .family = AF_INET6, + .fill_link_af = inet6_fill_link_af, + .get_link_af_size = inet6_get_link_af_size, + .set_link_af = inet6_set_link_af, +}; + /* * Init / cleanup code */ int __init addrconf_init(void) { - int err = 0; + int i, err; + + err = ipv6_addr_label_init(); + if (err < 0) { + pr_crit("%s: cannot initialize default policy table: %d\n", + __func__, err); + goto out; + } + + err = register_pernet_subsys(&addrconf_ops); + if (err < 0) + goto out_addrlabel; + + addrconf_wq = create_workqueue("ipv6_addrconf"); + if (!addrconf_wq) { + err = -ENOMEM; + goto out_nowq; + } /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup @@ -3510,91 +5346,84 @@ int __init addrconf_init(void) * device and it being up should be removed. */ rtnl_lock(); - if (!ipv6_add_dev(&loopback_dev)) + if (!ipv6_add_dev(init_net.loopback_dev)) err = -ENOMEM; rtnl_unlock(); if (err) - return err; + goto errlo; - ip6_null_entry.rt6i_idev = in6_dev_get(&loopback_dev); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_addr_lst[i]); register_netdevice_notifier(&ipv6_dev_notf); -#ifdef CONFIG_IPV6_PRIVACY - md5_tfm = crypto_alloc_tfm("md5", 0); - if (unlikely(md5_tfm == NULL)) - printk(KERN_WARNING - "failed to load transform for md5\n"); -#endif + addrconf_verify(); - addrconf_verify(0); - rtnetlink_links[PF_INET6] = inet6_rtnetlink_table; -#ifdef CONFIG_SYSCTL - addrconf_sysctl.sysctl_header = - register_sysctl_table(addrconf_sysctl.addrconf_root_dir, 0); - addrconf_sysctl_register(NULL, &ipv6_devconf_dflt); -#endif + rtnl_af_register(&inet6_ops); + + err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo, + NULL); + if (err < 0) + goto errout; + + /* Only the first call to __rtnl_register can fail */ + __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, + inet6_dump_ifaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, + inet6_dump_ifmcaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, + inet6_dump_ifacaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, + inet6_netconf_dump_devconf, NULL); + + ipv6_addr_label_rtnl_register(); return 0; +errout: + rtnl_af_unregister(&inet6_ops); + unregister_netdevice_notifier(&ipv6_dev_notf); +errlo: + destroy_workqueue(addrconf_wq); +out_nowq: + unregister_pernet_subsys(&addrconf_ops); +out_addrlabel: + ipv6_addr_label_cleanup(); +out: + return err; } -void __exit addrconf_cleanup(void) +void addrconf_cleanup(void) { - struct net_device *dev; - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + struct net_device *dev; int i; unregister_netdevice_notifier(&ipv6_dev_notf); - - rtnetlink_links[PF_INET6] = NULL; -#ifdef CONFIG_SYSCTL - addrconf_sysctl_unregister(&ipv6_devconf_dflt); - addrconf_sysctl_unregister(&ipv6_devconf); -#endif + unregister_pernet_subsys(&addrconf_ops); + ipv6_addr_label_cleanup(); rtnl_lock(); - /* - * clean dev list. - */ + __rtnl_af_unregister(&inet6_ops); - for (dev=dev_base; dev; dev=dev->next) { - if ((idev = __in6_dev_get(dev)) == NULL) + /* clean dev list */ + for_each_netdev(&init_net, dev) { + if (__in6_dev_get(dev) == NULL) continue; addrconf_ifdown(dev, 1); } - addrconf_ifdown(&loopback_dev, 2); + 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; ) { - struct inet6_ifaddr *bifa; - - bifa = ifa; - ifa = ifa->lst_next; - printk(KERN_DEBUG "bug: IPv6 address leakage detected: ifa=%p\n", bifa); - /* Do not free it; something is wrong. - Now we can investigate it with debugger. - */ - } - } - write_unlock_bh(&addrconf_hash_lock); - - del_timer(&addr_chk_timer); - + spin_lock_bh(&addrconf_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_addr_lst[i])); + spin_unlock_bh(&addrconf_hash_lock); + cancel_delayed_work(&addr_chk_work); rtnl_unlock(); -#ifdef CONFIG_IPV6_PRIVACY - crypto_free_tfm(md5_tfm); - md5_tfm = NULL; -#endif - -#ifdef CONFIG_PROC_FS - proc_net_remove("if_inet6"); -#endif + destroy_workqueue(addrconf_wq); } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c new file mode 100644 index 00000000000..e6960457f62 --- /dev/null +++ b/net/ipv6/addrconf_core.c @@ -0,0 +1,150 @@ +/* + * IPv6 library code, needed by static components when full IPv6 support is + * not configured or static. + */ + +#include <linux/export.h> +#include <net/ipv6.h> +#include <net/addrconf.h> +#include <net/ip.h> + +#define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) + +static inline unsigned int ipv6_addr_scope2type(unsigned int scope) +{ + switch (scope) { + case IPV6_ADDR_SCOPE_NODELOCAL: + return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_NODELOCAL) | + IPV6_ADDR_LOOPBACK); + case IPV6_ADDR_SCOPE_LINKLOCAL: + return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL) | + IPV6_ADDR_LINKLOCAL); + case IPV6_ADDR_SCOPE_SITELOCAL: + return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL) | + IPV6_ADDR_SITELOCAL); + } + return IPV6_ADDR_SCOPE_TYPE(scope); +} + +int __ipv6_addr_type(const struct in6_addr *addr) +{ + __be32 st; + + st = addr->s6_addr32[0]; + + /* Consider all addresses with the first three bits different of + 000 and 111 as unicasts. + */ + if ((st & htonl(0xE0000000)) != htonl(0x00000000) && + (st & htonl(0xE0000000)) != htonl(0xE0000000)) + return (IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); + + if ((st & htonl(0xFF000000)) == htonl(0xFF000000)) { + /* multicast */ + /* addr-select 3.1 */ + return (IPV6_ADDR_MULTICAST | + ipv6_addr_scope2type(IPV6_ADDR_MC_SCOPE(addr))); + } + + if ((st & htonl(0xFFC00000)) == htonl(0xFE800000)) + return (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.1 */ + if ((st & htonl(0xFFC00000)) == htonl(0xFEC00000)) + return (IPV6_ADDR_SITELOCAL | IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL)); /* addr-select 3.1 */ + if ((st & htonl(0xFE000000)) == htonl(0xFC000000)) + return (IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* RFC 4193 */ + + 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 | IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.4 */ + + return (IPV6_ADDR_COMPATv4 | IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ + } + + if (addr->s6_addr32[2] == htonl(0x0000ffff)) + return (IPV6_ADDR_MAPPED | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ + } + + return (IPV6_ADDR_UNICAST | + IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */ +} +EXPORT_SYMBOL(__ipv6_addr_type); + +static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); + +int register_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_notifier); + +int unregister_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_notifier); + +int inet6addr_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_notifier_call_chain); + +const struct ipv6_stub *ipv6_stub __read_mostly; +EXPORT_SYMBOL_GPL(ipv6_stub); + +/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ +const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +EXPORT_SYMBOL(in6addr_loopback); +const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +EXPORT_SYMBOL(in6addr_any); +const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +EXPORT_SYMBOL(in6addr_linklocal_allnodes); +const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +EXPORT_SYMBOL(in6addr_linklocal_allrouters); +const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); +const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); +const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +EXPORT_SYMBOL(in6addr_sitelocal_allrouters); + +static void snmp6_free_dev(struct inet6_dev *idev) +{ + kfree(idev->stats.icmpv6msgdev); + kfree(idev->stats.icmpv6dev); + free_percpu(idev->stats.ipv6); +} + +/* Nobody refers to this device, we may destroy it. */ + +void in6_dev_finish_destroy(struct inet6_dev *idev) +{ + struct net_device *dev = idev->dev; + + WARN_ON(!list_empty(&idev->addr_list)); + WARN_ON(idev->mc_list != NULL); + WARN_ON(timer_pending(&idev->rs_timer)); + +#ifdef NET_REFCNT_DEBUG + pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); +#endif + dev_put(dev); + if (!idev->dead) { + pr_warn("Freeing alive inet6 device %p\n", idev); + return; + } + snmp6_free_dev(idev); + kfree_rcu(idev, rcu); +} +EXPORT_SYMBOL(in6_dev_finish_destroy); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c new file mode 100644 index 00000000000..731e1e1722d --- /dev/null +++ b/net/ipv6/addrlabel.c @@ -0,0 +1,603 @@ +/* + * IPv6 Address Label subsystem + * for the IPv6 "Default" Source Address Selection + * + * Copyright (C)2007 USAGI/WIDE Project + */ +/* + * Author: + * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> + */ + +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/rcupdate.h> +#include <linux/in6.h> +#include <linux/slab.h> +#include <net/addrconf.h> +#include <linux/if_addrlabel.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> + +#if 0 +#define ADDRLABEL(x...) printk(x) +#else +#define ADDRLABEL(x...) do { ; } while (0) +#endif + +/* + * Policy Table + */ +struct ip6addrlbl_entry { +#ifdef CONFIG_NET_NS + struct net *lbl_net; +#endif + struct in6_addr prefix; + int prefixlen; + int ifindex; + int addrtype; + u32 label; + struct hlist_node list; + atomic_t refcnt; + struct rcu_head rcu; +}; + +static struct ip6addrlbl_table +{ + struct hlist_head head; + spinlock_t lock; + u32 seq; +} ip6addrlbl_table; + +static inline +struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) +{ + return read_pnet(&lbl->lbl_net); +} + +/* + * Default policy table (RFC6724 + extensions) + * + * prefix addr_type label + * ------------------------------------------------------------------------- + * ::1/128 LOOPBACK 0 + * ::/0 N/A 1 + * 2002::/16 N/A 2 + * ::/96 COMPATv4 3 + * ::ffff:0:0/96 V4MAPPED 4 + * fc00::/7 N/A 5 ULA (RFC 4193) + * 2001::/32 N/A 6 Teredo (RFC 4380) + * 2001:10::/28 N/A 7 ORCHID (RFC 4843) + * fec0::/10 N/A 11 Site-local + * (deprecated by RFC3879) + * 3ffe::/16 N/A 12 6bone + * + * Note: 0xffffffff is used if we do not have any policies. + * Note: Labels for ULA and 6to4 are different from labels listed in RFC6724. + */ + +#define IPV6_ADDR_LABEL_DEFAULT 0xffffffffUL + +static const __net_initconst struct ip6addrlbl_init_table +{ + const struct in6_addr *prefix; + int prefixlen; + u32 label; +} ip6addrlbl_init_table[] = { + { /* ::/0 */ + .prefix = &in6addr_any, + .label = 1, + }, { /* fc00::/7 */ + .prefix = &(struct in6_addr){ { { 0xfc } } } , + .prefixlen = 7, + .label = 5, + }, { /* fec0::/10 */ + .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } }, + .prefixlen = 10, + .label = 11, + }, { /* 2002::/16 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } }, + .prefixlen = 16, + .label = 2, + }, { /* 3ffe::/16 */ + .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } }, + .prefixlen = 16, + .label = 12, + }, { /* 2001::/32 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } }, + .prefixlen = 32, + .label = 6, + }, { /* 2001:10::/28 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } }, + .prefixlen = 28, + .label = 7, + }, { /* ::ffff:0:0 */ + .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } }, + .prefixlen = 96, + .label = 4, + }, { /* ::/96 */ + .prefix = &in6addr_any, + .prefixlen = 96, + .label = 3, + }, { /* ::1/128 */ + .prefix = &in6addr_loopback, + .prefixlen = 128, + .label = 0, + } +}; + +/* Object management */ +static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) +{ +#ifdef CONFIG_NET_NS + release_net(p->lbl_net); +#endif + kfree(p); +} + +static void ip6addrlbl_free_rcu(struct rcu_head *h) +{ + ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu)); +} + +static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) +{ + return atomic_inc_not_zero(&p->refcnt); +} + +static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) +{ + if (atomic_dec_and_test(&p->refcnt)) + call_rcu(&p->rcu, ip6addrlbl_free_rcu); +} + +/* Find label */ +static bool __ip6addrlbl_match(struct net *net, + const struct ip6addrlbl_entry *p, + const struct in6_addr *addr, + int addrtype, int ifindex) +{ + if (!net_eq(ip6addrlbl_net(p), net)) + return false; + if (p->ifindex && p->ifindex != ifindex) + return false; + if (p->addrtype && p->addrtype != addrtype) + return false; + if (!ipv6_prefix_equal(addr, &p->prefix, p->prefixlen)) + return false; + return true; +} + +static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, + const struct in6_addr *addr, + int type, int ifindex) +{ + struct ip6addrlbl_entry *p; + hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { + if (__ip6addrlbl_match(net, p, addr, type, ifindex)) + return p; + } + return NULL; +} + +u32 ipv6_addr_label(struct net *net, + const struct in6_addr *addr, int type, int ifindex) +{ + u32 label; + struct ip6addrlbl_entry *p; + + type &= IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK; + + rcu_read_lock(); + p = __ipv6_addr_label(net, addr, type, ifindex); + label = p ? p->label : IPV6_ADDR_LABEL_DEFAULT; + rcu_read_unlock(); + + ADDRLABEL(KERN_DEBUG "%s(addr=%pI6, type=%d, ifindex=%d) => %08x\n", + __func__, addr, type, ifindex, label); + + return label; +} + +/* allocate one entry */ +static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, + const struct in6_addr *prefix, + int prefixlen, int ifindex, + u32 label) +{ + struct ip6addrlbl_entry *newp; + int addrtype; + + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u)\n", + __func__, prefix, prefixlen, ifindex, (unsigned int)label); + + addrtype = ipv6_addr_type(prefix) & (IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK); + + switch (addrtype) { + case IPV6_ADDR_MAPPED: + if (prefixlen > 96) + return ERR_PTR(-EINVAL); + if (prefixlen < 96) + addrtype = 0; + break; + case IPV6_ADDR_COMPATv4: + if (prefixlen != 96) + addrtype = 0; + break; + case IPV6_ADDR_LOOPBACK: + if (prefixlen != 128) + addrtype = 0; + break; + } + + newp = kmalloc(sizeof(*newp), GFP_KERNEL); + if (!newp) + return ERR_PTR(-ENOMEM); + + ipv6_addr_prefix(&newp->prefix, prefix, prefixlen); + newp->prefixlen = prefixlen; + newp->ifindex = ifindex; + newp->addrtype = addrtype; + newp->label = label; + INIT_HLIST_NODE(&newp->list); +#ifdef CONFIG_NET_NS + newp->lbl_net = hold_net(net); +#endif + atomic_set(&newp->refcnt, 1); + return newp; +} + +/* add a label */ +static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) +{ + struct hlist_node *n; + struct ip6addrlbl_entry *last = NULL, *p = NULL; + int ret = 0; + + ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, + replace); + + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + if (p->prefixlen == newp->prefixlen && + net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && + p->ifindex == newp->ifindex && + ipv6_addr_equal(&p->prefix, &newp->prefix)) { + if (!replace) { + ret = -EEXIST; + goto out; + } + hlist_replace_rcu(&p->list, &newp->list); + ip6addrlbl_put(p); + goto out; + } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || + (p->prefixlen < newp->prefixlen)) { + hlist_add_before_rcu(&newp->list, &p->list); + goto out; + } + last = p; + } + if (last) + hlist_add_after_rcu(&last->list, &newp->list); + else + hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); +out: + if (!ret) + ip6addrlbl_table.seq++; + return ret; +} + +/* add a label */ +static int ip6addrlbl_add(struct net *net, + const struct in6_addr *prefix, int prefixlen, + int ifindex, u32 label, int replace) +{ + struct ip6addrlbl_entry *newp; + int ret = 0; + + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n", + __func__, prefix, prefixlen, ifindex, (unsigned int)label, + replace); + + newp = ip6addrlbl_alloc(net, prefix, prefixlen, ifindex, label); + if (IS_ERR(newp)) + return PTR_ERR(newp); + spin_lock(&ip6addrlbl_table.lock); + ret = __ip6addrlbl_add(newp, replace); + spin_unlock(&ip6addrlbl_table.lock); + if (ret) + ip6addrlbl_free(newp); + return ret; +} + +/* remove a label */ +static int __ip6addrlbl_del(struct net *net, + const struct in6_addr *prefix, int prefixlen, + int ifindex) +{ + struct ip6addrlbl_entry *p = NULL; + struct hlist_node *n; + int ret = -ESRCH; + + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", + __func__, prefix, prefixlen, ifindex); + + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + if (p->prefixlen == prefixlen && + net_eq(ip6addrlbl_net(p), net) && + p->ifindex == ifindex && + ipv6_addr_equal(&p->prefix, prefix)) { + hlist_del_rcu(&p->list); + ip6addrlbl_put(p); + ret = 0; + break; + } + } + return ret; +} + +static int ip6addrlbl_del(struct net *net, + const struct in6_addr *prefix, int prefixlen, + int ifindex) +{ + struct in6_addr prefix_buf; + int ret; + + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", + __func__, prefix, prefixlen, ifindex); + + ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); + spin_lock(&ip6addrlbl_table.lock); + ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex); + spin_unlock(&ip6addrlbl_table.lock); + return ret; +} + +/* add default label */ +static int __net_init ip6addrlbl_net_init(struct net *net) +{ + int err = 0; + int i; + + ADDRLABEL(KERN_DEBUG "%s\n", __func__); + + for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { + int ret = ip6addrlbl_add(net, + ip6addrlbl_init_table[i].prefix, + ip6addrlbl_init_table[i].prefixlen, + 0, + ip6addrlbl_init_table[i].label, 0); + /* XXX: should we free all rules when we catch an error? */ + if (ret && (!err || err != -ENOMEM)) + err = ret; + } + return err; +} + +static void __net_exit ip6addrlbl_net_exit(struct net *net) +{ + struct ip6addrlbl_entry *p = NULL; + struct hlist_node *n; + + /* Remove all labels belonging to the exiting net */ + spin_lock(&ip6addrlbl_table.lock); + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + if (net_eq(ip6addrlbl_net(p), net)) { + hlist_del_rcu(&p->list); + ip6addrlbl_put(p); + } + } + spin_unlock(&ip6addrlbl_table.lock); +} + +static struct pernet_operations ipv6_addr_label_ops = { + .init = ip6addrlbl_net_init, + .exit = ip6addrlbl_net_exit, +}; + +int __init ipv6_addr_label_init(void) +{ + spin_lock_init(&ip6addrlbl_table.lock); + + return register_pernet_subsys(&ipv6_addr_label_ops); +} + +void ipv6_addr_label_cleanup(void) +{ + unregister_pernet_subsys(&ipv6_addr_label_ops); +} + +static const struct nla_policy ifal_policy[IFAL_MAX+1] = { + [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, + [IFAL_LABEL] = { .len = sizeof(u32), }, +}; + +static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifaddrlblmsg *ifal; + struct nlattr *tb[IFAL_MAX+1]; + struct in6_addr *pfx; + u32 label; + int err = 0; + + err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy); + if (err < 0) + return err; + + ifal = nlmsg_data(nlh); + + if (ifal->ifal_family != AF_INET6 || + ifal->ifal_prefixlen > 128) + return -EINVAL; + + if (!tb[IFAL_ADDRESS]) + return -EINVAL; + pfx = nla_data(tb[IFAL_ADDRESS]); + + if (!tb[IFAL_LABEL]) + return -EINVAL; + label = nla_get_u32(tb[IFAL_LABEL]); + if (label == IPV6_ADDR_LABEL_DEFAULT) + return -EINVAL; + + switch (nlh->nlmsg_type) { + case RTM_NEWADDRLABEL: + if (ifal->ifal_index && + !__dev_get_by_index(net, ifal->ifal_index)) + return -EINVAL; + + err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen, + ifal->ifal_index, label, + nlh->nlmsg_flags & NLM_F_REPLACE); + break; + case RTM_DELADDRLABEL: + err = ip6addrlbl_del(net, pfx, ifal->ifal_prefixlen, + ifal->ifal_index); + break; + default: + err = -EOPNOTSUPP; + } + return err; +} + +static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, + int prefixlen, int ifindex, u32 lseq) +{ + struct ifaddrlblmsg *ifal = nlmsg_data(nlh); + ifal->ifal_family = AF_INET6; + ifal->ifal_prefixlen = prefixlen; + ifal->ifal_flags = 0; + ifal->ifal_index = ifindex; + ifal->ifal_seq = lseq; +}; + +static int ip6addrlbl_fill(struct sk_buff *skb, + struct ip6addrlbl_entry *p, + u32 lseq, + u32 portid, u32 seq, int event, + unsigned int flags) +{ + struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event, + sizeof(struct ifaddrlblmsg), flags); + if (!nlh) + return -EMSGSIZE; + + ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq); + + if (nla_put(skb, IFAL_ADDRESS, 16, &p->prefix) < 0 || + nla_put_u32(skb, IFAL_LABEL, p->label) < 0) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + + return nlmsg_end(skb, nlh); +} + +static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct ip6addrlbl_entry *p; + int idx = 0, s_idx = cb->args[0]; + int err; + + rcu_read_lock(); + hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { + if (idx >= s_idx && + net_eq(ip6addrlbl_net(p), net)) { + err = ip6addrlbl_fill(skb, p, + ip6addrlbl_table.seq, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWADDRLABEL, + NLM_F_MULTI); + if (err <= 0) + break; + } + idx++; + } + rcu_read_unlock(); + cb->args[0] = idx; + return skb->len; +} + +static inline int ip6addrlbl_msgsize(void) +{ + return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + + nla_total_size(16) /* IFAL_ADDRESS */ + + nla_total_size(4); /* IFAL_LABEL */ +} + +static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(in_skb->sk); + struct ifaddrlblmsg *ifal; + struct nlattr *tb[IFAL_MAX+1]; + struct in6_addr *addr; + u32 lseq; + int err = 0; + struct ip6addrlbl_entry *p; + struct sk_buff *skb; + + err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy); + if (err < 0) + return err; + + ifal = nlmsg_data(nlh); + + if (ifal->ifal_family != AF_INET6 || + ifal->ifal_prefixlen != 128) + return -EINVAL; + + if (ifal->ifal_index && + !__dev_get_by_index(net, ifal->ifal_index)) + return -EINVAL; + + if (!tb[IFAL_ADDRESS]) + return -EINVAL; + addr = nla_data(tb[IFAL_ADDRESS]); + + rcu_read_lock(); + p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); + if (p && ip6addrlbl_hold(p)) + p = NULL; + lseq = ip6addrlbl_table.seq; + rcu_read_unlock(); + + if (!p) { + err = -ESRCH; + goto out; + } + + skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); + if (!skb) { + ip6addrlbl_put(p); + return -ENOBUFS; + } + + err = ip6addrlbl_fill(skb, p, lseq, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, + RTM_NEWADDRLABEL, 0); + + ip6addrlbl_put(p); + + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto out; + } + + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +out: + return err; +} + +void __init ipv6_addr_label_rtnl_register(void) +{ + __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, + NULL, NULL); + __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, + NULL, NULL); + __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, + ip6addrlbl_dump, NULL); +} + diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4f8795af2ed..7cb4392690d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1,14 +1,12 @@ /* * PF_INET6 socket protocol family - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/af_inet.c * - * $Id: af_inet6.c,v 1.66 2002/02/01 22:01:04 davem Exp $ - * * Fixes: * piggy, Karl Knutson : Socket protocol table * Hideaki YOSHIFUJI : sin6_scope_id support @@ -20,15 +18,15 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> -#include <linux/config.h> +#include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> -#include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> @@ -39,42 +37,59 @@ #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> +#include <linux/slab.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/icmpv6.h> -#include <linux/smp_lock.h> #include <linux/netfilter_ipv6.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> +#include <net/udplite.h> #include <net/tcp.h> -#include <net/ipip.h> +#include <net/ping.h> #include <net/protocol.h> #include <net/inet_common.h> +#include <net/route.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> +#include <net/ndisc.h> #ifdef CONFIG_IPV6_TUNNEL #include <net/ip6_tunnel.h> #endif #include <asm/uaccess.h> -#include <asm/system.h> +#include <linux/mroute6.h> MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); MODULE_LICENSE("GPL"); -int sysctl_ipv6_bindv6only; - -/* The inetsw table contains everything that inet_create needs to +/* The inetsw6 table contains everything that inet6_create needs to * build a new socket. */ static struct list_head inetsw6[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw6_lock); +struct ipv6_params ipv6_defaults = { + .disable_ipv6 = 0, + .autoconf = 1, +}; + +static int disable_ipv6_mod; + +module_param_named(disable, disable_ipv6_mod, int, 0444); +MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); + +module_param_named(disable_ipv6, ipv6_defaults.disable_ipv6, int, 0444); +MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); + +module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); +MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); + static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); @@ -82,24 +97,25 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } -static int inet6_create(struct socket *sock, int protocol) +static int inet6_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct inet_sock *inet; struct ipv6_pinfo *np; struct sock *sk; - struct list_head *p; struct inet_protosw *answer; struct proto *answer_prot; unsigned char answer_flags; - char answer_no_check; - int rc; + int try_loading_module = 0; + int err; /* Look for the requested type/protocol pair. */ - answer = NULL; +lookup_protocol: + err = -ESOCKTNOSUPPORT; rcu_read_lock(); - list_for_each_rcu(p, &inetsw6[sock->type]) { - answer = list_entry(p, struct inet_protosw, list); + list_for_each_entry_rcu(answer, &inetsw6[sock->type], list) { + err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) @@ -113,44 +129,59 @@ static int inet6_create(struct socket *sock, int protocol) if (IPPROTO_IP == answer->protocol) break; } - answer = NULL; + err = -EPROTONOSUPPORT; } - rc = -ESOCKTNOSUPPORT; - if (!answer) - goto out_rcu_unlock; - rc = -EPERM; - if (answer->capability > 0 && !capable(answer->capability)) - goto out_rcu_unlock; - rc = -EPROTONOSUPPORT; - if (!protocol) + if (err) { + if (try_loading_module < 2) { + rcu_read_unlock(); + /* + * Be more specific, e.g. net-pf-10-proto-132-type-1 + * (net-pf-PF_INET6-proto-IPPROTO_SCTP-type-SOCK_STREAM) + */ + if (++try_loading_module == 1) + request_module("net-pf-%d-proto-%d-type-%d", + PF_INET6, protocol, sock->type); + /* + * Fall back to generic, e.g. net-pf-10-proto-132 + * (net-pf-PF_INET6-proto-IPPROTO_SCTP) + */ + else + request_module("net-pf-%d-proto-%d", + PF_INET6, protocol); + goto lookup_protocol; + } else + goto out_rcu_unlock; + } + + err = -EPERM; + if (sock->type == SOCK_RAW && !kern && + !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; - answer_prot = answer->prot; - answer_no_check = answer->no_check; answer_flags = answer->flags; rcu_read_unlock(); - BUG_TRAP(answer_prot->slab != NULL); + WARN_ON(answer_prot->slab == NULL); - rc = -ENOBUFS; - sk = sk_alloc(PF_INET6, GFP_KERNEL, answer_prot, 1); + err = -ENOBUFS; + sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot); if (sk == NULL) goto out; sock_init_data(sock, sk); - rc = 0; - sk->sk_no_check = answer_no_check; + err = 0; if (INET_PROTOSW_REUSE & answer_flags) - sk->sk_reuse = 1; + sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); + inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { - inet->num = protocol; + inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } @@ -163,11 +194,11 @@ static int inet6_create(struct socket *sock, int protocol) inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk); np->hop_limit = -1; - np->mcast_hops = -1; + np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->ipv6only = sysctl_ipv6_bindv6only; - + np->ipv6only = net->ipv6.sysctl.bindv6only; + /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. */ @@ -177,12 +208,13 @@ static int inet6_create(struct socket *sock, int protocol) inet->mc_ttl = 1; inet->mc_index = 0; inet->mc_list = NULL; + inet->rcv_tos = 0; - if (ipv4_config.no_pmtu_disc) + if (net->ipv4.sysctl_ip_no_pmtu_disc) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; - /* + /* * Increment only the relevant sk_prot->socks debug field, this changes * the previous behaviour of incrementing both the equivalent to * answer->prot->socks (inet6_sock_nr) and inet_sock_nr. @@ -193,23 +225,23 @@ static int inet6_create(struct socket *sock, int protocol) */ sk_refcnt_debug_inc(sk); - if (inet->num) { + if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically shares. */ - inet->sport = ntohs(inet->num); + inet->inet_sport = htons(inet->inet_num); sk->sk_prot->hash(sk); } if (sk->sk_prot->init) { - rc = sk->sk_prot->init(sk); - if (rc) { + err = sk->sk_prot->init(sk); + if (err) { sk_common_release(sk); goto out; } } out: - return rc; + return err; out_rcu_unlock: rcu_read_unlock(); goto out; @@ -219,11 +251,12 @@ out_rcu_unlock: /* bind for INET6 API */ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_in6 *addr=(struct sockaddr_in6 *)uaddr; + struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - __u32 v4addr = 0; + struct net *net = sock_net(sk); + __be32 v4addr = 0; unsigned short snum; int addr_type = 0; int err = 0; @@ -234,26 +267,47 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; + + if (addr->sin6_family != AF_INET6) + return -EAFNOSUPPORT; + addr_type = ipv6_addr_type(&addr->sin6_addr); if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM) return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; lock_sock(sk); /* Check these errors (active socket, double bind). */ - if (sk->sk_state != TCP_CLOSE || inet->num) { + if (sk->sk_state != TCP_CLOSE || inet->inet_num) { err = -EINVAL; goto out; } /* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { + int chk_addr_ret; + + /* Binding to v4-mapped address on a v6-only socket + * makes no sense + */ + if (np->ipv6only) { + err = -EINVAL; + goto out; + } + + /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; - if (inet_addr_type(v4addr) != RTN_LOCAL) { + chk_addr_ret = inet_addr_type(net, v4addr); + if (!sysctl_ip_nonlocal_bind && + !(inet->freebind || inet->transparent) && + v4addr != htonl(INADDR_ANY) && + chk_addr_ret != RTN_LOCAL && + chk_addr_ret != RTN_MULTICAST && + chk_addr_ret != RTN_BROADCAST) { err = -EADDRNOTAVAIL; goto out; } @@ -261,7 +315,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; - if (addr_type & IPV6_ADDR_LINKLOCAL) { + rcu_read_lock(); + if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another one @@ -269,16 +324,16 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ sk->sk_bound_dev_if = addr->sin6_scope_id; } - + /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; - goto out; + goto out_unlock; } - dev = dev_get_by_index(sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; - goto out; + goto out_unlock; } } @@ -287,25 +342,24 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); + if (!(inet->freebind || inet->transparent) && + !ipv6_chk_addr(net, &addr->sin6_addr, + dev, 0)) { err = -EADDRNOTAVAIL; - goto out; + goto out_unlock; } } - if (dev) - dev_put(dev); + rcu_read_unlock(); } } - inet->rcv_saddr = v4addr; - inet->saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + inet->inet_saddr = v4addr; + + sk->sk_v6_rcv_saddr = addr->sin6_addr; - ipv6_addr_copy(&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)) { @@ -314,17 +368,24 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - if (addr_type != IPV6_ADDR_ANY) + if (addr_type != IPV6_ADDR_ANY) { sk->sk_userlocks |= SOCK_BINDADDR_LOCK; + if (addr_type != IPV6_ADDR_MAPPED) + np->ipv6only = 1; + } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = ntohs(inet->num); - inet->dport = 0; - inet->daddr = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_dport = 0; + inet->inet_daddr = 0; out: release_sock(sk); return err; +out_unlock: + rcu_read_unlock(); + goto out; } +EXPORT_SYMBOL(inet6_bind); int inet6_release(struct socket *sock) { @@ -341,22 +402,22 @@ int inet6_release(struct socket *sock) return inet_release(sock); } +EXPORT_SYMBOL(inet6_release); -int inet6_destroy_sock(struct sock *sk) +void inet6_destroy_sock(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct ipv6_txoptions *opt; - /* - * Release destination entry - */ - - sk_dst_reset(sk); - /* Release rx options */ - if ((skb = xchg(&np->pktoptions, NULL)) != NULL) + skb = xchg(&np->pktoptions, NULL); + if (skb != NULL) + kfree_skb(skb); + + skb = xchg(&np->rxpmtu, NULL); + if (skb != NULL) kfree_skb(skb); /* Free flowlabels */ @@ -364,177 +425,159 @@ int inet6_destroy_sock(struct sock *sk) /* Free tx options */ - if ((opt = xchg(&np->opt, NULL)) != NULL) + opt = xchg(&np->opt, NULL); + if (opt != NULL) sock_kfree_s(sk, opt, opt->tot_len); - - return 0; } +EXPORT_SYMBOL_GPL(inet6_destroy_sock); /* * This does both peername and sockname. */ - + int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { - struct sockaddr_in6 *sin=(struct sockaddr_in6 *)uaddr; + struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - + sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (peer) { - if (!inet->dport) + if (!inet->inet_dport) return -ENOTCONN; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1) return -ENOTCONN; - sin->sin6_port = inet->dport; - ipv6_addr_copy(&sin->sin6_addr, &np->daddr); + sin->sin6_port = inet->inet_dport; + sin->sin6_addr = sk->sk_v6_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); + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + sin->sin6_addr = np->saddr; else - ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); + sin->sin6_addr = sk->sk_v6_rcv_saddr; - sin->sin6_port = inet->sport; + sin->sin6_port = inet->inet_sport; } - if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin->sin6_scope_id = sk->sk_bound_dev_if; + sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, + sk->sk_bound_dev_if); *uaddr_len = sizeof(*sin); - return(0); + return 0; } +EXPORT_SYMBOL(inet6_getname); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; - int err = -EINVAL; + struct net *net = sock_net(sk); - switch(cmd) - { + switch (cmd) { case SIOCGSTAMP: return sock_get_timestamp(sk, (struct timeval __user *)arg); + case SIOCGSTAMPNS: + return sock_get_timestampns(sk, (struct timespec __user *)arg); + case SIOCADDRT: case SIOCDELRT: - - return(ipv6_route_ioctl(cmd,(void __user *)arg)); + + return ipv6_route_ioctl(net, cmd, (void __user *)arg); case SIOCSIFADDR: - return addrconf_add_ifaddr((void __user *) arg); + return addrconf_add_ifaddr(net, (void __user *) arg); case SIOCDIFADDR: - return addrconf_del_ifaddr((void __user *) arg); + return addrconf_del_ifaddr(net, (void __user *) arg); case SIOCSIFDSTADDR: - return addrconf_set_dstaddr((void __user *) arg); + return addrconf_set_dstaddr(net, (void __user *) arg); default: - if (!sk->sk_prot->ioctl || - (err = sk->sk_prot->ioctl(sk, cmd, arg)) == -ENOIOCTLCMD) - return(dev_ioctl(cmd,(void __user *) arg)); - return err; + if (!sk->sk_prot->ioctl) + return -ENOIOCTLCMD; + return sk->sk_prot->ioctl(sk, cmd, arg); } /*NOTREACHED*/ - return(0); + return 0; } - -struct proto_ops inet6_stream_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_stream_connect, /* ok */ - .socketpair = sock_no_socketpair, /* a do nothing */ - .accept = inet_accept, /* ok */ - .getname = inet6_getname, - .poll = tcp_poll, /* ok */ - .ioctl = inet6_ioctl, /* must change */ - .listen = inet_listen, /* ok */ - .shutdown = inet_shutdown, /* ok */ - .setsockopt = sock_common_setsockopt, /* ok */ - .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = sock_common_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = tcp_sendpage +EXPORT_SYMBOL(inet6_ioctl); + +const struct proto_ops inet6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_stream_connect, /* ok */ + .socketpair = sock_no_socketpair, /* a do nothing */ + .accept = inet_accept, /* ok */ + .getname = inet6_getname, + .poll = tcp_poll, /* ok */ + .ioctl = inet6_ioctl, /* must change */ + .listen = inet_listen, /* ok */ + .shutdown = inet_shutdown, /* ok */ + .setsockopt = sock_common_setsockopt, /* ok */ + .getsockopt = sock_common_getsockopt, /* ok */ + .sendmsg = inet_sendmsg, /* ok */ + .recvmsg = inet_recvmsg, /* ok */ + .mmap = sock_no_mmap, + .sendpage = inet_sendpage, + .splice_read = tcp_splice_read, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; -struct proto_ops inet6_dgram_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_dgram_connect, /* ok */ - .socketpair = sock_no_socketpair, /* a do nothing */ - .accept = sock_no_accept, /* a do nothing */ - .getname = inet6_getname, - .poll = udp_poll, /* ok */ - .ioctl = inet6_ioctl, /* must change */ - .listen = sock_no_listen, /* ok */ - .shutdown = inet_shutdown, /* ok */ - .setsockopt = sock_common_setsockopt, /* ok */ - .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = sock_common_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, +const struct proto_ops inet6_dgram_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_dgram_connect, /* ok */ + .socketpair = sock_no_socketpair, /* a do nothing */ + .accept = sock_no_accept, /* a do nothing */ + .getname = inet6_getname, + .poll = udp_poll, /* ok */ + .ioctl = inet6_ioctl, /* must change */ + .listen = sock_no_listen, /* ok */ + .shutdown = inet_shutdown, /* ok */ + .setsockopt = sock_common_setsockopt, /* ok */ + .getsockopt = sock_common_getsockopt, /* ok */ + .sendmsg = inet_sendmsg, /* ok */ + .recvmsg = inet_recvmsg, /* ok */ + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; -static struct net_proto_family inet6_family_ops = { +static const struct net_proto_family inet6_family_ops = { .family = PF_INET6, .create = inet6_create, .owner = THIS_MODULE, }; -/* Same as inet6_dgram_ops, sans udp_poll. */ -static struct proto_ops inet6_sockraw_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_dgram_connect, /* ok */ - .socketpair = sock_no_socketpair, /* a do nothing */ - .accept = sock_no_accept, /* a do nothing */ - .getname = inet6_getname, - .poll = datagram_poll, /* ok */ - .ioctl = inet6_ioctl, /* must change */ - .listen = sock_no_listen, /* ok */ - .shutdown = inet_shutdown, /* ok */ - .setsockopt = sock_common_setsockopt, /* ok */ - .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = sock_common_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, -}; - -static struct inet_protosw rawv6_protosw = { - .type = SOCK_RAW, - .protocol = IPPROTO_IP, /* wild card */ - .prot = &rawv6_prot, - .ops = &inet6_sockraw_ops, - .capability = CAP_NET_RAW, - .no_check = UDP_CSUM_DEFAULT, - .flags = INET_PROTOSW_REUSE, -}; - -void -inet6_register_protosw(struct inet_protosw *p) +int inet6_register_protosw(struct inet_protosw *p) { struct list_head *lh; struct inet_protosw *answer; - int protocol = p->protocol; struct list_head *last_perm; + int protocol = p->protocol; + int ret; spin_lock_bh(&inetsw6_lock); + ret = -EINVAL; if (p->type >= SOCK_MAX) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ answer = NULL; + ret = -EPERM; last_perm = &inetsw6[p->type]; list_for_each(lh, &inetsw6[p->type]) { answer = list_entry(lh, struct inet_protosw, list); @@ -554,32 +597,31 @@ inet6_register_protosw(struct inet_protosw *p) /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with * a wild-card protocol. But it is allowed to override any existing - * non-permanent entry. This means that when we remove this entry, the + * non-permanent entry. This means that when we remove this entry, the * system automatically returns to the old behavior. */ list_add_rcu(&p->list, last_perm); + ret = 0; out: spin_unlock_bh(&inetsw6_lock); - return; + return ret; out_permanent: - printk(KERN_ERR "Attempt to override permanent protocol %d.\n", - protocol); + pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: - printk(KERN_ERR - "Ignoring attempt to register invalid socket type %d.\n", + pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } +EXPORT_SYMBOL(inet6_register_protosw); void inet6_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { - printk(KERN_ERR - "Attempt to unregister permanent protocol %d.\n", + pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw6_lock); @@ -589,89 +631,207 @@ inet6_unregister_protosw(struct inet_protosw *p) synchronize_net(); } } +EXPORT_SYMBOL(inet6_unregister_protosw); -int -snmp6_mib_init(void *ptr[2], size_t mibsize, size_t mibalign) +int inet6_sk_rebuild_header(struct sock *sk) { - if (ptr == NULL) - return -EINVAL; - - ptr[0] = __alloc_percpu(mibsize, mibalign); - if (!ptr[0]) - goto err0; + struct ipv6_pinfo *np = inet6_sk(sk); + struct dst_entry *dst; + + dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst == NULL) { + struct inet_sock *inet = inet_sk(sk); + struct in6_addr *final_p, final; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = sk->sk_protocol; + fl6.daddr = sk->sk_v6_daddr; + fl6.saddr = np->saddr; + fl6.flowlabel = np->flow_label; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_dport = inet->inet_dport; + fl6.fl6_sport = inet->inet_sport; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + final_p = fl6_update_dst(&fl6, np->opt, &final); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + sk->sk_route_caps = 0; + sk->sk_err_soft = -PTR_ERR(dst); + return PTR_ERR(dst); + } - ptr[1] = __alloc_percpu(mibsize, mibalign); - if (!ptr[1]) - goto err1; + __ip6_dst_store(sk, dst, NULL, NULL); + } return 0; +} +EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header); -err1: - free_percpu(ptr[0]); - ptr[0] = NULL; -err0: - return -ENOMEM; +bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) +{ + const struct ipv6_pinfo *np = inet6_sk(sk); + const struct inet6_skb_parm *opt = IP6CB(skb); + + if (np->rxopt.all) { + if ((opt->hop && (np->rxopt.bits.hopopts || + np->rxopt.bits.ohopopts)) || + (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) && + np->rxopt.bits.rxflow) || + (opt->srcrt && (np->rxopt.bits.srcrt || + np->rxopt.bits.osrcrt)) || + ((opt->dst1 || opt->dst0) && + (np->rxopt.bits.dstopts || np->rxopt.bits.odstopts))) + return true; + } + return false; } +EXPORT_SYMBOL_GPL(ipv6_opt_accepted); -void -snmp6_mib_free(void *ptr[2]) +static struct packet_type ipv6_packet_type __read_mostly = { + .type = cpu_to_be16(ETH_P_IPV6), + .func = ipv6_rcv, +}; + +static int __init ipv6_packet_init(void) +{ + dev_add_pack(&ipv6_packet_type); + return 0; +} + +static void ipv6_packet_cleanup(void) { - if (ptr == NULL) - return; - if (ptr[0]) - free_percpu(ptr[0]); - if (ptr[1]) - free_percpu(ptr[1]); - ptr[0] = ptr[1] = NULL; + dev_remove_pack(&ipv6_packet_type); } -static int __init init_ipv6_mibs(void) +static int __net_init ipv6_init_mibs(struct net *net) { - if (snmp6_mib_init((void **)ipv6_statistics, sizeof (struct ipstats_mib), - __alignof__(struct ipstats_mib)) < 0) + int i; + + net->mib.udp_stats_in6 = alloc_percpu(struct udp_mib); + if (!net->mib.udp_stats_in6) + return -ENOMEM; + net->mib.udplite_stats_in6 = alloc_percpu(struct udp_mib); + if (!net->mib.udplite_stats_in6) + goto err_udplite_mib; + net->mib.ipv6_statistics = alloc_percpu(struct ipstats_mib); + if (!net->mib.ipv6_statistics) goto err_ip_mib; - if (snmp6_mib_init((void **)icmpv6_statistics, sizeof (struct icmpv6_mib), - __alignof__(struct icmpv6_mib)) < 0) + + for_each_possible_cpu(i) { + struct ipstats_mib *af_inet6_stats; + af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics, i); + u64_stats_init(&af_inet6_stats->syncp); + } + + + net->mib.icmpv6_statistics = alloc_percpu(struct icmpv6_mib); + if (!net->mib.icmpv6_statistics) goto err_icmp_mib; - if (snmp6_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib), - __alignof__(struct udp_mib)) < 0) - goto err_udp_mib; + net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib), + GFP_KERNEL); + if (!net->mib.icmpv6msg_statistics) + goto err_icmpmsg_mib; return 0; -err_udp_mib: - snmp6_mib_free((void **)icmpv6_statistics); +err_icmpmsg_mib: + free_percpu(net->mib.icmpv6_statistics); err_icmp_mib: - snmp6_mib_free((void **)ipv6_statistics); + free_percpu(net->mib.ipv6_statistics); err_ip_mib: + free_percpu(net->mib.udplite_stats_in6); +err_udplite_mib: + free_percpu(net->mib.udp_stats_in6); return -ENOMEM; - } -static void cleanup_ipv6_mibs(void) +static void ipv6_cleanup_mibs(struct net *net) { - snmp6_mib_free((void **)ipv6_statistics); - snmp6_mib_free((void **)icmpv6_statistics); - snmp6_mib_free((void **)udp_stats_in6); + free_percpu(net->mib.udp_stats_in6); + free_percpu(net->mib.udplite_stats_in6); + free_percpu(net->mib.ipv6_statistics); + free_percpu(net->mib.icmpv6_statistics); + kfree(net->mib.icmpv6msg_statistics); } -static int __init inet6_init(void) +static int __net_init inet6_net_init(struct net *net) { - struct sk_buff *dummy_skb; - struct list_head *r; - int err; + int err = 0; + + net->ipv6.sysctl.bindv6only = 0; + net->ipv6.sysctl.icmpv6_time = 1*HZ; + net->ipv6.sysctl.flowlabel_consistency = 1; + atomic_set(&net->ipv6.rt_genid, 0); -#ifdef MODULE -#if 0 /* FIXME --RR */ - if (!mod_member_present(&__this_module, can_unload)) - return -EINVAL; + err = ipv6_init_mibs(net); + if (err) + return err; +#ifdef CONFIG_PROC_FS + err = udp6_proc_init(net); + if (err) + goto out; + err = tcp6_proc_init(net); + if (err) + goto proc_tcp6_fail; + err = ac6_proc_init(net); + if (err) + goto proc_ac6_fail; +#endif + return err; - __this_module.can_unload = &ipv6_unload; +#ifdef CONFIG_PROC_FS +proc_ac6_fail: + tcp6_proc_exit(net); +proc_tcp6_fail: + udp6_proc_exit(net); +out: + ipv6_cleanup_mibs(net); + return err; #endif +} + +static void __net_exit inet6_net_exit(struct net *net) +{ +#ifdef CONFIG_PROC_FS + udp6_proc_exit(net); + tcp6_proc_exit(net); + ac6_proc_exit(net); #endif + ipv6_cleanup_mibs(net); +} - if (sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)) { - printk(KERN_CRIT "inet6_proto_init: size fault\n"); - return -EINVAL; +static struct pernet_operations inet6_net_ops = { + .init = inet6_net_init, + .exit = inet6_net_exit, +}; + +static const struct ipv6_stub ipv6_stub_impl = { + .ipv6_sock_mc_join = ipv6_sock_mc_join, + .ipv6_sock_mc_drop = ipv6_sock_mc_drop, + .ipv6_dst_lookup = ip6_dst_lookup, + .udpv6_encap_enable = udpv6_encap_enable, + .ndisc_send_na = ndisc_send_na, + .nd_tbl = &nd_tbl, +}; + +static int __init inet6_init(void) +{ + struct list_head *r; + int err = 0; + + BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); + + /* Register the socket-side information for inet6_create. */ + for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) + INIT_LIST_HEAD(r); + + if (disable_ipv6_mod) { + pr_info("Loaded, but administratively disabled, reboot required to enable\n"); + goto out; } err = proto_register(&tcpv6_prot, 1); @@ -682,49 +842,57 @@ static int __init inet6_init(void) if (err) goto out_unregister_tcp_proto; - err = proto_register(&rawv6_prot, 1); + err = proto_register(&udplitev6_prot, 1); if (err) goto out_unregister_udp_proto; + err = proto_register(&rawv6_prot, 1); + if (err) + goto out_unregister_udplite_proto; - /* Register the socket-side information for inet6_create. */ - for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) - INIT_LIST_HEAD(r); + err = proto_register(&pingv6_prot, 1); + if (err) + goto out_unregister_ping_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ - inet6_register_protosw(&rawv6_protosw); + err = rawv6_init(); + if (err) + goto out_unregister_raw_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) */ - (void) sock_register(&inet6_family_ops); - - /* Initialise ipv6 mibs */ - err = init_ipv6_mibs(); + err = sock_register(&inet6_family_ops); if (err) - goto out_unregister_raw_proto; - + goto out_sock_register_fail; + /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance - * in a host availiable by both INET and INET6 APIs and + * in a host available by both INET and INET6 APIs and * able to communicate via both network protocols. */ -#ifdef CONFIG_SYSCTL - ipv6_sysctl_register(); -#endif - err = icmpv6_init(&inet6_family_ops); + err = register_pernet_subsys(&inet6_net_ops); + if (err) + goto register_pernet_fail; + err = icmpv6_init(); if (err) goto icmp_fail; - err = ndisc_init(&inet6_family_ops); + err = ip6_mr_init(); + if (err) + goto ipmr_fail; + err = ndisc_init(); if (err) goto ndisc_fail; - err = igmp6_init(&inet6_family_ops); + err = igmp6_init(); if (err) goto igmp_fail; + + ipv6_stub = &ipv6_stub_impl; + err = ipv6_netfilter_init(); if (err) goto netfilter_fail; @@ -733,54 +901,96 @@ static int __init inet6_init(void) err = -ENOMEM; if (raw6_proc_init()) goto proc_raw6_fail; - if (tcp6_proc_init()) - goto proc_tcp6_fail; - if (udp6_proc_init()) - goto proc_udp6_fail; + if (udplite6_proc_init()) + goto proc_udplite6_fail; if (ipv6_misc_proc_init()) goto proc_misc6_fail; - - if (ac6_proc_init()) - goto proc_anycast6_fail; if (if6_proc_init()) goto proc_if6_fail; #endif - ip6_route_init(); - ip6_flowlabel_init(); + err = ip6_route_init(); + if (err) + goto ip6_route_fail; + err = ndisc_late_init(); + if (err) + goto ndisc_late_fail; + err = ip6_flowlabel_init(); + if (err) + goto ip6_flowlabel_fail; err = addrconf_init(); if (err) goto addrconf_fail; - sit_init(); /* Init v6 extension headers. */ - ipv6_rthdr_init(); - ipv6_frag_init(); - ipv6_nodata_init(); - ipv6_destopt_init(); + err = ipv6_exthdrs_init(); + if (err) + goto ipv6_exthdrs_fail; + + err = ipv6_frag_init(); + if (err) + goto ipv6_frag_fail; /* Init v6 transport protocols. */ - udpv6_init(); - tcpv6_init(); + err = udpv6_init(); + if (err) + goto udpv6_fail; - ipv6_packet_init(); - err = 0; + err = udplitev6_init(); + if (err) + goto udplitev6_fail; + + err = tcpv6_init(); + if (err) + goto tcpv6_fail; + + err = ipv6_packet_init(); + if (err) + goto ipv6_packet_fail; + + err = pingv6_init(); + if (err) + goto pingv6_fail; + +#ifdef CONFIG_SYSCTL + err = ipv6_sysctl_register(); + if (err) + goto sysctl_fail; +#endif out: return err; +#ifdef CONFIG_SYSCTL +sysctl_fail: + pingv6_exit(); +#endif +pingv6_fail: + ipv6_packet_cleanup(); +ipv6_packet_fail: + tcpv6_exit(); +tcpv6_fail: + udplitev6_exit(); +udplitev6_fail: + udpv6_exit(); +udpv6_fail: + ipv6_frag_exit(); +ipv6_frag_fail: + ipv6_exthdrs_exit(); +ipv6_exthdrs_fail: + addrconf_cleanup(); addrconf_fail: ip6_flowlabel_cleanup(); +ip6_flowlabel_fail: + ndisc_late_cleanup(); +ndisc_late_fail: ip6_route_cleanup(); +ip6_route_fail: #ifdef CONFIG_PROC_FS if6_proc_exit(); proc_if6_fail: - ac6_proc_exit(); -proc_anycast6_fail: ipv6_misc_proc_exit(); proc_misc6_fail: - udp6_proc_exit(); -proc_udp6_fail: - tcp6_proc_exit(); -proc_tcp6_fail: + udplite6_proc_exit(); +proc_udplite6_fail: raw6_proc_exit(); proc_raw6_fail: #endif @@ -790,14 +1000,22 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: + ip6_mr_cleanup(); +ipmr_fail: icmpv6_cleanup(); icmp_fail: -#ifdef CONFIG_SYSCTL - ipv6_sysctl_unregister(); -#endif - cleanup_ipv6_mibs(); + unregister_pernet_subsys(&inet6_net_ops); +register_pernet_fail: + sock_unregister(PF_INET6); + rtnl_unregister_all(PF_INET6); +out_sock_register_fail: + rawv6_exit(); +out_unregister_ping_proto: + proto_unregister(&pingv6_prot); out_unregister_raw_proto: proto_unregister(&rawv6_prot); +out_unregister_udplite_proto: + proto_unregister(&udplitev6_prot); out_unregister_udp_proto: proto_unregister(&udpv6_prot); out_unregister_tcp_proto: @@ -806,36 +1024,4 @@ out_unregister_tcp_proto: } module_init(inet6_init); -static void __exit inet6_exit(void) -{ - /* First of all disallow new sockets creation. */ - sock_unregister(PF_INET6); -#ifdef CONFIG_PROC_FS - if6_proc_exit(); - ac6_proc_exit(); - ipv6_misc_proc_exit(); - udp6_proc_exit(); - tcp6_proc_exit(); - raw6_proc_exit(); -#endif - /* Cleanup code parts. */ - sit_cleanup(); - ip6_flowlabel_cleanup(); - addrconf_cleanup(); - ip6_route_cleanup(); - ipv6_packet_cleanup(); - igmp6_cleanup(); - ipv6_netfilter_fini(); - ndisc_cleanup(); - icmpv6_cleanup(); -#ifdef CONFIG_SYSCTL - ipv6_sysctl_unregister(); -#endif - cleanup_ipv6_mibs(); - proto_unregister(&rawv6_prot); - proto_unregister(&udpv6_prot); - proto_unregister(&tcpv6_prot); -} -module_exit(inet6_exit); - MODULE_ALIAS_NETPROTO(PF_INET6); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index f3629730eb1..72a4930bdc0 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -1,42 +1,119 @@ /* * Copyright (C)2002 USAGI/WIDE Project - * + * * 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. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * + * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors * - * Mitsuru KANDA @USAGI : IPv6 Support + * Mitsuru KANDA @USAGI : IPv6 Support * Kazunori MIYAZAWA @USAGI : * Kunihiro Ishiguro <kunihiro@ipinfusion.com> - * + * * This file is derived from net/ipv4/ah.c. */ -#include <linux/config.h> +#define pr_fmt(fmt) "IPv6: " fmt + +#include <crypto/hash.h> #include <linux/module.h> +#include <linux/slab.h> #include <net/ip.h> #include <net/ah.h> #include <linux/crypto.h> #include <linux/pfkeyv2.h> #include <linux/string.h> +#include <linux/scatterlist.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> +#include <net/protocol.h> #include <net/xfrm.h> -#include <asm/scatterlist.h> -static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) +#define IPV6HDR_BASELEN 8 + +struct tmp_ext { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + struct in6_addr saddr; +#endif + struct in6_addr daddr; + char hdrs[0]; +}; + +struct ah_skb_cb { + struct xfrm_skb_cb xfrm; + void *tmp; +}; + +#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0])) + +static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags, + unsigned int size) +{ + unsigned int len; + + len = size + crypto_ahash_digestsize(ahash) + + (crypto_ahash_alignmask(ahash) & + ~(crypto_tfm_ctx_alignment() - 1)); + + len = ALIGN(len, crypto_tfm_ctx_alignment()); + + len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash); + len = ALIGN(len, __alignof__(struct scatterlist)); + + len += sizeof(struct scatterlist) * nfrags; + + return kmalloc(len, GFP_ATOMIC); +} + +static inline struct tmp_ext *ah_tmp_ext(void *base) +{ + return base + IPV6HDR_BASELEN; +} + +static inline u8 *ah_tmp_auth(u8 *tmp, unsigned int offset) +{ + return tmp + offset; +} + +static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp, + unsigned int offset) +{ + return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1); +} + +static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash, + u8 *icv) +{ + struct ahash_request *req; + + req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash), + crypto_tfm_ctx_alignment()); + + ahash_request_set_tfm(req, ahash); + + return req; +} + +static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, + struct ahash_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_ahash_reqsize(ahash), + __alignof__(struct scatterlist)); +} + +static bool zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) { u8 *opt = (u8 *)opthdr; int len = ipv6_optlen(opthdr); @@ -50,11 +127,11 @@ static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) switch (opt[off]) { - case IPV6_TLV_PAD0: + case IPV6_TLV_PAD1: optlen = 1; break; default: - if (len < 2) + if (len < 2) goto bad; optlen = opt[off+1]+2; if (len < optlen) @@ -68,11 +145,73 @@ static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) len -= optlen; } if (len == 0) - return 1; + return true; bad: - return 0; + return false; +} + +#if IS_ENABLED(CONFIG_IPV6_MIP6) +/** + * ipv6_rearrange_destopt - rearrange IPv6 destination options header + * @iph: IPv6 header + * @destopt: destionation options header + */ +static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *destopt) +{ + u8 *opt = (u8 *)destopt; + int len = ipv6_optlen(destopt); + int off = 0; + int optlen = 0; + + off += 2; + len -= 2; + + while (len > 0) { + + switch (opt[off]) { + + case IPV6_TLV_PAD1: + optlen = 1; + break; + default: + if (len < 2) + goto bad; + optlen = opt[off+1]+2; + if (len < optlen) + goto bad; + + /* Rearrange the source address in @iph and the + * addresses in home address option for final source. + * See 11.3.2 of RFC 3775 for details. + */ + if (opt[off] == IPV6_TLV_HAO) { + struct in6_addr final_addr; + struct ipv6_destopt_hao *hao; + + hao = (struct ipv6_destopt_hao *)&opt[off]; + if (hao->length != sizeof(hao->addr)) { + net_warn_ratelimited("destopt hao: invalid header length: %u\n", + hao->length); + goto bad; + } + final_addr = hao->addr; + hao->addr = iph->saddr; + iph->saddr = final_addr; + } + break; + } + + off += optlen; + len -= optlen; + } + /* Note: ok if len == 0 */ +bad: + return; } +#else +static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *destopt) {} +#endif /** * ipv6_rearrange_rthdr - rearrange IPv6 routing header @@ -92,7 +231,7 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) segments_left = rthdr->segments_left; if (segments_left == 0) return; - rthdr->segments_left = 0; + rthdr->segments_left = 0; /* The value of rthdr->hdrlen has been verified either by the system * call if it is locally generated, or by ipv6_rthdr_rcv() for incoming @@ -104,16 +243,16 @@ 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) +static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) { union { struct ipv6hdr *iph; @@ -128,8 +267,10 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len) while (exthdr.raw < end) { switch (nexthdr) { - case NEXTHDR_HOP: case NEXTHDR_DEST: + if (dir == XFRM_POLICY_OUT) + ipv6_rearrange_destopt(iph, exthdr.opth); + case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { LIMIT_NETDEBUG( KERN_WARNING "overrun %sopts\n", @@ -154,49 +295,119 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len) return 0; } +static void ah6_output_done(struct crypto_async_request *base, int err) +{ + int extlen; + u8 *iph_base; + u8 *icv; + struct sk_buff *skb = base->data; + struct xfrm_state *x = skb_dst(skb)->xfrm; + struct ah_data *ahp = x->data; + struct ipv6hdr *top_iph = ipv6_hdr(skb); + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + struct tmp_ext *iph_ext; + + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + iph_base = AH_SKB_CB(skb)->tmp; + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahp->ahash, iph_ext, extlen); + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + memcpy(&top_iph->saddr, iph_ext, extlen); +#else + memcpy(&top_iph->daddr, iph_ext, extlen); +#endif + } + + kfree(AH_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + int nfrags; int extlen; + u8 *iph_base; + u8 *icv; + u8 nexthdr; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ipv6hdr *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - u8 nexthdr; - char tmp_base[8]; - struct { - struct in6_addr daddr; - char hdrs[0]; - } *tmp_ext; + struct tmp_ext *iph_ext; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; - top_iph = (struct ipv6hdr *)skb->data; + ahp = x->data; + ahash = ahp->ahash; + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; + + skb_push(skb, -skb_network_offset(skb)); + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + err = -ENOMEM; + iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN + + extlen + seqhi_len); + if (!iph_base) + goto out; + + iph_ext = ah_tmp_ext(iph_base); + seqhi = (__be32 *)((char *)iph_ext + extlen); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; + + ah = ip_auth_hdr(skb); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + + top_iph = ipv6_hdr(skb); top_iph->payload_len = htons(skb->len - sizeof(*top_iph)); - nexthdr = *skb->nh.raw; - *skb->nh.raw = IPPROTO_AH; + nexthdr = *skb_mac_header(skb); + *skb_mac_header(skb) = IPPROTO_AH; /* When there are no extension headers, we only need to save the first * 8 bytes of the base IP header. */ - memcpy(tmp_base, top_iph, sizeof(tmp_base)); + memcpy(iph_base, top_iph, IPV6HDR_BASELEN); - tmp_ext = NULL; - extlen = skb->h.raw - (unsigned char *)(top_iph + 1); if (extlen) { - extlen += sizeof(*tmp_ext); - tmp_ext = kmalloc(extlen, GFP_ATOMIC); - if (!tmp_ext) { - err = -ENOMEM; - goto error; - } - memcpy(tmp_ext, &top_iph->daddr, extlen); +#if IS_ENABLED(CONFIG_IPV6_MIP6) + memcpy(iph_ext, &top_iph->saddr, extlen); +#else + memcpy(iph_ext, &top_iph->daddr, extlen); +#endif err = ipv6_clear_mutable_options(top_iph, - extlen - sizeof(*tmp_ext) + - sizeof(*top_iph)); + extlen - sizeof(*iph_ext) + + sizeof(*top_iph), + XFRM_POLICY_OUT); if (err) - goto error_free_iph; + goto out_free; } - ah = (struct ip_auth_hdr *)skb->h.raw; ah->nexthdr = nexthdr; top_iph->priority = 0; @@ -205,29 +416,89 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->flow_lbl[2] = 0; top_iph->hop_limit = 0; - ahp = x->data; - ah->hdrlen = (XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + - ahp->icv_trunc_len) >> 2) - 2; + ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; ah->reserved = 0; ah->spi = x->id.spi; - ah->seq_no = htonl(++x->replay.oseq); - ahp->icv(ahp, skb, ah->auth_data); + ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - err = 0; + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - memcpy(top_iph, tmp_base, sizeof(tmp_base)); - if (tmp_ext) { - memcpy(&top_iph->daddr, tmp_ext, extlen); -error_free_iph: - kfree(tmp_ext); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); + ahash_request_set_callback(req, 0, ah6_output_done, skb); -error: + AH_SKB_CB(skb)->tmp = iph_base; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; + } + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + memcpy(&top_iph->saddr, iph_ext, extlen); +#else + memcpy(&top_iph->daddr, iph_ext, extlen); +#endif + } + +out_free: + kfree(iph_base); +out: return err; } -static int ah6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb) +static void ah6_input_done(struct crypto_async_request *base, int err) +{ + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = xfrm_input_state(skb); + struct ah_data *ahp = x->data; + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int hdr_len = skb_network_header_len(skb); + int ah_hlen = (ah->hdrlen + 2) << 2; + + work_iph = AH_SKB_CB(skb)->tmp; + auth_data = ah_tmp_auth(work_iph, hdr_len); + icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); + + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + 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); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); +out: + kfree(AH_SKB_CB(skb)->tmp); + xfrm_input_resume(skb, err); +} + + + +static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) { /* * Before process AH @@ -236,173 +507,233 @@ static int ah6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc * * To erase AH: * Keeping copy of cleared headers. After AH processing, - * Moving the pointer of skb->nh.raw by using skb_pull as long as AH - * header length. Then copy back the copy as long as hdr_len + * Moving the pointer of skb->network_header by using skb_pull as long + * as AH header length. Then copy back the copy as long as hdr_len * If destination header following AH exists, copy it into after [Ext2]. - * + * * |<>|[IPv6][Ext1][Ext2][Dest][Payload] * There is offset of AH before IPv6 header after the process. */ - struct ipv6_auth_hdr *ah; + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; + struct ip_auth_hdr *ah; + struct ipv6hdr *ip6h; struct ah_data *ahp; - unsigned char *tmp_hdr = NULL; u16 hdr_len; u16 ah_hlen; int nexthdr; + int nfrags; + int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; /* We are going to _remove_ AH header to keep sockets happy, * so... Later this can change. */ - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto out; - hdr_len = skb->data - skb->nh.raw; - ah = (struct ipv6_auth_hdr*)skb->data; + skb->ip_summed = CHECKSUM_NONE; + + hdr_len = skb_network_header_len(skb); + ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; + ahash = ahp->ahash; + nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; - if (ah_hlen != XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_full_len) && - ah_hlen != XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_trunc_len)) - goto out; + if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) && + ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len)) + goto out; if (!pskb_may_pull(skb, ah_hlen)) goto out; - tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC); - if (!tmp_hdr) + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) goto out; - memcpy(tmp_hdr, skb->nh.raw, hdr_len); - if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len)) + nfrags = err; + + ah = (struct ip_auth_hdr *)skb->data; + ip6h = ipv6_hdr(skb); + + skb_push(skb, hdr_len); + + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len + + ahp->icv_trunc_len + seqhi_len); + if (!work_iph) goto out; - skb->nh.ipv6h->priority = 0; - skb->nh.ipv6h->flow_lbl[0] = 0; - skb->nh.ipv6h->flow_lbl[1] = 0; - skb->nh.ipv6h->flow_lbl[2] = 0; - skb->nh.ipv6h->hop_limit = 0; - - { - u8 auth_data[MAX_AH_AUTH_LEN]; - - memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); - memset(ah->auth_data, 0, ahp->icv_trunc_len); - skb_push(skb, skb->data - skb->nh.raw); - ahp->icv(ahp, skb, ah->auth_data); - if (memcmp(ah->auth_data, auth_data, ahp->icv_trunc_len)) { - LIMIT_NETDEBUG(KERN_WARNING "ipsec ah authentication error\n"); - x->stats.integrity_failed++; - goto free_out; - } + + auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len); + seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; + + memcpy(work_iph, ip6h, hdr_len); + memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + + if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) + goto out_free; + + ip6h->priority = 0; + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + ip6h->hop_limit = 0; + + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); + + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); + ahash_request_set_callback(req, 0, ah6_input_done, skb); + + AH_SKB_CB(skb)->tmp = work_iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + goto out_free; } - skb->nh.raw = skb_pull(skb, ah_hlen); - memcpy(skb->nh.raw, tmp_hdr, hdr_len); - skb->nh.ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); - skb_pull(skb, hdr_len); - skb->h.raw = skb->data; + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + if (err) + goto out_free; + skb->network_header += ah_hlen; + memcpy(skb_network_header(skb), work_iph, hdr_len); + __skb_pull(skb, ah_hlen + hdr_len); - kfree(tmp_hdr); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); - return nexthdr; + err = nexthdr; -free_out: - kfree(tmp_hdr); +out_free: + kfree(work_iph); out: - return -EINVAL; + return err; } -static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) +static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) - return; + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) - return; - - NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - ntohl(ah->spi), NIP6(iph->daddr)); + return 0; + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static int ah6_init_state(struct xfrm_state *x) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; + struct crypto_ahash *ahash; if (!x->aalg) goto error; - /* null auth can use a zero length key */ - if (x->aalg->alg_key_len > 512) - goto error; - if (x->encap) goto error; - ahp = kmalloc(sizeof(*ahp), GFP_KERNEL); + ahp = kzalloc(sizeof(*ahp), GFP_KERNEL); if (ahp == NULL) return -ENOMEM; - memset(ahp, 0, sizeof(*ahp)); + ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); + if (IS_ERR(ahash)) + goto error; - ahp->key = x->aalg->alg_key; - ahp->key_len = (x->aalg->alg_key_len+7)/8; - ahp->tfm = crypto_alloc_tfm(x->aalg->alg_name, 0); - if (!ahp->tfm) + ahp->ahash = ahash; + if (crypto_ahash_setkey(ahash, x->aalg->alg_key, + (x->aalg->alg_key_len + 7) / 8)) goto error; - ahp->icv = ah_hmac_digest; - + /* * Lookup the algorithm description maintained by xfrm_algo, * verify crypto transform properties, and store information * we need for AH processing. This lookup cannot fail here - * after a successful crypto_alloc_tfm(). + * after a successful crypto_alloc_hash(). */ aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0); BUG_ON(!aalg_desc); if (aalg_desc->uinfo.auth.icv_fullbits/8 != - crypto_tfm_alg_digestsize(ahp->tfm)) { - printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_tfm_alg_digestsize(ahp->tfm), - aalg_desc->uinfo.auth.icv_fullbits/8); + crypto_ahash_digestsize(ahash)) { + pr_info("AH: %s digestsize %u != %hu\n", + x->aalg->alg_name, crypto_ahash_digestsize(ahash), + aalg_desc->uinfo.auth.icv_fullbits/8); goto error; } - + ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; - + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; + BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); - - ahp->work_icv = kmalloc(ahp->icv_full_len, GFP_KERNEL); - if (!ahp->work_icv) - goto error; - - x->props.header_len = XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_trunc_len); - if (x->props.mode) + + x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + + ahp->icv_trunc_len); + switch (x->props.mode) { + case XFRM_MODE_BEET: + case XFRM_MODE_TRANSPORT: + break; + case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); + break; + default: + goto error; + } x->data = ahp; return 0; error: if (ahp) { - kfree(ahp->work_icv); - crypto_free_tfm(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } return -EINVAL; @@ -415,39 +746,44 @@ static void ah6_destroy(struct xfrm_state *x) if (!ahp) return; - kfree(ahp->work_icv); - ahp->work_icv = NULL; - crypto_free_tfm(ahp->tfm); - ahp->tfm = NULL; + crypto_free_ahash(ahp->ahash); kfree(ahp); } -static struct xfrm_type ah6_type = +static int ah6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + +static const struct xfrm_type ah6_type = { .description = "AH6", .owner = THIS_MODULE, .proto = IPPROTO_AH, + .flags = XFRM_TYPE_REPLAY_PROT, .init_state = ah6_init_state, .destructor = ah6_destroy, .input = ah6_input, - .output = ah6_output + .output = ah6_output, + .hdr_offset = xfrm6_find_1stfragopt, }; -static struct inet6_protocol ah6_protocol = { +static struct xfrm6_protocol ah6_protocol = { .handler = xfrm6_rcv, + .cb_handler = ah6_rcv_cb, .err_handler = ah6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init ah6_init(void) { if (xfrm_register_type(&ah6_type, AF_INET6) < 0) { - printk(KERN_INFO "ipv6 ah init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) { - printk(KERN_INFO "ipv6 ah init: can't add protocol\n"); + if (xfrm6_protocol_register(&ah6_protocol, IPPROTO_AH) < 0) { + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah6_type, AF_INET6); return -EAGAIN; } @@ -457,11 +793,11 @@ static int __init ah6_init(void) static void __exit ah6_fini(void) { - if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0) - printk(KERN_INFO "ipv6 ah close: can't remove protocol\n"); + if (xfrm6_protocol_deregister(&ah6_protocol, IPPROTO_AH) < 0) + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0) - printk(KERN_INFO "ipv6 ah close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } @@ -469,3 +805,4 @@ module_init(ah6_init); module_exit(ah6_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 6b729404723..21018324468 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -1,6 +1,6 @@ /* * Anycast support for IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: * David L Stevens (dlstevens@us.ibm.com) @@ -13,7 +13,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> +#include <linux/capability.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> @@ -21,7 +21,6 @@ #include <linux/string.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> @@ -30,7 +29,9 @@ #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/slab.h> +#include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> @@ -43,96 +44,73 @@ #include <net/checksum.h> -static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr); +static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); /* Big ac list lock for all the sockets */ -static DEFINE_RWLOCK(ipv6_sk_ac_lock); +static DEFINE_SPINLOCK(ipv6_sk_ac_lock); -static int -ip6_onlink(struct in6_addr *addr, struct net_device *dev) -{ - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; - int onlink; - - onlink = 0; - read_lock(&addrconf_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); - } - read_unlock(&addrconf_lock); - return onlink; -} /* * socket join an anycast group */ -int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; struct inet6_dev *idev; struct ipv6_ac_socklist *pac; - int ishost = !ipv6_devconf.forwarding; + struct net *net = sock_net(sk); + int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; - if (ipv6_chk_addr(addr, NULL, 0)) + if (ipv6_chk_addr(net, addr, NULL, 0)) return -EINVAL; pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL); 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) { struct rt6_info *rt; - rt = rt6_lookup(addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; - dev_hold(dev); - dst_release(&rt->u.dst); + dev = rt->dst.dev; + ip6_rt_put(rt); } else if (ishost) { err = -EADDRNOTAVAIL; - goto out_free_pac; + goto error; } else { /* router, no matching interface: just pick one */ - - dev = dev_get_by_flags(IFF_UP, IFF_UP|IFF_LOOPBACK); + dev = dev_get_by_flags_rcu(net, IFF_UP, + IFF_UP | IFF_LOOPBACK); } } else - dev = dev_get_by_index(ifindex); + dev = dev_get_by_index_rcu(net, ifindex); if (dev == NULL) { err = -ENODEV; - goto out_free_pac; + goto error; } - idev = in6_dev_get(dev); + idev = __in6_dev_get(dev); if (!idev) { if (ifindex) err = -ENODEV; else err = -EADDRNOTAVAIL; - goto out_dev_put; + goto error; } /* reset ishost, now that we have a specific device */ ishost = !idev->cnf.forwarding; - in6_dev_put(idev); pac->acl_ifindex = dev->ifindex; @@ -141,43 +119,40 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) * This obviates the need for propagating anycast routes while * still allowing some non-router anycast participation. */ - if (!ip6_onlink(addr, dev)) { + if (!ipv6_chk_prefix(addr, dev)) { if (ishost) err = -EADDRNOTAVAIL; if (err) - goto out_dev_put; + goto error; } err = ipv6_dev_ac_inc(dev, addr); - if (err) - goto out_dev_put; - - write_lock_bh(&ipv6_sk_ac_lock); - pac->acl_next = np->ipv6_ac_list; - np->ipv6_ac_list = pac; - write_unlock_bh(&ipv6_sk_ac_lock); - - dev_put(dev); - - return 0; + if (!err) { + spin_lock_bh(&ipv6_sk_ac_lock); + pac->acl_next = np->ipv6_ac_list; + np->ipv6_ac_list = pac; + spin_unlock_bh(&ipv6_sk_ac_lock); + pac = NULL; + } -out_dev_put: - dev_put(dev); -out_free_pac: - sock_kfree_s(sk, pac, sizeof(*pac)); +error: + rcu_read_unlock(); + if (pac) + sock_kfree_s(sk, pac, sizeof(*pac)); return err; } /* * socket leave an anycast group */ -int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev; struct ipv6_ac_socklist *pac, *prev_pac; + struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_ac_lock); + spin_lock_bh(&ipv6_sk_ac_lock); prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -186,7 +161,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) prev_pac = pac; } if (!pac) { - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); return -ENOENT; } if (prev_pac) @@ -194,13 +169,14 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) else np->ipv6_ac_list = pac->acl_next; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); - dev = dev_get_by_index(pac->acl_ifindex); - if (dev) { + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, pac->acl_ifindex); + if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - dev_put(dev); - } + rcu_read_unlock(); + sock_kfree_s(sk, pac, sizeof(*pac)); return 0; } @@ -210,21 +186,24 @@ void ipv6_sock_ac_close(struct sock *sk) struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; struct ipv6_ac_socklist *pac; + struct net *net = sock_net(sk); int prev_index; - write_lock_bh(&ipv6_sk_ac_lock); + if (!np->ipv6_ac_list) + return; + + spin_lock_bh(&ipv6_sk_ac_lock); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; if (pac->acl_ifindex != prev_index) { - if (dev) - dev_put(dev); - dev = dev_get_by_index(pac->acl_ifindex); + dev = dev_get_by_index_rcu(net, pac->acl_ifindex); prev_index = pac->acl_ifindex; } if (dev) @@ -232,44 +211,14 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } - if (dev) - dev_put(dev); + rcu_read_unlock(); } -#if 0 -/* The function is not used, which is funny. Apparently, author - * supposed to use it to filter out datagrams inside udp/raw but forgot. - * - * It is OK, anycasts are not special comparing to delivery to unicasts. - */ - -int inet6_ac_check(struct sock *sk, struct in6_addr *addr, int ifindex) -{ - struct ipv6_ac_socklist *pac; - struct ipv6_pinfo *np = inet6_sk(sk); - int found; - - found = 0; - read_lock(&ipv6_sk_ac_lock); - for (pac=np->ipv6_ac_list; pac; pac=pac->acl_next) { - if (ifindex && pac->acl_ifindex != ifindex) - continue; - found = ipv6_addr_equal(&pac->acl_addr, addr); - if (found) - break; - } - read_unlock(&ipv6_sk_ac_lock); - - return found; -} - -#endif - static void aca_put(struct ifacaddr6 *ac) { if (atomic_dec_and_test(&ac->aca_refcnt)) { in6_dev_put(ac->aca_idev); - dst_release(&ac->aca_rt->u.dst); + dst_release(&ac->aca_rt->dst); kfree(ac); } } @@ -277,7 +226,7 @@ static void aca_put(struct ifacaddr6 *ac) /* * device anycast group inc (add if not found) */ -int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) +int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) { struct ifacaddr6 *aca; struct inet6_dev *idev; @@ -307,23 +256,21 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) * not found: create a new one. */ - aca = kmalloc(sizeof(struct ifacaddr6), GFP_ATOMIC); + aca = kzalloc(sizeof(struct ifacaddr6), GFP_ATOMIC); if (aca == NULL) { err = -ENOMEM; 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; } - memset(aca, 0, sizeof(struct ifacaddr6)); - - ipv6_addr_copy(&aca->aca_addr, addr); + aca->aca_addr = *addr; aca->aca_idev = idev; aca->aca_rt = rt; aca->aca_users = 1; @@ -336,9 +283,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) idev->ac_list = aca; write_unlock_bh(&idev->lock); - dst_hold(&rt->u.dst); - if (ip6_ins_rt(rt, NULL, NULL, NULL)) - dst_release(&rt->u.dst); + ip6_ins_rt(rt); addrconf_join_solict(dev, &aca->aca_addr); @@ -353,7 +298,7 @@ out: /* * device anycast group decrement */ -int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) +int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca, *prev_aca; @@ -379,66 +324,80 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) write_unlock_bh(&idev->lock); addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->u.dst); - if (ip6_del_rt(aca->aca_rt, NULL, NULL, NULL)) - dst_free(&aca->aca_rt->u.dst); - else - dst_release(&aca->aca_rt->u.dst); + dst_hold(&aca->aca_rt->dst); + ip6_del_rt(aca->aca_rt); aca_put(aca); return 0; } -static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr) +/* called with rcu_read_lock() */ +static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr) { - int ret; - struct inet6_dev *idev = in6_dev_get(dev); + struct inet6_dev *idev = __in6_dev_get(dev); + if (idev == NULL) return -ENODEV; - ret = __ipv6_dev_ac_dec(idev, addr); - in6_dev_put(idev); - return ret; + return __ipv6_dev_ac_dec(idev, addr); } - + /* * check if the interface has this anycast address + * called with rcu_read_lock() */ -static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr) +static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; struct ifacaddr6 *aca; - idev = in6_dev_get(dev); + idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); for (aca = idev->ac_list; aca; aca = aca->aca_next) if (ipv6_addr_equal(&aca->aca_addr, addr)) break; read_unlock_bh(&idev->lock); - in6_dev_put(idev); - return aca != 0; + return aca != NULL; } - return 0; + return false; } /* * check if given interface (or any, if dev==0) has this anycast address */ -int ipv6_chk_acast_addr(struct net_device *dev, struct in6_addr *addr) +bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, + const struct in6_addr *addr) { + bool found = false; + + rcu_read_lock(); if (dev) - return ipv6_chk_acast_dev(dev, addr); - read_lock(&dev_base_lock); - for (dev=dev_base; dev; dev=dev->next) - if (ipv6_chk_acast_dev(dev, addr)) - break; - read_unlock(&dev_base_lock); - return dev != 0; + found = ipv6_chk_acast_dev(dev, addr); + else + for_each_netdev_rcu(net, dev) + if (ipv6_chk_acast_dev(dev, addr)) { + found = true; + break; + } + rcu_read_unlock(); + return found; } +/* check if this anycast address is link-local on given interface or + * is global + */ +bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, + const struct in6_addr *addr) +{ + return ipv6_chk_acast_addr(net, + (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL ? + dev : NULL), + addr); +} #ifdef CONFIG_PROC_FS struct ac6_iter_state { + struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; @@ -449,12 +408,12 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) { struct ifacaddr6 *im = NULL; struct ac6_iter_state *state = ac6_seq_private(seq); + struct net *net = seq_file_net(seq); - for (state->dev = dev_base, state->idev = NULL; - state->dev; - state->dev = state->dev->next) { + state->idev = NULL; + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -474,16 +433,15 @@ static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im im = im->aca_next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = state->dev->next; + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -502,27 +460,30 @@ static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos) } static void *ac6_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return ac6_get_idx(seq, *pos); } static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifacaddr6 *im; - im = ac6_get_next(seq, v); + struct ifacaddr6 *im = ac6_get_next(seq, v); + ++*pos; return im; } static void ac6_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { struct ac6_iter_state *state = ac6_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); + state->idev = NULL; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int ac6_seq_show(struct seq_file *seq, void *v) @@ -530,17 +491,13 @@ static int ac6_seq_show(struct seq_file *seq, void *v) struct ifacaddr6 *im = (struct ifacaddr6 *)v; struct ac6_iter_state *state = ac6_seq_private(seq); - seq_printf(seq, - "%-4d %-15s " - "%04x%04x%04x%04x%04x%04x%04x%04x " - "%5d\n", + seq_printf(seq, "%-4d %-15s %pi6 %5d\n", state->dev->ifindex, state->dev->name, - NIP6(im->aca_addr), - im->aca_users); + &im->aca_addr, im->aca_users); return 0; } -static struct seq_operations ac6_seq_ops = { +static const struct seq_operations ac6_seq_ops = { .start = ac6_seq_start, .next = ac6_seq_next, .stop = ac6_seq_stop, @@ -549,46 +506,29 @@ static struct seq_operations ac6_seq_ops = { static int ac6_seq_open(struct inode *inode, struct file *file) { - struct seq_file *seq; - int rc = -ENOMEM; - struct ac6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); - - if (!s) - goto out; - - rc = seq_open(file, &ac6_seq_ops); - if (rc) - goto out_kfree; - - seq = file->private_data; - seq->private = s; - memset(s, 0, sizeof(*s)); -out: - return rc; -out_kfree: - kfree(s); - goto out; + return seq_open_net(inode, file, &ac6_seq_ops, + sizeof(struct ac6_iter_state)); } -static struct file_operations ac6_seq_fops = { +static const struct file_operations ac6_seq_fops = { .owner = THIS_MODULE, .open = ac6_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; -int __init ac6_proc_init(void) +int __net_init ac6_proc_init(struct net *net) { - if (!proc_net_fops_create("anycast6", S_IRUGO, &ac6_seq_fops)) + if (!proc_create("anycast6", S_IRUGO, net->proc_net, &ac6_seq_fops)) return -ENOMEM; return 0; } -void ac6_proc_exit(void) +void ac6_proc_exit(struct net *net) { - proc_net_remove("anycast6"); + remove_proc_entry("anycast6", net->proc_net); } #endif diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index cc518405b3e..c3bf2d2e519 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -1,11 +1,9 @@ /* * common UDP/RAW code - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> - * - * $Id: datagram.c,v 1.24 2002/02/01 22:01:04 davem Exp $ + * Pedro Roque <roque@di.fc.ul.pt> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -13,16 +11,18 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/sched.h> #include <linux/interrupt.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/route.h> +#include <linux/slab.h> +#include <linux/export.h> #include <net/ipv6.h> #include <net/ndisc.h> @@ -30,19 +30,26 @@ #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/tcp_states.h> +#include <net/dsfield.h> #include <linux/errqueue.h> #include <asm/uaccess.h> +static bool ipv6_mapped_addr_any(const struct in6_addr *a) +{ + return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); +} + int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr, *final_p = NULL, final; + struct in6_addr *daddr, *final_p, final; struct dst_entry *dst; - struct flowi fl; + struct flowi6 fl6; struct ip6_flowlabel *flowlabel = NULL; + struct ipv6_txoptions *opt; int addr_type; int err; @@ -54,19 +61,18 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (addr_len < SIN6_LEN_RFC2133) - return -EINVAL; + return -EINVAL; - if (usin->sin6_family != AF_INET6) - return -EAFNOSUPPORT; + if (usin->sin6_family != AF_INET6) + return -EAFNOSUPPORT; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); } } @@ -92,29 +98,32 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sin.sin_addr.s_addr = daddr->s6_addr32[3]; sin.sin_port = usin->sin6_port; - err = ip4_datagram_connect(sk, - (struct sockaddr*) &sin, + err = ip4_datagram_connect(sk, + (struct sockaddr *) &sin, sizeof(sin)); ipv4_connected: if (err) goto out; - - ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr); - if (ipv6_addr_any(&np->saddr)) { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff), - inet->saddr); - } + ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr); - if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff), - inet->rcv_saddr); + if (ipv6_addr_any(&np->saddr) || + ipv6_mapped_addr_any(&np->saddr)) + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || + ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) { + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &sk->sk_v6_rcv_saddr); + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } + goto out; } - if (addr_type&IPV6_ADDR_LINKLOCAL) { + if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { if (sk->sk_bound_dev_if && @@ -123,11 +132,11 @@ ipv4_connected: goto out; } sk->sk_bound_dev_if = usin->sin6_scope_id; - if (!sk->sk_bound_dev_if && - (addr_type & IPV6_ADDR_MULTICAST)) - fl.oif = np->mcast_oif; } + if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST)) + sk->sk_bound_dev_if = np->mcast_oif; + /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; @@ -135,74 +144,82 @@ ipv4_connected: } } - ipv6_addr_copy(&np->daddr, daddr); - np->flow_label = fl.fl6_flowlabel; + sk->sk_v6_daddr = *daddr; + np->flow_label = fl6.flowlabel; - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the * destination cache for it. */ - fl.proto = sk->sk_protocol; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; - - if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST)) - fl.oif = np->mcast_oif; - - if (flowlabel) { - if (flowlabel->opt && flowlabel->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } - } else if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + fl6.flowi6_proto = sk->sk_protocol; + fl6.daddr = sk->sk_v6_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; + fl6.fl6_sport = inet->inet_sport; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto out; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) + fl6.flowi6_oif = np->mcast_oif; + + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + opt = flowlabel ? flowlabel->opt : np->opt; + final_p = fl6_update_dst(&fl6, opt, &final); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + err = 0; + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto out; + } /* source address lookup done in ip6_dst_lookup */ if (ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&np->saddr, &fl.fl6_src); + np->saddr = fl6.saddr; - if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); - inet->rcv_saddr = LOOPBACK4_IPV6; + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + sk->sk_v6_rcv_saddr = fl6.saddr; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? - &np->daddr : NULL); + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl6.saddr, &np->saddr) ? + &np->saddr : +#endif + NULL); sk->sk_state = TCP_ESTABLISHED; out: fl6_sock_release(flowlabel); return err; } +EXPORT_SYMBOL_GPL(ip6_datagram_connect); + +int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr); + if (sin6->sin6_family != AF_INET6) + return -EAFNOSUPPORT; + return ip6_datagram_connect(sk, uaddr, addr_len); +} +EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only); -void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, - u16 port, u32 info, u8 *payload) +void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) { struct ipv6_pinfo *np = inet6_sk(sk); - struct icmp6hdr *icmph = (struct icmp6hdr *)skb->h.raw; + struct icmp6hdr *icmph = icmp6_hdr(skb); struct sock_exterr_skb *serr; if (!np->recverr) @@ -212,25 +229,28 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, if (!skb) return; + skb->protocol = htons(ETH_P_IPV6); + serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6; - serr->ee.ee_type = icmph->icmp6_type; + serr->ee.ee_type = icmph->icmp6_type; serr->ee.ee_code = icmph->icmp6_code; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; - serr->addr_offset = (u8*)&(((struct ipv6hdr*)(icmph+1))->daddr) - skb->nh.raw; + serr->addr_offset = (u8 *)&(((struct ipv6hdr *)(icmph + 1))->daddr) - + skb_network_header(skb); serr->port = port; - skb->h.raw = payload; __skb_pull(skb, payload - skb->data); + skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } -void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) +void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -244,37 +264,75 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) if (!skb) return; - iph = (struct ipv6hdr*)skb_put(skb, sizeof(struct ipv6hdr)); - skb->nh.ipv6h = iph; - ipv6_addr_copy(&iph->daddr, &fl->fl6_dst); + skb->protocol = htons(ETH_P_IPV6); + + skb_put(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + iph = ipv6_hdr(skb); + iph->daddr = fl6->daddr; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; - serr->ee.ee_type = 0; + serr->ee.ee_type = 0; serr->ee.ee_code = 0; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; - serr->addr_offset = (u8*)&iph->daddr - skb->nh.raw; - serr->port = fl->fl_ip_dport; + serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); + serr->port = fl6->fl6_dport; - skb->h.raw = skb->tail; - __skb_pull(skb, skb->tail - skb->data); + __skb_pull(skb, skb_tail_pointer(skb) - skb->data); + skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } -/* +void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6hdr *iph; + struct sk_buff *skb; + struct ip6_mtuinfo *mtu_info; + + if (!np->rxopt.bits.rxpmtu) + return; + + skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); + if (!skb) + return; + + skb_put(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + iph = ipv6_hdr(skb); + iph->daddr = fl6->daddr; + + mtu_info = IP6CBMTU(skb); + + 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; + mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr; + + __skb_pull(skb, skb_tail_pointer(skb) - skb->data); + skb_reset_transport_header(skb); + + skb = xchg(&np->rxpmtu, skb); + kfree_skb(skb); +} + +/* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct sk_buff *skb, *skb2; - struct sockaddr_in6 *sin; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in6 offender; @@ -300,24 +358,26 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) serr = SKB_EXT_ERR(skb); - sin = (struct sockaddr_in6 *)msg->msg_name; if (sin) { + const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; - sin->sin6_port = serr->port; - sin->sin6_scope_id = 0; - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) { - ipv6_addr_copy(&sin->sin6_addr, - (struct in6_addr *)(skb->nh.raw + serr->addr_offset)); + sin->sin6_port = serr->port; + if (skb->protocol == htons(ETH_P_IPV6)) { + const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset), + struct ipv6hdr, daddr); + sin->sin6_addr = ip6h->daddr; if (np->sndflow) - sin->sin6_flowinfo = *(u32*)(skb->nh.raw + serr->addr_offset - 24) & IPV6_FLOWINFO_MASK; - if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin->sin6_scope_id = IP6CB(skb)->iif; + sin->sin6_flowinfo = ip6_flowinfo(ip6h); + sin->sin6_scope_id = + ipv6_iface_scope_id(&sin->sin6_addr, + IP6CB(skb)->iif); } else { - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), - *(u32*)(skb->nh.raw + serr->addr_offset)); + ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), + &sin->sin6_addr); + sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); @@ -326,19 +386,22 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; - sin->sin6_scope_id = 0; - if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) { - ipv6_addr_copy(&sin->sin6_addr, &skb->nh.ipv6h->saddr); + sin->sin6_port = 0; + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); + if (skb->protocol == htons(ETH_P_IPV6)) { + 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) - sin->sin6_scope_id = IP6CB(skb)->iif; + ip6_datagram_recv_specific_ctl(sk, msg, skb); + sin->sin6_scope_id = + ipv6_iface_scope_id(&sin->sin6_addr, + IP6CB(skb)->iif); } else { struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), - skb->nh.iph->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin->sin6_addr); + sin->sin6_scope_id = 0; if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } @@ -362,45 +425,112 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) spin_unlock_bh(&sk->sk_error_queue.lock); } -out_free_skb: +out_free_skb: kfree_skb(skb); out: return err; } +EXPORT_SYMBOL_GPL(ipv6_recv_error); + +/* + * Handle IPV6_RECVPATHMTU + */ +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct sk_buff *skb; + struct ip6_mtuinfo mtu_info; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); + int err; + int copied; + + err = -EAGAIN; + skb = xchg(&np->rxpmtu, NULL); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); + + if (sin) { + sin->sin6_family = AF_INET6; + sin->sin6_flowinfo = 0; + sin->sin6_port = 0; + sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; + sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); + } + + put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); + err = copied; +out_free_skb: + kfree_skb(skb); +out: + return err; +} -int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) + +void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_skb_parm *opt = IP6CB(skb); + bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6); if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = opt->iif; - ipv6_addr_copy(&src_info.ipi6_addr, &skb->nh.ipv6h->daddr); + if (is_ipv6) { + src_info.ipi6_ifindex = IP6CB(skb)->iif; + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; + } else { + src_info.ipi6_ifindex = + PKTINFO_SKB_CB(skb)->ipi_ifindex; + ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, + &src_info.ipi6_addr); + } put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } +} + +void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet6_skb_parm *opt = IP6CB(skb); + unsigned char *nh = skb_network_header(skb); if (np->rxopt.bits.rxhlim) { - int hlim = skb->nh.ipv6h->hop_limit; + int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { - int tclass = (ntohl(*(u32 *)skb->nh.ipv6h) >> 20) & 0xff; + int tclass = ipv6_get_dsfield(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } - if (np->rxopt.bits.rxflow && (*(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK)) { - u32 flowinfo = *(u32*)skb->nh.raw & IPV6_FLOWINFO_MASK; - put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); + if (np->rxopt.bits.rxflow) { + __be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh); + if (flowinfo) + put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } /* HbH is allowed only once */ if (np->rxopt.bits.hopopts && opt->hop) { - u8 *ptr = skb->nh.raw + opt->hop; + u8 *ptr = nh + opt->hop; put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } @@ -411,18 +541,18 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) * report extension headers (except for HbH) * in order. * - * Also note that IPV6_RECVRTHDRDSTOPTS is NOT + * Also note that IPV6_RECVRTHDRDSTOPTS is NOT * (and WILL NOT be) defined because * IPV6_RECVDSTOPTS is more generic. --yoshfuji */ unsigned int off = sizeof(struct ipv6hdr); - u8 nexthdr = skb->nh.ipv6h->nexthdr; + u8 nexthdr = ipv6_hdr(skb)->nexthdr; while (off <= opt->lastopt) { - unsigned len; - u8 *ptr = skb->nh.raw + off; + unsigned int len; + u8 *ptr = nh + off; - switch(nexthdr) { + switch (nexthdr) { case IPPROTO_DSTOPTS: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; @@ -437,7 +567,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) break; case IPPROTO_AH: nexthdr = ptr[0]; - len = (ptr[1] + 1) << 2; + len = (ptr[1] + 2) << 2; break; default: nexthdr = ptr[0]; @@ -454,35 +584,64 @@ 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, &skb->nh.ipv6h->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) { - int hlim = skb->nh.ipv6h->hop_limit; + int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.ohopopts && opt->hop) { - u8 *ptr = skb->nh.raw + opt->hop; + u8 *ptr = nh + opt->hop; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { - u8 *ptr = skb->nh.raw + opt->dst0; + u8 *ptr = nh + opt->dst0; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.osrcrt && opt->srcrt) { - struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(skb->nh.raw + opt->srcrt); + struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt); put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr); } if (np->rxopt.bits.odstopts && opt->dst1) { - u8 *ptr = skb->nh.raw + opt->dst1; + u8 *ptr = nh + opt->dst1; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } - return 0; + if (np->rxopt.bits.rxorigdstaddr) { + struct sockaddr_in6 sin6; + __be16 *ports = (__be16 *) skb_transport_header(skb); + + if (skb_transport_offset(skb) + 4 <= skb->len) { + /* All current transport protocols have the port numbers in the + * first four bytes of the transport header and this function is + * written with this assumption in mind. + */ + + sin6.sin6_family = AF_INET6; + sin6.sin6_addr = ipv6_hdr(skb)->daddr; + sin6.sin6_port = ports[1]; + sin6.sin6_flowinfo = 0; + sin6.sin6_scope_id = + ipv6_iface_scope_id(&ipv6_hdr(skb)->daddr, + opt->iif); + + put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); + } + } +} + +void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + ip6_datagram_recv_common_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); } +EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); -int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, - struct ipv6_txoptions *opt, - int *hlimit, int *tclass) +int ip6_datagram_send_ctl(struct net *net, struct sock *sk, + struct msghdr *msg, struct flowi6 *fl6, + struct ipv6_txoptions *opt, + int *hlimit, int *tclass, int *dontfrag) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -493,7 +652,6 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { int addr_type; - struct net_device *dev = NULL; if (!CMSG_OK(msg, cmsg)) { err = -EINVAL; @@ -504,65 +662,77 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, continue; switch (cmsg->cmsg_type) { - case IPV6_PKTINFO: - case IPV6_2292PKTINFO: - if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { + case IPV6_PKTINFO: + case IPV6_2292PKTINFO: + { + struct net_device *dev = NULL; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; goto exit_f; } src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); - + if (src_info->ipi6_ifindex) { - if (fl->oif && src_info->ipi6_ifindex != fl->oif) + if (fl6->flowi6_oif && + src_info->ipi6_ifindex != fl6->flowi6_oif) return -EINVAL; - fl->oif = src_info->ipi6_ifindex; + fl6->flowi6_oif = src_info->ipi6_ifindex; } - addr_type = ipv6_addr_type(&src_info->ipi6_addr); + addr_type = __ipv6_addr_type(&src_info->ipi6_addr); - if (addr_type == IPV6_ADDR_ANY) - break; - - if (addr_type & IPV6_ADDR_LINKLOCAL) { - if (!src_info->ipi6_ifindex) - return -EINVAL; - else { - dev = dev_get_by_index(src_info->ipi6_ifindex); - if (!dev) - return -ENODEV; + rcu_read_lock(); + if (fl6->flowi6_oif) { + dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; } + } else if (addr_type & IPV6_ADDR_LINKLOCAL) { + rcu_read_unlock(); + return -EINVAL; } - if (!ipv6_chk_addr(&src_info->ipi6_addr, dev, 0)) { - if (dev) - dev_put(dev); - err = -EINVAL; - goto exit_f; + + if (addr_type != IPV6_ADDR_ANY) { + int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; + if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && + !ipv6_chk_addr(net, &src_info->ipi6_addr, + strict ? dev : NULL, 0) && + !ipv6_chk_acast_addr_src(net, dev, + &src_info->ipi6_addr)) + err = -EINVAL; + else + fl6->saddr = src_info->ipi6_addr; } - if (dev) - dev_put(dev); - ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); + rcu_read_unlock(); + + if (err) + goto exit_f; + break; + } case IPV6_FLOWINFO: - if (cmsg->cmsg_len < CMSG_LEN(4)) { + if (cmsg->cmsg_len < CMSG_LEN(4)) { err = -EINVAL; goto exit_f; } - if (fl->fl6_flowlabel&IPV6_FLOWINFO_MASK) { - if ((fl->fl6_flowlabel^*(u32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { + if (fl6->flowlabel&IPV6_FLOWINFO_MASK) { + if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { err = -EINVAL; goto exit_f; } } - fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(u32 *)CMSG_DATA(cmsg); + fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); break; case IPV6_2292HOPOPTS: case IPV6_HOPOPTS: - if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { + if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } @@ -573,7 +743,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -582,7 +752,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, break; case IPV6_2292DSTOPTS: - if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } @@ -593,7 +763,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -618,7 +788,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -633,24 +803,31 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, case IPV6_2292RTHDR: case IPV6_RTHDR: - if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) { + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) { err = -EINVAL; goto exit_f; } rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); - /* - * TYPE 0 - */ - if (rthdr->type) { + switch (rthdr->type) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_SRCRT_TYPE_2: + if (rthdr->hdrlen != 2 || + rthdr->segments_left != 1) { + err = -EINVAL; + goto exit_f; + } + break; +#endif + default: err = -EINVAL; goto exit_f; } len = ((rthdr->hdrlen + 1) << 3); - if (cmsg->cmsg_len < CMSG_LEN(len)) { + if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } @@ -683,6 +860,11 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, } *hlimit = *(int *)CMSG_DATA(cmsg); + if (*hlimit < -1 || *hlimit > 0xff) { + err = -EINVAL; + goto exit_f; + } + break; case IPV6_TCLASS: @@ -690,12 +872,11 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, int tc; err = -EINVAL; - if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; - } tc = *(int *)CMSG_DATA(cmsg); - if (tc < 0 || tc > 0xff) + if (tc < -1 || tc > 0xff) goto exit_f; err = 0; @@ -703,14 +884,59 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, break; } + + case IPV6_DONTFRAG: + { + int df; + + err = -EINVAL; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + goto exit_f; + + df = *(int *)CMSG_DATA(cmsg); + if (df < 0 || df > 1) + goto exit_f; + + err = 0; + *dontfrag = df; + + break; + } default: LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n", - cmsg->cmsg_type); + cmsg->cmsg_type); err = -EINVAL; - break; - }; + goto exit_f; + } } exit_f: return err; } +EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); + +void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, + __u16 srcp, __u16 destp, int bucket) +{ + const struct in6_addr *dest, *src; + + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; + seq_printf(seq, + "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n", + bucket, + src->s6_addr32[0], src->s6_addr32[1], + src->s6_addr32[2], src->s6_addr32[3], srcp, + dest->s6_addr32[0], dest->s6_addr32[1], + dest->s6_addr32[2], dest->s6_addr32[3], destp, + sp->sk_state, + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), + 0, + sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp, + atomic_read(&sp->sk_drops)); +} diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 40d9a1935ab..d15da137714 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -1,401 +1,655 @@ /* * Copyright (C)2002 USAGI/WIDE Project - * + * * 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. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * + * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors * - * Mitsuru KANDA @USAGI : IPv6 Support + * Mitsuru KANDA @USAGI : IPv6 Support * Kazunori MIYAZAWA @USAGI : * Kunihiro Ishiguro <kunihiro@ipinfusion.com> - * + * * This file is derived from net/ipv4/esp.c */ -#include <linux/config.h> +#define pr_fmt(fmt) "IPv6: " fmt + +#include <crypto/aead.h> +#include <crypto/authenc.h> +#include <linux/err.h> #include <linux/module.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> -#include <asm/scatterlist.h> -#include <linux/crypto.h> +#include <linux/scatterlist.h> #include <linux/kernel.h> #include <linux/pfkeyv2.h> #include <linux/random.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> +#include <net/protocol.h> #include <linux/icmpv6.h> +struct esp_skb_cb { + struct xfrm_skb_cb xfrm; + void *tmp; +}; + +#define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) + +static u32 esp6_get_mtu(struct xfrm_state *x, int mtu); + +/* + * Allocate an AEAD request structure with extra space for SG and IV. + * + * For alignment considerations the upper 32 bits of the sequence number are + * placed at the front, if present. Followed by the IV, the request and finally + * the SG list. + * + * TODO: Use spare space in skb for this where possible. + */ +static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqihlen) +{ + unsigned int len; + + len = seqihlen; + + len += crypto_aead_ivsize(aead); + + if (len) { + len += crypto_aead_alignmask(aead) & + ~(crypto_tfm_ctx_alignment() - 1); + len = ALIGN(len, crypto_tfm_ctx_alignment()); + } + + len += sizeof(struct aead_givcrypt_request) + crypto_aead_reqsize(aead); + len = ALIGN(len, __alignof__(struct scatterlist)); + + len += sizeof(struct scatterlist) * nfrags; + + return kmalloc(len, GFP_ATOMIC); +} + +static inline __be32 *esp_tmp_seqhi(void *tmp) +{ + return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32)); +} + +static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) +{ + return crypto_aead_ivsize(aead) ? + PTR_ALIGN((u8 *)tmp + seqhilen, + crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; +} + +static inline struct aead_givcrypt_request *esp_tmp_givreq( + struct crypto_aead *aead, u8 *iv) +{ + struct aead_givcrypt_request *req; + + req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead), + crypto_tfm_ctx_alignment()); + aead_givcrypt_set_tfm(req, aead); + return req; +} + +static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) +{ + struct aead_request *req; + + req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead), + crypto_tfm_ctx_alignment()); + aead_request_set_tfm(req, aead); + return req; +} + +static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, + struct aead_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_aead_reqsize(aead), + __alignof__(struct scatterlist)); +} + +static inline struct scatterlist *esp_givreq_sg( + struct crypto_aead *aead, struct aead_givcrypt_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_aead_reqsize(aead), + __alignof__(struct scatterlist)); +} + +static void esp_output_done(struct crypto_async_request *base, int err) +{ + struct sk_buff *skb = base->data; + + kfree(ESP_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) { int err; - int hdr_len; - struct ipv6hdr *top_iph; - struct ipv6_esp_hdr *esph; - struct crypto_tfm *tfm; - struct esp_data *esp; + struct ip_esp_hdr *esph; + struct crypto_aead *aead; + struct aead_givcrypt_request *req; + struct scatterlist *sg; + struct scatterlist *asg; struct sk_buff *trailer; + void *tmp; int blksize; int clen; int alen; + int plen; + int tfclen; int nfrags; + int assoclen; + int sglists; + int seqhilen; + u8 *iv; + u8 *tail; + __be32 *seqhi; + + /* skb is pure payload to encrypt */ + aead = x->data; + alen = crypto_aead_authsize(aead); + + tfclen = 0; + if (x->tfcpad) { + struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); + u32 padto; + + padto = min(x->tfcpad, esp6_get_mtu(x, dst->child_mtu_cached)); + if (skb->len < padto) + tfclen = padto - skb->len; + } + blksize = ALIGN(crypto_aead_blocksize(aead), 4); + clen = ALIGN(skb->len + 2 + tfclen, blksize); + plen = clen - skb->len - tfclen; - esp = x->data; - hdr_len = skb->h.raw - skb->data + - sizeof(*esph) + esp->conf.ivlen; - - /* Strip IP+ESP header. */ - __skb_pull(skb, hdr_len); - - /* Now skb is pure payload to encrypt */ - err = -ENOMEM; + err = skb_cow_data(skb, tfclen + plen + alen, &trailer); + if (err < 0) + goto error; + nfrags = err; - /* Round to block size */ - clen = skb->len; + assoclen = sizeof(*esph); + sglists = 1; + seqhilen = 0; - alen = esp->auth.icv_trunc_len; - tfm = esp->conf.tfm; - blksize = ALIGN(crypto_tfm_alg_blocksize(tfm), 4); - clen = ALIGN(clen + 2, blksize); - if (esp->conf.padlen) - clen = ALIGN(clen, esp->conf.padlen); + if (x->props.flags & XFRM_STATE_ESN) { + sglists += 2; + seqhilen += sizeof(__be32); + assoclen += seqhilen; + } - if ((nfrags = skb_cow_data(skb, clen-skb->len+alen, &trailer)) < 0) { + tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); + if (!tmp) { + err = -ENOMEM; goto error; } + seqhi = esp_tmp_seqhi(tmp); + iv = esp_tmp_iv(aead, tmp, seqhilen); + req = esp_tmp_givreq(aead, iv); + asg = esp_givreq_sg(aead, req); + sg = asg + sglists; + /* Fill padding... */ + tail = skb_tail_pointer(trailer); + if (tfclen) { + memset(tail, 0, tfclen); + tail += tfclen; + } do { int i; - for (i=0; i<clen-skb->len - 2; i++) - *(u8*)(trailer->tail + i) = i+1; + for (i = 0; i < plen - 2; i++) + tail[i] = i + 1; } while (0); - *(u8*)(trailer->tail + clen-skb->len - 2) = (clen - skb->len)-2; - pskb_put(skb, trailer, clen - skb->len); + tail[plen - 2] = plen - 2; + tail[plen - 1] = *skb_mac_header(skb); + pskb_put(skb, trailer, clen - skb->len + alen); - top_iph = (struct ipv6hdr *)__skb_push(skb, hdr_len); - esph = (struct ipv6_esp_hdr *)skb->h.raw; - top_iph->payload_len = htons(skb->len + alen - sizeof(*top_iph)); - *(u8*)(trailer->tail - 1) = *skb->nh.raw; - *skb->nh.raw = IPPROTO_ESP; + skb_push(skb, -skb_network_offset(skb)); + esph = ip_esp_hdr(skb); + *skb_mac_header(skb) = IPPROTO_ESP; esph->spi = x->id.spi; - esph->seq_no = htonl(++x->replay.oseq); + esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); + + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, + esph->enc_data + crypto_aead_ivsize(aead) - skb->data, + clen + alen); + + if ((x->props.flags & XFRM_STATE_ESN)) { + sg_init_table(asg, 3); + sg_set_buf(asg, &esph->spi, sizeof(__be32)); + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(asg + 1, seqhi, seqhilen); + sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); + } else + sg_init_one(asg, esph, sizeof(*esph)); + + aead_givcrypt_set_callback(req, 0, esp_output_done, skb); + aead_givcrypt_set_crypt(req, sg, sg, clen, iv); + aead_givcrypt_set_assoc(req, asg, assoclen); + aead_givcrypt_set_giv(req, esph->enc_data, + XFRM_SKB_CB(skb)->seq.output.low); + + ESP_SKB_CB(skb)->tmp = tmp; + err = crypto_aead_givencrypt(req); + if (err == -EINPROGRESS) + goto error; - if (esp->conf.ivlen) - crypto_cipher_set_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm)); + if (err == -EBUSY) + err = NET_XMIT_DROP; - do { - struct scatterlist *sg = &esp->sgbuf[0]; + kfree(tmp); - if (unlikely(nfrags > ESP_NUM_FAST_SG)) { - sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC); - if (!sg) - goto error; - } - skb_to_sgvec(skb, sg, esph->enc_data+esp->conf.ivlen-skb->data, clen); - crypto_cipher_encrypt(tfm, sg, sg, clen); - if (unlikely(sg != &esp->sgbuf[0])) - kfree(sg); - } while (0); +error: + return err; +} - if (esp->conf.ivlen) { - memcpy(esph->enc_data, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm)); - crypto_cipher_get_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm)); - } +static int esp_input_done2(struct sk_buff *skb, int err) +{ + struct xfrm_state *x = xfrm_input_state(skb); + struct crypto_aead *aead = x->data; + int alen = crypto_aead_authsize(aead); + int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); + int elen = skb->len - hlen; + int hdr_len = skb_network_header_len(skb); + int padlen; + u8 nexthdr[2]; + + kfree(ESP_SKB_CB(skb)->tmp); + + if (unlikely(err)) + goto out; + + if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2)) + BUG(); - if (esp->auth.icv_full_len) { - esp->auth.icv(esp, skb, (u8*)esph-skb->data, - sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen+clen, trailer->tail); - pskb_put(skb, trailer, alen); + err = -EINVAL; + padlen = nexthdr[0]; + if (padlen + 2 + alen >= elen) { + LIMIT_NETDEBUG(KERN_WARNING "ipsec esp packet is garbage " + "padlen=%d, elen=%d\n", padlen + 2, elen - alen); + goto out; } - err = 0; + /* ... check padding bits here. Silly. :-) */ -error: + pskb_trim(skb, skb->len - alen - padlen - 2); + __skb_pull(skb, hlen); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); + + err = nexthdr[1]; + + /* RFC4303: Drop dummy packets without any error */ + if (err == IPPROTO_NONE) + err = -EINVAL; + +out: return err; } -static int esp6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb) +static void esp_input_done(struct crypto_async_request *base, int err) { - struct ipv6hdr *iph; - struct ipv6_esp_hdr *esph; - struct esp_data *esp = x->data; - struct sk_buff *trailer; - int blksize = ALIGN(crypto_tfm_alg_blocksize(esp->conf.tfm), 4); - int alen = esp->auth.icv_trunc_len; - int elen = skb->len - sizeof(struct ipv6_esp_hdr) - esp->conf.ivlen - alen; + struct sk_buff *skb = base->data; - int hdr_len = skb->h.raw - skb->nh.raw; + xfrm_input_resume(skb, esp_input_done2(skb, err)); +} + +static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ip_esp_hdr *esph; + struct crypto_aead *aead = x->data; + struct aead_request *req; + struct sk_buff *trailer; + int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead); int nfrags; - unsigned char *tmp_hdr = NULL; + int assoclen; + int sglists; + int seqhilen; int ret = 0; + void *tmp; + __be32 *seqhi; + u8 *iv; + struct scatterlist *sg; + struct scatterlist *asg; - if (!pskb_may_pull(skb, sizeof(struct ipv6_esp_hdr))) { + if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) { ret = -EINVAL; - goto out_nofree; + goto out; } - if (elen <= 0 || (elen & (blksize-1))) { + if (elen <= 0) { ret = -EINVAL; - goto out_nofree; + goto out; } - tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC); - if (!tmp_hdr) { - ret = -ENOMEM; - goto out_nofree; + if ((nfrags = skb_cow_data(skb, 0, &trailer)) < 0) { + ret = -EINVAL; + goto out; } - memcpy(tmp_hdr, skb->nh.raw, hdr_len); - - /* If integrity check is required, do this. */ - if (esp->auth.icv_full_len) { - u8 sum[esp->auth.icv_full_len]; - u8 sum1[alen]; - esp->auth.icv(esp, skb, 0, skb->len-alen, sum); + ret = -ENOMEM; - if (skb_copy_bits(skb, skb->len-alen, sum1, alen)) - BUG(); + assoclen = sizeof(*esph); + sglists = 1; + seqhilen = 0; - if (unlikely(memcmp(sum, sum1, alen))) { - x->stats.integrity_failed++; - ret = -EINVAL; - goto out; - } + if (x->props.flags & XFRM_STATE_ESN) { + sglists += 2; + seqhilen += sizeof(__be32); + assoclen += seqhilen; } - if ((nfrags = skb_cow_data(skb, 0, &trailer)) < 0) { - ret = -EINVAL; + tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); + if (!tmp) goto out; - } + + ESP_SKB_CB(skb)->tmp = tmp; + seqhi = esp_tmp_seqhi(tmp); + iv = esp_tmp_iv(aead, tmp, seqhilen); + req = esp_tmp_req(aead, iv); + asg = esp_req_sg(aead, req); + sg = asg + sglists; skb->ip_summed = CHECKSUM_NONE; - esph = (struct ipv6_esp_hdr*)skb->data; - iph = skb->nh.ipv6h; + esph = (struct ip_esp_hdr *)skb->data; /* Get ivec. This can be wrong, check against another impls. */ - if (esp->conf.ivlen) - crypto_cipher_set_iv(esp->conf.tfm, esph->enc_data, crypto_tfm_alg_ivsize(esp->conf.tfm)); - - { - u8 nexthdr[2]; - struct scatterlist *sg = &esp->sgbuf[0]; - u8 padlen; - - if (unlikely(nfrags > ESP_NUM_FAST_SG)) { - sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC); - if (!sg) { - ret = -ENOMEM; - goto out; - } - } - skb_to_sgvec(skb, sg, sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen, elen); - crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen); - if (unlikely(sg != &esp->sgbuf[0])) - kfree(sg); - - if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2)) - BUG(); - - padlen = nexthdr[0]; - if (padlen+2 >= elen) { - LIMIT_NETDEBUG(KERN_WARNING "ipsec esp packet is garbage padlen=%d, elen=%d\n", padlen+2, elen); - ret = -EINVAL; - goto out; - } - /* ... check padding bits here. Silly. :-) */ - - pskb_trim(skb, skb->len - alen - padlen - 2); - skb->h.raw = skb_pull(skb, sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen); - skb->nh.raw += sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen; - memcpy(skb->nh.raw, tmp_hdr, hdr_len); - skb->nh.ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); - ret = nexthdr[1]; - } + iv = esph->enc_data; + + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, sizeof(*esph) + crypto_aead_ivsize(aead), elen); + + if ((x->props.flags & XFRM_STATE_ESN)) { + sg_init_table(asg, 3); + sg_set_buf(asg, &esph->spi, sizeof(__be32)); + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(asg + 1, seqhi, seqhilen); + sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32)); + } else + sg_init_one(asg, esph, sizeof(*esph)); + + aead_request_set_callback(req, 0, esp_input_done, skb); + aead_request_set_crypt(req, sg, sg, elen, iv); + aead_request_set_assoc(req, asg, assoclen); + + ret = crypto_aead_decrypt(req); + if (ret == -EINPROGRESS) + goto out; + + ret = esp_input_done2(skb, ret); out: - kfree(tmp_hdr); -out_nofree: return ret; } -static u32 esp6_get_max_size(struct xfrm_state *x, int mtu) +static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) { - struct esp_data *esp = x->data; - u32 blksize = ALIGN(crypto_tfm_alg_blocksize(esp->conf.tfm), 4); + struct crypto_aead *aead = x->data; + u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4); + unsigned int net_adj; - if (x->props.mode) { - mtu = ALIGN(mtu + 2, blksize); - } else { - /* The worst case. */ - u32 padsize = ((blksize - 1) & 7) + 1; - mtu = ALIGN(mtu + 2, padsize) + blksize - padsize; - } - if (esp->conf.padlen) - mtu = ALIGN(mtu, esp->conf.padlen); + if (x->props.mode != XFRM_MODE_TUNNEL) + net_adj = sizeof(struct ipv6hdr); + else + net_adj = 0; - return mtu + x->props.header_len + esp->auth.icv_full_len; + return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - + net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) +static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { - struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; - struct ipv6_esp_hdr *esph = (struct ipv6_esp_hdr*)(skb->data+offset); + struct net *net = dev_net(skb->dev); + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG) - return; + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + esph->spi, IPPROTO_ESP, AF_INET6); if (!x) - return; - printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - ntohl(esph->spi), NIP6(iph->daddr)); + return 0; + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static void esp6_destroy(struct xfrm_state *x) { - struct esp_data *esp = x->data; + struct crypto_aead *aead = x->data; - if (!esp) + if (!aead) return; - crypto_free_tfm(esp->conf.tfm); - esp->conf.tfm = NULL; - kfree(esp->conf.ivec); - esp->conf.ivec = NULL; - crypto_free_tfm(esp->auth.tfm); - esp->auth.tfm = NULL; - kfree(esp->auth.work_icv); - esp->auth.work_icv = NULL; - kfree(esp); + crypto_free_aead(aead); } -static int esp6_init_state(struct xfrm_state *x) +static int esp_init_aead(struct xfrm_state *x) +{ + struct crypto_aead *aead; + int err; + + aead = crypto_alloc_aead(x->aead->alg_name, 0, 0); + err = PTR_ERR(aead); + if (IS_ERR(aead)) + goto error; + + x->data = aead; + + err = crypto_aead_setkey(aead, x->aead->alg_key, + (x->aead->alg_key_len + 7) / 8); + if (err) + goto error; + + err = crypto_aead_setauthsize(aead, x->aead->alg_icv_len / 8); + if (err) + goto error; + +error: + return err; +} + +static int esp_init_authenc(struct xfrm_state *x) { - struct esp_data *esp = NULL; + struct crypto_aead *aead; + struct crypto_authenc_key_param *param; + struct rtattr *rta; + char *key; + char *p; + char authenc_name[CRYPTO_MAX_ALG_NAME]; + unsigned int keylen; + int err; - /* null auth and encryption can have zero length keys */ - if (x->aalg) { - if (x->aalg->alg_key_len > 512) - goto error; - } + err = -EINVAL; if (x->ealg == NULL) goto error; - if (x->encap) + err = -ENAMETOOLONG; + + if ((x->props.flags & XFRM_STATE_ESN)) { + if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, + "authencesn(%s,%s)", + x->aalg ? x->aalg->alg_name : "digest_null", + x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + goto error; + } else { + if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, + "authenc(%s,%s)", + x->aalg ? x->aalg->alg_name : "digest_null", + x->ealg->alg_name) >= CRYPTO_MAX_ALG_NAME) + goto error; + } + + aead = crypto_alloc_aead(authenc_name, 0, 0); + err = PTR_ERR(aead); + if (IS_ERR(aead)) goto error; - esp = kmalloc(sizeof(*esp), GFP_KERNEL); - if (esp == NULL) - return -ENOMEM; + x->data = aead; + + keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) + + (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param)); + err = -ENOMEM; + key = kmalloc(keylen, GFP_KERNEL); + if (!key) + goto error; - memset(esp, 0, sizeof(*esp)); + p = key; + rta = (void *)p; + rta->rta_type = CRYPTO_AUTHENC_KEYA_PARAM; + rta->rta_len = RTA_LENGTH(sizeof(*param)); + param = RTA_DATA(rta); + p += RTA_SPACE(sizeof(*param)); if (x->aalg) { struct xfrm_algo_desc *aalg_desc; - esp->auth.key = x->aalg->alg_key; - esp->auth.key_len = (x->aalg->alg_key_len+7)/8; - esp->auth.tfm = crypto_alloc_tfm(x->aalg->alg_name, 0); - if (esp->auth.tfm == NULL) - goto error; - esp->auth.icv = esp_hmac_digest; - + memcpy(p, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8); + p += (x->aalg->alg_key_len + 7) / 8; + aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0); BUG_ON(!aalg_desc); - + + err = -EINVAL; if (aalg_desc->uinfo.auth.icv_fullbits/8 != - crypto_tfm_alg_digestsize(esp->auth.tfm)) { - printk(KERN_INFO "ESP: %s digestsize %u != %hu\n", - x->aalg->alg_name, - crypto_tfm_alg_digestsize(esp->auth.tfm), - aalg_desc->uinfo.auth.icv_fullbits/8); - goto error; + crypto_aead_authsize(aead)) { + NETDEBUG(KERN_INFO "ESP: %s digestsize %u != %hu\n", + x->aalg->alg_name, + crypto_aead_authsize(aead), + aalg_desc->uinfo.auth.icv_fullbits/8); + goto free_key; } - - esp->auth.icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - esp->auth.icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; - - esp->auth.work_icv = kmalloc(esp->auth.icv_full_len, GFP_KERNEL); - if (!esp->auth.work_icv) - goto error; + + err = crypto_aead_setauthsize( + aead, x->aalg->alg_trunc_len / 8); + if (err) + goto free_key; } - esp->conf.key = x->ealg->alg_key; - esp->conf.key_len = (x->ealg->alg_key_len+7)/8; - if (x->props.ealgo == SADB_EALG_NULL) - esp->conf.tfm = crypto_alloc_tfm(x->ealg->alg_name, CRYPTO_TFM_MODE_ECB); + + param->enckeylen = cpu_to_be32((x->ealg->alg_key_len + 7) / 8); + memcpy(p, x->ealg->alg_key, (x->ealg->alg_key_len + 7) / 8); + + err = crypto_aead_setkey(aead, key, keylen); + +free_key: + kfree(key); + +error: + return err; +} + +static int esp6_init_state(struct xfrm_state *x) +{ + struct crypto_aead *aead; + u32 align; + int err; + + if (x->encap) + return -EINVAL; + + x->data = NULL; + + if (x->aead) + err = esp_init_aead(x); else - esp->conf.tfm = crypto_alloc_tfm(x->ealg->alg_name, CRYPTO_TFM_MODE_CBC); - if (esp->conf.tfm == NULL) - goto error; - esp->conf.ivlen = crypto_tfm_alg_ivsize(esp->conf.tfm); - esp->conf.padlen = 0; - if (esp->conf.ivlen) { - esp->conf.ivec = kmalloc(esp->conf.ivlen, GFP_KERNEL); - if (unlikely(esp->conf.ivec == NULL)) - goto error; - get_random_bytes(esp->conf.ivec, esp->conf.ivlen); - } - if (crypto_cipher_setkey(esp->conf.tfm, esp->conf.key, esp->conf.key_len)) + err = esp_init_authenc(x); + + if (err) goto error; - x->props.header_len = sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen; - if (x->props.mode) + + aead = x->data; + + x->props.header_len = sizeof(struct ip_esp_hdr) + + crypto_aead_ivsize(aead); + switch (x->props.mode) { + case XFRM_MODE_BEET: + if (x->sel.family != AF_INET6) + x->props.header_len += IPV4_BEET_PHMAXLEN + + (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); + break; + case XFRM_MODE_TRANSPORT: + break; + case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); - x->data = esp; - return 0; + break; + default: + goto error; + } + + align = ALIGN(crypto_aead_blocksize(aead), 4); + x->props.trailer_len = align + 1 + crypto_aead_authsize(aead); error: - x->data = esp; - esp6_destroy(x); - x->data = NULL; - return -EINVAL; + return err; +} + +static int esp6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; } -static struct xfrm_type esp6_type = +static const struct xfrm_type esp6_type = { .description = "ESP6", .owner = THIS_MODULE, .proto = IPPROTO_ESP, + .flags = XFRM_TYPE_REPLAY_PROT, .init_state = esp6_init_state, .destructor = esp6_destroy, - .get_max_size = esp6_get_max_size, + .get_mtu = esp6_get_mtu, .input = esp6_input, - .output = esp6_output + .output = esp6_output, + .hdr_offset = xfrm6_find_1stfragopt, }; -static struct inet6_protocol esp6_protocol = { - .handler = xfrm6_rcv, +static struct xfrm6_protocol esp6_protocol = { + .handler = xfrm6_rcv, + .cb_handler = esp6_rcv_cb, .err_handler = esp6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init esp6_init(void) { if (xfrm_register_type(&esp6_type, AF_INET6) < 0) { - printk(KERN_INFO "ipv6 esp init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) { - printk(KERN_INFO "ipv6 esp init: can't add protocol\n"); + if (xfrm6_protocol_register(&esp6_protocol, IPPROTO_ESP) < 0) { + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp6_type, AF_INET6); return -EAGAIN; } @@ -405,13 +659,14 @@ static int __init esp6_init(void) static void __exit esp6_fini(void) { - if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0) - printk(KERN_INFO "ipv6 esp close: can't remove protocol\n"); + if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0) + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0) - printk(KERN_INFO "ipv6 esp close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(esp6_init); module_exit(esp6_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 922549581ab..8d67900aa00 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -7,8 +7,6 @@ * Andi Kleen <ak@muc.de> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * - * $Id: exthdrs.c,v 1.13 2001/06/19 15:58:56 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 @@ -16,7 +14,7 @@ */ /* Changes: - * yoshfuji : ensure not to overrun while parsing + * yoshfuji : ensure not to overrun while parsing * tlv options. * Mitsuru KANDA @USAGI and: Remove ipv6_parse_exthdrs(). * YOSHIFUJI Hideaki @USAGI Register inbound extension header @@ -27,12 +25,14 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> -#include <linux/sched.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/icmpv6.h> +#include <linux/slab.h> +#include <linux/export.h> +#include <net/dst.h> #include <net/sock.h> #include <net/snmp.h> @@ -43,20 +43,23 @@ #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> +#if IS_ENABLED(CONFIG_IPV6_MIP6) +#include <net/xfrm.h> +#endif #include <asm/uaccess.h> /* * Parsing tlv encoded headers. * - * Parsing function "func" returns 1, if parsing succeed - * and 0, if it failed. + * Parsing function "func" returns true, if parsing succeed + * and false, if it failed. * It MUST NOT touch skb->h. */ struct tlvtype_proc { int type; - int (*func)(struct sk_buff *skb, int offset); + bool (*func)(struct sk_buff *skb, int offset); }; /********************* @@ -65,11 +68,11 @@ struct tlvtype_proc { /* An unknown option is detected, decide what to do */ -static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) +static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) { - switch ((skb->nh.raw[optoff] & 0xC0) >> 6) { + switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ - return 1; + return true; case 1: /* drop packet */ break; @@ -78,191 +81,294 @@ static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) /* Actually, it is redundant check. icmp_send will recheck in any case. */ - if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr)) + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); - return 0; - }; + return false; + } kfree_skb(skb); - return 0; + return false; } /* Parse tlv encoded option header (hop-by-hop or destination) */ -static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb) +static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) { - struct tlvtype_proc *curr; - int off = skb->h.raw - skb->nh.raw; - int len = ((skb->h.raw[1]+1)<<3); + const struct tlvtype_proc *curr; + const unsigned char *nh = skb_network_header(skb); + int off = skb_network_header_len(skb); + int len = (skb_transport_header(skb)[1] + 1) << 3; + int padlen = 0; - if ((skb->h.raw + len) - skb->data > skb_headlen(skb)) + if (skb_transport_offset(skb) + len > skb_headlen(skb)) goto bad; off += 2; len -= 2; while (len > 0) { - int optlen = skb->nh.raw[off+1]+2; + int optlen = nh[off + 1] + 2; + int i; - switch (skb->nh.raw[off]) { - case IPV6_TLV_PAD0: + switch (nh[off]) { + case IPV6_TLV_PAD1: optlen = 1; + padlen++; + if (padlen > 7) + goto bad; break; case IPV6_TLV_PADN: + /* RFC 2460 states that the purpose of PadN is + * to align the containing header to multiples + * of 8. 7 is therefore the highest valid value. + * See also RFC 4942, Section 2.1.9.5. + */ + padlen += optlen; + if (padlen > 7) + goto bad; + /* RFC 4942 recommends receiving hosts to + * actively check PadN payload to contain + * only zeroes. + */ + for (i = 2; i < optlen; i++) { + if (nh[off + i] != 0) + goto bad; + } break; default: /* Other TLV code so scan list */ if (optlen > len) goto bad; for (curr=procs; curr->type >= 0; curr++) { - if (curr->type == skb->nh.raw[off]) { - /* type specific length/alignment - checks will be performed in the + if (curr->type == nh[off]) { + /* type specific length/alignment + checks will be performed in the func(). */ - if (curr->func(skb, off) == 0) - return 0; + if (curr->func(skb, off) == false) + return false; break; } } if (curr->type < 0) { if (ip6_tlvopt_unknown(skb, off) == 0) - return 0; + return false; } + padlen = 0; break; } off += optlen; len -= optlen; } + if (len == 0) - return 1; + return true; bad: kfree_skb(skb); - return 0; + return false; } /***************************** Destination options header. *****************************/ -static struct tlvtype_proc tlvprocdestopt_lst[] = { - /* No destination options are defined now */ - {-1, NULL} -}; - -static int ipv6_destopt_rcv(struct sk_buff **skbp, unsigned int *nhoffp) +#if IS_ENABLED(CONFIG_IPV6_MIP6) +static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { - struct sk_buff *skb = *skbp; + struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct in6_addr tmp_addr; + int ret; - if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+8) || - !pskb_may_pull(skb, (skb->h.raw-skb->data)+((skb->h.raw[1]+1)<<3))) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - kfree_skb(skb); - return -1; + if (opt->dsthao) { + LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n"); + goto discard; } + opt->dsthao = opt->dst1; + opt->dst1 = 0; - opt->lastopt = skb->h.raw - skb->nh.raw; - opt->dst1 = skb->h.raw - skb->nh.raw; + hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); - if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { - skb->h.raw += ((skb->h.raw[1]+1)<<3); - *nhoffp = opt->dst1; - return 1; + if (hao->length != 16) { + LIMIT_NETDEBUG( + KERN_DEBUG "hao invalid option length = %d\n", hao->length); + goto discard; } - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - return -1; -} + if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { + LIMIT_NETDEBUG( + KERN_DEBUG "hao is not an unicast addr: %pI6\n", &hao->addr); + goto discard; + } -static struct inet6_protocol destopt_protocol = { - .handler = ipv6_destopt_rcv, - .flags = INET6_PROTO_NOPOLICY, -}; + ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr, + (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS); + if (unlikely(ret < 0)) + goto discard; -void __init ipv6_destopt_init(void) -{ - if (inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS) < 0) - printk(KERN_ERR "ipv6_destopt_init: Could not register protocol\n"); -} + if (skb_cloned(skb)) { + if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + goto discard; -/******************************** - NONE header. No data in packet. - ********************************/ + /* update all variable using below by copied skbuff */ + hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + + optoff); + ipv6h = ipv6_hdr(skb); + } -static int ipv6_nodata_rcv(struct sk_buff **skbp, unsigned int *nhoffp) -{ - struct sk_buff *skb = *skbp; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + tmp_addr = ipv6h->saddr; + ipv6h->saddr = hao->addr; + hao->addr = tmp_addr; + + if (skb->tstamp.tv64 == 0) + __net_timestamp(skb); + + return true; + + discard: kfree_skb(skb); - return 0; + return false; } +#endif -static struct inet6_protocol nodata_protocol = { - .handler = ipv6_nodata_rcv, - .flags = INET6_PROTO_NOPOLICY, +static const struct tlvtype_proc tlvprocdestopt_lst[] = { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + { + .type = IPV6_TLV_HAO, + .func = ipv6_dest_hao, + }, +#endif + {-1, NULL} }; -void __init ipv6_nodata_init(void) +static int ipv6_destopt_rcv(struct sk_buff *skb) { - if (inet6_add_protocol(&nodata_protocol, IPPROTO_NONE) < 0) - printk(KERN_ERR "ipv6_nodata_init: Could not register protocol\n"); + struct inet6_skb_parm *opt = IP6CB(skb); +#if IS_ENABLED(CONFIG_IPV6_MIP6) + __u16 dstbuf; +#endif + 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(dst->dev), ip6_dst_idev(dst), + IPSTATS_MIB_INHDRERRORS); + kfree_skb(skb); + return -1; + } + + opt->lastopt = opt->dst1 = skb_network_header_len(skb); +#if IS_ENABLED(CONFIG_IPV6_MIP6) + dstbuf = opt->dst1; +#endif + + if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { + skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; + opt = IP6CB(skb); +#if IS_ENABLED(CONFIG_IPV6_MIP6) + opt->nhoff = dstbuf; +#else + opt->nhoff = opt->dst1; +#endif + return 1; + } + + IP6_INC_STATS_BH(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); + return -1; } /******************************** Routing header. ********************************/ -static int ipv6_rthdr_rcv(struct sk_buff **skbp, unsigned int *nhoffp) +/* called with rcu_read_lock() */ +static int ipv6_rthdr_rcv(struct sk_buff *skb) { - struct sk_buff *skb = *skbp; struct inet6_skb_parm *opt = IP6CB(skb); - struct in6_addr *addr; + struct in6_addr *addr = NULL; struct in6_addr daddr; + struct inet6_dev *idev; int n, i; - struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; - - if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+8) || - !pskb_may_pull(skb, (skb->h.raw-skb->data)+((skb->h.raw[1]+1)<<3))) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + struct net *net = dev_net(skb->dev); + int accept_source_route = net->ipv6.devconf_all->accept_source_route; + + idev = __in6_dev_get(skb->dev); + if (idev && accept_source_route > idev->cnf.accept_source_route) + accept_source_route = idev->cnf.accept_source_route; + + 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(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } - hdr = (struct ipv6_rt_hdr *) skb->h.raw; + hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); - if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr) || + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } looped_back: if (hdr->segments_left == 0) { - opt->lastopt = skb->h.raw - skb->nh.raw; - opt->srcrt = skb->h.raw - skb->nh.raw; - skb->h.raw += (hdr->hdrlen + 1) << 3; + switch (hdr->type) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_SRCRT_TYPE_2: + /* Silently discard type 2 header unless it was + * processed by own + */ + if (!addr) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INADDRERRORS); + kfree_skb(skb); + return -1; + } + break; +#endif + default: + break; + } + + opt->lastopt = opt->srcrt = skb_network_header_len(skb); + skb->transport_header += (hdr->hdrlen + 1) << 3; opt->dst0 = opt->dst1; opt->dst1 = 0; - *nhoffp = (&hdr->nexthdr) - skb->nh.raw; + opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } - if (hdr->type != IPV6_SRCRT_TYPE_0) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb->nh.raw); - return -1; - } - - if (hdr->hdrlen & 0x01) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw); - return -1; + switch (hdr->type) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_SRCRT_TYPE_2: + if (accept_source_route < 0) + goto unknown_rh; + /* Silently discard invalid RTH type 2 */ + if (hdr->hdrlen != 2 || hdr->segments_left != 1) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + kfree_skb(skb); + return -1; + } + break; +#endif + default: + goto unknown_rh; } /* @@ -273,8 +379,11 @@ looped_back: n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->segments_left) - skb->nh.raw); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, + ((&hdr->segments_left) - + skb_network_header(skb))); return -1; } @@ -282,19 +391,17 @@ looped_back: Do not damage packets queued somewhere. */ if (skb_cloned(skb)) { - struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC); - kfree_skb(skb); /* the copy is a forwarded packet */ - if (skb2 == NULL) { - IP6_INC_STATS_BH(IPSTATS_MIB_OUTDISCARDS); + if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); return -1; } - *skbp = skb = skb2; - opt = IP6CB(skb2); - hdr = (struct ipv6_rt_hdr *) skb2->h.raw; + hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; i = n - --hdr->segments_left; @@ -303,175 +410,200 @@ looped_back: addr = rthdr->addr; addr += i - 1; + switch (hdr->type) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_SRCRT_TYPE_2: + if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, + (xfrm_address_t *)&ipv6_hdr(skb)->saddr, + IPPROTO_ROUTING) < 0) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INADDRERRORS); + kfree_skb(skb); + return -1; + } + if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INADDRERRORS); + kfree_skb(skb); + return -1; + } + break; +#endif + default: + break; + } + if (ipv6_addr_is_multicast(addr)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } - ipv6_addr_copy(&daddr, addr); - ipv6_addr_copy(addr, &skb->nh.ipv6h->daddr); - ipv6_addr_copy(&skb->nh.ipv6h->daddr, &daddr); + daddr = *addr; + *addr = ipv6_hdr(skb)->daddr; + ipv6_hdr(skb)->daddr = daddr; - dst_release(xchg(&skb->dst, NULL)); + skb_dst_drop(skb); ip6_route_input(skb); - if (skb->dst->error) { - skb_push(skb, skb->data - skb->nh.raw); + if (skb_dst(skb)->error) { + skb_push(skb, skb->data - skb_network_header(skb)); dst_input(skb); return -1; } - if (skb->dst->dev->flags&IFF_LOOPBACK) { - if (skb->nh.ipv6h->hop_limit <= 1) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { + if (ipv6_hdr(skb)->hop_limit <= 1) { + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - 0, skb->dev); + 0); kfree_skb(skb); return -1; } - skb->nh.ipv6h->hop_limit--; + ipv6_hdr(skb)->hop_limit--; goto looped_back; } - skb_push(skb, skb->data - skb->nh.raw); + skb_push(skb, skb->data - skb_network_header(skb)); dst_input(skb); return -1; + +unknown_rh: + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, + (&hdr->type) - skb_network_header(skb)); + return -1; } -static struct inet6_protocol rthdr_protocol = { +static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, .flags = INET6_PROTO_NOPOLICY, }; -void __init ipv6_rthdr_init(void) -{ - if (inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING) < 0) - printk(KERN_ERR "ipv6_rthdr_init: Could not register protocol\n"); +static const struct inet6_protocol destopt_protocol = { + .handler = ipv6_destopt_rcv, + .flags = INET6_PROTO_NOPOLICY, }; -/* - This function inverts received rthdr. - NOTE: specs allow to make it automatically only if - packet authenticated. - - I will not discuss it here (though, I am really pissed off at - this stupid requirement making rthdr idea useless) - - Actually, it creates severe problems for us. - Embryonic requests has no associated sockets, - so that user have no control over it and - cannot not only to set reply options, but - even to know, that someone wants to connect - without success. :-( - - For now we need to test the engine, so that I created - temporary (or permanent) backdoor. - If listening socket set IPV6_RTHDR to 2, then we invert header. - --ANK (980729) - */ +static const struct inet6_protocol nodata_protocol = { + .handler = dst_discard, + .flags = INET6_PROTO_NOPOLICY, +}; -struct ipv6_txoptions * -ipv6_invert_rthdr(struct sock *sk, struct ipv6_rt_hdr *hdr) +int __init ipv6_exthdrs_init(void) { - /* Received rthdr: + int ret; - [ H1 -> H2 -> ... H_prev ] daddr=ME + ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING); + if (ret) + goto out; - Inverted result: - [ H_prev -> ... -> H1 ] daddr =sender + ret = inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS); + if (ret) + goto out_rthdr; - Note, that IP output engine will rewrite this rthdr - by rotating it left by one addr. - */ + ret = inet6_add_protocol(&nodata_protocol, IPPROTO_NONE); + if (ret) + goto out_destopt; - int n, i; - struct rt0_hdr *rthdr = (struct rt0_hdr*)hdr; - struct rt0_hdr *irthdr; - struct ipv6_txoptions *opt; - int hdrlen = ipv6_optlen(hdr); - - if (hdr->segments_left || - hdr->type != IPV6_SRCRT_TYPE_0 || - hdr->hdrlen & 0x01) - return NULL; +out: + return ret; +out_destopt: + inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); +out_rthdr: + inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); + goto out; +}; - n = hdr->hdrlen >> 1; - opt = sock_kmalloc(sk, sizeof(*opt) + hdrlen, GFP_ATOMIC); - if (opt == NULL) - return NULL; - memset(opt, 0, sizeof(*opt)); - opt->tot_len = sizeof(*opt) + hdrlen; - opt->srcrt = (void*)(opt+1); - opt->opt_nflen = hdrlen; - - memcpy(opt->srcrt, hdr, sizeof(*hdr)); - irthdr = (struct rt0_hdr*)opt->srcrt; - irthdr->reserved = 0; - opt->srcrt->segments_left = n; - for (i=0; i<n; i++) - memcpy(irthdr->addr+i, rthdr->addr+(n-1-i), 16); - return opt; +void ipv6_exthdrs_exit(void) +{ + inet6_del_protocol(&nodata_protocol, IPPROTO_NONE); + inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); + inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); } /********************************** Hop-by-hop options. **********************************/ +/* + * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input(). + */ +static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb) +{ + return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev); +} + +static inline struct net *ipv6_skb_net(struct sk_buff *skb) +{ + return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev); +} + /* Router Alert as of RFC 2711 */ -static int ipv6_hop_ra(struct sk_buff *skb, int optoff) +static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) { - if (skb->nh.raw[optoff+1] == 2) { - IP6CB(skb)->ra = optoff; - return 1; + const unsigned char *nh = skb_network_header(skb); + + if (nh[optoff + 1] == 2) { + IP6CB(skb)->flags |= IP6SKB_ROUTERALERT; + memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); + return true; } LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", - skb->nh.raw[optoff+1]); + nh[optoff + 1]); kfree_skb(skb); - return 0; + return false; } /* Jumbo payload */ -static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) +static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { + const unsigned char *nh = skb_network_header(skb); + struct net *net = ipv6_skb_net(skb); u32 pkt_len; - if (skb->nh.raw[optoff+1] != 4 || (optoff&3) != 2) { + if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", - skb->nh.raw[optoff+1]); - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + nh[optoff+1]); + IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), + IPSTATS_MIB_INHDRERRORS); goto drop; } - pkt_len = ntohl(*(u32*)(skb->nh.raw+optoff+2)); + pkt_len = ntohl(*(__be32 *)(nh + optoff + 2)); if (pkt_len <= IPV6_MAXPLEN) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2); - return 0; + return false; } - if (skb->nh.ipv6h->payload_len) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + if (ipv6_hdr(skb)->payload_len) { + IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff); - return 0; + return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS); + IP6_INC_STATS_BH(net, ipv6_skb_idev(skb), + IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto drop; - return 1; + return true; drop: kfree_skb(skb); - return 0; + return false; } -static struct tlvtype_proc tlvprochopopt_lst[] = { +static const struct tlvtype_proc tlvprochopopt_lst[] = { { .type = IPV6_TLV_ROUTERALERT, .func = ipv6_hop_ra, @@ -483,11 +615,30 @@ static struct tlvtype_proc tlvprochopopt_lst[] = { { -1, } }; -int ipv6_parse_hopopts(struct sk_buff *skb, int nhoff) +int ipv6_parse_hopopts(struct sk_buff *skb) { - IP6CB(skb)->hop = sizeof(struct ipv6hdr); - if (ip6_parse_tlv(tlvprochopopt_lst, skb)) - return sizeof(struct ipv6hdr); + struct inet6_skb_parm *opt = IP6CB(skb); + + /* + * skb_network_header(skb) is equal to skb->data, and + * skb_network_header_len(skb) is always equal to + * sizeof(struct ipv6hdr) by definition of + * hop-by-hop options. + */ + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) || + !pskb_may_pull(skb, (sizeof(struct ipv6hdr) + + ((skb_transport_header(skb)[1] + 1) << 3)))) { + kfree_skb(skb); + return -1; + } + + opt->hop = sizeof(struct ipv6hdr); + if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { + skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; + opt = IP6CB(skb); + opt->nhoff = sizeof(struct ipv6hdr); + return 1; + } return -1; } @@ -509,7 +660,7 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, int hops; ihdr = (struct rt0_hdr *) opt; - + phdr = (struct rt0_hdr *) skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); memcpy(phdr, ihdr, sizeof(struct rt0_hdr)); @@ -519,7 +670,7 @@ 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; @@ -551,6 +702,7 @@ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, if (opt->hopopt) ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt); } +EXPORT_SYMBOL(ipv6_push_nfrag_opts); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto) { @@ -565,19 +717,20 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC); if (opt2) { - long dif = (char*)opt2 - (char*)opt; + long dif = (char *)opt2 - (char *)opt; memcpy(opt2, opt, opt->tot_len); if (opt2->hopopt) - *((char**)&opt2->hopopt) += dif; + *((char **)&opt2->hopopt) += dif; if (opt2->dst0opt) - *((char**)&opt2->dst0opt) += dif; + *((char **)&opt2->dst0opt) += dif; if (opt2->dst1opt) - *((char**)&opt2->dst1opt) += dif; + *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) - *((char**)&opt2->srcrt) += dif; + *((char **)&opt2->srcrt) += dif; } return opt2; } +EXPORT_SYMBOL_GPL(ipv6_dup_options); static int ipv6_renew_option(void *ohdr, struct ipv6_opt_hdr __user *newopt, int newoptlen, @@ -589,14 +742,14 @@ static int ipv6_renew_option(void *ohdr, if (ohdr) { memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*(struct ipv6_opt_hdr **)hdr)); + *p += CMSG_ALIGN(ipv6_optlen(*hdr)); } } else { if (newopt) { if (copy_from_user(*p, newopt, newoptlen)) return -EFAULT; *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*(struct ipv6_opt_hdr **)hdr) > newoptlen) + if (ipv6_optlen(*hdr) > newoptlen) return -EINVAL; *p += CMSG_ALIGN(newoptlen); } @@ -614,20 +767,24 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, struct ipv6_txoptions *opt2; int err; - if (newtype != IPV6_HOPOPTS && opt->hopopt) - tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt)); - if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt) - tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt)); - if (newtype != IPV6_RTHDR && opt->srcrt) - tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt)); - if (newtype != IPV6_DSTOPTS && opt->dst1opt) - tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); + if (opt) { + if (newtype != IPV6_HOPOPTS && opt->hopopt) + tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt)); + if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt) + tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt)); + if (newtype != IPV6_RTHDR && opt->srcrt) + tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt)); + if (newtype != IPV6_DSTOPTS && opt->dst1opt) + tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); + } + if (newopt && newoptlen) tot_len += CMSG_ALIGN(newoptlen); if (!tot_len) return NULL; + tot_len += sizeof(*opt2); opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC); if (!opt2) return ERR_PTR(-ENOBUFS); @@ -637,25 +794,25 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->tot_len = tot_len; p = (char *)(opt2 + 1); - err = ipv6_renew_option(opt->hopopt, newopt, newoptlen, + err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen, newtype != IPV6_HOPOPTS, &opt2->hopopt, &p); if (err) goto out; - err = ipv6_renew_option(opt->dst0opt, newopt, newoptlen, + err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen, newtype != IPV6_RTHDRDSTOPTS, &opt2->dst0opt, &p); if (err) goto out; - err = ipv6_renew_option(opt->srcrt, newopt, newoptlen, + err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen, newtype != IPV6_RTHDR, - (struct ipv6_opt_hdr **)opt2->srcrt, &p); + (struct ipv6_opt_hdr **)&opt2->srcrt, &p); if (err) goto out; - err = ipv6_renew_option(opt->dst1opt, newopt, newoptlen, + err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen, newtype != IPV6_DSTOPTS, &opt2->dst1opt, &p); if (err) @@ -668,7 +825,50 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return opt2; out: - sock_kfree_s(sk, p, tot_len); + sock_kfree_s(sk, opt2, opt2->tot_len); return ERR_PTR(err); } +struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt) +{ + /* + * ignore the dest before srcrt unless srcrt is being included. + * --yoshfuji + */ + if (opt && opt->dst0opt && !opt->srcrt) { + if (opt_space != opt) { + memcpy(opt_space, opt, sizeof(*opt_space)); + opt = opt_space; + } + opt->opt_nflen -= ipv6_optlen(opt->dst0opt); + opt->dst0opt = NULL; + } + + return opt; +} +EXPORT_SYMBOL_GPL(ipv6_fixup_options); + +/** + * fl6_update_dst - update flowi destination address with info given + * by srcrt option, if any. + * + * @fl6: flowi6 for which daddr is to be updated + * @opt: struct ipv6_txoptions in which to look for srcrt opt + * @orig: copy of original daddr address if modified + * + * Returns NULL if no txoptions or no srcrt, otherwise returns orig + * and initial value of fl6->daddr set in orig + */ +struct in6_addr *fl6_update_dst(struct flowi6 *fl6, + const struct ipv6_txoptions *opt, + struct in6_addr *orig) +{ + if (!opt || !opt->srcrt) + return NULL; + + *orig = fl6->daddr; + fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; + return orig; +} +EXPORT_SYMBOL_GPL(fl6_update_dst); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 315bc1fbec3..8af3eb57f43 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -2,41 +2,43 @@ * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. */ +#include <linux/export.h> #include <net/ipv6.h> -/* +/* * find out if nexthdr is a well-known extension header or a protocol */ -int ipv6_ext_hdr(u8 nexthdr) +bool ipv6_ext_hdr(u8 nexthdr) { - /* + /* * find out if nexthdr is an extension header or a protocol */ - return ( (nexthdr == NEXTHDR_HOP) || + return (nexthdr == NEXTHDR_HOP) || (nexthdr == NEXTHDR_ROUTING) || (nexthdr == NEXTHDR_FRAGMENT) || (nexthdr == NEXTHDR_AUTH) || (nexthdr == NEXTHDR_NONE) || - (nexthdr == NEXTHDR_DEST) ); + (nexthdr == NEXTHDR_DEST); } +EXPORT_SYMBOL(ipv6_ext_hdr); /* * Skip any extension headers. This is used by the ICMP module. * * Note that strictly speaking this conflicts with RFC 2460 4.0: - * ...The contents and semantics of each extension header determine whether + * ...The contents and semantics of each extension header determine whether * or not to proceed to the next header. Therefore, extension headers must * be processed strictly in the order they appear in the packet; a * receiver must not, for example, scan through a packet looking for a * particular kind of extension header and process that header prior to * processing all preceding ones. - * + * * We do exactly this. This is a protocol bug. We can't decide after a - * seeing an unknown discard-with-error flavour TLV option if it's a + * seeing an unknown discard-with-error flavour TLV option if it's a * ICMP error message or not (errors should never be send in reply to * ICMP error messages). - * + * * But I see no other way to do this. This might need to be reexamined * when Linux implements ESP (and maybe AUTH) headers. * --AK @@ -56,6 +58,9 @@ 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 +68,13 @@ 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; @@ -77,7 +85,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp) if (hp == NULL) return -1; if (nexthdr == NEXTHDR_FRAGMENT) { - unsigned short _frag_off, *fp; + __be16 _frag_off, *fp; fp = skb_header_pointer(skb, start+offsetof(struct frag_hdr, frag_off), @@ -86,13 +94,14 @@ 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) - hdrlen = (hp->hdrlen+2)<<2; + hdrlen = (hp->hdrlen+2)<<2; else - hdrlen = ipv6_optlen(hp); + hdrlen = ipv6_optlen(hp); nexthdr = hp->nexthdr; start += hdrlen; @@ -101,6 +110,172 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp) *nexthdrp = nexthdr; return start; } - -EXPORT_SYMBOL(ipv6_ext_hdr); EXPORT_SYMBOL(ipv6_skip_exthdr); + +int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) +{ + const unsigned char *nh = skb_network_header(skb); + int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); + struct ipv6_opt_hdr *hdr; + int len; + + if (offset + 2 > packet_len) + goto bad; + hdr = (struct ipv6_opt_hdr *)(nh + offset); + len = ((hdr->hdrlen + 1) << 3); + + if (offset + len > packet_len) + goto bad; + + offset += 2; + len -= 2; + + while (len > 0) { + int opttype = nh[offset]; + int optlen; + + if (opttype == type) + return offset; + + switch (opttype) { + case IPV6_TLV_PAD1: + optlen = 1; + break; + default: + optlen = nh[offset + 1] + 2; + if (optlen > len) + goto bad; + break; + } + offset += optlen; + len -= optlen; + } + /* not_found */ + bad: + return -1; +} +EXPORT_SYMBOL_GPL(ipv6_find_tlv); + +/* + * find the offset to specified header or the protocol number of last header + * if target < 0. "last header" is transport protocol header, ESP, or + * "No next header". + * + * Note that *offset is used as input/output parameter. an if it is not zero, + * then it must be a valid offset to an inner IPv6 header. This can be used + * to explore inner IPv6 header, eg. ICMPv6 error messages. + * + * If target header is found, its offset is set in *offset and return protocol + * number. Otherwise, return -1. + * + * If the first fragment doesn't contain the final protocol header or + * NEXTHDR_NONE it is considered invalid. + * + * Note that non-1st fragment is special case that "the protocol number + * of last header" is "next header" field in Fragment header. In this case, + * *offset is meaningless and fragment offset is stored in *fragoff if fragoff + * isn't NULL. + * + * if flags is not NULL and it's a fragment, then the frag flag + * IP6_FH_F_FRAG will be set. If it's an AH header, the + * IP6_FH_F_AUTH flag is set and target < 0, then this function will + * stop at the AH header. If IP6_FH_F_SKIP_RH flag was passed, then this + * function will skip all those routing headers, where segements_left was 0. + */ +int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, + int target, unsigned short *fragoff, int *flags) +{ + unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + unsigned int len; + bool found; + + if (fragoff) + *fragoff = 0; + + if (*offset) { + struct ipv6hdr _ip6, *ip6; + + ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); + if (!ip6 || (ip6->version != 6)) { + printk(KERN_ERR "IPv6 header not found\n"); + return -EBADMSG; + } + start = *offset + sizeof(struct ipv6hdr); + nexthdr = ip6->nexthdr; + } + len = skb->len - start; + + do { + struct ipv6_opt_hdr _hdr, *hp; + unsigned int hdrlen; + found = (nexthdr == target); + + if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { + if (target < 0 || found) + break; + return -ENOENT; + } + + hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); + if (hp == NULL) + return -EBADMSG; + + if (nexthdr == NEXTHDR_ROUTING) { + struct ipv6_rt_hdr _rh, *rh; + + rh = skb_header_pointer(skb, start, sizeof(_rh), + &_rh); + if (rh == NULL) + return -EBADMSG; + + if (flags && (*flags & IP6_FH_F_SKIP_RH) && + rh->segments_left == 0) + found = false; + } + + if (nexthdr == NEXTHDR_FRAGMENT) { + unsigned short _frag_off; + __be16 *fp; + + if (flags) /* Indicate that this is a fragment */ + *flags |= IP6_FH_F_FRAG; + fp = skb_header_pointer(skb, + start+offsetof(struct frag_hdr, + frag_off), + sizeof(_frag_off), + &_frag_off); + if (fp == NULL) + return -EBADMSG; + + _frag_off = ntohs(*fp) & ~0x7; + if (_frag_off) { + if (target < 0 && + ((!ipv6_ext_hdr(hp->nexthdr)) || + hp->nexthdr == NEXTHDR_NONE)) { + if (fragoff) + *fragoff = _frag_off; + return hp->nexthdr; + } + return -ENOENT; + } + hdrlen = 8; + } else if (nexthdr == NEXTHDR_AUTH) { + if (flags && (*flags & IP6_FH_F_AUTH) && (target < 0)) + break; + hdrlen = (hp->hdrlen + 2) << 2; + } else + hdrlen = ipv6_optlen(hp); + + if (!found) { + nexthdr = hp->nexthdr; + len -= hdrlen; + start += hdrlen; + } + } while (!found); + + *offset = start; + return nexthdr; +} +EXPORT_SYMBOL(ipv6_find_hdr); + diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c new file mode 100644 index 00000000000..447a7fbd1bb --- /dev/null +++ b/net/ipv6/exthdrs_offload.c @@ -0,0 +1,41 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * 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. + * + * IPV6 Extension Header GSO/GRO support + */ +#include <net/protocol.h> +#include "ip6_offload.h" + +static const struct net_offload rthdr_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +static const struct net_offload dstopt_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +int __init ipv6_exthdrs_offload_init(void) +{ + int ret; + + ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); + if (ret) + goto out; + + ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); + if (ret) + goto out_rt; + +out: + return ret; + +out_rt: + inet_del_offload(&rthdr_offload, IPPROTO_ROUTING); + goto out; +} diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c new file mode 100644 index 00000000000..b4d5e1d97c1 --- /dev/null +++ b/net/ipv6/fib6_rules.c @@ -0,0 +1,341 @@ +/* + * net/ipv6/fib6_rules.c IPv6 Routing Policy Rules + * + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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, version 2. + * + * Authors + * Thomas Graf <tgraf@suug.ch> + * Ville Nuorvala <vnuorval@tcs.hut.fi> + */ + +#include <linux/netdevice.h> +#include <linux/export.h> + +#include <net/fib_rules.h> +#include <net/ipv6.h> +#include <net/addrconf.h> +#include <net/ip6_route.h> +#include <net/netlink.h> + +struct fib6_rule { + struct fib_rule common; + struct rt6key src; + struct rt6key dst; + u8 tclass; +}; + +struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + int flags, pol_lookup_t lookup) +{ + struct fib_lookup_arg arg = { + .lookup_ptr = lookup, + .flags = FIB_LOOKUP_NOREF, + }; + + fib_rules_lookup(net->ipv6.fib6_rules_ops, + flowi6_to_flowi(fl6), flags, &arg); + + if (arg.result) + return arg.result; + + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; +} + +static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct flowi6 *flp6 = &flp->u.ip6; + struct rt6_info *rt = NULL; + struct fib6_table *table; + struct net *net = rule->fr_net; + pol_lookup_t lookup = arg->lookup_ptr; + int err = 0; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + err = -ENETUNREACH; + rt = net->ipv6.ip6_null_entry; + goto discard_pkt; + default: + case FR_ACT_BLACKHOLE: + err = -EINVAL; + rt = net->ipv6.ip6_blk_hole_entry; + goto discard_pkt; + case FR_ACT_PROHIBIT: + err = -EACCES; + rt = net->ipv6.ip6_prohibit_entry; + goto discard_pkt; + } + + table = fib6_get_table(net, rule->table); + if (!table) { + err = -EAGAIN; + goto out; + } + + rt = lookup(net, table, flp6, flags); + if (rt != net->ipv6.ip6_null_entry) { + struct fib6_rule *r = (struct fib6_rule *)rule; + + /* + * If we need to find a source address for this traffic, + * we check the result if it meets requirement of the rule. + */ + if ((rule->flags & FIB_RULE_FIND_SADDR) && + r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { + struct in6_addr saddr; + + if (ipv6_dev_get_saddr(net, + ip6_dst_idev(&rt->dst)->dev, + &flp6->daddr, + rt6_flags2srcprefs(flags), + &saddr)) + goto again; + if (!ipv6_prefix_equal(&saddr, &r->src.addr, + r->src.plen)) + goto again; + flp6->saddr = saddr; + } + goto out; + } +again: + ip6_rt_put(rt); + err = -EAGAIN; + rt = NULL; + goto out; + +discard_pkt: + dst_hold(&rt->dst); +out: + arg->result = rt; + return err; +} + +static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +{ + struct rt6_info *rt = (struct rt6_info *) arg->result; + struct net_device *dev = NULL; + + if (rt->rt6i_idev) + dev = rt->rt6i_idev->dev; + + /* do not accept result if the route does + * not meet the required prefix length + */ + if (rt->rt6i_dst.plen <= rule->suppress_prefixlen) + goto suppress_route; + + /* do not accept result if the route uses a device + * belonging to a forbidden interface group + */ + if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) + goto suppress_route; + + return false; + +suppress_route: + ip6_rt_put(rt); + return true; +} + +static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +{ + struct fib6_rule *r = (struct fib6_rule *) rule; + struct flowi6 *fl6 = &fl->u.ip6; + + if (r->dst.plen && + !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen)) + return 0; + + /* + * If FIB_RULE_FIND_SADDR is set and we do not have a + * source address for the traffic, we defer check for + * source address. + */ + if (r->src.plen) { + if (flags & RT6_LOOKUP_F_HAS_SADDR) { + if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr, + r->src.plen)) + return 0; + } else if (!(r->common.flags & FIB_RULE_FIND_SADDR)) + return 0; + } + + if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) + return 0; + + return 1; +} + +static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = { + FRA_GENERIC_POLICY, +}; + +static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + int err = -EINVAL; + struct net *net = sock_net(skb->sk); + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + if (rule->action == FR_ACT_TO_TBL) { + if (rule->table == RT6_TABLE_UNSPEC) + goto errout; + + if (fib6_new_table(net, rule->table) == NULL) { + err = -ENOBUFS; + goto errout; + } + } + + if (frh->src_len) + nla_memcpy(&rule6->src.addr, tb[FRA_SRC], + sizeof(struct in6_addr)); + + if (frh->dst_len) + nla_memcpy(&rule6->dst.addr, tb[FRA_DST], + sizeof(struct in6_addr)); + + rule6->src.plen = frh->src_len; + rule6->dst.plen = frh->dst_len; + rule6->tclass = frh->tos; + + err = 0; +errout: + return err; +} + +static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + if (frh->src_len && (rule6->src.plen != frh->src_len)) + return 0; + + if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) + return 0; + + if (frh->tos && (rule6->tclass != frh->tos)) + return 0; + + if (frh->src_len && + nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) + return 0; + + if (frh->dst_len && + nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr))) + return 0; + + return 1; +} + +static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + frh->dst_len = rule6->dst.plen; + frh->src_len = rule6->src.plen; + frh->tos = rule6->tclass; + + if ((rule6->dst.plen && + nla_put(skb, FRA_DST, sizeof(struct in6_addr), + &rule6->dst.addr)) || + (rule6->src.plen && + nla_put(skb, FRA_SRC, sizeof(struct in6_addr), + &rule6->src.addr))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +static u32 fib6_rule_default_pref(struct fib_rules_ops *ops) +{ + return 0x3FFF; +} + +static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) +{ + return nla_total_size(16) /* dst */ + + nla_total_size(16); /* src */ +} + +static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { + .family = AF_INET6, + .rule_size = sizeof(struct fib6_rule), + .addr_size = sizeof(struct in6_addr), + .action = fib6_rule_action, + .match = fib6_rule_match, + .suppress = fib6_rule_suppress, + .configure = fib6_rule_configure, + .compare = fib6_rule_compare, + .fill = fib6_rule_fill, + .default_pref = fib6_rule_default_pref, + .nlmsg_payload = fib6_rule_nlmsg_payload, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = fib6_rule_policy, + .owner = THIS_MODULE, + .fro_net = &init_net, +}; + +static int __net_init fib6_rules_net_init(struct net *net) +{ + struct fib_rules_ops *ops; + int err = -ENOMEM; + + ops = fib_rules_register(&fib6_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv6.fib6_rules_ops = ops; + + + err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0, + RT6_TABLE_LOCAL, 0); + if (err) + goto out_fib6_rules_ops; + + err = fib_default_rule_add(net->ipv6.fib6_rules_ops, + 0x7FFE, RT6_TABLE_MAIN, 0); + if (err) + goto out_fib6_rules_ops; + +out: + return err; + +out_fib6_rules_ops: + fib_rules_unregister(ops); + goto out; +} + +static void __net_exit fib6_rules_net_exit(struct net *net) +{ + fib_rules_unregister(net->ipv6.fib6_rules_ops); +} + +static struct pernet_operations fib6_rules_net_ops = { + .init = fib6_rules_net_init, + .exit = fib6_rules_net_exit, +}; + +int __init fib6_rules_init(void) +{ + return register_pernet_subsys(&fib6_rules_net_ops); +} + + +void fib6_rules_cleanup(void) +{ + unregister_pernet_subsys(&fib6_rules_net_ops); +} diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 23e540365a1..f6c84a6eb23 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -5,8 +5,6 @@ * Authors: * Pedro Roque <roque@di.fc.ul.pt> * - * $Id: icmp.c,v 1.38 2002/02/08 03:57:19 davem Exp $ - * * Based on net/ipv4/icmp.c * * RFC 1885 @@ -31,17 +29,20 @@ * Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data */ +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> -#include <linux/sched.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/init.h> +#include <linux/netfilter.h> +#include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> @@ -56,6 +57,7 @@ #include <net/ipv6.h> #include <net/ip6_checksum.h> +#include <net/ping.h> #include <net/protocol.h> #include <net/raw.h> #include <net/rawv6.h> @@ -63,11 +65,11 @@ #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> +#include <net/xfrm.h> +#include <net/inet_common.h> +#include <net/dsfield.h> #include <asm/uaccess.h> -#include <asm/system.h> - -DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly; /* * The ICMP socket(s). This is the most convenient way to flow control @@ -76,43 +78,57 @@ DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly; * * On SMP we have one ICMP socket per-cpu. */ -static DEFINE_PER_CPU(struct socket *, __icmpv6_socket) = NULL; -#define icmpv6_socket __get_cpu_var(__icmpv6_socket) +static inline struct sock *icmpv6_sk(struct net *net) +{ + return net->ipv6.icmp_sk[smp_processor_id()]; +} + +static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ + struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); + struct net *net = dev_net(skb->dev); + + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, 0, 0); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); -static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp); + if (!(type & ICMPV6_INFOMSG_MASK)) + if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) + ping_err(skb, offset, info); +} + +static int icmpv6_rcv(struct sk_buff *skb); -static struct inet6_protocol icmpv6_protocol = { +static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, - .flags = INET6_PROTO_FINAL, + .err_handler = icmpv6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; -static __inline__ int icmpv6_xmit_lock(void) +static __inline__ struct sock *icmpv6_xmit_lock(struct net *net) { + struct sock *sk; + local_bh_disable(); - if (unlikely(!spin_trylock(&icmpv6_socket->sk->sk_lock.slock))) { + sk = icmpv6_sk(net); + if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an * outgoing ICMP6 packet. */ local_bh_enable(); - return 1; + return NULL; } - return 0; + return sk; } -static __inline__ void icmpv6_xmit_unlock(void) -{ - spin_unlock_bh(&icmpv6_socket->sk->sk_lock.slock); -} - -/* - * Slightly more convenient version of icmpv6_send. - */ -void icmpv6_param_prob(struct sk_buff *skb, int code, int pos) +static __inline__ void icmpv6_xmit_unlock(struct sock *sk) { - icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); - kfree_skb(skb); + spin_unlock_bh(&sk->sk_lock.slock); } /* @@ -126,18 +142,19 @@ void icmpv6_param_prob(struct sk_buff *skb, int code, int pos) * --ANK (980726) */ -static int is_ineligible(struct sk_buff *skb) +static bool is_ineligible(const struct sk_buff *skb) { - int ptr = (u8*)(skb->nh.ipv6h+1) - skb->data; + int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; int len = skb->len - ptr; - __u8 nexthdr = skb->nh.ipv6h->nexthdr; + __u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; if (len < 0) - return 1; + return true; - ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr); + ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off); if (ptr < 0) - return 0; + return false; if (nexthdr == IPPROTO_ICMPV6) { u8 _type, *tp; tp = skb_header_pointer(skb, @@ -145,49 +162,53 @@ static int is_ineligible(struct sk_buff *skb) sizeof(_type), &_type); if (tp == NULL || !(*tp & ICMPV6_INFOMSG_MASK)) - return 1; + return true; } - return 0; + return false; } -static int sysctl_icmpv6_time = 1*HZ; - -/* - * Check the ICMP output rate limit +/* + * Check the ICMP output rate limit */ -static inline int icmpv6_xrlim_allow(struct sock *sk, int type, - struct flowi *fl) +static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, + struct flowi6 *fl6) { struct dst_entry *dst; - int res = 0; + struct net *net = sock_net(sk); + bool res = false; /* Informational messages are not limited. */ if (type & ICMPV6_INFOMSG_MASK) - return 1; + return true; /* Do not limit pmtu discovery, it would break it. */ if (type == ICMPV6_PKT_TOOBIG) - return 1; + return true; - /* + /* * Look up the output route. * XXX: perhaps the expire for routing entries cloned by * this lookup should be more aggressive (not longer than timeout). */ - dst = ip6_route_output(sk, fl); + dst = ip6_route_output(net, sk, fl6); if (dst->error) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(net, ip6_dst_idev(dst), + IPSTATS_MIB_OUTNOROUTES); } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { - res = 1; + res = true; } else { struct rt6_info *rt = (struct rt6_info *)dst; - int tmo = sysctl_icmpv6_time; + int tmo = net->ipv6.sysctl.icmpv6_time; + struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - res = xrlim_allow(dst, tmo); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + res = inet_peer_xrlim_allow(peer, tmo); + if (peer) + inet_putpeer(peer); } dst_release(dst); return res; @@ -196,22 +217,23 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type, /* * an inline helper for the "simple" if statement below * checks if parameter problem report is caused by an - * unrecognized IPv6 option that has the Option Type + * unrecognized IPv6 option that has the Option Type * highest-order two bits set to 10 */ -static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset) +static bool opt_unrec(struct sk_buff *skb, __u32 offset) { u8 _optval, *op; - offset += skb->nh.raw - skb->data; + offset += skb_network_offset(skb); op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval); if (op == NULL) - return 1; + return true; return (*op & 0xC0) == 0x80; } -static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6hdr *thdr, int len) +int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; @@ -220,33 +242,31 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) goto out; - icmp6h = (struct icmp6hdr*) skb->h.raw; + icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); icmp6h->icmp6_cksum = 0; if (skb_queue_len(&sk->sk_write_queue) == 1) { - skb->csum = csum_partial((char *)icmp6h, + skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); - icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - len, fl->proto, + icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, + &fl6->daddr, + len, fl6->flowi6_proto, skb->csum); } else { - u32 tmp_csum = 0; + __wsum tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); } - tmp_csum = csum_partial((char *)icmp6h, + tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); - tmp_csum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - len, fl->proto, tmp_csum); - icmp6h->icmp6_cksum = tmp_csum; + icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, + &fl6->daddr, + len, fl6->flowi6_proto, + tmp_csum); } - if (icmp6h->icmp6_cksum == 0) - icmp6h->icmp6_cksum = -1; ip6_push_pending_frames(sk); out: return err; @@ -255,53 +275,147 @@ out: struct icmpv6_msg { struct sk_buff *skb; int offset; + uint8_t type; }; static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct icmpv6_msg *msg = (struct icmpv6_msg *) from; struct sk_buff *org_skb = msg->skb; - __u32 csum = 0; + __wsum csum = 0; csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, to, len, csum); skb->csum = csum_block_add(skb->csum, csum, odd); + if (!(msg->type & ICMPV6_INFOMSG_MASK)) + nf_ct_attach(skb, org_skb); return 0; } +#if IS_ENABLED(CONFIG_IPV6_MIP6) +static void mip6_addr_swap(struct sk_buff *skb) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + struct inet6_skb_parm *opt = IP6CB(skb); + struct ipv6_destopt_hao *hao; + struct in6_addr tmp; + int off; + + if (opt->dsthao) { + off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); + if (likely(off >= 0)) { + hao = (struct ipv6_destopt_hao *) + (skb_network_header(skb) + off); + tmp = iph->saddr; + iph->saddr = hao->addr; + hao->addr = tmp; + } + } +} +#else +static inline void mip6_addr_swap(struct sk_buff *skb) {} +#endif + +static struct dst_entry *icmpv6_route_lookup(struct net *net, + struct sk_buff *skb, + struct sock *sk, + struct flowi6 *fl6) +{ + struct dst_entry *dst, *dst2; + struct flowi6 fl2; + int err; + + err = ip6_dst_lookup(sk, &dst, fl6); + if (err) + return ERR_PTR(err); + + /* + * We won't send icmp if the destination is known + * anycast. + */ + if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) { + LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: acast source\n"); + dst_release(dst); + return ERR_PTR(-EINVAL); + } + + /* No need to clone since we're just using its address. */ + dst2 = dst; + + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0); + if (!IS_ERR(dst)) { + if (dst != dst2) + return dst; + } else { + if (PTR_ERR(dst) == -EPERM) + dst = NULL; + else + return dst; + } + + err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6); + if (err) + goto relookup_failed; + + err = ip6_dst_lookup(sk, &dst2, &fl2); + if (err) + goto relookup_failed; + + dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP); + if (!IS_ERR(dst2)) { + dst_release(dst); + dst = dst2; + } else { + err = PTR_ERR(dst2); + if (err == -EPERM) { + dst_release(dst); + return dst2; + } else + goto relookup_failed; + } + +relookup_failed: + if (dst) + return dst; + return ERR_PTR(err); +} + /* * Send an ICMP message in response to a packet in error */ -void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, - struct net_device *dev) +static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { + struct net *net = dev_net(skb->dev); struct inet6_dev *idev = NULL; - struct ipv6hdr *hdr = skb->nh.ipv6h; + struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; struct ipv6_pinfo *np; - struct in6_addr *saddr = NULL; + const struct in6_addr *saddr = NULL; struct dst_entry *dst; struct icmp6hdr tmp_hdr; - struct flowi fl; + struct flowi6 fl6; struct icmpv6_msg msg; int iif = 0; int addr_type = 0; int len; - int hlimit, tclass; + int hlimit; int err = 0; + u32 mark = IP6_REPLY_MARK(net, skb->mark); - if ((u8*)hdr < skb->head || (u8*)(hdr+1) > skb->tail) + if ((u8 *)hdr < skb->head || + (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; /* - * Make sure we respect the rules + * Make sure we respect the rules * i.e. RFC 1885 2.4(e) - * Rule (e.1) is enforced by not using icmpv6_send + * Rule (e.1) is enforced by not using icmp6_send * in any code that processes icmp errors. */ addr_type = ipv6_addr_type(&hdr->daddr); - if (ipv6_chk_addr(&hdr->daddr, skb->dev, 0)) + if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) || + ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr)) saddr = &hdr->daddr; /* @@ -310,8 +424,8 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) { if (type != ICMPV6_PKT_TOOBIG && - !(type == ICMPV6_PARAMPROB && - code == ICMPV6_UNK_OPTION && + !(type == ICMPV6_PARAMPROB && + code == ICMPV6_UNK_OPTION && (opt_unrec(skb, info)))) return; @@ -324,42 +438,48 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, * Source addr check */ - if (addr_type & IPV6_ADDR_LINKLOCAL) + if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; /* - * Must not send if we know that source is Anycast also. - * for now we don't know that. + * Must not send error if the source does not uniquely + * identify a single node (RFC2463 Section 2.4). + * We check unspecified / multicast addresses here, + * and anycast addresses will be checked later. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { - LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n"); + LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: addr_any/mcast source\n"); return; } - /* + /* * Never answer to a ICMP packet. */ if (is_ineligible(skb)) { - LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: no reply to icmp error\n"); + LIMIT_NETDEBUG(KERN_DEBUG "icmp6_send: no reply to icmp error\n"); return; } - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr); - if (saddr) - ipv6_addr_copy(&fl.fl6_src, saddr); - fl.oif = iif; - fl.fl_icmp_type = type; - fl.fl_icmp_code = code; + mip6_addr_swap(skb); - if (icmpv6_xmit_lock()) + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_ICMPV6; + fl6.daddr = hdr->saddr; + if (saddr) + fl6.saddr = *saddr; + fl6.flowi6_mark = mark; + fl6.flowi6_oif = iif; + fl6.fl6_icmp_type = type; + fl6.fl6_icmp_code = code; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); + + sk = icmpv6_xmit_lock(net); + if (sk == NULL) return; - - sk = icmpv6_socket->sk; + sk->sk_mark = mark; np = inet6_sk(sk); - if (!icmpv6_xrlim_allow(sk, type, &fl)) + if (!icmpv6_xrlim_allow(sk, type, &fl6)) goto out; tmp_hdr.icmp6_type = type; @@ -367,30 +487,20 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, tmp_hdr.icmp6_cksum = 0; tmp_hdr.icmp6_pointer = htonl(info); - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) - fl.oif = np->mcast_oif; + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + dst = icmpv6_route_lookup(net, skb, sk, &fl6); + if (IS_ERR(dst)) goto out; - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) - goto out; - - if (ipv6_addr_is_multicast(&fl.fl6_dst)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hlimit < 0) - hlimit = ipv6_get_hoplimit(dst->dev); - tclass = np->cork.tclass; - if (tclass < 0) - tclass = 0; + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); msg.skb = skb; - msg.offset = skb->nh.raw - skb->data; + msg.offset = skb_network_offset(skb); + msg.type = type; len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr)); @@ -399,124 +509,122 @@ void icmpv6_send(struct sk_buff *skb, int type, int 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), - sizeof(struct icmp6hdr), - hlimit, tclass, NULL, &fl, (struct rt6_info*)dst, - MSG_DONTWAIT); + sizeof(struct icmp6hdr), hlimit, + np->tclass, NULL, &fl6, (struct rt6_info *)dst, + MSG_DONTWAIT, np->dontfrag); if (err) { + ICMP6_INC_STATS(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, &fl, &tmp_hdr, len + sizeof(struct icmp6hdr)); - - if (type >= ICMPV6_DEST_UNREACH && type <= ICMPV6_PARAMPROB) - ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_OUTDESTUNREACHS, type - ICMPV6_DEST_UNREACH); - ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS); - -out_put: - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); out_dst_release: dst_release(dst); out: - icmpv6_xmit_unlock(); + icmpv6_xmit_unlock(sk); +} + +/* Slightly more convenient version of icmp6_send. + */ +void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) +{ + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos); + kfree_skb(skb); } static void icmpv6_echo_reply(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; - struct in6_addr *saddr = NULL; - struct icmp6hdr *icmph = (struct icmp6hdr *) skb->h.raw; + const struct in6_addr *saddr = NULL; + struct icmp6hdr *icmph = icmp6_hdr(skb); struct icmp6hdr tmp_hdr; - struct flowi fl; + struct flowi6 fl6; struct icmpv6_msg msg; struct dst_entry *dst; int err = 0; int hlimit; - int tclass; + u8 tclass; + u32 mark = IP6_REPLY_MARK(net, skb->mark); - saddr = &skb->nh.ipv6h->daddr; + saddr = &ipv6_hdr(skb)->daddr; - if (!ipv6_unicast_destination(skb)) + if (!ipv6_unicast_destination(skb) && + !(net->ipv6.sysctl.anycast_src_echo_reply && + ipv6_anycast_destination(skb))) saddr = NULL; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY; - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr); + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_ICMPV6; + fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) - ipv6_addr_copy(&fl.fl6_src, saddr); - fl.oif = skb->dev->ifindex; - fl.fl_icmp_type = ICMPV6_ECHO_REPLY; - - if (icmpv6_xmit_lock()) + fl6.saddr = *saddr; + fl6.flowi6_oif = skb->dev->ifindex; + fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; + fl6.flowi6_mark = mark; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); + + sk = icmpv6_xmit_lock(net); + if (sk == NULL) return; - - sk = icmpv6_socket->sk; + sk->sk_mark = mark; np = inet6_sk(sk); - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) - fl.oif = np->mcast_oif; + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(sk, &dst, &fl); + err = ip6_dst_lookup(sk, &dst, &fl6); if (err) goto out; - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); + if (IS_ERR(dst)) goto out; - if (ipv6_addr_is_multicast(&fl.fl6_dst)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hlimit < 0) - hlimit = ipv6_get_hoplimit(dst->dev); - - tclass = np->cork.tclass; - if (tclass < 0) - tclass = 0; + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); - idev = in6_dev_get(skb->dev); + idev = __in6_dev_get(skb->dev); msg.skb = skb; msg.offset = 0; + msg.type = ICMPV6_ECHO_REPLY; + tclass = ipv6_get_dsfield(ipv6_hdr(skb)); err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl, - (struct rt6_info*)dst, MSG_DONTWAIT); + sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl6, + (struct rt6_info *)dst, MSG_DONTWAIT, + np->dontfrag); 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, &fl, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); - - ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTECHOREPLIES); - ICMP6_INC_STATS_BH(idev, ICMP6_MIB_OUTMSGS); - -out_put: - if (likely(idev != NULL)) - in6_dev_put(idev); dst_release(dst); -out: - icmpv6_xmit_unlock(); +out: + icmpv6_xmit_unlock(sk); } -static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info) +void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { - struct in6_addr *saddr, *daddr; - struct inet6_protocol *ipprot; - struct sock *sk; + const struct inet6_protocol *ipprot; int inner_offset; - int hash; + __be16 frag_off; u8 nexthdr; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) @@ -525,7 +633,8 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 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 { @@ -536,9 +645,6 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info) if (!pskb_may_pull(skb, inner_offset+8)) return; - saddr = &skb->nh.ipv6h->saddr; - daddr = &skb->nh.ipv6h->daddr; - /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed pmtu discovery. @@ -546,73 +652,67 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info) --ANK (980726) */ - hash = nexthdr & (MAX_INET_PROTOS - 1); - rcu_read_lock(); - ipprot = rcu_dereference(inet6_protos[hash]); + ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, NULL, type, code, inner_offset, info); rcu_read_unlock(); - read_lock(&raw_v6_lock); - if ((sk = sk_head(&raw_v6_htable[hash])) != NULL) { - while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, - IP6CB(skb)->iif))) { - rawv6_err(sk, skb, NULL, type, code, inner_offset, info); - sk = sk_next(sk); - } - } - read_unlock(&raw_v6_lock); + raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); } - + /* * Handle icmp messages */ -static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) +static int icmpv6_rcv(struct sk_buff *skb) { - struct sk_buff *skb = *pskb; struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); - struct in6_addr *saddr, *daddr; - struct ipv6hdr *orig_hdr; + const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; - int type; + u8 type; - ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INMSGS); + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { + struct sec_path *sp = skb_sec_path(skb); + int nh; - saddr = &skb->nh.ipv6h->saddr; - daddr = &skb->nh.ipv6h->daddr; + if (!(sp && sp->xvec[sp->len - 1]->props.flags & + XFRM_STATE_ICMP)) + goto drop_no_count; - /* Perform checksum. */ - if (skb->ip_summed == CHECKSUM_HW) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, - skb->csum)) { - LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 hw checksum failed\n"); - skb->ip_summed = CHECKSUM_NONE; - } + if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) + goto drop_no_count; + + nh = skb_network_offset(skb); + skb_set_network_header(skb, sizeof(*hdr)); + + if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) + goto drop_no_count; + + skb_set_network_header(skb, nh); } - if (skb->ip_summed == CHECKSUM_NONE) { - if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, - skb_checksum(skb, 0, skb->len, 0))) { - LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x > %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x]\n", - NIP6(*saddr), NIP6(*daddr)); - goto discard_it; - } + + ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_INMSGS); + + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + + if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { + LIMIT_NETDEBUG(KERN_DEBUG + "ICMPv6 checksum failed [%pI6c > %pI6c]\n", + saddr, daddr); + goto csum_error; } - if (!pskb_pull(skb, sizeof(struct icmp6hdr))) + if (!pskb_pull(skb, sizeof(*hdr))) goto discard_it; - hdr = (struct icmp6hdr *) skb->h.raw; + hdr = icmp6_hdr(skb); type = hdr->icmp6_type; - if (type >= ICMPV6_DEST_UNREACH && type <= ICMPV6_PARAMPROB) - ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_INDESTUNREACHS, type - ICMPV6_DEST_UNREACH); - else if (type >= ICMPV6_ECHO_REQUEST && type <= NDISC_REDIRECT) - ICMP6_INC_STATS_OFFSET_BH(idev, ICMP6_MIB_INECHOS, type - ICMPV6_ECHO_REQUEST); + ICMP6MSGIN_INC_STATS_BH(dev_net(dev), idev, type); switch (type) { case ICMPV6_ECHO_REQUEST: @@ -620,7 +720,7 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) break; case ICMPV6_ECHO_REPLY: - /* we couldn't care less */ + ping_rcv(skb); break; case ICMPV6_PKT_TOOBIG: @@ -631,10 +731,7 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto discard_it; - hdr = (struct icmp6hdr *) skb->h.raw; - orig_hdr = (struct ipv6hdr *) (hdr + 1); - rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev, - ntohl(hdr->icmp6_mtu)); + hdr = icmp6_hdr(skb); /* * Drop through to notify @@ -679,80 +776,140 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) if (type & ICMPV6_INFOMSG_MASK) break; - /* - * error of unknown type. - * must pass to upper level + /* + * error of unknown type. + * must pass to upper level */ icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); - }; + } + kfree_skb(skb); return 0; +csum_error: + ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS); discard_it: - ICMP6_INC_STATS_BH(idev, ICMP6_MIB_INERRORS); + ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_INERRORS); +drop_no_count: kfree_skb(skb); return 0; } -int __init icmpv6_init(struct net_proto_family *ops) +void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, + u8 type, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int oif) +{ + memset(fl6, 0, sizeof(*fl6)); + fl6->saddr = *saddr; + fl6->daddr = *daddr; + fl6->flowi6_proto = IPPROTO_ICMPV6; + fl6->fl6_icmp_type = type; + fl6->fl6_icmp_code = 0; + fl6->flowi6_oif = oif; + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); +} + +/* + * Special lock-class for __icmpv6_sk: + */ +static struct lock_class_key icmpv6_socket_sk_dst_lock_key; + +static int __net_init icmpv6_sk_init(struct net *net) { struct sock *sk; int err, i, j; - for_each_cpu(i) { - err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, - &per_cpu(__icmpv6_socket, i)); + net->ipv6.icmp_sk = + kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL); + if (net->ipv6.icmp_sk == NULL) + return -ENOMEM; + + for_each_possible_cpu(i) { + err = inet_ctl_sock_create(&sk, PF_INET6, + SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - printk(KERN_ERR - "Failed to initialize the ICMP6 control socket " - "(err %d).\n", + pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); goto fail; } - sk = per_cpu(__icmpv6_socket, i)->sk; - sk->sk_allocation = GFP_ATOMIC; + net->ipv6.icmp_sk[i] = sk; + + /* + * Split off their lock-class, because sk->sk_dst_lock + * gets used from softirqs, which is safe for + * __icmpv6_sk (because those never get directly used + * via userspace syscalls), but unsafe for normal sockets. + */ + lockdep_set_class(&sk->sk_dst_lock, + &icmpv6_socket_sk_dst_lock_key); /* 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; - sk->sk_prot->unhash(sk); + fail: + for (j = 0; j < i; j++) + inet_ctl_sock_destroy(net->ipv6.icmp_sk[j]); + kfree(net->ipv6.icmp_sk); + return err; +} + +static void __net_exit icmpv6_sk_exit(struct net *net) +{ + int i; + + for_each_possible_cpu(i) { + inet_ctl_sock_destroy(net->ipv6.icmp_sk[i]); } + kfree(net->ipv6.icmp_sk); +} + +static struct pernet_operations icmpv6_sk_ops = { + .init = icmpv6_sk_init, + .exit = icmpv6_sk_exit, +}; + +int __init icmpv6_init(void) +{ + int err; + err = register_pernet_subsys(&icmpv6_sk_ops); + if (err < 0) + return err; - if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) { - printk(KERN_ERR "Failed to register ICMP6 protocol\n"); - err = -EAGAIN; + err = -EAGAIN; + if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) goto fail; - } + err = inet6_register_icmp_sender(icmp6_send); + if (err) + goto sender_reg_err; return 0; - fail: - for (j = 0; j < i; j++) { - if (!cpu_possible(j)) - continue; - sock_release(per_cpu(__icmpv6_socket, j)); - } - +sender_reg_err: + inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); +fail: + pr_err("Failed to register ICMP6 protocol\n"); + unregister_pernet_subsys(&icmpv6_sk_ops); return err; } void icmpv6_cleanup(void) { - int i; - - for_each_cpu(i) { - sock_release(per_cpu(__icmpv6_socket, i)); - } + inet6_unregister_icmp_sender(icmp6_send); + unregister_pernet_subsys(&icmpv6_sk_ops); inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); } -static struct icmp6_err { + +static const struct icmp6_err { int err; int fatal; } tab_unreach[] = { @@ -776,9 +933,17 @@ static struct icmp6_err { .err = ECONNREFUSED, .fatal = 1, }, + { /* POLICY_FAIL */ + .err = EACCES, + .fatal = 1, + }, + { /* REJECT_ROUTE */ + .err = EACCES, + .fatal = 1, + }, }; -int icmpv6_err_convert(int type, int code, int *err) +int icmpv6_err_convert(u8 type, u8 code, int *err) { int fatal = 0; @@ -787,7 +952,7 @@ int icmpv6_err_convert(int type, int code, int *err) switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; - if (code <= ICMPV6_PORT_UNREACH) { + if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } @@ -796,7 +961,7 @@ int icmpv6_err_convert(int type, int code, int *err) case ICMPV6_PKT_TOOBIG: *err = EMSGSIZE; break; - + case ICMPV6_PARAMPROB: *err = EPROTO; fatal = 1; @@ -805,22 +970,36 @@ int icmpv6_err_convert(int type, int code, int *err) case ICMPV6_TIME_EXCEED: *err = EHOSTUNREACH; break; - }; + } return fatal; } +EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL -ctl_table ipv6_icmp_table[] = { +static struct ctl_table ipv6_icmp_table_template[] = { { - .ctl_name = NET_IPV6_ICMP_RATELIMIT, .procname = "ratelimit", - .data = &sysctl_icmpv6_time, + .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec_ms_jiffies, }, - { .ctl_name = 0 }, + { }, }; + +struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) +{ + struct ctl_table *table; + + table = kmemdup(ipv6_icmp_table_template, + sizeof(ipv6_icmp_table_template), + GFP_KERNEL); + + if (table) + table[0].data = &net->ipv6.sysctl.icmpv6_time; + + return table; +} #endif diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c new file mode 100644 index 00000000000..a245e5ddffb --- /dev/null +++ b/net/ipv6/inet6_connection_sock.c @@ -0,0 +1,266 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Support for INET6 connection oriented protocols. + * + * Authors: See the TCPv6 sources + * + * 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. + */ + +#include <linux/module.h> +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/jhash.h> +#include <linux/slab.h> + +#include <net/addrconf.h> +#include <net/inet_connection_sock.h> +#include <net/inet_ecn.h> +#include <net/inet_hashtables.h> +#include <net/ip6_route.h> +#include <net/sock.h> +#include <net/inet6_connection_sock.h> + +int inet6_csk_bind_conflict(const struct sock *sk, + const struct inet_bind_bucket *tb, bool relax) +{ + const struct sock *sk2; + int reuse = sk->sk_reuse; + int reuseport = sk->sk_reuseport; + kuid_t uid = sock_i_uid((struct sock *)sk); + + /* We must walk the whole port owner list in this case. -DaveM */ + /* + * See comment in inet_csk_bind_conflict about sock lookup + * vs net namespaces issues. + */ + sk_for_each_bound(sk2, &tb->owners) { + if (sk != sk2 && + (!sk->sk_bound_dev_if || + !sk2->sk_bound_dev_if || + sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { + if ((!reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + (!reuseport || !sk2->sk_reuseport || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, + sock_i_uid((struct sock *)sk2))))) { + if (ipv6_rcv_saddr_equal(sk, sk2)) + break; + } + if (!relax && reuse && sk2->sk_reuse && + sk2->sk_state != TCP_LISTEN && + ipv6_rcv_saddr_equal(sk, sk2)) + break; + } + } + + return sk2 != NULL; +} + +EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); + +struct dst_entry *inet6_csk_route_req(struct sock *sk, + struct flowi6 *fl6, + const struct request_sock *req) +{ + struct inet_request_sock *ireq = inet_rsk(req); + struct ipv6_pinfo *np = inet6_sk(sk); + struct in6_addr *final_p, final; + struct dst_entry *dst; + + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = IPPROTO_TCP; + fl6->daddr = ireq->ir_v6_rmt_addr; + final_p = fl6_update_dst(fl6, np->opt, &final); + fl6->saddr = ireq->ir_v6_loc_addr; + fl6->flowi6_oif = ireq->ir_iif; + fl6->flowi6_mark = ireq->ir_mark; + fl6->fl6_dport = ireq->ir_rmt_port; + fl6->fl6_sport = htons(ireq->ir_num); + security_req_classify_flow(req, flowi6_to_flowi(fl6)); + + dst = ip6_dst_lookup_flow(sk, fl6, final_p); + if (IS_ERR(dst)) + return NULL; + + return dst; +} + +/* + * request_sock (formerly open request) hash tables. + */ +static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, + const u32 rnd, const u32 synq_hsize) +{ + u32 c; + + c = jhash_3words((__force u32)raddr->s6_addr32[0], + (__force u32)raddr->s6_addr32[1], + (__force u32)raddr->s6_addr32[2], + rnd); + + c = jhash_2words((__force u32)raddr->s6_addr32[3], + (__force u32)rport, + c); + + return c & (synq_hsize - 1); +} + +struct request_sock *inet6_csk_search_req(const struct sock *sk, + struct request_sock ***prevp, + const __be16 rport, + const struct in6_addr *raddr, + const struct in6_addr *laddr, + const int iif) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; + struct request_sock *req, **prev; + + for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport, + lopt->hash_rnd, + lopt->nr_table_entries)]; + (req = *prev) != NULL; + prev = &req->dl_next) { + const struct inet_request_sock *ireq = inet_rsk(req); + + if (ireq->ir_rmt_port == rport && + req->rsk_ops->family == AF_INET6 && + ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) && + ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && + (!ireq->ir_iif || ireq->ir_iif == iif)) { + WARN_ON(req->sk != NULL); + *prevp = prev; + return req; + } + } + + return NULL; +} + +EXPORT_SYMBOL_GPL(inet6_csk_search_req); + +void inet6_csk_reqsk_queue_hash_add(struct sock *sk, + struct request_sock *req, + const unsigned long timeout) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; + const u32 h = inet6_synq_hash(&inet_rsk(req)->ir_v6_rmt_addr, + inet_rsk(req)->ir_rmt_port, + lopt->hash_rnd, lopt->nr_table_entries); + + reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout); + inet_csk_reqsk_queue_added(sk, timeout); +} + +EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add); + +void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; + + sin6->sin6_family = AF_INET6; + sin6->sin6_addr = sk->sk_v6_daddr; + sin6->sin6_port = inet_sk(sk)->inet_dport; + /* We do not store received flowlabel for TCP */ + sin6->sin6_flowinfo = 0; + sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, + sk->sk_bound_dev_if); +} + +EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); + +static inline +void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + __ip6_dst_store(sk, dst, daddr, saddr); +} + +static inline +struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) +{ + return __sk_dst_check(sk, cookie); +} + +static struct dst_entry *inet6_csk_route_socket(struct sock *sk, + struct flowi6 *fl6) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct in6_addr *final_p, final; + struct dst_entry *dst; + + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = sk->sk_protocol; + fl6->daddr = sk->sk_v6_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; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_sport = inet->inet_sport; + fl6->fl6_dport = inet->inet_dport; + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); + + final_p = fl6_update_dst(fl6, np->opt, &final); + + dst = __inet6_csk_dst_check(sk, np->dst_cookie); + if (!dst) { + dst = ip6_dst_lookup_flow(sk, fl6, final_p); + + if (!IS_ERR(dst)) + __inet6_csk_dst_store(sk, dst, NULL, NULL); + } + return dst; +} + +int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct flowi6 fl6; + struct dst_entry *dst; + int res; + + dst = inet6_csk_route_socket(sk, &fl6); + if (IS_ERR(dst)) { + sk->sk_err_soft = -PTR_ERR(dst); + sk->sk_route_caps = 0; + kfree_skb(skb); + return PTR_ERR(dst); + } + + rcu_read_lock(); + skb_dst_set_noref(skb, dst); + + /* Restore final destination back after routing done */ + fl6.daddr = sk->sk_v6_daddr; + + res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + rcu_read_unlock(); + return res; +} +EXPORT_SYMBOL_GPL(inet6_csk_xmit); + +struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) +{ + struct flowi6 fl6; + struct dst_entry *dst = inet6_csk_route_socket(sk, &fl6); + + if (IS_ERR(dst)) + return NULL; + dst->ops->update_pmtu(dst, sk, NULL, mtu); + + dst = inet6_csk_route_socket(sk, &fl6); + return IS_ERR(dst) ? NULL : dst; +} +EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 01d5f46d4e4..262e13c02ec 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -5,7 +5,8 @@ * * Generic INET6 transport hashtables * - * Authors: Lotsa people, from code originally in tcp + * Authors: Lotsa people, from code originally in tcp, generalised here + * by Arnaldo Carvalho de Melo <acme@mandriva.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -13,69 +14,315 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> - #include <linux/module.h> +#include <linux/random.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> +#include <net/secure_seq.h> +#include <net/ip.h> + +static unsigned int inet6_ehashfn(struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) +{ + static u32 inet6_ehash_secret __read_mostly; + static u32 ipv6_hash_secret __read_mostly; + + u32 lhash, fhash; + + net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); + net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); -struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, - const struct in6_addr *daddr, - const unsigned short hnum, const int dif) + lhash = (__force u32)laddr->s6_addr32[3]; + fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); + + return __inet6_ehashfn(lhash, lport, fhash, fport, + inet6_ehash_secret + net_hash_mix(net)); +} + +static int inet6_sk_ehashfn(const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr; + const struct in6_addr *faddr = &sk->sk_v6_daddr; + const __u16 lport = inet->inet_num; + const __be16 fport = inet->inet_dport; + struct net *net = sock_net(sk); + + return inet6_ehashfn(net, laddr, lport, faddr, fport); +} + +int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) +{ + struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + int twrefcnt = 0; + + WARN_ON(!sk_unhashed(sk)); + + if (sk->sk_state == TCP_LISTEN) { + struct inet_listen_hashbucket *ilb; + + ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + spin_lock(&ilb->lock); + __sk_nulls_add_node_rcu(sk, &ilb->head); + spin_unlock(&ilb->lock); + } else { + unsigned int hash; + struct hlist_nulls_head *list; + spinlock_t *lock; + + sk->sk_hash = hash = inet6_sk_ehashfn(sk); + list = &inet_ehash_bucket(hashinfo, hash)->chain; + lock = inet_ehash_lockp(hashinfo, hash); + spin_lock(lock); + __sk_nulls_add_node_rcu(sk, list); + if (tw) { + WARN_ON(sk->sk_hash != tw->tw_hash); + twrefcnt = inet_twsk_unhash(tw); + } + spin_unlock(lock); + } + + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + return twrefcnt; +} +EXPORT_SYMBOL(__inet6_hash); + +/* + * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so + * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM + * + * The sockhash lock must be held as a reader here. + */ +struct sock *__inet6_lookup_established(struct net *net, + struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, + const __be16 sport, + const struct in6_addr *daddr, + const u16 hnum, + const int dif) { struct sock *sk; - const struct hlist_node *node; - struct sock *result = NULL; - int score, hiscore = 0; - - read_lock(&hashinfo->lhash_lock); - sk_for_each(sk, node, &hashinfo->listening_hash[inet_lhashfn(hnum)]) { - if (inet_sk(sk)->num == hnum && sk->sk_family == PF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); - - score = 1; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - continue; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score++; - } - if (score == 3) { - result = sk; - break; + const struct hlist_nulls_node *node; + const __portpair ports = INET_COMBINED_PORTS(sport, hnum); + /* Optimize here for direct hit, only listening connections can + * have wildcards anyways. + */ + unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); + unsigned int slot = hash & hashinfo->ehash_mask; + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; + + + rcu_read_lock(); +begin: + sk_nulls_for_each_rcu(sk, node, &head->chain) { + if (sk->sk_hash != hash) + continue; + if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) + continue; + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + goto out; + + if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { + sock_gen_put(sk); + goto begin; + } + goto found; + } + if (get_nulls_value(node) != slot) + goto begin; +out: + sk = NULL; +found: + rcu_read_unlock(); + return sk; +} +EXPORT_SYMBOL(__inet6_lookup_established); + +static inline int compute_score(struct sock *sk, struct net *net, + const unsigned short hnum, + const struct in6_addr *daddr, + const int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && + sk->sk_family == PF_INET6) { + + score = 1; + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + +struct sock *inet6_lookup_listener(struct net *net, + struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, + const __be16 sport, const struct in6_addr *daddr, + const unsigned short hnum, const int dif) +{ + struct sock *sk; + const struct hlist_nulls_node *node; + struct sock *result; + int score, hiscore, matches = 0, reuseport = 0; + u32 phash = 0; + unsigned int hash = inet_lhashfn(net, hnum); + struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; + + rcu_read_lock(); +begin: + result = NULL; + hiscore = 0; + sk_nulls_for_each(sk, node, &ilb->head) { + score = compute_score(sk, net, hnum, daddr, dif); + if (score > hiscore) { + hiscore = score; + result = sk; + reuseport = sk->sk_reuseport; + if (reuseport) { + phash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; } - if (score > hiscore) { - hiscore = score; + } else if (score == hiscore && reuseport) { + matches++; + if (((u64)phash * matches) >> 32 == 0) result = sk; - } + phash = next_pseudo_random32(phash); } } - if (result) - sock_hold(result); - read_unlock(&hashinfo->lhash_lock); + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) + goto begin; + if (result) { + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score(result, net, hnum, daddr, + dif) < hiscore)) { + sock_put(result); + goto begin; + } + } + rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); -struct sock *inet6_lookup(struct inet_hashinfo *hashinfo, - const struct in6_addr *saddr, const u16 sport, - const struct in6_addr *daddr, const u16 dport, +struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, const __be16 sport, + const struct in6_addr *daddr, const __be16 dport, const int dif) { struct sock *sk; local_bh_disable(); - sk = __inet6_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif); + sk = __inet6_lookup(net, hashinfo, saddr, sport, daddr, ntohs(dport), dif); local_bh_enable(); return sk; } EXPORT_SYMBOL_GPL(inet6_lookup); + +static int __inet6_check_established(struct inet_timewait_death_row *death_row, + struct sock *sk, const __u16 lport, + struct inet_timewait_sock **twp) +{ + struct inet_hashinfo *hinfo = death_row->hashinfo; + struct inet_sock *inet = inet_sk(sk); + const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; + const struct in6_addr *saddr = &sk->sk_v6_daddr; + const int dif = sk->sk_bound_dev_if; + const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); + struct net *net = sock_net(sk); + const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, + inet->inet_dport); + struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); + spinlock_t *lock = inet_ehash_lockp(hinfo, hash); + struct sock *sk2; + const struct hlist_nulls_node *node; + struct inet_timewait_sock *tw = NULL; + int twrefcnt = 0; + + spin_lock(lock); + + sk_nulls_for_each(sk2, node, &head->chain) { + if (sk2->sk_hash != hash) + continue; + + if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) { + if (sk2->sk_state == TCP_TIME_WAIT) { + tw = inet_twsk(sk2); + if (twsk_unique(sk, sk2, twp)) + break; + } + goto not_unique; + } + } + + /* Must record num and sport now. Otherwise we will see + * in hash table socket with a funny identity. + */ + inet->inet_num = lport; + inet->inet_sport = htons(lport); + sk->sk_hash = hash; + WARN_ON(!sk_unhashed(sk)); + __sk_nulls_add_node_rcu(sk, &head->chain); + if (tw) { + twrefcnt = inet_twsk_unhash(tw); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); + } + spin_unlock(lock); + if (twrefcnt) + inet_twsk_put(tw); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + + if (twp) { + *twp = tw; + } else if (tw) { + /* Silly. Should hash-dance instead... */ + inet_twsk_deschedule(tw, death_row); + + inet_twsk_put(tw); + } + return 0; + +not_unique: + spin_unlock(lock); + return -EADDRNOTAVAIL; +} + +static inline u32 inet6_sk_port_offset(const struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + + return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_dport); +} + +int inet6_hash_connect(struct inet_timewait_death_row *death_row, + struct sock *sk) +{ + return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk), + __inet6_check_established, __inet6_hash); +} + +EXPORT_SYMBOL_GPL(inet6_hash_connect); diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c new file mode 100644 index 00000000000..9a4d7322fb2 --- /dev/null +++ b/net/ipv6/ip6_checksum.c @@ -0,0 +1,124 @@ +#include <net/ip.h> +#include <net/udp.h> +#include <net/udplite.h> +#include <asm/checksum.h> + +#ifndef _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, unsigned short proto, + __wsum csum) +{ + + int carry; + __u32 ulen; + __u32 uproto; + __u32 sum = (__force u32)csum; + + sum += (__force u32)saddr->s6_addr32[0]; + carry = (sum < (__force u32)saddr->s6_addr32[0]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[1]; + carry = (sum < (__force u32)saddr->s6_addr32[1]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[2]; + carry = (sum < (__force u32)saddr->s6_addr32[2]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[3]; + carry = (sum < (__force u32)saddr->s6_addr32[3]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[0]; + carry = (sum < (__force u32)daddr->s6_addr32[0]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[1]; + carry = (sum < (__force u32)daddr->s6_addr32[1]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[2]; + carry = (sum < (__force u32)daddr->s6_addr32[2]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[3]; + carry = (sum < (__force u32)daddr->s6_addr32[3]); + sum += carry; + + ulen = (__force u32)htonl((__u32) len); + sum += ulen; + carry = (sum < ulen); + sum += carry; + + uproto = (__force u32)htonl(proto); + sum += uproto; + carry = (sum < uproto); + sum += carry; + + return csum_fold((__force __wsum)sum); +} +EXPORT_SYMBOL(csum_ipv6_magic); +#endif + +int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) +{ + int err; + + UDP_SKB_CB(skb)->partial_cov = 0; + UDP_SKB_CB(skb)->cscov = skb->len; + + if (proto == IPPROTO_UDPLITE) { + err = udplite_checksum_init(skb, uh); + if (err) + return err; + } + + /* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels) + * we accept a checksum of zero here. When we find the socket + * for the UDP packet we'll check if that socket allows zero checksum + * for IPv6 (set by socket option). + */ + return skb_checksum_init_zero_check(skb, proto, uh->check, + ip6_compute_pseudo); +} +EXPORT_SYMBOL(udp6_csum_init); + +/* Function to set UDP checksum for an IPv6 UDP packet. This is intended + * for the simple case like when setting the checksum for a UDP tunnel. + */ +void udp6_set_csum(bool nocheck, struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int len) +{ + struct udphdr *uh = udp_hdr(skb); + + if (nocheck) + uh->check = 0; + else if (skb_is_gso(skb)) + uh->check = ~udp_v6_check(len, saddr, daddr, 0); + else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~udp_v6_check(len, saddr, daddr, 0); + } else { + __wsum csum; + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + uh->check = 0; + csum = skb_checksum(skb, 0, len, 0); + uh->check = udp_v6_check(len, saddr, daddr, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + } +} +EXPORT_SYMBOL(udp6_set_csum); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4fcc5a7acf6..cb4459bd1d2 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1,25 +1,24 @@ /* - * Linux INET6 implementation + * Linux INET6 implementation * Forwarding Information Database * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> - * - * $Id: ip6_fib.c,v 1.25 2001/10/31 21:55:55 davem Exp $ + * Pedro Roque <roque@di.fc.ul.pt> * * 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: + * Yuji SEKIYA @USAGI: Support default route on router node; + * remove ip6_null_entry from the top of + * routing table. + * Ville Nuorvala: Fixed routing subtrees. */ -/* - * Changes: - * Yuji SEKIYA @USAGI: Support default route on router node; - * remove ip6_null_entry from the top of - * routing table. - */ -#include <linux/config.h> +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> @@ -27,10 +26,8 @@ #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> - -#ifdef CONFIG_PROC_FS -#include <linux/proc_fs.h> -#endif +#include <linux/list.h> +#include <linux/slab.h> #include <net/ipv6.h> #include <net/ndisc.h> @@ -42,17 +39,14 @@ #define RT6_DEBUG 2 #if RT6_DEBUG >= 3 -#define RT6_TRACE(x...) printk(KERN_DEBUG x) +#define RT6_TRACE(x...) pr_debug(x) #else #define RT6_TRACE(x...) do { ; } while (0) #endif -struct rt6_statistics rt6_stats; - -static kmem_cache_t * fib6_node_kmem __read_mostly; +static struct kmem_cache *fib6_node_kmem __read_mostly; -enum fib_walk_state_t -{ +enum fib_walk_state_t { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif @@ -62,26 +56,26 @@ enum fib_walk_state_t FWS_U }; -struct fib6_cleaner_t -{ +struct fib6_cleaner_t { struct fib6_walker_t w; + struct net *net; int (*func)(struct rt6_info *, void *arg); void *arg; }; -DEFINE_RWLOCK(fib6_walker_lock); - +static DEFINE_RWLOCK(fib6_walker_lock); #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S -#define SUBTREE(fn) ((fn)->subtree) #else #define FWS_INIT FWS_L -#define SUBTREE(fn) NULL #endif -static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt); -static struct fib6_node * fib6_repair_tree(struct fib6_node *fn); +static void fib6_prune_clones(struct net *net, struct fib6_node *fn); +static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); +static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); +static int fib6_walk(struct fib6_walker_t *w); +static int fib6_walk_continue(struct fib6_walker_t *w); /* * A routing update causes an increase of the serial number on the @@ -92,15 +86,24 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn); static __u32 rt_sernum; -static DEFINE_TIMER(ip6_fib_timer, fib6_run_gc, 0, 0); +static void fib6_gc_timer_cb(unsigned long arg); -struct fib6_walker_t fib6_walker_list = { - .prev = &fib6_walker_list, - .next = &fib6_walker_list, -}; +static LIST_HEAD(fib6_walkers); +#define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh) -#define FOR_WALKERS(w) for ((w)=fib6_walker_list.next; (w) != &fib6_walker_list; (w)=(w)->next) +static inline void fib6_walker_link(struct fib6_walker_t *w) +{ + write_lock_bh(&fib6_walker_lock); + list_add(&w->lh, &fib6_walkers); + write_unlock_bh(&fib6_walker_lock); +} +static inline void fib6_walker_unlink(struct fib6_walker_t *w) +{ + write_lock_bh(&fib6_walker_lock); + list_del(&w->lh); + write_unlock_bh(&fib6_walker_lock); +} static __inline__ u32 fib6_new_sernum(void) { u32 n = ++rt_sernum; @@ -112,92 +115,302 @@ static __inline__ u32 fib6_new_sernum(void) /* * Auxiliary address test functions for the radix tree. * - * These assume a 32bit processor (although it will work on + * These assume a 32bit processor (although it will work on * 64bit processors) */ /* * test bit */ +#if defined(__LITTLE_ENDIAN) +# define BITOP_BE32_SWIZZLE (0x1F & ~7) +#else +# define BITOP_BE32_SWIZZLE 0 +#endif -static __inline__ int addr_bit_set(void *token, int fn_bit) +static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) { - __u32 *addr = token; + const __be32 *addr = token; + /* + * Here, + * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) + * is optimized version of + * htonl(1 << ((~fn_bit)&0x1F)) + * See include/asm-generic/bitops/le.h. + */ + return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & + addr[fn_bit >> 5]; +} - return htonl(1 << ((~fn_bit)&0x1F)) & addr[fn_bit>>5]; +static __inline__ struct fib6_node *node_alloc(void) +{ + struct fib6_node *fn; + + fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); + + return fn; } -/* - * find the first different bit between two addresses - * length of address must be a multiple of 32bits - */ +static __inline__ void node_free(struct fib6_node *fn) +{ + kmem_cache_free(fib6_node_kmem, fn); +} -static __inline__ int addr_diff(void *token1, void *token2, int addrlen) +static __inline__ void rt6_release(struct rt6_info *rt) { - __u32 *a1 = token1; - __u32 *a2 = token2; - int i; + if (atomic_dec_and_test(&rt->rt6i_ref)) + dst_free(&rt->dst); +} - addrlen >>= 2; +static void fib6_link_table(struct net *net, struct fib6_table *tb) +{ + unsigned int h; - for (i = 0; i < addrlen; i++) { - __u32 xb; + /* + * Initialize table lock at a single place to give lockdep a key, + * tables aren't visible prior to being linked to the list. + */ + rwlock_init(&tb->tb6_lock); - xb = a1[i] ^ a2[i]; + h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); - if (xb) { - int j = 31; + /* + * No protection necessary, this is the only list mutatation + * operation, tables never disappear once they exist. + */ + hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); +} - xb = ntohl(xb); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES - while ((xb & (1 << j)) == 0) - j--; +static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) +{ + struct fib6_table *table; + + table = kzalloc(sizeof(*table), GFP_ATOMIC); + 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; + inet_peer_base_init(&table->tb6_peers); + } - return (i * 32 + 31 - j); + return table; +} + +struct fib6_table *fib6_new_table(struct net *net, u32 id) +{ + struct fib6_table *tb; + + if (id == 0) + id = RT6_TABLE_MAIN; + tb = fib6_get_table(net, id); + if (tb) + return tb; + + tb = fib6_alloc_table(net, id); + if (tb) + fib6_link_table(net, tb); + + return tb; +} + +struct fib6_table *fib6_get_table(struct net *net, u32 id) +{ + struct fib6_table *tb; + struct hlist_head *head; + unsigned int h; + + if (id == 0) + id = RT6_TABLE_MAIN; + h = id & (FIB6_TABLE_HASHSZ - 1); + rcu_read_lock(); + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { + if (tb->tb6_id == id) { + rcu_read_unlock(); + return tb; } } + rcu_read_unlock(); - /* - * we should *never* get to this point since that - * would mean the addrs are equal - * - * However, we do get to it 8) And exacly, when - * addresses are equal 8) - * - * ip route add 1111::/128 via ... - * ip route add 1111::/64 via ... - * and we are here. - * - * Ideally, this function should stop comparison - * at prefix length. It does not, but it is still OK, - * if returned value is greater than prefix length. - * --ANK (980803) - */ + return NULL; +} - return addrlen<<5; +static void __net_init fib6_tables_init(struct net *net) +{ + fib6_link_table(net, net->ipv6.fib6_main_tbl); + fib6_link_table(net, net->ipv6.fib6_local_tbl); } +#else -static __inline__ struct fib6_node * node_alloc(void) +struct fib6_table *fib6_new_table(struct net *net, u32 id) { - struct fib6_node *fn; + return fib6_get_table(net, id); +} - if ((fn = kmem_cache_alloc(fib6_node_kmem, SLAB_ATOMIC)) != NULL) - memset(fn, 0, sizeof(struct fib6_node)); +struct fib6_table *fib6_get_table(struct net *net, u32 id) +{ + return net->ipv6.fib6_main_tbl; +} - return fn; +struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + int flags, pol_lookup_t lookup) +{ + return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); } -static __inline__ void node_free(struct fib6_node * fn) +static void __net_init fib6_tables_init(struct net *net) { - kmem_cache_free(fib6_node_kmem, fn); + fib6_link_table(net, net->ipv6.fib6_main_tbl); } -static __inline__ void rt6_release(struct rt6_info *rt) +#endif + +static int fib6_dump_node(struct fib6_walker_t *w) { - if (atomic_dec_and_test(&rt->rt6i_ref)) - dst_free(&rt->u.dst); + int res; + struct rt6_info *rt; + + for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + res = rt6_dump_route(rt, w->args); + if (res < 0) { + /* Frame is full, suspend walking */ + w->leaf = rt; + return 1; + } + WARN_ON(res == 0); + } + w->leaf = NULL; + return 0; } +static void fib6_dump_end(struct netlink_callback *cb) +{ + struct fib6_walker_t *w = (void *)cb->args[2]; + + if (w) { + if (cb->args[4]) { + cb->args[4] = 0; + fib6_walker_unlink(w); + } + cb->args[2] = 0; + kfree(w); + } + cb->done = (void *)cb->args[3]; + cb->args[1] = 3; +} + +static int fib6_dump_done(struct netlink_callback *cb) +{ + fib6_dump_end(cb); + return cb->done ? cb->done(cb) : 0; +} + +static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct fib6_walker_t *w; + int res; + + w = (void *)cb->args[2]; + w->root = &table->tb6_root; + + if (cb->args[4] == 0) { + w->count = 0; + w->skip = 0; + + read_lock_bh(&table->tb6_lock); + res = fib6_walk(w); + read_unlock_bh(&table->tb6_lock); + if (res > 0) { + cb->args[4] = 1; + cb->args[5] = w->root->fn_sernum; + } + } else { + if (cb->args[5] != w->root->fn_sernum) { + /* Begin at the root if the tree changed */ + cb->args[5] = w->root->fn_sernum; + w->state = FWS_INIT; + w->node = w->root; + w->skip = w->count; + } else + w->skip = 0; + + read_lock_bh(&table->tb6_lock); + res = fib6_walk_continue(w); + read_unlock_bh(&table->tb6_lock); + if (res <= 0) { + fib6_walker_unlink(w); + cb->args[4] = 0; + } + } + + return res; +} + +static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + unsigned int h, s_h; + unsigned int e = 0, s_e; + struct rt6_rtnl_dump_arg arg; + struct fib6_walker_t *w; + struct fib6_table *tb; + struct hlist_head *head; + int res = 0; + + s_h = cb->args[0]; + s_e = cb->args[1]; + + w = (void *)cb->args[2]; + if (!w) { + /* New dump: + * + * 1. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + + /* + * 2. allocate and initialize walker. + */ + w = kzalloc(sizeof(*w), GFP_ATOMIC); + if (!w) + return -ENOMEM; + w->func = fib6_dump_node; + cb->args[2] = (long)w; + } + + arg.skb = skb; + arg.cb = cb; + arg.net = net; + w->args = &arg; + + rcu_read_lock(); + for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { + e = 0; + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { + if (e < s_e) + goto next; + res = fib6_dump_table(tb, skb, cb); + if (res != 0) + goto out; +next: + e++; + } + } +out: + rcu_read_unlock(); + cb->args[1] = e; + cb->args[0] = h; + + res = res < 0 ? res : skb->len; + if (res <= 0) + fib6_dump_end(cb); + return res; +} /* * Routing Table @@ -207,15 +420,16 @@ static __inline__ void rt6_release(struct rt6_info *rt) * node. */ -static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, - int addrlen, int plen, - int offset) +static struct fib6_node *fib6_add_1(struct fib6_node *root, + struct in6_addr *addr, int plen, + int offset, int allow_create, + int replace_required) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; - int dir = 0; + __be32 dir = 0; __u32 sernum = fib6_new_sernum(); RT6_TRACE("fib6_add_1\n"); @@ -231,36 +445,60 @@ 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("Can't replace route, no match found\n"); + return ERR_PTR(-ENOENT); + } + pr_warn("NLM_F_CREATE should be set when creating new route\n"); + } goto insert_above; - + } + /* * Exact match ? */ - + 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; } - + fn->fn_sernum = sernum; - + return fn; } /* * We have more bits to go */ - + /* Try to walk down on tree. */ fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right: fn->left; + 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("Can't replace route, no match found\n"); + return ERR_PTR(-ENOENT); + } + pr_warn("NLM_F_CREATE should be set when creating new route\n"); + } /* * We walked to the bottom of tree. * Create new leaf node without children. @@ -268,10 +506,10 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, ln = node_alloc(); - if (ln == NULL) - return NULL; + if (!ln) + return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - + ln->parent = pn; ln->fn_sernum = sernum; @@ -285,7 +523,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, insert_above: /* - * split since we don't have a common prefix anymore or + * split since we don't have a common prefix anymore or * we have a less significant route. * we've to insert an intermediate node on the list * this new node will point to the one we need to create @@ -296,31 +534,31 @@ insert_above: /* find 1st bit in difference between the 2 addrs. - See comment in addr_diff: bit may be an invalid value, + See comment in __ipv6_addr_diff: bit may be an invalid value, but if it is >= plen, the value is ignored in any case. */ - - bit = addr_diff(addr, &key->addr, addrlen); - /* - * (intermediate)[in] + bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); + + /* + * (intermediate)[in] * / \ * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { in = node_alloc(); ln = node_alloc(); - - if (in == NULL || ln == NULL) { + + if (!in || !ln) { if (in) node_free(in); if (ln) node_free(ln); - return NULL; + return ERR_PTR(-ENOMEM); } - /* - * new intermediate node. + /* + * new intermediate node. * RTN_RTINFO will * be off since that an address that chooses one of * the branches would not match less specific routes @@ -357,7 +595,7 @@ insert_above: } } else { /* plen <= bit */ - /* + /* * (new leaf node)[ln] * / \ * (old node)[fn] NULL @@ -365,15 +603,15 @@ insert_above: ln = node_alloc(); - if (ln == NULL) - return NULL; + if (!ln) + return ERR_PTR(-ENOMEM); ln->fn_bit = plen; ln->parent = pn; ln->fn_sernum = sernum; - + if (dir) pn->right = ln; else @@ -389,27 +627,61 @@ insert_above: return ln; } +static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + +static int fib6_commit_metrics(struct dst_entry *dst, + struct nlattr *mx, int mx_len) +{ + struct nlattr *nla; + int remaining; + u32 *mp; + + if (dst->flags & DST_HOST) { + mp = dst_metrics_write_ptr(dst); + } else { + mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + if (!mp) + return -ENOMEM; + dst_init_metrics(dst, mp, 0); + } + + nla_for_each_attr(nla, mx, mx_len, remaining) { + int type = nla_type(nla); + + if (type) { + if (type > RTAX_MAX) + return -EINVAL; + + mp[type - 1] = nla_get_u32(nla); + } + } + return 0; +} + /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nlmsghdr *nlh, struct netlink_skb_parms *req) + struct nl_info *info, struct nlattr *mx, int mx_len) { 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; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + int err; ins = &fn->leaf; - if (fn->fn_flags&RTN_TL_ROOT && - fn->leaf == &ip6_null_entry && - !(rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ){ - fn->leaf = rt; - rt->u.next = NULL; - goto out; - } - - for (iter = fn->leaf; iter; iter=iter->u.next) { + for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) { /* * Search for duplicates */ @@ -418,59 +690,149 @@ 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 (rt->rt6i_nsiblings) + rt->rt6i_nsiblings = 0; + if (!(iter->rt6i_flags & RTF_EXPIRES)) return -EEXIST; - iter->rt6i_expires = rt->rt6i_expires; - if (!(rt->rt6i_flags&RTF_EXPIRES)) { - iter->rt6i_flags &= ~RTF_EXPIRES; - iter->rt6i_expires = 0; - } + if (!(rt->rt6i_flags & RTF_EXPIRES)) + rt6_clean_expires(iter); + else + rt6_set_expires(iter, rt->dst.expires); return -EEXIST; } + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) + rt->rt6i_nsiblings++; } if (iter->rt6i_metric > rt->rt6i_metric) break; - ins = &iter->u.next; + ins = &iter->dst.rt6_next; + } + + /* Reset round-robin state, if necessary */ + if (ins == &fn->leaf) + fn->rr_ptr = NULL; + + /* Link this route to others same route. */ + if (rt->rt6i_nsiblings) { + unsigned int rt6i_nsiblings; + struct rt6_info *sibling, *temp_sibling; + + /* Find the first route that have the same metric */ + sibling = fn->leaf; + while (sibling) { + if (sibling->rt6i_metric == rt->rt6i_metric && + rt6_qualify_for_ecmp(sibling)) { + list_add_tail(&rt->rt6i_siblings, + &sibling->rt6i_siblings); + break; + } + sibling = sibling->dst.rt6_next; + } + /* For each sibling in the list, increment the counter of + * siblings. BUG() if counters does not match, list of siblings + * is broken! + */ + rt6i_nsiblings = 0; + list_for_each_entry_safe(sibling, temp_sibling, + &rt->rt6i_siblings, rt6i_siblings) { + sibling->rt6i_nsiblings++; + BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings); + rt6i_nsiblings++; + } + BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings); } /* * insert node */ + if (!replace) { + if (!add) + pr_warn("NLM_F_CREATE should be set when creating new route\n"); + +add: + if (mx) { + err = fib6_commit_metrics(&rt->dst, mx, mx_len); + if (err) + return err; + } + 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; + } -out: - rt->u.next = iter; - *ins = rt; - rt->rt6i_node = fn; - atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, nlh, req); - rt6_stats.fib_rt_entries++; - - if ((fn->fn_flags & RTN_RTINFO) == 0) { - rt6_stats.fib_route_nodes++; - fn->fn_flags |= RTN_RTINFO; + } else { + if (!found) { + if (add) + goto add; + pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); + return -ENOENT; + } + if (mx) { + err = fib6_commit_metrics(&rt->dst, mx, mx_len); + if (err) + return err; + } + *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; } -static __inline__ void fib6_start_gc(struct rt6_info *rt) +static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt) { - if (ip6_fib_timer.expires == 0 && - (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE))) - mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval); + if (!timer_pending(&net->ipv6.ip6_fib_timer) && + (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE))) + mod_timer(&net->ipv6.ip6_fib_timer, + jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } -void fib6_force_start_gc(void) +void fib6_force_start_gc(struct net *net) { - if (ip6_fib_timer.expires == 0) - mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval); + if (!timer_pending(&net->ipv6.ip6_fib_timer)) + mod_timer(&net->ipv6.ip6_fib_timer, + jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } /* @@ -479,23 +841,39 @@ void fib6_force_start_gc(void) * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { - struct fib6_node *fn; + struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; - - fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst)); - - if (fn == NULL) + 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("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); + + fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + offsetof(struct rt6_info, rt6i_dst), allow_create, + replace_required); + if (IS_ERR(fn)) { + err = PTR_ERR(fn); + fn = NULL; goto out; + } + + pn = fn; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen) { struct fib6_node *sn; - if (fn->subtree == NULL) { + if (!fn->subtree) { struct fib6_node *sfn; /* @@ -510,60 +888,85 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, /* Create subtree root node */ sfn = node_alloc(); - if (sfn == NULL) + if (!sfn) goto st_failure; - sfn->leaf = &ip6_null_entry; - atomic_inc(&ip6_null_entry.rt6i_ref); + sfn->leaf = info->nl_net->ipv6.ip6_null_entry; + atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); sfn->fn_flags = RTN_ROOT; sfn->fn_sernum = fib6_new_sernum(); /* Now add the first leaf node to new subtree */ sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src)); + rt->rt6i_src.plen, + offsetof(struct rt6_info, rt6i_src), + allow_create, replace_required); - if (sn == NULL) { + if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in st_failure) stale node in main tree. */ node_free(sfn); + err = PTR_ERR(sn); goto st_failure; } /* Now link new subtree to main tree */ sfn->parent = fn; fn->subtree = sfn; - if (fn->leaf == NULL) { - fn->leaf = rt; - atomic_inc(&rt->rt6i_ref); - } } 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)); + rt->rt6i_src.plen, + offsetof(struct rt6_info, rt6i_src), + allow_create, replace_required); - if (sn == NULL) + if (IS_ERR(sn)) { + err = PTR_ERR(sn); goto st_failure; + } } + if (!fn->leaf) { + fn->leaf = rt; + atomic_inc(&rt->rt6i_ref); + } fn = sn; } #endif - err = fib6_add_rt2node(fn, rt, nlh, req); - - if (err == 0) { - fib6_start_gc(rt); - if (!(rt->rt6i_flags&RTF_CACHE)) - fib6_prune_clones(fn, rt); + err = fib6_add_rt2node(fn, rt, info, mx, mx_len); + if (!err) { + fib6_start_gc(info->nl_net, rt); + if (!(rt->rt6i_flags & RTF_CACHE)) + fib6_prune_clones(info->nl_net, pn); } out: - if (err) - dst_free(&rt->u.dst); + if (err) { +#ifdef CONFIG_IPV6_SUBTREES + /* + * If fib6_add_1 has cleared the old leaf pointer in the + * super-tree leaf node we have to find a new one for it. + */ + if (pn != fn && pn->leaf == rt) { + pn->leaf = NULL; + atomic_dec(&rt->rt6i_ref); + } + if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn->leaf = fib6_find_prefix(info->nl_net, pn); +#if RT6_DEBUG >= 2 + if (!pn->leaf) { + WARN_ON(pn->leaf == NULL); + pn->leaf = info->nl_net->ipv6.ip6_null_entry; + } +#endif + atomic_inc(&pn->leaf->rt6i_ref); + } +#endif + dst_free(&rt->dst); + } return err; #ifdef CONFIG_IPV6_SUBTREES @@ -572,8 +975,8 @@ out: */ st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) - fib6_repair_tree(fn); - dst_free(&rt->u.dst); + fib6_repair_tree(info->nl_net, fn); + dst_free(&rt->dst); return err; #endif } @@ -584,15 +987,18 @@ st_failure: */ struct lookup_args { - int offset; /* key offset on rt6_info */ - struct in6_addr *addr; /* search key */ + int offset; /* key offset on rt6_info */ + const struct in6_addr *addr; /* search key */ }; -static struct fib6_node * fib6_lookup_1(struct fib6_node *root, - struct lookup_args *args) +static struct fib6_node *fib6_lookup_1(struct fib6_node *root, + struct lookup_args *args) { struct fib6_node *fn; - int dir; + __be32 dir; + + if (unlikely(args->offset == 0)) + return NULL; /* * Descend on a tree @@ -611,36 +1017,36 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, fn = next; continue; } - break; } - while ((fn->fn_flags & RTN_ROOT) == 0) { -#ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) { - struct fib6_node *st; - struct lookup_args *narg; - - narg = args + 1; - - if (narg->addr) { - st = fib6_lookup_1(fn->subtree, narg); - - if (st && !(st->fn_flags & RTN_ROOT)) - return st; - } - } -#endif - - if (fn->fn_flags & RTN_RTINFO) { + while (fn) { + if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { struct rt6key *key; key = (struct rt6key *) ((u8 *) fn->leaf + args->offset); - if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) - return fn; + if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { +#ifdef CONFIG_IPV6_SUBTREES + if (fn->subtree) { + struct fib6_node *sfn; + sfn = fib6_lookup_1(fn->subtree, + args + 1); + if (!sfn) + goto backtrack; + fn = sfn; + } +#endif + if (fn->fn_flags & RTN_RTINFO) + return fn; + } } +#ifdef CONFIG_IPV6_SUBTREES +backtrack: +#endif + if (fn->fn_flags & RTN_ROOT) + break; fn = fn->parent; } @@ -648,23 +1054,28 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, return NULL; } -struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr, - struct in6_addr *saddr) +struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, + const struct in6_addr *saddr) { - struct lookup_args args[2]; struct fib6_node *fn; - - args[0].offset = offsetof(struct rt6_info, rt6i_dst); - args[0].addr = daddr; - + struct lookup_args args[] = { + { + .offset = offsetof(struct rt6_info, rt6i_dst), + .addr = daddr, + }, #ifdef CONFIG_IPV6_SUBTREES - args[1].offset = offsetof(struct rt6_info, rt6i_src); - args[1].addr = saddr; + { + .offset = offsetof(struct rt6_info, rt6i_src), + .addr = saddr, + }, #endif + { + .offset = 0, /* sentinel */ + } + }; - fn = fib6_lookup_1(root, args); - - if (fn == NULL || fn->fn_flags & RTN_TL_ROOT) + fn = fib6_lookup_1(root, daddr ? args : args + 1); + if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; @@ -676,9 +1087,9 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr, */ -static struct fib6_node * fib6_locate_1(struct fib6_node *root, - struct in6_addr *addr, - int plen, int offset) +static struct fib6_node *fib6_locate_1(struct fib6_node *root, + const struct in6_addr *addr, + int plen, int offset) { struct fib6_node *fn; @@ -706,9 +1117,9 @@ static struct fib6_node * fib6_locate_1(struct fib6_node *root, return NULL; } -struct fib6_node * fib6_locate(struct fib6_node *root, - struct in6_addr *daddr, int dst_len, - struct in6_addr *saddr, int src_len) +struct fib6_node *fib6_locate(struct fib6_node *root, + const struct in6_addr *daddr, int dst_len, + const struct in6_addr *saddr, int src_len) { struct fib6_node *fn; @@ -717,16 +1128,14 @@ struct fib6_node * fib6_locate(struct fib6_node *root, #ifdef CONFIG_IPV6_SUBTREES if (src_len) { - BUG_TRAP(saddr!=NULL); - if (fn == NULL) - fn = fn->subtree; - if (fn) - fn = fib6_locate_1(fn, saddr, src_len, + WARN_ON(saddr == NULL); + if (fn && fn->subtree) + fn = fib6_locate_1(fn->subtree, saddr, src_len, offsetof(struct rt6_info, rt6i_src)); } #endif - if (fn && fn->fn_flags&RTN_RTINFO) + if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; @@ -738,19 +1147,18 @@ struct fib6_node * fib6_locate(struct fib6_node *root, * */ -static struct rt6_info * fib6_find_prefix(struct fib6_node *fn) +static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) { - if (fn->fn_flags&RTN_ROOT) - return &ip6_null_entry; + 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 = SUBTREE(fn); + fn = FIB6_SUBTREE(fn); } return NULL; } @@ -760,7 +1168,8 @@ static struct rt6_info * fib6_find_prefix(struct fib6_node *fn) * is the node we want to try and remove. */ -static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) +static struct fib6_node *fib6_repair_tree(struct net *net, + struct fib6_node *fn) { int children; int nstate; @@ -772,26 +1181,28 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; - BUG_TRAP(!(fn->fn_flags&RTN_RTINFO)); - BUG_TRAP(!(fn->fn_flags&RTN_TL_ROOT)); - BUG_TRAP(fn->leaf==NULL); + WARN_ON(fn->fn_flags & RTN_RTINFO); + WARN_ON(fn->fn_flags & RTN_TL_ROOT); + WARN_ON(fn->leaf != NULL); children = 0; child = NULL; - if (fn->right) child = fn->right, children |= 1; - if (fn->left) child = fn->left, children |= 2; + if (fn->right) + child = fn->right, children |= 1; + if (fn->left) + child = fn->left, children |= 2; - if (children == 3 || SUBTREE(fn) + 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(fn); + fn->leaf = fib6_find_prefix(net, fn); #if RT6_DEBUG >= 2 - if (fn->leaf==NULL) { - BUG_TRAP(fn->leaf); - fn->leaf = &ip6_null_entry; + if (!fn->leaf) { + WARN_ON(!fn->leaf); + fn->leaf = net->ipv6.ip6_null_entry; } #endif atomic_inc(&fn->leaf->rt6i_ref); @@ -800,17 +1211,20 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES - if (SUBTREE(pn) == fn) { - BUG_TRAP(fn->fn_flags&RTN_ROOT); - SUBTREE(pn) = NULL; + if (FIB6_SUBTREE(pn) == fn) { + WARN_ON(!(fn->fn_flags & RTN_ROOT)); + FIB6_SUBTREE(pn) = NULL; nstate = FWS_L; } else { - BUG_TRAP(!(fn->fn_flags&RTN_ROOT)); + WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) pn->right = child; - else if (pn->left == fn) pn->left = child; + if (pn->right == fn) + pn->right = child; + else if (pn->left == fn) + pn->left = child; #if RT6_DEBUG >= 2 - else BUG_TRAP(0); + else + WARN_ON(1); #endif if (child) child->parent = pn; @@ -821,7 +1235,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) 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); @@ -839,10 +1253,10 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) w->node = child; if (children&2) { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_R ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_C ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } @@ -850,7 +1264,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) read_unlock(&fib6_walker_lock); node_free(fn); - if (pn->fn_flags&RTN_RTINFO || SUBTREE(pn)) + if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; rt6_release(pn->leaf); @@ -860,41 +1274,54 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) } static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) + struct nl_info *info) { struct fib6_walker_t *w; struct rt6_info *rt = *rtp; + struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); /* Unlink it */ - *rtp = rt->u.next; + *rtp = rt->dst.rt6_next; rt->rt6i_node = NULL; - rt6_stats.fib_rt_entries--; - rt6_stats.fib_discarded_routes++; + net->ipv6.rt6_stats->fib_rt_entries--; + net->ipv6.rt6_stats->fib_discarded_routes++; + + /* Reset round-robin state, if necessary */ + if (fn->rr_ptr == rt) + fn->rr_ptr = NULL; + + /* Remove this entry from other siblings */ + if (rt->rt6i_nsiblings) { + struct rt6_info *sibling, *next_sibling; + + list_for_each_entry_safe(sibling, next_sibling, + &rt->rt6i_siblings, rt6i_siblings) + sibling->rt6i_nsiblings--; + rt->rt6i_nsiblings = 0; + list_del_init(&rt->rt6i_siblings); + } /* Adjust walkers */ read_lock(&fib6_walker_lock); FOR_WALKERS(w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rt->u.next; - if (w->leaf == NULL) + w->leaf = rt->dst.rt6_next; + if (!w->leaf) w->state = FWS_U; } } read_unlock(&fib6_walker_lock); - rt->u.next = NULL; - - if (fn->leaf == NULL && fn->fn_flags&RTN_TL_ROOT) - fn->leaf = &ip6_null_entry; + 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; - rt6_stats.fib_route_nodes--; - fn = fib6_repair_tree(fn); + net->ipv6.rt6_stats->fib_route_nodes--; + fn = fib6_repair_tree(net, fn); } if (atomic_read(&rt->rt6i_ref) != 1) { @@ -905,47 +1332,58 @@ 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) { - fn->leaf = fib6_find_prefix(fn); + 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); } fn = fn->parent; } /* No more references are possible at this point. */ - if (atomic_read(&rt->rt6i_ref) != 1) BUG(); + BUG_ON(atomic_read(&rt->rt6i_ref) != 1); } - inet6_rt_notify(RTM_DELROUTE, rt, nlh, req); + inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); } -int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int fib6_del(struct rt6_info *rt, struct nl_info *info) { + struct net *net = info->nl_net; struct fib6_node *fn = rt->rt6i_node; struct rt6_info **rtp; #if RT6_DEBUG >= 2 - if (rt->u.dst.obsolete>0) { - BUG_TRAP(fn==NULL); + if (rt->dst.obsolete > 0) { + WARN_ON(fn != NULL); return -ENOENT; } #endif - if (fn == NULL || rt == &ip6_null_entry) + if (!fn || rt == net->ipv6.ip6_null_entry) return -ENOENT; - BUG_TRAP(fn->fn_flags&RTN_RTINFO); + WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - if (!(rt->rt6i_flags&RTF_CACHE)) - fib6_prune_clones(fn, rt); + 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)) + pn = pn->parent; + pn = pn->parent; + } +#endif + fib6_prune_clones(info->nl_net, pn); + } /* * Walk the leaf entries looking for ourself */ - for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.next) { + for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) { if (*rtp == rt) { - fib6_del_route(fn, rtp, nlh, _rtattr, req); + fib6_del_route(fn, rtp, info); return 0; } } @@ -959,7 +1397,7 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne * However, it is internally reenterable wrt itself and fib6_add/fib6_del. * It means, that we can modify tree during walking * and use this function for garbage collection, clone pruning, - * cleaning tree when a device goes down etc. etc. + * cleaning tree when a device goes down etc. etc. * * It guarantees that every node will be traversed, * and that it will be traversed only once. @@ -976,29 +1414,29 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne * <0 -> walk is terminated by an error. */ -int fib6_walk_continue(struct fib6_walker_t *w) +static int fib6_walk_continue(struct fib6_walker_t *w) { struct fib6_node *fn, *pn; 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; } switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: - if (SUBTREE(fn)) { - w->node = SUBTREE(fn); + if (FIB6_SUBTREE(fn)) { + w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; -#endif +#endif case FWS_L: if (fn->left) { w->node = fn->left; @@ -1015,12 +1453,22 @@ 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) { - int err = w->func(w); + if (w->leaf && fn->fn_flags & RTN_RTINFO) { + int err; + + if (w->skip) { + w->skip--; + goto skip; + } + + err = w->func(w); if (err) return err; + + w->count++; continue; } +skip: w->state = FWS_U; case FWS_U: if (fn == w->root) @@ -1028,8 +1476,8 @@ int fib6_walk_continue(struct fib6_walker_t *w) pn = fn->parent; w->node = pn; #ifdef CONFIG_IPV6_SUBTREES - if (SUBTREE(pn) == fn) { - BUG_TRAP(fn->fn_flags&RTN_ROOT); + if (FIB6_SUBTREE(pn) == fn) { + WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } @@ -1044,13 +1492,13 @@ int fib6_walk_continue(struct fib6_walker_t *w) continue; } #if RT6_DEBUG >= 2 - BUG_TRAP(0); + WARN_ON(1); #endif } } } -int fib6_walk(struct fib6_walker_t *w) +static int fib6_walk(struct fib6_walker_t *w) { int res; @@ -1068,22 +1516,26 @@ static int fib6_clean_node(struct fib6_walker_t *w) { int res; struct rt6_info *rt; - struct fib6_cleaner_t *c = (struct fib6_cleaner_t*)w; + struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w); + struct nl_info info = { + .nl_net = c->net, + }; - for (rt = w->leaf; rt; rt = rt->u.next) { + for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; - res = fib6_del(rt, NULL, NULL, NULL); + res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 - printk(KERN_DEBUG "fib6_clean_node: del failed: rt=%p@%p err=%d\n", rt, rt->rt6i_node, res); + pr_debug("%s: del failed: rt=%p@%p err=%d\n", + __func__, rt, rt->rt6i_node, res); #endif continue; } return 0; } - BUG_TRAP(res==0); + WARN_ON(res != 0); } w->leaf = rt; return 0; @@ -1091,7 +1543,7 @@ static int fib6_clean_node(struct fib6_walker_t *w) /* * Convenient frontend to tree walker. - * + * * func is called on each route. * It may return -1 -> delete this route. * 0 -> continue walking @@ -1100,21 +1552,44 @@ static int fib6_clean_node(struct fib6_walker_t *w) * ignoring pure split nodes) will be scanned. */ -void fib6_clean_tree(struct fib6_node *root, - int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) +static void fib6_clean_tree(struct net *net, struct fib6_node *root, + int (*func)(struct rt6_info *, void *arg), + int prune, void *arg) { struct fib6_cleaner_t c; c.w.root = root; c.w.func = fib6_clean_node; c.w.prune = prune; + c.w.count = 0; + c.w.skip = 0; c.func = func; c.arg = arg; + c.net = net; fib6_walk(&c.w); } +void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), + void *arg) +{ + struct fib6_table *table; + 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, head, tb6_hlist) { + write_lock_bh(&table->tb6_lock); + fib6_clean_tree(net, &table->tb6_root, + func, 0, arg); + write_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} + static int fib6_prune_clone(struct rt6_info *rt, void *arg) { if (rt->rt6i_flags & RTF_CACHE) { @@ -1125,9 +1600,9 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg) return 0; } -static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt) +static void fib6_prune_clones(struct net *net, struct fib6_node *fn) { - fib6_clean_tree(fn, fib6_prune_clone, 1, rt); + fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL); } /* @@ -1152,23 +1627,31 @@ 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); - rt6_reset_dflt_pointer(rt); return -1; } gc_args.more++; } else if (rt->rt6i_flags & RTF_CACHE) { - if (atomic_read(&rt->u.dst.__refcnt) == 0 && - time_after_eq(now, rt->u.dst.lastuse + gc_args.timeout)) { + if (atomic_read(&rt->dst.__refcnt) == 0 && + time_after_eq(now, rt->dst.lastuse + gc_args.timeout)) { RT6_TRACE("aging clone %p\n", rt); return -1; - } else if ((rt->rt6i_flags & RTF_GATEWAY) && - (!(rt->rt6i_nexthop->flags & NTF_ROUTER))) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); - return -1; + } else if (rt->rt6i_flags & RTF_GATEWAY) { + struct neighbour *neigh; + __u8 neigh_flags = 0; + + neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); + if (neigh) { + neigh_flags = neigh->flags; + neigh_release(neigh); + } + if (!(neigh_flags & NTF_ROUTER)) { + RT6_TRACE("purging route %p via non-router but gateway\n", + rt); + return -1; + } } gc_args.more++; } @@ -1178,49 +1661,331 @@ static int fib6_age(struct rt6_info *rt, void *arg) static DEFINE_SPINLOCK(fib6_gc_lock); -void fib6_run_gc(unsigned long dummy) +void fib6_run_gc(unsigned long expires, struct net *net, bool force) { - if (dummy != ~0UL) { + unsigned long now; + + if (force) { spin_lock_bh(&fib6_gc_lock); - gc_args.timeout = dummy ? (int)dummy : ip6_rt_gc_interval; - } else { - local_bh_disable(); - if (!spin_trylock(&fib6_gc_lock)) { - mod_timer(&ip6_fib_timer, jiffies + HZ); - local_bh_enable(); - return; - } - gc_args.timeout = ip6_rt_gc_interval; + } else if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); + return; } - gc_args.more = 0; + gc_args.timeout = expires ? (int)expires : + net->ipv6.sysctl.ip6_rt_gc_interval; + gc_args.more = icmp6_dst_gc(); - write_lock_bh(&rt6_lock); - ndisc_dst_gc(&gc_args.more); - fib6_clean_tree(&ip6_routing_table, fib6_age, 0, NULL); - write_unlock_bh(&rt6_lock); + fib6_clean_all(net, fib6_age, NULL); + now = jiffies; + net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) - mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval); - else { - del_timer(&ip6_fib_timer); - ip6_fib_timer.expires = 0; - } + mod_timer(&net->ipv6.ip6_fib_timer, + round_jiffies(now + + net->ipv6.sysctl.ip6_rt_gc_interval)); + else + del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&fib6_gc_lock); } -void __init fib6_init(void) +static void fib6_gc_timer_cb(unsigned long arg) +{ + fib6_run_gc(0, (struct net *)arg, true); +} + +static int __net_init fib6_net_init(struct net *net) +{ + size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + + setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); + + net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); + if (!net->ipv6.rt6_stats) + goto out_timer; + + /* Avoid false sharing : Use at least a full cache line */ + size = max_t(size_t, size, L1_CACHE_BYTES); + + net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); + if (!net->ipv6.fib_table_hash) + goto out_rt6_stats; + + net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl), + GFP_KERNEL); + if (!net->ipv6.fib6_main_tbl) + goto out_fib_table_hash; + + net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; + net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + net->ipv6.fib6_main_tbl->tb6_root.fn_flags = + RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), + GFP_KERNEL); + if (!net->ipv6.fib6_local_tbl) + goto out_fib6_main_tbl; + net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; + net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + net->ipv6.fib6_local_tbl->tb6_root.fn_flags = + RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); +#endif + fib6_tables_init(net); + + return 0; + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +out_fib6_main_tbl: + kfree(net->ipv6.fib6_main_tbl); +#endif +out_fib_table_hash: + kfree(net->ipv6.fib_table_hash); +out_rt6_stats: + kfree(net->ipv6.rt6_stats); +out_timer: + return -ENOMEM; +} + +static void fib6_net_exit(struct net *net) { + rt6_ifdown(net, NULL); + del_timer_sync(&net->ipv6.ip6_fib_timer); + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers); + kfree(net->ipv6.fib6_local_tbl); +#endif + inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers); + kfree(net->ipv6.fib6_main_tbl); + kfree(net->ipv6.fib_table_hash); + kfree(net->ipv6.rt6_stats); +} + +static struct pernet_operations fib6_net_ops = { + .init = fib6_net_init, + .exit = fib6_net_exit, +}; + +int __init fib6_init(void) +{ + int ret = -ENOMEM; + fib6_node_kmem = kmem_cache_create("fib6_nodes", sizeof(struct fib6_node), 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + NULL); if (!fib6_node_kmem) - panic("cannot create fib6_nodes cache"); + goto out; + + ret = register_pernet_subsys(&fib6_net_ops); + if (ret) + goto out_kmem_cache_create; + + ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib, + NULL); + if (ret) + goto out_unregister_subsys; +out: + return ret; + +out_unregister_subsys: + unregister_pernet_subsys(&fib6_net_ops); +out_kmem_cache_create: + kmem_cache_destroy(fib6_node_kmem); + goto out; } void fib6_gc_cleanup(void) { - del_timer(&ip6_fib_timer); + unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } + +#ifdef CONFIG_PROC_FS + +struct ipv6_route_iter { + struct seq_net_private p; + struct fib6_walker_t w; + loff_t skip; + struct fib6_table *tbl; + __u32 sernum; +}; + +static int ipv6_route_seq_show(struct seq_file *seq, void *v) +{ + struct rt6_info *rt = v; + struct ipv6_route_iter *iter = seq->private; + + seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); + +#ifdef CONFIG_IPV6_SUBTREES + seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); +#else + seq_puts(seq, "00000000000000000000000000000000 00 "); +#endif + if (rt->rt6i_flags & RTF_GATEWAY) + seq_printf(seq, "%pi6", &rt->rt6i_gateway); + else + seq_puts(seq, "00000000000000000000000000000000"); + + seq_printf(seq, " %08x %08x %08x %08x %8s\n", + rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), + rt->dst.__use, rt->rt6i_flags, + rt->dst.dev ? rt->dst.dev->name : ""); + iter->w.leaf = NULL; + return 0; +} + +static int ipv6_route_yield(struct fib6_walker_t *w) +{ + struct ipv6_route_iter *iter = w->args; + + if (!iter->skip) + return 1; + + do { + iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->skip--; + if (!iter->skip && iter->w.leaf) + return 1; + } while (iter->w.leaf); + + return 0; +} + +static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) +{ + memset(&iter->w, 0, sizeof(iter->w)); + iter->w.func = ipv6_route_yield; + iter->w.root = &iter->tbl->tb6_root; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + iter->w.args = iter; + iter->sernum = iter->w.root->fn_sernum; + INIT_LIST_HEAD(&iter->w.lh); + fib6_walker_link(&iter->w); +} + +static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, + struct net *net) +{ + unsigned int h; + struct hlist_node *node; + + if (tbl) { + h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; + node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + } else { + h = 0; + node = NULL; + } + + while (!node && h < FIB6_TABLE_HASHSZ) { + node = rcu_dereference_bh( + hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); + } + return hlist_entry_safe(node, struct fib6_table, tb6_hlist); +} + +static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) +{ + if (iter->sernum != iter->w.root->fn_sernum) { + iter->sernum = iter->w.root->fn_sernum; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + WARN_ON(iter->w.skip); + iter->w.skip = iter->w.count; + } +} + +static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + int r; + struct rt6_info *n; + struct net *net = seq_file_net(seq); + struct ipv6_route_iter *iter = seq->private; + + if (!v) + goto iter_table; + + n = ((struct rt6_info *)v)->dst.rt6_next; + if (n) { + ++*pos; + return n; + } + +iter_table: + ipv6_route_check_sernum(iter); + read_lock(&iter->tbl->tb6_lock); + r = fib6_walk_continue(&iter->w); + read_unlock(&iter->tbl->tb6_lock); + if (r > 0) { + if (v) + ++*pos; + return iter->w.leaf; + } else if (r < 0) { + fib6_walker_unlink(&iter->w); + return NULL; + } + fib6_walker_unlink(&iter->w); + + iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); + if (!iter->tbl) + return NULL; + + ipv6_route_seq_setup_walk(iter); + goto iter_table; +} + +static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU_BH) +{ + struct net *net = seq_file_net(seq); + struct ipv6_route_iter *iter = seq->private; + + rcu_read_lock_bh(); + iter->tbl = ipv6_route_seq_next_table(NULL, net); + iter->skip = *pos; + + if (iter->tbl) { + ipv6_route_seq_setup_walk(iter); + return ipv6_route_seq_next(seq, NULL, pos); + } else { + return NULL; + } +} + +static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) +{ + struct fib6_walker_t *w = &iter->w; + return w->node && !(w->state == FWS_U && w->node == w->root); +} + +static void ipv6_route_seq_stop(struct seq_file *seq, void *v) + __releases(RCU_BH) +{ + struct ipv6_route_iter *iter = seq->private; + + if (ipv6_route_iter_active(iter)) + fib6_walker_unlink(&iter->w); + + rcu_read_unlock_bh(); +} + +static const struct seq_operations ipv6_route_seq_ops = { + .start = ipv6_route_seq_start, + .next = ipv6_route_seq_next, + .stop = ipv6_route_seq_stop, + .show = ipv6_route_seq_show +}; + +int ipv6_route_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter)); +} + +#endif /* CONFIG_PROC_FS */ diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index bbbe80cdaf7..4052694c6f2 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -9,27 +9,24 @@ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ -#include <linux/config.h> +#include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> #include <linux/in6.h> -#include <linux/route.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/pid_namespace.h> +#include <net/net_namespace.h> #include <net/sock.h> #include <net/ipv6.h> -#include <net/ndisc.h> -#include <net/protocol.h> -#include <net/ip6_route.h> -#include <net/addrconf.h> #include <net/rawv6.h> -#include <net/icmp.h> #include <net/transp_v6.h> #include <asm/uaccess.h> @@ -37,7 +34,7 @@ #define FL_MIN_LINGER 6 /* Minimal linger. It is set to 6sec specified in old IPv6 RFC. Well, it was reasonable value. */ -#define FL_MAX_LINGER 60 /* Maximal linger timeout */ +#define FL_MAX_LINGER 150 /* Maximal linger timeout */ /* FL hash table */ @@ -47,54 +44,71 @@ #define FL_HASH(l) (ntohl(l)&FL_HASH_MASK) static atomic_t fl_size = ATOMIC_INIT(0); -static struct ip6_flowlabel *fl_ht[FL_HASH_MASK+1]; +static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(unsigned long dummy); static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc, 0, 0); /* FL hash table lock: it protects only of GC */ -static DEFINE_RWLOCK(ip6_fl_lock); +static DEFINE_SPINLOCK(ip6_fl_lock); /* Big socket sock */ -static DEFINE_RWLOCK(ip6_sk_fl_lock); +static DEFINE_SPINLOCK(ip6_sk_fl_lock); +#define for_each_fl_rcu(hash, fl) \ + for (fl = rcu_dereference_bh(fl_ht[(hash)]); \ + fl != NULL; \ + fl = rcu_dereference_bh(fl->next)) +#define for_each_fl_continue_rcu(fl) \ + for (fl = rcu_dereference_bh(fl->next); \ + fl != NULL; \ + fl = rcu_dereference_bh(fl->next)) -static __inline__ struct ip6_flowlabel * __fl_lookup(u32 label) +#define for_each_sk_fl_rcu(np, sfl) \ + for (sfl = rcu_dereference_bh(np->ipv6_fl_list); \ + sfl != NULL; \ + sfl = rcu_dereference_bh(sfl->next)) + +static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; - for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) { - if (fl->label == label) + for_each_fl_rcu(FL_HASH(label), fl) { + if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } return NULL; } -static struct ip6_flowlabel * fl_lookup(u32 label) +static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; - read_lock_bh(&ip6_fl_lock); - fl = __fl_lookup(label); - if (fl) - atomic_inc(&fl->users); - read_unlock_bh(&ip6_fl_lock); + rcu_read_lock_bh(); + fl = __fl_lookup(net, label); + if (fl && !atomic_inc_not_zero(&fl->users)) + fl = NULL; + rcu_read_unlock_bh(); return fl; } static void fl_free(struct ip6_flowlabel *fl) { - if (fl) + if (fl) { + if (fl->share == IPV6_FL_S_PROCESS) + put_pid(fl->owner.pid); + release_net(fl->fl_net); kfree(fl->opt); - kfree(fl); + kfree_rcu(fl, rcu); + } } static void fl_release(struct ip6_flowlabel *fl) { - write_lock_bh(&ip6_fl_lock); + spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (atomic_dec_and_test(&fl->users)) { @@ -111,8 +125,7 @@ static void fl_release(struct ip6_flowlabel *fl) time_after(ip6_fl_gc_timer.expires, ttd)) mod_timer(&ip6_fl_gc_timer, ttd); } - - write_unlock_bh(&ip6_fl_lock); + spin_unlock_bh(&ip6_fl_lock); } static void ip6_fl_gc(unsigned long dummy) @@ -121,12 +134,15 @@ static void ip6_fl_gc(unsigned long dummy) unsigned long now = jiffies; unsigned long sched = 0; - write_lock(&ip6_fl_lock); + spin_lock(&ip6_fl_lock); for (i=0; i<=FL_HASH_MASK; i++) { - struct ip6_flowlabel *fl, **flp; + struct ip6_flowlabel *fl; + struct ip6_flowlabel __rcu **flp; + flp = &fl_ht[i]; - while ((fl=*flp) != NULL) { + while ((fl = rcu_dereference_protected(*flp, + lockdep_is_held(&ip6_fl_lock))) != NULL) { if (atomic_read(&fl->users) == 0) { unsigned long ttd = fl->lastuse + fl->linger; if (time_after(ttd, fl->expires)) @@ -147,69 +163,125 @@ static void ip6_fl_gc(unsigned long dummy) if (!sched && atomic_read(&fl_size)) sched = now + FL_MAX_LINGER; if (sched) { - ip6_fl_gc_timer.expires = sched; - add_timer(&ip6_fl_gc_timer); + mod_timer(&ip6_fl_gc_timer, sched); + } + spin_unlock(&ip6_fl_lock); +} + +static void __net_exit ip6_fl_purge(struct net *net) +{ + int i; + + spin_lock(&ip6_fl_lock); + for (i = 0; i <= FL_HASH_MASK; i++) { + struct ip6_flowlabel *fl; + struct ip6_flowlabel __rcu **flp; + + flp = &fl_ht[i]; + while ((fl = rcu_dereference_protected(*flp, + lockdep_is_held(&ip6_fl_lock))) != NULL) { + if (net_eq(fl->fl_net, net) && + atomic_read(&fl->users) == 0) { + *flp = fl->next; + fl_free(fl); + atomic_dec(&fl_size); + continue; + } + flp = &fl->next; + } } - write_unlock(&ip6_fl_lock); + spin_unlock(&ip6_fl_lock); } -static int fl_intern(struct ip6_flowlabel *fl, __u32 label) +static struct ip6_flowlabel *fl_intern(struct net *net, + struct ip6_flowlabel *fl, __be32 label) { + struct ip6_flowlabel *lfl; + fl->label = label & IPV6_FLOWLABEL_MASK; - write_lock_bh(&ip6_fl_lock); + spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { - fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK; + fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { - struct ip6_flowlabel *lfl; - lfl = __fl_lookup(fl->label); + lfl = __fl_lookup(net, fl->label); if (lfl == NULL) break; } } + } else { + /* + * we dropper the ip6_fl_lock, so this entry could reappear + * and we need to recheck with it. + * + * OTOH no need to search the active socket first, like it is + * done in ipv6_flowlabel_opt - sock is locked, so new entry + * with the same label can only appear on another sock + */ + lfl = __fl_lookup(net, fl->label); + if (lfl != NULL) { + atomic_inc(&lfl->users); + spin_unlock_bh(&ip6_fl_lock); + return lfl; + } } fl->lastuse = jiffies; fl->next = fl_ht[FL_HASH(fl->label)]; - fl_ht[FL_HASH(fl->label)] = fl; + rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl); atomic_inc(&fl_size); - write_unlock_bh(&ip6_fl_lock); - return 0; + spin_unlock_bh(&ip6_fl_lock); + return NULL; } /* Socket flowlabel lists */ -struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, u32 label) +struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label) { struct ipv6_fl_socklist *sfl; struct ipv6_pinfo *np = inet6_sk(sk); label &= IPV6_FLOWLABEL_MASK; - for (sfl=np->ipv6_fl_list; sfl; sfl = sfl->next) { + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { struct ip6_flowlabel *fl = sfl->fl; if (fl->label == label) { fl->lastuse = jiffies; atomic_inc(&fl->users); + rcu_read_unlock_bh(); return fl; } } + rcu_read_unlock_bh(); return NULL; } +EXPORT_SYMBOL_GPL(fl6_sock_lookup); + void fl6_free_socklist(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; - while ((sfl = np->ipv6_fl_list) != NULL) { + if (!rcu_access_pointer(np->ipv6_fl_list)) + return; + + spin_lock_bh(&ip6_sk_fl_lock); + while ((sfl = rcu_dereference_protected(np->ipv6_fl_list, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL) { np->ipv6_fl_list = sfl->next; + spin_unlock_bh(&ip6_sk_fl_lock); + fl_release(sfl->fl); - kfree(sfl); + kfree_rcu(sfl, rcu); + + spin_lock_bh(&ip6_sk_fl_lock); } + spin_unlock_bh(&ip6_sk_fl_lock); } /* Service routines */ @@ -225,20 +297,16 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space, struct ip6_flowlabel * fl, struct ipv6_txoptions * fopt) { - struct ipv6_txoptions * fl_opt = fl ? fl->opt : NULL; + struct ipv6_txoptions * fl_opt = fl->opt; - if (fopt == NULL || fopt->opt_flen == 0) { - if (!fl_opt || !fl_opt->dst0opt || fl_opt->srcrt) - return fl_opt; - } + if (fopt == NULL || fopt->opt_flen == 0) + return fl_opt; if (fl_opt != NULL) { opt_space->hopopt = fl_opt->hopopt; - opt_space->dst0opt = fl_opt->srcrt ? fl_opt->dst0opt : NULL; + opt_space->dst0opt = fl_opt->dst0opt; opt_space->srcrt = fl_opt->srcrt; opt_space->opt_nflen = fl_opt->opt_nflen; - if (fl_opt->dst0opt && !fl_opt->srcrt) - opt_space->opt_nflen -= ipv6_optlen(fl_opt->dst0opt); } else { if (fopt->opt_nflen == 0) return fopt; @@ -251,6 +319,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space, opt_space->opt_flen = fopt->opt_flen; return opt_space; } +EXPORT_SYMBOL_GPL(fl6_merge_options); static unsigned long check_linger(unsigned long ttl) { @@ -269,6 +338,8 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo expires = check_linger(expires); if (!expires) return -EPERM; + + spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (time_before(fl->linger, linger)) fl->linger = linger; @@ -276,27 +347,33 @@ static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned lo expires = fl->linger; if (time_before(fl->expires, fl->lastuse + expires)) fl->expires = fl->lastuse + expires; + spin_unlock_bh(&ip6_fl_lock); + return 0; } static struct ip6_flowlabel * -fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *err_p) +fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, + char __user *optval, int optlen, int *err_p) { - struct ip6_flowlabel *fl; + struct ip6_flowlabel *fl = NULL; int olen; int addr_type; int err; + olen = optlen - CMSG_ALIGN(sizeof(*freq)); + err = -EINVAL; + if (olen > 64 * 1024) + goto done; + err = -ENOMEM; - fl = kmalloc(sizeof(*fl), GFP_KERNEL); + fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (fl == NULL) goto done; - memset(fl, 0, sizeof(*fl)); - olen = optlen - CMSG_ALIGN(sizeof(*freq)); if (olen > 0) { struct msghdr msg; - struct flowi flowi; + struct flowi6 flowi6; int junk; err = -ENOMEM; @@ -312,9 +389,10 @@ fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int * msg.msg_controllen = olen; msg.msg_control = (void*)(fl->opt+1); - flowi.oif = 0; + memset(&flowi6, 0, sizeof(flowi6)); - err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk); + err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, + &junk, &junk, &junk); if (err) goto done; err = -EINVAL; @@ -326,26 +404,29 @@ fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int * } } + fl->fl_net = hold_net(net); fl->expires = jiffies; err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); if (err) goto done; fl->share = freq->flr_share; addr_type = ipv6_addr_type(&freq->flr_dst); - if ((addr_type&IPV6_ADDR_MAPPED) - || addr_type == IPV6_ADDR_ANY) + if ((addr_type & IPV6_ADDR_MAPPED) || + addr_type == IPV6_ADDR_ANY) { + 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: case IPV6_FL_S_ANY: break; case IPV6_FL_S_PROCESS: - fl->owner = current->pid; + fl->owner.pid = get_task_pid(current, PIDTYPE_PID); break; case IPV6_FL_S_USER: - fl->owner = current->euid; + fl->owner.uid = current_euid(); break; default: err = -EINVAL; @@ -369,54 +450,78 @@ static int mem_check(struct sock *sk) if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; - for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) count++; + rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || - (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) - && !capable(CAP_NET_ADMIN))) + (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && + !capable(CAP_NET_ADMIN))) return -ENOBUFS; return 0; } -static int ipv6_hdr_cmp(struct ipv6_opt_hdr *h1, struct ipv6_opt_hdr *h2) +static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, + struct ip6_flowlabel *fl) { - if (h1 == h2) - return 0; - if (h1 == NULL || h2 == NULL) - return 1; - if (h1->hdrlen != h2->hdrlen) - return 1; - return memcmp(h1+1, h2+1, ((h1->hdrlen+1)<<3) - sizeof(*h1)); + spin_lock_bh(&ip6_sk_fl_lock); + sfl->fl = fl; + sfl->next = np->ipv6_fl_list; + rcu_assign_pointer(np->ipv6_fl_list, sfl); + spin_unlock_bh(&ip6_sk_fl_lock); } -static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2) +int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, + int flags) { - if (o1 == o2) + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_fl_socklist *sfl; + + if (flags & IPV6_FL_F_REMOTE) { + freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK; return 0; - if (o1 == NULL || o2 == NULL) - return 1; - if (o1->opt_nflen != o2->opt_nflen) - return 1; - if (ipv6_hdr_cmp(o1->hopopt, o2->hopopt)) - return 1; - if (ipv6_hdr_cmp(o1->dst0opt, o2->dst0opt)) - return 1; - if (ipv6_hdr_cmp((struct ipv6_opt_hdr *)o1->srcrt, (struct ipv6_opt_hdr *)o2->srcrt)) - return 1; - return 0; + } + + if (np->repflow) { + freq->flr_label = np->flow_label; + return 0; + } + + rcu_read_lock_bh(); + + for_each_sk_fl_rcu(np, sfl) { + if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) { + spin_lock_bh(&ip6_fl_lock); + freq->flr_label = sfl->fl->label; + freq->flr_dst = sfl->fl->dst; + freq->flr_share = sfl->fl->share; + freq->flr_expires = (sfl->fl->expires - jiffies) / HZ; + freq->flr_linger = sfl->fl->linger / HZ; + + spin_unlock_bh(&ip6_fl_lock); + rcu_read_unlock_bh(); + return 0; + } + } + rcu_read_unlock_bh(); + + return -ENOENT; } int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { - int err; + int uninitialized_var(err); + struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_flowlabel_req freq; struct ipv6_fl_socklist *sfl1=NULL; - struct ipv6_fl_socklist *sfl, **sflp; - struct ip6_flowlabel *fl; + struct ipv6_fl_socklist *sfl; + struct ipv6_fl_socklist __rcu **sflp; + struct ip6_flowlabel *fl, *fl1 = NULL; + if (optlen < sizeof(freq)) return -EINVAL; @@ -426,34 +531,46 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) switch (freq.flr_action) { case IPV6_FL_A_PUT: - write_lock_bh(&ip6_sk_fl_lock); - for (sflp = &np->ipv6_fl_list; (sfl=*sflp)!=NULL; sflp = &sfl->next) { + if (freq.flr_flags & IPV6_FL_F_REFLECT) { + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + if (!np->repflow) + return -ESRCH; + np->flow_label = 0; + np->repflow = 0; + return 0; + } + spin_lock_bh(&ip6_sk_fl_lock); + for (sflp = &np->ipv6_fl_list; + (sfl = rcu_dereference(*sflp))!=NULL; + sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = sfl->next; - write_unlock_bh(&ip6_sk_fl_lock); + *sflp = rcu_dereference(sfl->next); + spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); - kfree(sfl); + kfree_rcu(sfl, rcu); return 0; } } - write_unlock_bh(&ip6_sk_fl_lock); + spin_unlock_bh(&ip6_sk_fl_lock); return -ESRCH; case IPV6_FL_A_RENEW: - read_lock_bh(&ip6_sk_fl_lock); - for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) { + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq.flr_label) { err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires); - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); return err; } } - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); - if (freq.flr_share == IPV6_FL_S_NONE && capable(CAP_NET_ADMIN)) { - fl = fl_lookup(freq.flr_label); + if (freq.flr_share == IPV6_FL_S_NONE && + ns_capable(net->user_ns, CAP_NET_ADMIN)) { + fl = fl_lookup(net, freq.flr_label); if (fl) { err = fl6_renew(fl, freq.flr_linger, freq.flr_expires); fl_release(fl); @@ -463,23 +580,35 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) return -ESRCH; case IPV6_FL_A_GET: + if (freq.flr_flags & IPV6_FL_F_REFLECT) { + struct net *net = sock_net(sk); + if (net->ipv6.sysctl.flowlabel_consistency) { + net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n"); + return -EPERM; + } + + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + + np->repflow = 1; + return 0; + } + if (freq.flr_label & ~IPV6_FLOWLABEL_MASK) return -EINVAL; - fl = fl_create(&freq, optval, optlen, &err); + fl = fl_create(net, sk, &freq, optval, optlen, &err); if (fl == NULL) return err; sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); if (freq.flr_label) { - struct ip6_flowlabel *fl1 = NULL; - err = -EEXIST; - read_lock_bh(&ip6_sk_fl_lock); - for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) { + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_flags&IPV6_FL_F_EXCL) { - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); goto done; } fl1 = sfl->fl; @@ -487,23 +616,22 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) break; } } - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); if (fl1 == NULL) - fl1 = fl_lookup(freq.flr_label); + fl1 = fl_lookup(net, freq.flr_label); if (fl1) { +recheck: err = -EEXIST; if (freq.flr_flags&IPV6_FL_F_EXCL) goto release; err = -EPERM; if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || - fl1->owner != fl->owner) - goto release; - - err = -EINVAL; - if (!ipv6_addr_equal(&fl1->dst, &fl->dst) || - ipv6_opt_cmp(fl1->opt, fl->opt)) + ((fl1->share == IPV6_FL_S_PROCESS) && + (fl1->owner.pid == fl->owner.pid)) || + ((fl1->share == IPV6_FL_S_USER) && + uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -ENOMEM; @@ -513,11 +641,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) fl1->expires = fl->expires; - write_lock_bh(&ip6_sk_fl_lock); - sfl1->fl = fl1; - sfl1->next = np->ipv6_fl_list; - np->ipv6_fl_list = sfl1; - write_unlock_bh(&ip6_sk_fl_lock); + fl_link(np, sfl1, fl1); fl_free(fl); return 0; @@ -534,9 +658,9 @@ release: if (sfl1 == NULL || (err = mem_check(sk)) != 0) goto done; - err = fl_intern(fl, freq.flr_label); - if (err) - goto done; + fl1 = fl_intern(net, fl, freq.flr_label); + if (fl1 != NULL) + goto recheck; if (!freq.flr_label) { if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label, @@ -545,9 +669,7 @@ release: } } - sfl1->fl = fl; - sfl1->next = np->ipv6_fl_list; - np->ipv6_fl_list = sfl1; + fl_link(np, sfl1, fl); return 0; default: @@ -563,6 +685,8 @@ done: #ifdef CONFIG_PROC_FS struct ip6fl_iter_state { + struct seq_net_private p; + struct pid_namespace *pid_ns; int bucket; }; @@ -572,25 +696,40 @@ static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) { struct ip6_flowlabel *fl = NULL; struct ip6fl_iter_state *state = ip6fl_seq_private(seq); + struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { - if (fl_ht[state->bucket]) { - fl = fl_ht[state->bucket]; - break; + for_each_fl_rcu(state->bucket, fl) { + if (net_eq(fl->fl_net, net)) + goto out; } } + fl = NULL; +out: return fl; } static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flowlabel *fl) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); + struct net *net = seq_file_net(seq); - fl = fl->next; - while (!fl) { - if (++state->bucket <= FL_HASH_MASK) - fl = fl_ht[state->bucket]; + for_each_fl_continue_rcu(fl) { + if (net_eq(fl->fl_net, net)) + goto out; } + +try_again: + if (++state->bucket <= FL_HASH_MASK) { + for_each_fl_rcu(state->bucket, fl) { + if (net_eq(fl->fl_net, net)) + goto out; + } + goto try_again; + } + fl = NULL; + +out: return fl; } @@ -604,8 +743,9 @@ static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos) } static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) { - read_lock_bh(&ip6_fl_lock); + rcu_read_lock_bh(); return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -622,40 +762,38 @@ static void *ip6fl_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void ip6fl_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { - read_unlock_bh(&ip6_fl_lock); + rcu_read_unlock_bh(); } -static void ip6fl_fl_seq_show(struct seq_file *seq, struct ip6_flowlabel *fl) +static int ip6fl_seq_show(struct seq_file *seq, void *v) { - while(fl) { + struct ip6fl_iter_state *state = ip6fl_seq_private(seq); + if (v == SEQ_START_TOKEN) + seq_printf(seq, "%-5s %-1s %-6s %-6s %-6s %-8s %-32s %s\n", + "Label", "S", "Owner", "Users", "Linger", "Expires", "Dst", "Opt"); + else { + struct ip6_flowlabel *fl = v; seq_printf(seq, - "%05X %-1d %-6d %-6d %-6ld %-8ld " - "%02x%02x%02x%02x%02x%02x%02x%02x " - "%-4d\n", - (unsigned)ntohl(fl->label), + "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", + (unsigned int)ntohl(fl->label), fl->share, - (unsigned)fl->owner, + ((fl->share == IPV6_FL_S_PROCESS) ? + pid_nr_ns(fl->owner.pid, state->pid_ns) : + ((fl->share == IPV6_FL_S_USER) ? + from_kuid_munged(seq_user_ns(seq), fl->owner.uid) : + 0)), atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, - NIP6(fl->dst), + &fl->dst, fl->opt ? fl->opt->opt_nflen : 0); - fl = fl->next; } -} - -static int ip6fl_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Label S Owner Users Linger Expires " - "Dst Opt\n"); - else - ip6fl_fl_seq_show(seq, v); return 0; } -static struct seq_operations ip6fl_seq_ops = { +static const struct seq_operations ip6fl_seq_ops = { .start = ip6fl_seq_start, .next = ip6fl_seq_next, .stop = ip6fl_seq_stop, @@ -665,47 +803,78 @@ static struct seq_operations ip6fl_seq_ops = { static int ip6fl_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; - int rc = -ENOMEM; - struct ip6fl_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct ip6fl_iter_state *state; + int err; - if (!s) - goto out; + err = seq_open_net(inode, file, &ip6fl_seq_ops, + sizeof(struct ip6fl_iter_state)); - rc = seq_open(file, &ip6fl_seq_ops); - if (rc) - goto out_kfree; + if (!err) { + seq = file->private_data; + state = ip6fl_seq_private(seq); + rcu_read_lock(); + state->pid_ns = get_pid_ns(task_active_pid_ns(current)); + rcu_read_unlock(); + } + return err; +} - seq = file->private_data; - seq->private = s; - memset(s, 0, sizeof(*s)); -out: - return rc; -out_kfree: - kfree(s); - goto out; +static int ip6fl_seq_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct ip6fl_iter_state *state = ip6fl_seq_private(seq); + put_pid_ns(state->pid_ns); + return seq_release_net(inode, file); } -static struct file_operations ip6fl_seq_fops = { +static const struct file_operations ip6fl_seq_fops = { .owner = THIS_MODULE, .open = ip6fl_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = ip6fl_seq_release, }; -#endif +static int __net_init ip6_flowlabel_proc_init(struct net *net) +{ + if (!proc_create("ip6_flowlabel", S_IRUGO, net->proc_net, + &ip6fl_seq_fops)) + return -ENOMEM; + return 0; +} -void ip6_flowlabel_init(void) +static void __net_exit ip6_flowlabel_proc_fini(struct net *net) { -#ifdef CONFIG_PROC_FS - proc_net_fops_create("ip6_flowlabel", S_IRUGO, &ip6fl_seq_fops); + remove_proc_entry("ip6_flowlabel", net->proc_net); +} +#else +static inline int ip6_flowlabel_proc_init(struct net *net) +{ + return 0; +} +static inline void ip6_flowlabel_proc_fini(struct net *net) +{ +} #endif + +static void __net_exit ip6_flowlabel_net_exit(struct net *net) +{ + ip6_fl_purge(net); + ip6_flowlabel_proc_fini(net); +} + +static struct pernet_operations ip6_flowlabel_net_ops = { + .init = ip6_flowlabel_proc_init, + .exit = ip6_flowlabel_net_exit, +}; + +int ip6_flowlabel_init(void) +{ + return register_pernet_subsys(&ip6_flowlabel_net_ops); } void ip6_flowlabel_cleanup(void) { del_timer(&ip6_fl_gc_timer); -#ifdef CONFIG_PROC_FS - proc_net_remove("ip6_flowlabel"); -#endif + unregister_pernet_subsys(&ip6_flowlabel_net_ops); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c new file mode 100644 index 00000000000..3873181ed85 --- /dev/null +++ b/net/ipv6/ip6_gre.c @@ -0,0 +1,1722 @@ +/* + * GRE over IPv6 protocol decoder. + * + * Authors: Dmitry Kozlov (xeb@mail.ru) + * + * 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. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/if_arp.h> +#include <linux/mroute.h> +#include <linux/init.h> +#include <linux/in6.h> +#include <linux/inetdevice.h> +#include <linux/igmp.h> +#include <linux/netfilter_ipv4.h> +#include <linux/etherdevice.h> +#include <linux/if_ether.h> +#include <linux/hash.h> +#include <linux/if_tunnel.h> +#include <linux/ip6_tunnel.h> + +#include <net/sock.h> +#include <net/ip.h> +#include <net/ip_tunnels.h> +#include <net/icmp.h> +#include <net/protocol.h> +#include <net/addrconf.h> +#include <net/arp.h> +#include <net/checksum.h> +#include <net/dsfield.h> +#include <net/inet_ecn.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/rtnetlink.h> + +#include <net/ipv6.h> +#include <net/ip6_fib.h> +#include <net/ip6_route.h> +#include <net/ip6_tunnel.h> + + +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) + +static int ip6gre_net_id __read_mostly; +struct ip6gre_net { + struct ip6_tnl __rcu *tunnels[4][HASH_SIZE]; + + struct net_device *fb_tunnel_dev; +}; + +static struct rtnl_link_ops ip6gre_link_ops __read_mostly; +static struct rtnl_link_ops ip6gre_tap_ops __read_mostly; +static int ip6gre_tunnel_init(struct net_device *dev); +static void ip6gre_tunnel_setup(struct net_device *dev); +static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t); +static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu); + +/* Tunnel hash table */ + +/* + 4 hash tables: + + 3: (remote,local) + 2: (remote,*) + 1: (*,local) + 0: (*,*) + + We require exact key match i.e. if a key is present in packet + it will match only tunnel with the same key; if it is not present, + it will match only keyless tunnel. + + All keysless packets, if not matched configured keyless tunnels + will match fallback tunnel. + */ + +#define HASH_KEY(key) (((__force u32)key^((__force u32)key>>4))&(HASH_SIZE - 1)) +static u32 HASH_ADDR(const struct in6_addr *addr) +{ + u32 hash = ipv6_addr_hash(addr); + + return hash_32(hash, HASH_SIZE_SHIFT); +} + +#define tunnels_r_l tunnels[3] +#define tunnels_r tunnels[2] +#define tunnels_l tunnels[1] +#define tunnels_wc tunnels[0] + +/* Given src, dst and key, find appropriate for input tunnel. */ + +static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, + const struct in6_addr *remote, const struct in6_addr *local, + __be32 key, __be16 gre_proto) +{ + struct net *net = dev_net(dev); + int link = dev->ifindex; + unsigned int h0 = HASH_ADDR(remote); + unsigned int h1 = HASH_KEY(key); + struct ip6_tnl *t, *cand = NULL; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + int dev_type = (gre_proto == htons(ETH_P_TEB)) ? + ARPHRD_ETHER : ARPHRD_IP6GRE; + int score, cand_score = 4; + + for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { + if (!ipv6_addr_equal(local, &t->parms.laddr) || + !ipv6_addr_equal(remote, &t->parms.raddr) || + key != t->parms.i_key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { + if (!ipv6_addr_equal(remote, &t->parms.raddr) || + key != t->parms.i_key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { + if ((!ipv6_addr_equal(local, &t->parms.laddr) && + (!ipv6_addr_equal(local, &t->parms.raddr) || + !ipv6_addr_is_multicast(local))) || + key != t->parms.i_key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { + if (t->parms.i_key != key || + !(t->dev->flags & IFF_UP)) + continue; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + continue; + + score = 0; + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) + return t; + + if (score < cand_score) { + cand = t; + cand_score = score; + } + } + + if (cand != NULL) + return cand; + + dev = ign->fb_tunnel_dev; + if (dev->flags & IFF_UP) + return netdev_priv(dev); + + return NULL; +} + +static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign, + const struct __ip6_tnl_parm *p) +{ + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + unsigned int h = HASH_KEY(p->i_key); + int prio = 0; + + if (!ipv6_addr_any(local)) + prio |= 1; + if (!ipv6_addr_any(remote) && !ipv6_addr_is_multicast(remote)) { + prio |= 2; + h ^= HASH_ADDR(remote); + } + + return &ign->tunnels[prio][h]; +} + +static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign, + const struct ip6_tnl *t) +{ + return __ip6gre_bucket(ign, &t->parms); +} + +static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t); + + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = ip6gre_bucket(ign, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); + break; + } + } +} + +static struct ip6_tnl *ip6gre_tunnel_find(struct net *net, + const struct __ip6_tnl_parm *parms, + int type) +{ + const struct in6_addr *remote = &parms->raddr; + const struct in6_addr *local = &parms->laddr; + __be32 key = parms->i_key; + int link = parms->link; + struct ip6_tnl *t; + struct ip6_tnl __rcu **tp; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + for (tp = __ip6gre_bucket(ign, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) + if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_equal(remote, &t->parms.raddr) && + key == t->parms.i_key && + link == t->parms.link && + type == t->dev->type) + break; + + return t; +} + +static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, + const struct __ip6_tnl_parm *parms, int create) +{ + struct ip6_tnl *t, *nt; + struct net_device *dev; + char name[IFNAMSIZ]; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + t = ip6gre_tunnel_find(net, parms, ARPHRD_IP6GRE); + if (t || !create) + return t; + + if (parms->name[0]) + strlcpy(name, parms->name, IFNAMSIZ); + else + strcpy(name, "ip6gre%d"); + + dev = alloc_netdev(sizeof(*t), name, ip6gre_tunnel_setup); + if (!dev) + return NULL; + + dev_net_set(dev, net); + + nt = netdev_priv(dev); + nt->parms = *parms; + dev->rtnl_link_ops = &ip6gre_link_ops; + + nt->dev = dev; + nt->net = dev_net(dev); + ip6gre_tnl_link_config(nt, 1); + + if (register_netdevice(dev) < 0) + goto failed_free; + + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + + dev_hold(dev); + ip6gre_tunnel_link(ign, nt); + return nt; + +failed_free: + free_netdev(dev); + return NULL; +} + +static void ip6gre_tunnel_uninit(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); + + ip6gre_tunnel_unlink(ign, t); + dev_put(dev); +} + + +static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; + __be16 *p = (__be16 *)(skb->data + offset); + int grehlen = offset + 4; + struct ip6_tnl *t; + __be16 flags; + + flags = p[0]; + if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) { + if (flags&(GRE_VERSION|GRE_ROUTING)) + return; + if (flags&GRE_KEY) { + grehlen += 4; + if (flags&GRE_CSUM) + grehlen += 4; + } + } + + /* If only 8 bytes returned, keyed message will be dropped here */ + if (!pskb_may_pull(skb, grehlen)) + return; + ipv6h = (const struct ipv6hdr *)skb->data; + p = (__be16 *)(skb->data + offset); + + t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, + flags & GRE_KEY ? + *(((__be32 *)p) + (grehlen / 4) - 1) : 0, + p[1]); + if (t == NULL) + return; + + switch (type) { + __u32 teli; + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 mtu; + case ICMPV6_DEST_UNREACH: + net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); + break; + case ICMPV6_TIME_EXCEED: + if (code == ICMPV6_EXC_HOPLIMIT) { + net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); + } + break; + case ICMPV6_PARAMPROB: + teli = 0; + if (code == ICMPV6_HDR_FIELD) + teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); + + if (teli && teli == info - 2) { + tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; + if (tel->encap_limit == 0) { + net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); + } + } else { + net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); + } + break; + case ICMPV6_PKT_TOOBIG: + mtu = info - offset; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + t->dev->mtu = mtu; + break; + } + + if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO)) + t->err_count++; + else + t->err_count = 1; + t->err_time = jiffies; +} + +static int ip6gre_rcv(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + u8 *h; + __be16 flags; + __sum16 csum = 0; + __be32 key = 0; + u32 seqno = 0; + struct ip6_tnl *tunnel; + int offset = 4; + __be16 gre_proto; + int err; + + if (!pskb_may_pull(skb, sizeof(struct in6_addr))) + goto drop; + + ipv6h = ipv6_hdr(skb); + h = skb->data; + flags = *(__be16 *)h; + + if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) { + /* - Version must be 0. + - We do not support routing headers. + */ + if (flags&(GRE_VERSION|GRE_ROUTING)) + goto drop; + + if (flags&GRE_CSUM) { + csum = skb_checksum_simple_validate(skb); + offset += 4; + } + if (flags&GRE_KEY) { + key = *(__be32 *)(h + offset); + offset += 4; + } + if (flags&GRE_SEQ) { + seqno = ntohl(*(__be32 *)(h + offset)); + offset += 4; + } + } + + gre_proto = *(__be16 *)(h + 2); + + tunnel = ip6gre_tunnel_lookup(skb->dev, + &ipv6h->saddr, &ipv6h->daddr, key, + gre_proto); + if (tunnel) { + struct pcpu_sw_netstats *tstats; + + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + if (!ip6_tnl_rcv_ctl(tunnel, &ipv6h->daddr, &ipv6h->saddr)) { + tunnel->dev->stats.rx_dropped++; + goto drop; + } + + skb->protocol = gre_proto; + /* WCCP version 1 and 2 protocol decoding. + * - Change protocol to IP + * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header + */ + if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) { + skb->protocol = htons(ETH_P_IP); + if ((*(h + offset) & 0xF0) != 0x40) + offset += 4; + } + + skb->mac_header = skb->network_header; + __pskb_pull(skb, offset); + skb_postpull_rcsum(skb, skb_transport_header(skb), offset); + + if (((flags&GRE_CSUM) && csum) || + (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) { + tunnel->dev->stats.rx_crc_errors++; + tunnel->dev->stats.rx_errors++; + goto drop; + } + if (tunnel->parms.i_flags&GRE_SEQ) { + if (!(flags&GRE_SEQ) || + (tunnel->i_seqno && + (s32)(seqno - tunnel->i_seqno) < 0)) { + tunnel->dev->stats.rx_fifo_errors++; + tunnel->dev->stats.rx_errors++; + goto drop; + } + tunnel->i_seqno = seqno + 1; + } + + /* Warning: All skb pointers will be invalidated! */ + if (tunnel->dev->type == ARPHRD_ETHER) { + if (!pskb_may_pull(skb, ETH_HLEN)) { + tunnel->dev->stats.rx_length_errors++; + tunnel->dev->stats.rx_errors++; + goto drop; + } + + ipv6h = ipv6_hdr(skb); + skb->protocol = eth_type_trans(skb, tunnel->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + } + + __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); + + skb_reset_network_header(skb); + + err = IP6_ECN_decapsulate(ipv6h, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", + &ipv6h->saddr, + ipv6_get_dsfield(ipv6h)); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto drop; + } + } + + tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + netif_rx(skb); + + return 0; + } + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + +drop: + kfree_skb(skb); + return 0; +} + +struct ipv6_tel_txoption { + struct ipv6_txoptions ops; + __u8 dst_opt[8]; +}; + +static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) +{ + memset(opt, 0, sizeof(struct ipv6_tel_txoption)); + + opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; + opt->dst_opt[3] = 1; + opt->dst_opt[4] = encap_limit; + opt->dst_opt[5] = IPV6_TLV_PADN; + opt->dst_opt[6] = 1; + + opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt; + opt->ops.opt_nflen = 8; +} + +static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, + struct net_device *dev, + __u8 dsfield, + struct flowi6 *fl6, + int encap_limit, + __u32 *pmtu) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct net *net = tunnel->net; + struct net_device *tdev; /* Device to other host */ + struct ipv6hdr *ipv6h; /* Our new IP header */ + unsigned int max_headroom = 0; /* The extra header space needed */ + int gre_hlen; + struct ipv6_tel_txoption opt; + int mtu; + struct dst_entry *dst = NULL, *ndst = NULL; + struct net_device_stats *stats = &tunnel->dev->stats; + int err = -1; + u8 proto; + struct sk_buff *new_skb; + + if (dev->type == ARPHRD_ETHER) + IPCB(skb)->flags = 0; + + if (dev->header_ops && dev->type == ARPHRD_IP6GRE) { + gre_hlen = 0; + ipv6h = (struct ipv6hdr *)skb->data; + fl6->daddr = ipv6h->daddr; + } else { + gre_hlen = tunnel->hlen; + fl6->daddr = tunnel->parms.raddr; + } + + if (!fl6->flowi6_mark) + dst = ip6_tnl_dst_check(tunnel); + + if (!dst) { + ndst = ip6_route_output(net, NULL, fl6); + + if (ndst->error) + goto tx_err_link_failure; + 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; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + tunnel->parms.name); + goto tx_err_dst_release; + } + + mtu = dst_mtu(dst) - sizeof(*ipv6h); + if (encap_limit >= 0) { + max_headroom += 8; + mtu -= 8; + } + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + if (skb->len > mtu) { + *pmtu = mtu; + err = -EMSGSIZE; + goto tx_err_dst_release; + } + + if (tunnel->err_count > 0) { + if (time_before(jiffies, + tunnel->err_time + IP6TUNNEL_ERR_TIMEO)) { + tunnel->err_count--; + + dst_link_failure(skb); + } else + tunnel->err_count = 0; + } + + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); + + max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + + if (skb_headroom(skb) < max_headroom || skb_shared(skb) || + (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { + new_skb = skb_realloc_headroom(skb, max_headroom); + if (max_headroom > dev->needed_headroom) + dev->needed_headroom = max_headroom; + if (!new_skb) + goto tx_err_dst_release; + + if (skb->sk) + skb_set_owner_w(new_skb, skb->sk); + consume_skb(skb); + skb = new_skb; + } + + if (fl6->flowi6_mark) { + skb_dst_set(skb, dst); + ndst = NULL; + } else { + skb_dst_set_noref(skb, dst); + } + + proto = NEXTHDR_GRE; + if (encap_limit >= 0) { + init_tel_txopt(&opt, encap_limit); + ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); + } + + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + + skb_push(skb, gre_hlen); + skb_reset_network_header(skb); + skb_set_transport_header(skb, sizeof(*ipv6h)); + + /* + * Push down and install the IP header. + */ + ipv6h = ipv6_hdr(skb); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); + ipv6h->hop_limit = tunnel->parms.hop_limit; + ipv6h->nexthdr = proto; + ipv6h->saddr = fl6->saddr; + ipv6h->daddr = fl6->daddr; + + ((__be16 *)(ipv6h + 1))[0] = tunnel->parms.o_flags; + ((__be16 *)(ipv6h + 1))[1] = (dev->type == ARPHRD_ETHER) ? + htons(ETH_P_TEB) : skb->protocol; + + if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) { + __be32 *ptr = (__be32 *)(((u8 *)ipv6h) + tunnel->hlen - 4); + + if (tunnel->parms.o_flags&GRE_SEQ) { + ++tunnel->o_seqno; + *ptr = htonl(tunnel->o_seqno); + ptr--; + } + if (tunnel->parms.o_flags&GRE_KEY) { + *ptr = tunnel->parms.o_key; + ptr--; + } + if (tunnel->parms.o_flags&GRE_CSUM) { + *ptr = 0; + *(__sum16 *)ptr = ip_compute_csum((void *)(ipv6h+1), + skb->len - sizeof(struct ipv6hdr)); + } + } + + ip6tunnel_xmit(skb, dev); + if (ndst) + ip6_tnl_dst_store(tunnel, ndst); + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(ndst); + return err; +} + +static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + const struct iphdr *iph = ip_hdr(skb); + int encap_limit = -1; + struct flowi6 fl6; + __u8 dsfield; + __u32 mtu; + int err; + + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; + + dsfield = ipv4_get_dsfield(iph); + + 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 = ip6gre_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); + if (err != 0) { + /* XXX: send ICMP error even if DF is not set. */ + if (err == -EMSGSIZE) + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + return -1; + } + + return 0; +} + +static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int encap_limit = -1; + __u16 offset; + struct flowi6 fl6; + __u8 dsfield; + __u32 mtu; + int err; + + if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr)) + return -1; + + offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + if (offset > 0) { + struct ipv6_tlv_tnl_enc_lim *tel; + tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; + if (tel->encap_limit == 0) { + icmpv6_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); + return -1; + } + encap_limit = tel->encap_limit - 1; + } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; + + dsfield = ipv6_get_dsfield(ipv6h); + 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) + fl6.flowlabel |= ip6_flowlabel(ipv6h); + if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) + fl6.flowi6_mark = skb->mark; + + err = ip6gre_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); + if (err != 0) { + if (err == -EMSGSIZE) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + return -1; + } + + return 0; +} + +/** + * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own + * @t: the outgoing tunnel device + * @hdr: IPv6 header from the incoming packet + * + * Description: + * Avoid trivial tunneling loop by checking that tunnel exit-point + * doesn't match source of incoming packet. + * + * Return: + * 1 if conflict, + * 0 else + **/ + +static inline bool ip6gre_tnl_addr_conflict(const struct ip6_tnl *t, + const struct ipv6hdr *hdr) +{ + return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); +} + +static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + int encap_limit = -1; + struct flowi6 fl6; + __u32 mtu; + int err; + + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = skb->protocol; + + err = ip6gre_xmit2(skb, dev, 0, &fl6, encap_limit, &mtu); + + return err; +} + +static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + int ret; + + if (!ip6_tnl_xmit_ctl(t)) + goto tx_err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + ret = ip6gre_xmit_ipv4(skb, dev); + break; + case htons(ETH_P_IPV6): + ret = ip6gre_xmit_ipv6(skb, dev); + break; + default: + ret = ip6gre_xmit_other(skb, dev); + break; + } + + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) +{ + struct net_device *dev = t->dev; + struct __ip6_tnl_parm *p = &t->parms; + struct flowi6 *fl6 = &t->fl.u.ip6; + int addend = sizeof(struct ipv6hdr) + 4; + + if (dev->type != ARPHRD_ETHER) { + memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); + } + + /* Set up flowi template */ + fl6->saddr = p->laddr; + fl6->daddr = p->raddr; + fl6->flowi6_oif = p->link; + fl6->flowlabel = 0; + + if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) + fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; + if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) + fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; + + p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); + p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); + + if (p->flags&IP6_TNL_F_CAP_XMIT && + p->flags&IP6_TNL_F_CAP_RCV && dev->type != ARPHRD_ETHER) + dev->flags |= IFF_POINTOPOINT; + else + dev->flags &= ~IFF_POINTOPOINT; + + dev->iflink = p->link; + + /* Precalculate GRE options length */ + if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { + if (t->parms.o_flags&GRE_CSUM) + addend += 4; + if (t->parms.o_flags&GRE_KEY) + addend += 4; + if (t->parms.o_flags&GRE_SEQ) + addend += 4; + } + t->hlen = addend; + + if (p->flags & IP6_TNL_F_CAP_XMIT) { + int strict = (ipv6_addr_type(&p->raddr) & + (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); + + struct rt6_info *rt = rt6_lookup(t->net, + &p->raddr, &p->laddr, + p->link, strict); + + if (rt == NULL) + return; + + if (rt->dst.dev) { + dev->hard_header_len = rt->dst.dev->hard_header_len + addend; + + if (set_mtu) { + dev->mtu = rt->dst.dev->mtu - addend; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu -= 8; + + if (dev->mtu < IPV6_MIN_MTU) + dev->mtu = IPV6_MIN_MTU; + } + } + ip6_rt_put(rt); + } +} + +static int ip6gre_tnl_change(struct ip6_tnl *t, + const struct __ip6_tnl_parm *p, int set_mtu) +{ + 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; + t->parms.flowinfo = p->flowinfo; + t->parms.link = p->link; + t->parms.proto = p->proto; + t->parms.i_key = p->i_key; + t->parms.o_key = p->o_key; + t->parms.i_flags = p->i_flags; + t->parms.o_flags = p->o_flags; + ip6_tnl_dst_reset(t); + ip6gre_tnl_link_config(t, set_mtu); + return 0; +} + +static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p, + const struct ip6_tnl_parm2 *u) +{ + p->laddr = u->laddr; + p->raddr = u->raddr; + p->flags = u->flags; + p->hop_limit = u->hop_limit; + p->encap_limit = u->encap_limit; + p->flowinfo = u->flowinfo; + p->link = u->link; + p->i_key = u->i_key; + p->o_key = u->o_key; + p->i_flags = u->i_flags; + p->o_flags = u->o_flags; + memcpy(p->name, u->name, sizeof(u->name)); +} + +static void ip6gre_tnl_parm_to_user(struct ip6_tnl_parm2 *u, + const struct __ip6_tnl_parm *p) +{ + u->proto = IPPROTO_GRE; + u->laddr = p->laddr; + u->raddr = p->raddr; + u->flags = p->flags; + u->hop_limit = p->hop_limit; + u->encap_limit = p->encap_limit; + u->flowinfo = p->flowinfo; + u->link = p->link; + u->i_key = p->i_key; + u->o_key = p->o_key; + u->i_flags = p->i_flags; + u->o_flags = p->o_flags; + memcpy(u->name, p->name, sizeof(u->name)); +} + +static int ip6gre_tunnel_ioctl(struct net_device *dev, + struct ifreq *ifr, int cmd) +{ + int err = 0; + struct ip6_tnl_parm2 p; + struct __ip6_tnl_parm p1; + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + switch (cmd) { + case SIOCGETTUNNEL: + if (dev == ign->fb_tunnel_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + err = -EFAULT; + break; + } + ip6gre_tnl_parm_from_user(&p1, &p); + t = ip6gre_tunnel_locate(net, &p1, 0); + if (t == NULL) + t = netdev_priv(dev); + } + memset(&p, 0, sizeof(p)); + ip6gre_tnl_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + break; + + case SIOCADDTUNNEL: + case SIOCCHGTUNNEL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + goto done; + + err = -EINVAL; + if ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)) + goto done; + + if (!(p.i_flags&GRE_KEY)) + p.i_key = 0; + if (!(p.o_flags&GRE_KEY)) + p.o_key = 0; + + ip6gre_tnl_parm_from_user(&p1, &p); + t = ip6gre_tunnel_locate(net, &p1, cmd == SIOCADDTUNNEL); + + if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else { + t = netdev_priv(dev); + + ip6gre_tunnel_unlink(ign, t); + synchronize_net(); + ip6gre_tnl_change(t, &p1, 1); + ip6gre_tunnel_link(ign, t); + netdev_state_change(dev); + } + } + + if (t) { + err = 0; + + memset(&p, 0, sizeof(p)); + ip6gre_tnl_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + break; + + case SIOCDELTUNNEL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + goto done; + + if (dev == ign->fb_tunnel_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + goto done; + err = -ENOENT; + ip6gre_tnl_parm_from_user(&p1, &p); + t = ip6gre_tunnel_locate(net, &p1, 0); + if (t == NULL) + goto done; + err = -EPERM; + if (t == netdev_priv(ign->fb_tunnel_dev)) + goto done; + dev = t->dev; + } + unregister_netdevice(dev); + err = 0; + break; + + default: + err = -EINVAL; + } + +done: + return err; +} + +static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < 68 || + new_mtu > 0xFFF8 - dev->hard_header_len) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + const void *daddr, const void *saddr, unsigned int len) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); + __be16 *p = (__be16 *)(ipv6h+1); + + ip6_flow_hdr(ipv6h, 0, t->fl.u.ip6.flowlabel); + ipv6h->hop_limit = t->parms.hop_limit; + ipv6h->nexthdr = NEXTHDR_GRE; + ipv6h->saddr = t->parms.laddr; + ipv6h->daddr = t->parms.raddr; + + p[0] = t->parms.o_flags; + p[1] = htons(type); + + /* + * Set the source hardware address. + */ + + if (saddr) + memcpy(&ipv6h->saddr, saddr, sizeof(struct in6_addr)); + if (daddr) + memcpy(&ipv6h->daddr, daddr, sizeof(struct in6_addr)); + if (!ipv6_addr_any(&ipv6h->daddr)) + return t->hlen; + + return -t->hlen; +} + +static const struct header_ops ip6gre_header_ops = { + .create = ip6gre_header, +}; + +static const struct net_device_ops ip6gre_netdev_ops = { + .ndo_init = ip6gre_tunnel_init, + .ndo_uninit = ip6gre_tunnel_uninit, + .ndo_start_xmit = ip6gre_tunnel_xmit, + .ndo_do_ioctl = ip6gre_tunnel_ioctl, + .ndo_change_mtu = ip6gre_tunnel_change_mtu, + .ndo_get_stats64 = ip_tunnel_get_stats64, +}; + +static void ip6gre_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static void ip6gre_tunnel_setup(struct net_device *dev) +{ + struct ip6_tnl *t; + + dev->netdev_ops = &ip6gre_netdev_ops; + dev->destructor = ip6gre_dev_free; + + dev->type = ARPHRD_IP6GRE; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr) + 4; + dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr) - 4; + t = netdev_priv(dev); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu -= 8; + dev->flags |= IFF_NOARP; + dev->iflink = 0; + dev->addr_len = sizeof(struct in6_addr); + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; +} + +static int ip6gre_tunnel_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel; + int i; + + tunnel = netdev_priv(dev); + + tunnel->dev = dev; + tunnel->net = dev_net(dev); + strcpy(tunnel->parms.name, dev->name); + + memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); + + if (ipv6_addr_any(&tunnel->parms.raddr)) + dev->header_ops = &ip6gre_header_ops; + + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + for_each_possible_cpu(i) { + struct pcpu_sw_netstats *ip6gre_tunnel_stats; + ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); + u64_stats_init(&ip6gre_tunnel_stats->syncp); + } + + + return 0; +} + +static void ip6gre_fb_tunnel_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + + tunnel->dev = dev; + tunnel->net = dev_net(dev); + strcpy(tunnel->parms.name, dev->name); + + tunnel->hlen = sizeof(struct ipv6hdr) + 4; + + dev_hold(dev); +} + + +static struct inet6_protocol ip6gre_protocol __read_mostly = { + .handler = ip6gre_rcv, + .err_handler = ip6gre_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) +{ + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct net_device *dev, *aux; + int prio; + + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &ip6gre_link_ops || + dev->rtnl_link_ops == &ip6gre_tap_ops) + unregister_netdevice_queue(dev, head); + + for (prio = 0; prio < 4; prio++) { + int h; + for (h = 0; h < HASH_SIZE; h++) { + struct ip6_tnl *t; + + t = rtnl_dereference(ign->tunnels[prio][h]); + + while (t != NULL) { + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, + head); + t = rtnl_dereference(t->next); + } + } + } +} + +static int __net_init ip6gre_init_net(struct net *net) +{ + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + int err; + + ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", + ip6gre_tunnel_setup); + if (!ign->fb_tunnel_dev) { + err = -ENOMEM; + goto err_alloc_dev; + } + dev_net_set(ign->fb_tunnel_dev, net); + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + + + ip6gre_fb_tunnel_init(ign->fb_tunnel_dev); + ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops; + + err = register_netdev(ign->fb_tunnel_dev); + if (err) + goto err_reg_dev; + + rcu_assign_pointer(ign->tunnels_wc[0], + netdev_priv(ign->fb_tunnel_dev)); + return 0; + +err_reg_dev: + ip6gre_dev_free(ign->fb_tunnel_dev); +err_alloc_dev: + return err; +} + +static void __net_exit ip6gre_exit_net(struct net *net) +{ + LIST_HEAD(list); + + rtnl_lock(); + ip6gre_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations ip6gre_net_ops = { + .init = ip6gre_init_net, + .exit = ip6gre_exit_net, + .id = &ip6gre_net_id, + .size = sizeof(struct ip6gre_net), +}; + +static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + __be16 flags; + + if (!data) + return 0; + + flags = 0; + if (data[IFLA_GRE_IFLAGS]) + flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); + if (data[IFLA_GRE_OFLAGS]) + flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); + if (flags & (GRE_VERSION|GRE_ROUTING)) + return -EINVAL; + + return 0; +} + +static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + struct in6_addr daddr; + + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } + + if (!data) + goto out; + + if (data[IFLA_GRE_REMOTE]) { + nla_memcpy(&daddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr)); + if (ipv6_addr_any(&daddr)) + return -EINVAL; + } + +out: + return ip6gre_tunnel_validate(tb, data); +} + + +static void ip6gre_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_GRE_LINK]) + parms->link = nla_get_u32(data[IFLA_GRE_LINK]); + + if (data[IFLA_GRE_IFLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]); + + if (data[IFLA_GRE_OFLAGS]) + parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]); + + if (data[IFLA_GRE_IKEY]) + parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); + + if (data[IFLA_GRE_OKEY]) + parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); + + if (data[IFLA_GRE_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_GRE_LOCAL], sizeof(struct in6_addr)); + + if (data[IFLA_GRE_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_GRE_REMOTE], sizeof(struct in6_addr)); + + if (data[IFLA_GRE_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_GRE_TTL]); + + if (data[IFLA_GRE_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_GRE_ENCAP_LIMIT]); + + if (data[IFLA_GRE_FLOWINFO]) + parms->flowinfo = nla_get_u32(data[IFLA_GRE_FLOWINFO]); + + if (data[IFLA_GRE_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]); +} + +static int ip6gre_tap_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel; + + tunnel = netdev_priv(dev); + + tunnel->dev = dev; + tunnel->net = dev_net(dev); + strcpy(tunnel->parms.name, dev->name); + + ip6gre_tnl_link_config(tunnel, 1); + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; +} + +static const struct net_device_ops ip6gre_tap_netdev_ops = { + .ndo_init = ip6gre_tap_init, + .ndo_uninit = ip6gre_tunnel_uninit, + .ndo_start_xmit = ip6gre_tunnel_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = ip6gre_tunnel_change_mtu, + .ndo_get_stats64 = ip_tunnel_get_stats64, +}; + +static void ip6gre_tap_setup(struct net_device *dev) +{ + + ether_setup(dev); + + dev->netdev_ops = &ip6gre_tap_netdev_ops; + dev->destructor = ip6gre_dev_free; + + dev->iflink = 0; + dev->features |= NETIF_F_NETNS_LOCAL; +} + +static int ip6gre_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct ip6_tnl *nt; + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + int err; + + nt = netdev_priv(dev); + ip6gre_netlink_parms(data, &nt->parms); + + if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) + return -EEXIST; + + if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) + eth_hw_addr_random(dev); + + nt->dev = dev; + nt->net = dev_net(dev); + ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); + + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + + err = register_netdevice(dev); + if (err) + goto out; + + dev_hold(dev); + ip6gre_tunnel_link(ign, nt); + +out: + return err; +} + +static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t, *nt = netdev_priv(dev); + struct net *net = nt->net; + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct __ip6_tnl_parm p; + + if (dev == ign->fb_tunnel_dev) + return -EINVAL; + + ip6gre_netlink_parms(data, &p); + + t = ip6gre_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else { + t = nt; + + ip6gre_tunnel_unlink(ign, t); + ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6gre_tunnel_link(ign, t); + netdev_state_change(dev); + } + + return 0; +} + +static void ip6gre_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + if (dev != ign->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + +static size_t ip6gre_get_size(const struct net_device *dev) +{ + return + /* IFLA_GRE_LINK */ + nla_total_size(4) + + /* IFLA_GRE_IFLAGS */ + nla_total_size(2) + + /* IFLA_GRE_OFLAGS */ + nla_total_size(2) + + /* IFLA_GRE_IKEY */ + nla_total_size(4) + + /* IFLA_GRE_OKEY */ + nla_total_size(4) + + /* IFLA_GRE_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_GRE_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_GRE_TTL */ + nla_total_size(1) + + /* IFLA_GRE_TOS */ + nla_total_size(1) + + /* IFLA_GRE_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_GRE_FLOWINFO */ + nla_total_size(4) + + /* IFLA_GRE_FLAGS */ + nla_total_size(4) + + 0; +} + +static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct __ip6_tnl_parm *p = &t->parms; + + if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || + nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) || + nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || + nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || + nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || + nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || + /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ + nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || + nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || + nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { + [IFLA_GRE_LINK] = { .type = NLA_U32 }, + [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, + [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, + [IFLA_GRE_IKEY] = { .type = NLA_U32 }, + [IFLA_GRE_OKEY] = { .type = NLA_U32 }, + [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_TTL] = { .type = NLA_U8 }, + [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_GRE_FLAGS] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { + .kind = "ip6gre", + .maxtype = IFLA_GRE_MAX, + .policy = ip6gre_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6gre_tunnel_setup, + .validate = ip6gre_tunnel_validate, + .newlink = ip6gre_newlink, + .changelink = ip6gre_changelink, + .dellink = ip6gre_dellink, + .get_size = ip6gre_get_size, + .fill_info = ip6gre_fill_info, +}; + +static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = { + .kind = "ip6gretap", + .maxtype = IFLA_GRE_MAX, + .policy = ip6gre_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6gre_tap_setup, + .validate = ip6gre_tap_validate, + .newlink = ip6gre_newlink, + .changelink = ip6gre_changelink, + .get_size = ip6gre_get_size, + .fill_info = ip6gre_fill_info, +}; + +/* + * And now the modules code and kernel interface. + */ + +static int __init ip6gre_init(void) +{ + int err; + + pr_info("GRE over IPv6 tunneling driver\n"); + + err = register_pernet_device(&ip6gre_net_ops); + if (err < 0) + return err; + + err = inet6_add_protocol(&ip6gre_protocol, IPPROTO_GRE); + if (err < 0) { + pr_info("%s: can't add protocol\n", __func__); + goto add_proto_failed; + } + + err = rtnl_link_register(&ip6gre_link_ops); + if (err < 0) + goto rtnl_link_failed; + + err = rtnl_link_register(&ip6gre_tap_ops); + if (err < 0) + goto tap_ops_failed; + +out: + return err; + +tap_ops_failed: + rtnl_link_unregister(&ip6gre_link_ops); +rtnl_link_failed: + inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE); +add_proto_failed: + unregister_pernet_device(&ip6gre_net_ops); + goto out; +} + +static void __exit ip6gre_fini(void) +{ + rtnl_link_unregister(&ip6gre_tap_ops); + rtnl_link_unregister(&ip6gre_link_ops); + inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE); + unregister_pernet_device(&ip6gre_net_ops); +} + +module_init(ip6gre_init); +module_exit(ip6gre_fini); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); +MODULE_DESCRIPTION("GRE over IPv6 tunneling device"); +MODULE_ALIAS_RTNL_LINK("ip6gre"); +MODULE_ALIAS_NETDEV("ip6gre0"); diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c new file mode 100644 index 00000000000..4578e23834f --- /dev/null +++ b/net/ipv6/ip6_icmp.c @@ -0,0 +1,47 @@ +#include <linux/export.h> +#include <linux/icmpv6.h> +#include <linux/mutex.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> + +#include <net/ipv6.h> + +#if IS_ENABLED(CONFIG_IPV6) + +static ip6_icmp_send_t __rcu *ip6_icmp_send; + +int inet6_register_icmp_sender(ip6_icmp_send_t *fn) +{ + return (cmpxchg((ip6_icmp_send_t **)&ip6_icmp_send, NULL, fn) == NULL) ? + 0 : -EBUSY; +} +EXPORT_SYMBOL(inet6_register_icmp_sender); + +int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) +{ + int ret; + + ret = (cmpxchg((ip6_icmp_send_t **)&ip6_icmp_send, fn, NULL) == fn) ? + 0 : -EINVAL; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet6_unregister_icmp_sender); + +void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + ip6_icmp_send_t *send; + + rcu_read_lock(); + send = rcu_dereference(ip6_icmp_send); + + if (!send) + goto out; + send(skb, type, code, info); +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(icmpv6_send); +#endif diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 6e348042693..51d54dc376f 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -1,13 +1,11 @@ /* * IPv6 input - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Ian P. Morris <I.P.Morris@soton.ac.uk> * - * $Id: ip6_input.c,v 1.19 2000/12/13 18:31:50 davem Exp $ - * * Based in linux/net/ipv4/ip_input.c * * This program is free software; you can redistribute it and/or @@ -25,11 +23,12 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> -#include <linux/sched.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/icmpv6.h> +#include <linux/mroute6.h> +#include <linux/slab.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> @@ -45,12 +44,19 @@ #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/xfrm.h> +#include <net/inet_ecn.h> - -static inline int ip6_rcv_finish( struct sk_buff *skb) +int ip6_rcv_finish(struct sk_buff *skb) { - if (skb->dst == NULL) + if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { + const struct inet6_protocol *ipprot; + + ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); + if (ipprot && ipprot->early_demux) + ipprot->early_demux(skb); + } + if (!skb_dst(skb)) ip6_route_input(skb); return dst_input(skb); @@ -58,76 +64,133 @@ static inline int ip6_rcv_finish( struct sk_buff *skb) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; u32 pkt_len; + struct inet6_dev *idev; + struct net *net = dev_net(skb->dev); - if (skb->pkt_type == PACKET_OTHERHOST) - goto drop; + if (skb->pkt_type == PACKET_OTHERHOST) { + kfree_skb(skb); + return NET_RX_DROP; + } - IP6_INC_STATS_BH(IPSTATS_MIB_INRECEIVES); + rcu_read_lock(); + + idev = __in6_dev_get(skb->dev); - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { - IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS); - goto out; + IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_IN, skb->len); + + if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || + !idev || unlikely(idev->cnf.disable_ipv6)) { + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); + goto drop; } + memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); + /* * Store incoming device index. When the packet will * be queued, we cannot refer to skb->dev anymore. * * BTW, when we send a packet for our own local address on a * non-loopback interface (e.g. ethX), it is being delivered - * via the loopback interface (lo) here; skb->dev = &loopback_dev. + * via the loopback interface (lo) here; skb->dev = loopback_dev. * It, however, should be considered as if it is being * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ - IP6CB(skb)->iif = skb->dst ? ((struct rt6_info *)skb->dst)->rt6i_idev->dev->ifindex : dev->ifindex; + IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; - if (skb->len < sizeof(struct ipv6hdr)) + if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - goto drop; - } - - hdr = skb->nh.ipv6h; + hdr = ipv6_hdr(skb); if (hdr->version != 6) goto err; + IP6_ADD_STATS_BH(dev_net(dev), idev, + IPSTATS_MIB_NOECTPKTS + + (ipv6_get_dsfield(hdr) & INET_ECN_MASK), + max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); + /* + * RFC4291 2.5.3 + * A packet received on an interface with a destination address + * of loopback must be dropped. + */ + if (!(dev->flags & IFF_LOOPBACK) && + ipv6_addr_loopback(&hdr->daddr)) + goto err; + + /* RFC4291 Errata ID: 3480 + * Interface-Local scope spans only a single interface on a + * node and is useful only for loopback transmission of + * multicast. Packets with interface-local scope received + * from another node must be discarded. + */ + if (!(skb->pkt_type == PACKET_LOOPBACK || + dev->flags & IFF_LOOPBACK) && + ipv6_addr_is_multicast(&hdr->daddr) && + IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1) + goto err; + + /* RFC4291 2.7 + * Nodes must not originate a packet to a multicast address whose scope + * field contains the reserved value 0; if such a packet is received, it + * must be silently dropped. + */ + if (ipv6_addr_is_multicast(&hdr->daddr) && + IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0) + 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); + pkt_len = ntohs(hdr->payload_len); /* pkt_len may be zero if Jumbo payload option is present */ if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { - if (pkt_len + sizeof(struct ipv6hdr) > skb->len) - goto truncated; + if (pkt_len + sizeof(struct ipv6hdr) > skb->len) { + IP6_INC_STATS_BH(net, + idev, IPSTATS_MIB_INTRUNCATEDPKTS); + goto drop; + } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); goto drop; } - hdr = skb->nh.ipv6h; + hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP) { - skb->h.raw = (u8*)(hdr+1); - if (ipv6_parse_hopopts(skb, offsetof(struct ipv6hdr, nexthdr)) < 0) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - return 0; + if (ipv6_parse_hopopts(skb) < 0) { + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); + rcu_read_unlock(); + return NET_RX_DROP; } - hdr = skb->nh.ipv6h; } - return NF_HOOK(PF_INET6,NF_IP6_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); -truncated: - IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS); + rcu_read_unlock(); + + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + + return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL, + ip6_rcv_finish); err: - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); drop: + rcu_read_unlock(); kfree_skb(skb); -out: - return 0; + return NET_RX_DROP; } /* @@ -135,82 +198,76 @@ out: */ -static inline int ip6_input_finish(struct sk_buff *skb) +static int ip6_input_finish(struct sk_buff *skb) { - struct inet6_protocol *ipprot; - struct sock *raw_sk; + struct net *net = dev_net(skb_dst(skb)->dev); + const struct inet6_protocol *ipprot; + struct inet6_dev *idev; unsigned int nhoff; int nexthdr; - u8 hash; - - skb->h.raw = skb->nh.raw + sizeof(struct ipv6hdr); + bool raw; /* * Parse extension headers */ - nexthdr = skb->nh.ipv6h->nexthdr; - nhoff = offsetof(struct ipv6hdr, nexthdr); - - /* Skip hop-by-hop options, they are already parsed. */ - if (nexthdr == NEXTHDR_HOP) { - nhoff = sizeof(struct ipv6hdr); - nexthdr = skb->h.raw[0]; - skb->h.raw += (skb->h.raw[1]+1)<<3; - } - rcu_read_lock(); resubmit: - if (!pskb_pull(skb, skb->h.raw - skb->data)) + idev = ip6_dst_idev(skb_dst(skb)); + if (!pskb_pull(skb, skb_transport_offset(skb))) goto discard; - nexthdr = skb->nh.raw[nhoff]; + nhoff = IP6CB(skb)->nhoff; + nexthdr = skb_network_header(skb)[nhoff]; - raw_sk = sk_head(&raw_v6_htable[nexthdr & (MAX_INET_PROTOS - 1)]); - if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) - raw_sk = NULL; - - hash = nexthdr & (MAX_INET_PROTOS - 1); - if ((ipprot = rcu_dereference(inet6_protos[hash])) != NULL) { + raw = raw6_local_deliver(skb, nexthdr); + if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) { int ret; - + if (ipprot->flags & INET6_PROTO_FINAL) { - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr; - skb_postpull_rcsum(skb, skb->nh.raw, - skb->h.raw - skb->nh.raw); - hdr = skb->nh.ipv6h; + /* Free reference early: we don't need it any more, + and it may hold ip_conntrack module loaded + indefinitely. */ + nf_reset(skb); + + skb_postpull_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); + hdr = ipv6_hdr(skb); if (ipv6_addr_is_multicast(&hdr->daddr) && !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, &hdr->saddr) && - !ipv6_is_mld(skb, nexthdr)) + !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) goto discard; } if (!(ipprot->flags & INET6_PROTO_NOPOLICY) && - !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) + !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; - - ret = ipprot->handler(&skb, &nhoff); + + ret = ipprot->handler(skb); if (ret > 0) goto resubmit; else if (ret == 0) - IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS); + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS); } else { - if (!raw_sk) { + if (!raw) { if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INUNKNOWNPROTOS); + IP6_INC_STATS_BH(net, idev, + IPSTATS_MIB_INUNKNOWNPROTOS); icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_UNK_NEXTHDR, nhoff, - skb->dev); + ICMPV6_UNK_NEXTHDR, nhoff); } - } else - IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS); - kfree_skb(skb); + kfree_skb(skb); + } else { + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS); + consume_skb(skb); + } } rcu_read_unlock(); return 0; discard: - IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); rcu_read_unlock(); kfree_skb(skb); return 0; @@ -219,52 +276,86 @@ discard: int ip6_input(struct sk_buff *skb) { - return NF_HOOK(PF_INET6,NF_IP6_LOCAL_IN, skb, skb->dev, NULL, ip6_input_finish); + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, skb, skb->dev, NULL, + ip6_input_finish); } int ip6_mc_input(struct sk_buff *skb) { - struct ipv6hdr *hdr; - int deliver; + const struct ipv6hdr *hdr; + bool deliver; - IP6_INC_STATS_BH(IPSTATS_MIB_INMCASTPKTS); + IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev), + ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, + skb->len); - hdr = skb->nh.ipv6h; - deliver = likely(!(skb->dev->flags & (IFF_PROMISC|IFF_ALLMULTI))) || - ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); + hdr = ipv6_hdr(skb); + deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); +#ifdef CONFIG_IPV6_MROUTE /* - * IPv6 multicast router mode isnt currently supported. + * IPv6 multicast router mode is now supported ;) */ -#if 0 - if (ipv6_config.multicast_route) { - int addr_type; - - addr_type = ipv6_addr_type(&hdr->daddr); - - if (!(addr_type & (IPV6_ADDR_LOOPBACK | IPV6_ADDR_LINKLOCAL))) { - struct sk_buff *skb2; - struct dst_entry *dst; - - dst = skb->dst; - - if (deliver) { - skb2 = skb_clone(skb, GFP_ATOMIC); - dst_output(skb2); - } else { - dst_output(skb); - return 0; + if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && + !(ipv6_addr_type(&hdr->daddr) & + (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && + likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { + /* + * Okay, we try to forward - split and duplicate + * packets. + */ + struct sk_buff *skb2; + struct inet6_skb_parm *opt = IP6CB(skb); + + /* Check for MLD */ + if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { + /* Check if this is a mld message */ + u8 nexthdr = hdr->nexthdr; + __be16 frag_off; + int offset; + + /* Check if the value of Router Alert + * is for MLD (0x0000). + */ + if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) { + deliver = false; + + if (!ipv6_ext_hdr(nexthdr)) { + /* BUG */ + goto out; + } + offset = ipv6_skip_exthdr(skb, sizeof(*hdr), + &nexthdr, &frag_off); + if (offset < 0) + goto out; + + if (!ipv6_is_mld(skb, nexthdr, offset)) + goto out; + + deliver = true; } + /* unknown RA - process it normally */ + } + + if (deliver) + skb2 = skb_clone(skb, GFP_ATOMIC); + else { + skb2 = skb; + skb = NULL; + } + + if (skb2) { + ip6_mr_input(skb2); } } +out: #endif - - if (likely(deliver)) { + if (likely(deliver)) ip6_input(skb); - return 0; + else { + /* discard */ + kfree_skb(skb); } - /* discard */ - kfree_skb(skb); return 0; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c new file mode 100644 index 00000000000..65eda2a8af4 --- /dev/null +++ b/net/ipv6/ip6_offload.c @@ -0,0 +1,337 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/socket.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/printk.h> + +#include <net/protocol.h> +#include <net/ipv6.h> + +#include "ip6_offload.h" + +static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) +{ + const struct net_offload *ops = NULL; + + for (;;) { + struct ipv6_opt_hdr *opth; + int len; + + if (proto != NEXTHDR_HOP) { + ops = rcu_dereference(inet6_offloads[proto]); + + if (unlikely(!ops)) + break; + + if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + + if (unlikely(!pskb_may_pull(skb, 8))) + break; + + opth = (void *)skb->data; + len = ipv6_optlen(opth); + + if (unlikely(!pskb_may_pull(skb, len))) + break; + + proto = opth->nexthdr; + __skb_pull(skb, len); + } + + return proto; +} + +static int ipv6_gso_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + const struct net_offload *ops; + int err = -EINVAL; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + err = -EPROTONOSUPPORT; + + ops = rcu_dereference(inet6_offloads[ + ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); + + if (likely(ops && ops->callbacks.gso_send_check)) { + skb_reset_transport_header(skb); + err = ops->callbacks.gso_send_check(skb); + } + +out: + return err; +} + +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; + const struct net_offload *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; + bool encap, udpfrag; + int nhoff; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_IPIP | + SKB_GSO_SIT | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | + SKB_GSO_MPLS | + SKB_GSO_TCPV6 | + 0))) + goto out; + + skb_reset_network_header(skb); + nhoff = skb_network_header(skb) - skb_mac_header(skb); + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + encap = SKB_GSO_CB(skb)->encap_level > 0; + if (encap) + features = skb->dev->hw_enc_features & netif_skb_features(skb); + SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + segs = ERR_PTR(-EPROTONOSUPPORT); + + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + + ops = rcu_dereference(inet6_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) { + skb_reset_transport_header(skb); + segs = ops->callbacks.gso_segment(skb, features); + } + + if (IS_ERR(segs)) + goto out; + + for (skb = segs; skb; skb = skb->next) { + ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); + ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); + skb->network_header = (u8 *)ipv6h - skb->head; + + if (udpfrag) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } + if (encap) + skb_reset_inner_headers(skb); + } + +out: + return segs; +} + +/* Return the total length of all the extension hdrs, following the same + * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs. + */ +static int ipv6_exthdrs_len(struct ipv6hdr *iph, + const struct net_offload **opps) +{ + struct ipv6_opt_hdr *opth = (void *)iph; + int len = 0, proto, optlen = sizeof(*iph); + + proto = iph->nexthdr; + for (;;) { + if (proto != NEXTHDR_HOP) { + *opps = rcu_dereference(inet6_offloads[proto]); + if (unlikely(!(*opps))) + break; + if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + opth = (void *)opth + optlen; + optlen = ipv6_optlen(opth); + len += optlen; + proto = opth->nexthdr; + } + return len; +} + +static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct net_offload *ops; + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct ipv6hdr *iph; + unsigned int nlen; + unsigned int hlen; + unsigned int off; + u16 flush = 1; + int proto; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } + + skb_set_network_header(skb, off); + skb_gro_pull(skb, sizeof(*iph)); + skb_set_transport_header(skb, skb_gro_offset(skb)); + + flush += ntohs(iph->payload_len) != skb_gro_len(skb); + + rcu_read_lock(); + proto = iph->nexthdr; + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) { + __pskb_pull(skb, skb_gro_offset(skb)); + proto = ipv6_gso_pull_exthdrs(skb, proto); + skb_gro_pull(skb, -skb_transport_offset(skb)); + skb_reset_transport_header(skb); + __skb_push(skb, skb_gro_offset(skb)); + + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) + goto out_unlock; + + iph = ipv6_hdr(skb); + } + + NAPI_GRO_CB(skb)->proto = proto; + + flush--; + nlen = skb_network_header_len(skb); + + for (p = *head; p; p = p->next) { + const struct ipv6hdr *iph2; + __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + iph2 = (struct ipv6hdr *)(p->data + off); + first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; + + /* All fields must match except length and Traffic Class. + * XXX skbs on the gro_list have all been parsed and pulled + * already so we don't need to compare nlen + * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops))) + * memcmp() alone below is suffcient, right? + */ + if ((first_word & htonl(0xF00FFFFF)) || + memcmp(&iph->nexthdr, &iph2->nexthdr, + nlen - offsetof(struct ipv6hdr, nexthdr))) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + /* flush if Traffic Class fields are different */ + NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); + NAPI_GRO_CB(p)->flush |= flush; + } + + NAPI_GRO_CB(skb)->flush |= flush; + + skb_gro_postpull_rcsum(skb, iph, nlen); + + pp = ops->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) +{ + const struct net_offload *ops; + struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); + int err = -ENOSYS; + + iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); + + rcu_read_lock(); + + nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) + goto out_unlock; + + err = ops->callbacks.gro_complete(skb, nhoff); + +out_unlock: + rcu_read_unlock(); + + return err; +} + +static struct packet_offload ipv6_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, +}; + +static const struct net_offload sit_offload = { + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + }, +}; + +static int __init ipv6_offload_init(void) +{ + + if (tcpv6_offload_init() < 0) + pr_crit("%s: Cannot add TCP protocol offload\n", __func__); + if (udp_offload_init() < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (ipv6_exthdrs_offload_init() < 0) + pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); + + dev_add_offload(&ipv6_packet_offload); + + inet_add_offload(&sit_offload, IPPROTO_IPV6); + + return 0; +} + +fs_initcall(ipv6_offload_init); diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h new file mode 100644 index 00000000000..2e155c651b3 --- /dev/null +++ b/net/ipv6/ip6_offload.h @@ -0,0 +1,18 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * 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. + */ + +#ifndef __ip6_offload_h +#define __ip6_offload_h + +int ipv6_exthdrs_offload_init(void); +int udp_offload_init(void); +int tcpv6_offload_init(void); + +#endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 614296a920c..45702b8cd14 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1,11 +1,9 @@ /* * IPv6 output functions - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> - * - * $Id: ip6_output.c,v 1.34 2002/02/01 22:01:04 davem Exp $ + * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_output.c * @@ -28,9 +26,8 @@ * for datagram xmit */ -#include <linux/config.h> #include <linux/errno.h> -#include <linux/types.h> +#include <linux/kernel.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> @@ -39,6 +36,8 @@ #include <linux/in6.h> #include <linux/tcp.h> #include <linux/route.h> +#include <linux/module.h> +#include <linux/slab.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> @@ -55,123 +54,119 @@ #include <net/icmp.h> #include <net/xfrm.h> #include <net/checksum.h> +#include <linux/mroute6.h> -static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); - -static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *fhdr) -{ - static u32 ipv6_fragmentation_id = 1; - static DEFINE_SPINLOCK(ip6_id_lock); - - spin_lock_bh(&ip6_id_lock); - fhdr->identification = htonl(ipv6_fragmentation_id); - if (++ipv6_fragmentation_id == 0) - ipv6_fragmentation_id = 1; - spin_unlock_bh(&ip6_id_lock); -} - -static inline int ip6_output_finish(struct sk_buff *skb) -{ - - struct dst_entry *dst = skb->dst; - struct hh_cache *hh = dst->hh; - - if (hh) { - int hh_alen; - - read_lock_bh(&hh->hh_lock); - hh_alen = HH_DATA_ALIGN(hh->hh_len); - memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); - read_unlock_bh(&hh->hh_lock); - skb_push(skb, hh->hh_len); - return hh->hh_output(skb); - } else if (dst->neighbour) - return dst->neighbour->output(skb); - - IP6_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); - kfree_skb(skb); - return -EINVAL; - -} - -/* dev_loopback_xmit for use with netfilter. */ -static int ip6_dev_loopback_xmit(struct sk_buff *newskb) -{ - newskb->mac.raw = newskb->data; - __skb_pull(newskb, newskb->nh.raw - newskb->data); - newskb->pkt_type = PACKET_LOOPBACK; - newskb->ip_summed = CHECKSUM_UNNECESSARY; - BUG_TRAP(newskb->dst); - - netif_rx(newskb); - return 0; -} - - -static int ip6_output2(struct sk_buff *skb) +static int ip6_finish_output2(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + struct neighbour *neigh; + struct in6_addr *nexthop; + int ret; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr)) { - struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; + if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && - ipv6_chk_mcast_addr(dev, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr)) { + if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && + ((mroute6_socket(dev_net(dev), skb) && + !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || + ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, + &ipv6_hdr(skb)->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing is not supported in any case. */ if (newskb) - NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, newskb, NULL, - newskb->dev, - ip6_dev_loopback_xmit); + NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, + newskb, NULL, newskb->dev, + dev_loopback_xmit); - if (skb->nh.ipv6h->hop_limit == 0) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + if (ipv6_hdr(skb)->hop_limit == 0) { + IP6_INC_STATS(dev_net(dev), idev, + IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); + IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST, + skb->len); + + if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <= + IPV6_ADDR_SCOPE_NODELOCAL && + !(dev->flags & IFF_LOOPBACK)) { + kfree_skb(skb); + return 0; + } + } + + rcu_read_lock_bh(); + nexthop = rt6_nexthop((struct rt6_info *)dst); + neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); + if (unlikely(!neigh)) + neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); + if (!IS_ERR(neigh)) { + ret = dst_neigh_output(dst, neigh, skb); + rcu_read_unlock_bh(); + return ret; } + rcu_read_unlock_bh(); - return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb,NULL, skb->dev,ip6_output_finish); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + kfree_skb(skb); + return -EINVAL; } -int ip6_output(struct sk_buff *skb) +static int ip6_finish_output(struct sk_buff *skb) { - if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->ufo_size) || - dst_allfrag(skb->dst)) - return ip6_fragment(skb, ip6_output2); + if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + dst_allfrag(skb_dst(skb)) || + (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) + return ip6_fragment(skb, ip6_finish_output2); else - return ip6_output2(skb); + return ip6_finish_output2(skb); +} + +int ip6_output(struct sock *sk, struct sk_buff *skb) +{ + struct net_device *dev = skb_dst(skb)->dev; + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + if (unlikely(idev->cnf.disable_ipv6)) { + IP6_INC_STATS(dev_net(dev), idev, + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + return 0; + } + + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, dev, + ip6_finish_output, + !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* - * xmit an sk_buff (used by TCP) + * xmit an sk_buff (used by TCP, SCTP and DCCP) */ -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct ipv6_txoptions *opt, int ipfragok) +int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, + struct ipv6_txoptions *opt, int tclass) { - struct ipv6_pinfo *np = sk ? inet6_sk(sk) : NULL; - struct in6_addr *first_hop = &fl->fl6_dst; - struct dst_entry *dst = skb->dst; + struct net *net = sock_net(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct in6_addr *first_hop = &fl6->daddr; + struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; - u8 proto = fl->proto; + u8 proto = fl6->flowi6_proto; int seg_len = skb->len; - int hlimit, tclass; + int hlimit = -1; u32 mtu; if (opt) { - int head_room; + unsigned int head_room; /* First: exthdrs may take lots of space (~8K for now) MAX_HEADER is not enough. @@ -182,14 +177,15 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (skb_headroom(skb) < head_room) { struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); - kfree_skb(skb); - skb = skb2; - if (skb == NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + if (skb2 == NULL) { + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); return -ENOBUFS; } - if (sk) - skb_set_owner_w(skb, sk); + consume_skb(skb); + skb = skb2; + skb_set_owner_w(skb, sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -197,85 +193,47 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop); } - hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ - - hlimit = -1; if (np) hlimit = np->hop_limit; if (hlimit < 0) - hlimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hlimit < 0) - hlimit = ipv6_get_hoplimit(dst->dev); - - tclass = -1; - if (np) - tclass = np->tclass; - if (tclass < 0) - tclass = 0; + hlimit = ip6_dst_hoplimit(dst); - *(u32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; + ip6_flow_hdr(hdr, tclass, fl6->flowlabel); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; - ipv6_addr_copy(&hdr->saddr, &fl->fl6_src); - ipv6_addr_copy(&hdr->daddr, first_hop); + hdr->saddr = fl6->saddr; + hdr->daddr = *first_hop; + + skb->protocol = htons(ETH_P_IPV6); + skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; mtu = dst_mtu(dst); - if ((skb->len <= mtu) || ipfragok) { - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, - dst_output); + if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { + IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUT, skb->len); + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + dst->dev, dst_output); } - if (net_ratelimit()) - printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + ipv6_local_error(sk, EMSGSIZE, fl6, mtu); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } -/* - * To avoid extra problems ND packets are send through this - * routine. It's code duplication but I really want to avoid - * extra checks since ipv6_build_header is used by TCP (which - * is for us performance critical) - */ - -int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, - struct in6_addr *saddr, struct in6_addr *daddr, - int proto, int len) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6hdr *hdr; - int totlen; - - skb->protocol = htons(ETH_P_IPV6); - skb->dev = dev; - - totlen = len + sizeof(struct ipv6hdr); - - hdr = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); - skb->nh.ipv6h = hdr; - - *(u32*)hdr = htonl(0x60000000); - - hdr->payload_len = htons(len); - hdr->nexthdr = proto; - hdr->hop_limit = np->hop_limit; - - ipv6_addr_copy(&hdr->saddr, saddr); - ipv6_addr_copy(&hdr->daddr, daddr); - - return 0; -} +EXPORT_SYMBOL(ip6_xmit); static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { @@ -306,26 +264,126 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel) return 0; } +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, &frag_off); + if (offset < 0) + return 0; + } else + offset = sizeof(struct ipv6hdr); + + if (nexthdr == IPPROTO_ICMPV6) { + struct icmp6hdr *icmp6; + + if (!pskb_may_pull(skb, (skb_network_header(skb) + + offset + 1 - skb->data))) + return 0; + + icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); + + switch (icmp6->icmp6_type) { + case NDISC_ROUTER_SOLICITATION: + case NDISC_ROUTER_ADVERTISEMENT: + case NDISC_NEIGHBOUR_SOLICITATION: + case NDISC_NEIGHBOUR_ADVERTISEMENT: + case NDISC_REDIRECT: + /* For reaction involving unicast neighbor discovery + * message destined to the proxied address, pass it to + * input function. + */ + return 1; + default: + break; + } + } + + /* + * The proxying router can't forward traffic sent to a link-local + * address, so signal the sender and discard the packet. This + * behavior is clarified by the MIPv6 specification. + */ + if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) { + dst_link_failure(skb); + return -1; + } + + return 0; +} + static inline int ip6_forward_finish(struct sk_buff *skb) { return dst_output(skb); } +static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) +{ + unsigned int mtu; + struct inet6_dev *idev; + + if (dst_metric_locked(dst, RTAX_MTU)) { + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + } + + mtu = IPV6_MIN_MTU; + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); + if (idev) + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + + return mtu; +} + +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + /* ipv6 conntrack defrag sets max_frag_size + ignore_df */ + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb->ignore_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; - struct ipv6hdr *hdr = skb->nh.ipv6h; + struct dst_entry *dst = skb_dst(skb); + struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); - - if (ipv6_devconf.forwarding == 0) + struct net *net = dev_net(dst->dev); + u32 mtu; + + if (net->ipv6.devconf_all->forwarding == 0) goto error; + if (skb->pkt_type != PACKET_HOST) + goto drop; + + if (skb_warn_if_lro(skb)) + goto drop; + if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INDISCARDS); goto drop; } - skb->ip_summed = CHECKSUM_NONE; + skb_forward_csum(skb); /* * We DO NOT make any processing on @@ -340,9 +398,8 @@ int ip6_forward(struct sk_buff *skb) * cannot be fragmented, because there is no warranty * that different fragments will go along one path. --ANK */ - if (opt->ra) { - u8 *ptr = skb->nh.raw + opt->ra; - if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3])) + if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { + if (ip6_call_ra_chain(skb, ntohs(opt->ra))) return 0; } @@ -352,26 +409,42 @@ int ip6_forward(struct sk_buff *skb) if (hdr->hop_limit <= 1) { /* Force OUTPUT device used as source address */ skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - 0, skb->dev); + icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; } + /* XXX: idev->cnf.proxy_ndp? */ + if (net->ipv6.devconf_all->proxy_ndp && + pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { + int proxied = ip6_forward_proxy_check(skb); + if (proxied > 0) + return ip6_input(skb); + else if (proxied < 0) { + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INDISCARDS); + goto drop; + } + } + if (!xfrm6_route_forward(skb)) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INDISCARDS); goto drop; } - dst = skb->dst; + dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. + We don't send redirects to frames decapsulated from IPsec. */ - if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0) { + if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; + struct inet_peer *peer; struct rt6_info *rt; - struct neighbour *n = dst->neighbour; /* * incoming and outgoing devices are the same @@ -379,48 +452,69 @@ int ip6_forward(struct sk_buff *skb) */ rt = (struct rt6_info *) dst; - if ((rt->rt6i_flags & RTF_GATEWAY)) - target = (struct in6_addr*)&n->primary_key; + if (rt->rt6i_flags & RTF_GATEWAY) + target = &rt->rt6i_gateway; else target = &hdr->daddr; + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (xrlim_allow(dst, 1*HZ)) - ndisc_send_redirect(skb, n, target); - } else if (ipv6_addr_type(&hdr->saddr)&(IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK - |IPV6_ADDR_LINKLOCAL)) { + if (inet_peer_xrlim_allow(peer, 1*HZ)) + ndisc_send_redirect(skb, target); + if (peer) + inet_putpeer(peer); + } else { + int addrtype = ipv6_addr_type(&hdr->saddr); + /* This check is security critical. */ - goto error; + if (addrtype == IPV6_ADDR_ANY || + addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) + goto error; + if (addrtype & IPV6_ADDR_LINKLOCAL) { + icmpv6_send(skb, ICMPV6_DEST_UNREACH, + ICMPV6_NOT_NEIGHBOUR, 0); + goto error; + } } - if (skb->len > dst_mtu(dst)) { + mtu = ip6_dst_mtu_forward(dst); + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev); - IP6_INC_STATS_BH(IPSTATS_MIB_INTOOBIGERRORS); - IP6_INC_STATS_BH(IPSTATS_MIB_FRAGFAILS); + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INTOOBIGERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_OUTDISCARDS); goto drop; } - hdr = skb->nh.ipv6h; + hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ - + hdr->hop_limit--; - IP6_INC_STATS_BH(IPSTATS_MIB_OUTFORWDATAGRAMS); - return NF_HOOK(PF_INET6,NF_IP6_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev, + ip6_forward_finish); error: - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); drop: kfree_skb(skb); return -EINVAL; @@ -431,122 +525,123 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; - dst_release(to->dst); - to->dst = dst_clone(from->dst); + skb_dst_drop(to); + skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; + to->mark = from->mark; #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif -#ifdef CONFIG_NETFILTER - to->nfmark = from->nfmark; - /* Connection association is same as pre-frag packet */ - to->nfct = from->nfct; - nf_conntrack_get(to->nfct); - to->nfctinfo = from->nfctinfo; -#ifdef CONFIG_BRIDGE_NETFILTER - nf_bridge_put(to->nf_bridge); - to->nf_bridge = from->nf_bridge; - nf_bridge_get(to->nf_bridge); -#endif -#endif + nf_copy(to, from); + skb_copy_secmark(to, from); } -int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) +static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) { - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1); - unsigned int packet_len = skb->tail - skb->nh.raw; - int found_rhdr = 0; - *nexthdr = &skb->nh.ipv6h->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - - case NEXTHDR_HOP: - case NEXTHDR_ROUTING: - case NEXTHDR_DEST: - if (**nexthdr == NEXTHDR_ROUTING) found_rhdr = 1; - if (**nexthdr == NEXTHDR_DEST && found_rhdr) return offset; - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); - break; - default : - return offset; - } - } + static u32 ip6_idents_hashrnd __read_mostly; + u32 hash, id; - return offset; + net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + + hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); + hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); + + id = ip_idents_reserve(hash, 1); + fhdr->identification = htonl(id); } -static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { - struct net_device *dev; struct sk_buff *frag; - struct rt6_info *rt = (struct rt6_info*)skb->dst; + struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); + struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; - u32 frag_id = 0; + int hroom, troom; + __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; + struct net *net = dev_net(skb_dst(skb)->dev); - dev = rt->u.dst.dev; hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; - mtu = dst_mtu(&rt->u.dst) - hlen - sizeof(struct frag_hdr); + mtu = ip6_skb_dst_mtu(skb); + + /* We must not fragment if the socket is set to force MTU discovery + * or if the skb it not generated by a local socket. + */ + if (unlikely(!skb->ignore_df && skb->len > mtu) || + (IP6CB(skb)->frag_max_size && + IP6CB(skb)->frag_max_size > mtu)) { + if (skb->sk && dst_allfrag(skb_dst(skb))) + sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK); + + skb->dev = skb_dst(skb)->dev; + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_FRAGFAILS); + kfree_skb(skb); + return -EMSGSIZE; + } + + if (np && np->frag_size < mtu) { + if (np->frag_size) + mtu = np->frag_size; + } + mtu -= hlen + sizeof(struct frag_hdr); - if (skb_shinfo(skb)->frag_list) { + if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); + struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb)) goto slow_path; - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) { + skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { - sock_hold(skb->sk); frag->sk = skb->sk; frag->destructor = sock_wfree; - skb->truesize -= frag->truesize; } + skb->truesize -= frag->truesize; } err = 0; offset = 0; frag = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = NULL; + skb_frag_list_init(skb); /* BUILD HEADER */ - tmp_hdr = kmalloc(hlen, GFP_ATOMIC); + *prevhdr = NEXTHDR_FRAGMENT; + tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } - *prevhdr = NEXTHDR_FRAGMENT; - memcpy(tmp_hdr, skb->nh.raw, hlen); __skb_pull(skb, hlen); fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr)); - skb->nh.raw = __skb_push(skb, hlen); - memcpy(skb->nh.raw, tmp_hdr, hlen); + __skb_push(skb, hlen); + skb_reset_network_header(skb); + memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(skb, fh); + ipv6_select_ident(fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); @@ -555,18 +650,22 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; - skb->nh.ipv6h->payload_len = htons(first_len - sizeof(struct ipv6hdr)); - + ipv6_hdr(skb)->payload_len = htons(first_len - + sizeof(struct ipv6hdr)); + + dst_hold(&rt->dst); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; - frag->h.raw = frag->data; + skb_reset_transport_header(frag); fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr)); - frag->nh.raw = __skb_push(frag, hlen); - memcpy(frag->nh.raw, tmp_hdr, hlen); + __skb_push(frag, hlen); + skb_reset_network_header(frag); + memcpy(skb_network_header(frag), tmp_hdr, + hlen); offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = nexthdr; fh->reserved = 0; @@ -574,11 +673,17 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->next != NULL) fh->frag_off |= htons(IP6_MF); fh->identification = frag_id; - frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); + ipv6_hdr(frag)->payload_len = + htons(frag->len - + sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } - + err = output(skb); + if(!err) + IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), + IPSTATS_MIB_FRAGCREATES); + if (err || !frag) break; @@ -587,11 +692,12 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb->next = NULL; } - if (tmp_hdr) - kfree(tmp_hdr); + kfree(tmp_hdr); if (err == 0) { - IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); + IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), + IPSTATS_MIB_FRAGOKS); + ip6_rt_put(rt); return 0; } @@ -601,11 +707,26 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb; } - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), + IPSTATS_MIB_FRAGFAILS); + ip6_rt_put(rt); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: + if ((skb->ip_summed == CHECKSUM_PARTIAL) && + skb_checksum_help(skb)) + goto fail; + left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ @@ -614,6 +735,8 @@ 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. @@ -623,7 +746,7 @@ slow_path: /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; - /* IF: we are not sending upto and including the packet end + /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; @@ -632,9 +755,11 @@ slow_path: * Allocate buffer. */ - if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_RESERVED_SPACE(rt->u.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(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -644,11 +769,12 @@ slow_path: */ ip6_copy_metadata(frag, skb); - skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev)); + skb_reserve(frag, hroom); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); - frag->nh.raw = frag->data; - fh = (struct frag_hdr*)(frag->data + hlen); - frag->h.raw = frag->data + hlen + sizeof(struct frag_hdr); + skb_reset_network_header(frag); + fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); + frag->transport_header = (frag->network_header + hlen + + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner @@ -660,7 +786,7 @@ slow_path: /* * Copy the packet header into the new buffer. */ - memcpy(frag->nh.raw, skb->data, hlen); + skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); /* * Build fragment header. @@ -668,7 +794,7 @@ slow_path: fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { - ipv6_select_ident(skb, fh); + ipv6_select_ident(fh, rt); frag_id = fh->identification; } else fh->identification = frag_id; @@ -676,14 +802,15 @@ slow_path: /* * Copy a block of the IP datagram. */ - if (skb_copy_bits(skb, ptr, frag->h.raw, len)) + if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len)) BUG(); left -= len; fh->frag_off = htons(offset); if (left > 0) fh->frag_off |= htons(IP6_MF); - frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); + ipv6_hdr(frag)->payload_len = htons(frag->len - + sizeof(struct ipv6hdr)); ptr += len; offset += len; @@ -691,92 +818,242 @@ slow_path: /* * Put this fragment into the sending queue. */ - - IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); - err = output(frag); if (err) goto fail; + + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_FRAGCREATES); } - kfree_skb(skb); - IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_FRAGOKS); + consume_skb(skb); return err; fail: - kfree_skb(skb); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_FRAGFAILS); + kfree_skb(skb); return err; } -int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) +static inline int ip6_rt_check(const struct rt6key *rt_key, + const struct in6_addr *fl_addr, + const struct in6_addr *addr_cache) { - int err = 0; + return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && + (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)); +} - *dst = NULL; - if (sk) { - struct ipv6_pinfo *np = inet6_sk(sk); - - *dst = sk_dst_check(sk, np->dst_cookie); - if (*dst) { - struct rt6_info *rt = (struct rt6_info*)*dst; - - /* Yes, checking route validity in not connected - case is not very simple. Take into account, - that we do not support routing by source, TOS, - and MSG_DONTROUTE --ANK (980726) - - 1. If route was host route, check that - cached destination is current. - If it is network route, we still may - check its validity using saved pointer - to the last used address: daddr_cache. - We do not want to save whole address now, - (because main consumer of this service - is tcp, which has not this problem), - so that the last trick works only on connected - sockets. - 2. oif also should be the same. - */ - - if (((rt->rt6i_dst.plen != 128 || - !ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr)) - && (np->daddr_cache == NULL || - !ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache))) - || (fl->oif && fl->oif != (*dst)->dev->ifindex)) { - dst_release(*dst); - *dst = NULL; - } - } +static struct dst_entry *ip6_sk_dst_check(struct sock *sk, + struct dst_entry *dst, + const struct flowi6 *fl6) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct rt6_info *rt; + + if (!dst) + goto out; + + if (dst->ops->family != AF_INET6) { + dst_release(dst); + return NULL; + } + + rt = (struct rt6_info *)dst; + /* Yes, checking route validity in not connected + * case is not very simple. Take into account, + * that we do not support routing by source, TOS, + * and MSG_DONTROUTE --ANK (980726) + * + * 1. ip6_rt_check(): If route was host route, + * check that cached destination is current. + * If it is network route, we still may + * check its validity using saved pointer + * to the last used address: daddr_cache. + * We do not want to save whole address now, + * (because main consumer of this service + * is tcp, which has not this problem), + * so that the last trick works only on connected + * sockets. + * 2. oif also should be the same. + */ + if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) || +#ifdef CONFIG_IPV6_SUBTREES + ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || +#endif + (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { + dst_release(dst); + dst = NULL; } +out: + return dst; +} + +static int ip6_dst_lookup_tail(struct sock *sk, + struct dst_entry **dst, struct flowi6 *fl6) +{ + struct net *net = sock_net(sk); +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + struct neighbour *n; + struct rt6_info *rt; +#endif + int err; + if (*dst == NULL) - *dst = ip6_route_output(sk, fl); + *dst = ip6_route_output(net, sk, fl6); if ((err = (*dst)->error)) goto out_err_release; - if (ipv6_addr_any(&fl->fl6_src)) { - err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src); - + if (ipv6_addr_any(&fl6->saddr)) { + struct rt6_info *rt = (struct rt6_info *) *dst; + err = ip6_route_get_saddr(net, rt, &fl6->daddr, + sk ? inet6_sk(sk)->srcprefs : 0, + &fl6->saddr); if (err) goto out_err_release; } +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + /* + * Here if the dst entry we've looked up + * has a neighbour entry that is in the INCOMPLETE + * state and the src address from the flow is + * marked as OPTIMISTIC, we release the found + * dst entry and replace it instead with the + * dst entry of the nexthop router + */ + rt = (struct rt6_info *) *dst; + rcu_read_lock_bh(); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); + err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; + rcu_read_unlock_bh(); + + if (err) { + struct inet6_ifaddr *ifp; + struct flowi6 fl_gw6; + int redirect; + + ifp = ipv6_get_ifaddr(net, &fl6->saddr, + (*dst)->dev, 1); + + redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); + if (ifp) + in6_ifa_put(ifp); + + if (redirect) { + /* + * We need to get the dst entry for the + * default router instead + */ + dst_release(*dst); + memcpy(&fl_gw6, fl6, sizeof(struct flowi6)); + memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr)); + *dst = ip6_route_output(net, sk, &fl_gw6); + if ((err = (*dst)->error)) + goto out_err_release; + } + } +#endif + return 0; out_err_release: + if (err == -ENETUNREACH) + IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); dst_release(*dst); *dst = NULL; return err; } -inline int ip6_ufo_append_data(struct sock *sk, + +/** + * ip6_dst_lookup - perform route lookup on flow + * @sk: socket which provides route info + * @dst: pointer to dst_entry * for result + * @fl6: flow to lookup + * + * This function performs a route lookup on the given flow. + * + * It returns zero on success, or a standard errno code on error. + */ +int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) +{ + *dst = NULL; + return ip6_dst_lookup_tail(sk, dst, fl6); +} +EXPORT_SYMBOL_GPL(ip6_dst_lookup); + +/** + * ip6_dst_lookup_flow - perform route lookup on flow with ipsec + * @sk: socket which provides route info + * @fl6: flow to lookup + * @final_dst: final destination address for ipsec lookup + * + * This function performs a route lookup on the given flow. + * + * It returns a valid dst pointer on success, or a pointer encoded + * error code. + */ +struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, + const struct in6_addr *final_dst) +{ + struct dst_entry *dst = NULL; + int err; + + err = ip6_dst_lookup_tail(sk, &dst, fl6); + if (err) + return ERR_PTR(err); + if (final_dst) + fl6->daddr = *final_dst; + + return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); +} +EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); + +/** + * ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow + * @sk: socket which provides the dst cache and route info + * @fl6: flow to lookup + * @final_dst: final destination address for ipsec lookup + * + * This function performs a route lookup on the given flow with the + * possibility of using the cached route in the socket if it is valid. + * It will take the socket dst lock when operating on the dst cache. + * As a result, this function can only be used in process context. + * + * It returns a valid dst pointer on success, or a pointer encoded + * error code. + */ +struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, + const struct in6_addr *final_dst) +{ + struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); + int err; + + dst = ip6_sk_dst_check(sk, dst, fl6); + + err = ip6_dst_lookup_tail(sk, &dst, fl6); + if (err) + return ERR_PTR(err); + if (final_dst) + fl6->daddr = *final_dst; + + return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); +} +EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); + +static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu,unsigned int flags) + int transhdrlen, int mtu,unsigned int flags, + struct rt6_info *rt) { struct sk_buff *skb; + struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -788,7 +1065,7 @@ 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); @@ -797,112 +1074,207 @@ inline int ip6_ufo_append_data(struct sock *sk, skb_put(skb,fragheaderlen + transhdrlen); /* initialize network header pointer */ - skb->nh.raw = skb->data; + skb_reset_network_header(skb); /* initialize protocol header pointer */ - skb->h.raw = skb->data + fragheaderlen; + skb->transport_header = skb->network_header + fragheaderlen; - skb->ip_summed = CHECKSUM_HW; + skb->protocol = htons(ETH_P_IPV6); skb->csum = 0; - sk->sk_sndmsg_off = 0; - } - err = skb_append_datato_frags(sk,skb, getfrag, from, - (length - transhdrlen)); - if (!err) { - struct frag_hdr fhdr; - - /* specify the length of each IP datagram fragment*/ - skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen) - - sizeof(struct frag_hdr); - ipv6_select_ident(skb, &fhdr); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); - - return 0; + } else if (skb_is_gso(skb)) { + goto append; } - /* There is not enough support do UPD LSO, - * so follow normal path + + skb->ip_summed = CHECKSUM_PARTIAL; + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. */ - kfree_skb(skb); + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + ipv6_select_ident(&fhdr, rt); + skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + +append: + return skb_append_datato_frags(sk, skb, getfrag, from, + (length - transhdrlen)); +} - return err; +static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, + gfp_t gfp) +{ + return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; +} + +static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, + gfp_t gfp) +{ + return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; +} + +static void ip6_append_data_mtu(unsigned int *mtu, + int *maxfraglen, + unsigned int fragheaderlen, + struct sk_buff *skb, + struct rt6_info *rt, + unsigned int orig_mtu) +{ + if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { + if (skb == NULL) { + /* first fragment, reserve header_len */ + *mtu = orig_mtu - rt->dst.header_len; + + } else { + /* + * this fragment is not first, the headers + * space is regarded as data space. + */ + *mtu = orig_mtu; + } + *maxfraglen = ((*mtu - fragheaderlen) & ~7) + + fragheaderlen - sizeof(struct frag_hdr); + } } int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl, - struct rt6_info *rt, unsigned int flags) + int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6, + struct rt6_info *rt, unsigned int flags, int dontfrag) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct sk_buff *skb; - unsigned int maxfraglen, fragheaderlen; + struct inet_cork *cork; + struct sk_buff *skb, *skb_prev = NULL; + unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen; + int dst_exthdrlen; int hh_len; - int mtu; int copy; int err; int offset = 0; - int csummode = CHECKSUM_NONE; + __u8 tx_flags = 0; if (flags&MSG_PROBE) return 0; + cork = &inet->cork.base; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ if (opt) { - if (np->cork.opt == NULL) { - np->cork.opt = kmalloc(opt->tot_len, - sk->sk_allocation); - if (unlikely(np->cork.opt == NULL)) - return -ENOBUFS; - } else if (np->cork.opt->tot_len < opt->tot_len) { - printk(KERN_DEBUG "ip6_append_data: invalid option length\n"); + if (WARN_ON(np->cork.opt)) return -EINVAL; - } - memcpy(np->cork.opt, opt, opt->tot_len); - inet->cork.flags |= IPCORK_OPT; + + np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation); + if (unlikely(np->cork.opt == NULL)) + return -ENOBUFS; + + np->cork.opt->tot_len = opt->tot_len; + np->cork.opt->opt_flen = opt->opt_flen; + np->cork.opt->opt_nflen = opt->opt_nflen; + + np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt, + sk->sk_allocation); + if (opt->dst0opt && !np->cork.opt->dst0opt) + return -ENOBUFS; + + np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt, + sk->sk_allocation); + if (opt->dst1opt && !np->cork.opt->dst1opt) + return -ENOBUFS; + + np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt, + sk->sk_allocation); + if (opt->hopopt && !np->cork.opt->hopopt) + return -ENOBUFS; + + np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt, + sk->sk_allocation); + if (opt->srcrt && !np->cork.opt->srcrt) + return -ENOBUFS; + /* need source address above miyazawa*/ } - dst_hold(&rt->u.dst); - np->cork.rt = rt; - inet->cork.fl = *fl; + dst_hold(&rt->dst); + cork->dst = &rt->dst; + inet->cork.fl.u.ip6 = *fl6; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; - inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path); - if (dst_allfrag(rt->u.dst.path)) - inet->cork.flags |= IPCORK_ALLFRAG; - inet->cork.length = 0; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; - exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0); + if (rt->dst.flags & DST_XFRM_TUNNEL) + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? + rt->dst.dev->mtu : dst_mtu(&rt->dst); + else + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? + rt->dst.dev->mtu : dst_mtu(rt->dst.path); + if (np->frag_size < mtu) { + if (np->frag_size) + mtu = np->frag_size; + } + cork->fragsize = mtu; + if (dst_allfrag(rt->dst.path)) + cork->flags |= IPCORK_ALLFRAG; + cork->length = 0; + exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; + dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { - rt = np->cork.rt; - fl = &inet->cork.fl; - if (inet->cork.flags & IPCORK_OPT) - opt = np->cork.opt; + rt = (struct rt6_info *)cork->dst; + fl6 = &inet->cork.fl.u.ip6; + opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; - mtu = inet->cork.fragsize; + dst_exthdrlen = 0; + mtu = cork->fragsize; } + orig_mtu = mtu; - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); + hh_len = LL_RESERVED_SPACE(rt->dst.dev); - fragheaderlen = sizeof(struct ipv6hdr) + (opt ? opt->opt_nflen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); + fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + + (opt ? opt->opt_nflen : 0); + maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - + sizeof(struct frag_hdr); if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { - if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) { - ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen); + unsigned int maxnonfragsize, headersize; + + headersize = sizeof(struct ipv6hdr) + + (opt ? opt->opt_flen + opt->opt_nflen : 0) + + (dst_allfrag(&rt->dst) ? + sizeof(struct frag_hdr) : 0) + + rt->rt6i_nfheader_len; + + if (ip6_sk_ignore_df(sk)) + maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + else + maxnonfragsize = mtu; + + /* dontfrag active */ + if ((cork->length + length > mtu - headersize) && dontfrag && + (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu - headersize + + sizeof(struct ipv6hdr)); + goto emsgsize; + } + + if (cork->length + length > maxnonfragsize - headersize) { +emsgsize: + ipv6_local_error(sk, EMSGSIZE, fl6, + mtu - headersize + + sizeof(struct ipv6hdr)); return -EMSGSIZE; } } + /* For UDP, check if TX timestamp is enabled */ + if (sk->sk_type == SOCK_DGRAM) + sock_tx_timestamp(sk, &tx_flags); + /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -910,32 +1282,35 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail of - * of the buffer to the new fragment when we split + * of the buffer to the new fragment when we split * the message. * - * FIXME: It may be fragmented into multiple chunks + * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. - * --yoshfuji + * --yoshfuji */ - inet->cork.length += length; - if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) && - (rt->u.dst.dev->features & NETIF_F_UFO)) { - - if(ip6_ufo_append_data(sk, getfrag, from, length, hh_len, - fragheaderlen, transhdrlen, mtu, flags)) + skb = skb_peek_tail(&sk->sk_write_queue); + cork->length += length; + if (((length > mtu) || + (skb && skb_is_gso(skb))) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->dst.dev->features & NETIF_F_UFO)) { + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags, rt); + if (err) goto error; - return 0; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ - copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; + copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; @@ -945,42 +1320,50 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; - struct sk_buff *skb_prev; alloc_new_skb: - skb_prev = skb; - /* There's no room in the current skb */ - if (skb_prev) - fraggap = skb_prev->len - maxfraglen; + if (skb) + fraggap = skb->len - maxfraglen; else fraggap = 0; + /* update mtu and maxfraglen if necessary */ + if (skb == NULL || skb_prev == NULL) + ip6_append_data_mtu(&mtu, &maxfraglen, + fragheaderlen, skb, rt, + orig_mtu); + + skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; - if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) - datalen = maxfraglen - fragheaderlen; - fraglen = datalen + fragheaderlen; + if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) + datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; if ((flags & MSG_MORE) && - !(rt->u.dst.dev->features&NETIF_F_SG)) + !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else alloclen = datalen + fragheaderlen; - /* - * The last fragment gets additional space at tail. - * Note: we overallocate on fragments with MSG_MODE - * because we have no idea if we're the last one. - */ - if (datalen == length + fraggap) - alloclen += rt->u.dst.trailer_len; + alloclen += dst_exthdrlen; + + if (datalen != length + fraggap) { + /* + * this is not the last fragment, the trailer + * space is regarded as data space. + */ + datalen += rt->dst.trailer_len; + } + + alloclen += rt->dst.trailer_len; + fraglen = datalen + fragheaderlen; /* * We just reserve space for fragment header. - * Note: this may be overallocation if the message + * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloclen += sizeof(struct frag_hdr); @@ -998,25 +1381,36 @@ alloc_new_skb: sk->sk_allocation); if (unlikely(skb == NULL)) err = -ENOBUFS; + else { + /* Only the initial fragment + * is time stamped. + */ + tx_flags = 0; + } } if (skb == NULL) goto error; /* * Fill in the control structures */ - skb->ip_summed = csummode; + skb->protocol = htons(ETH_P_IPV6); + skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; - /* reserve for fragmentation */ - skb_reserve(skb, hh_len+sizeof(struct frag_hdr)); + /* reserve for fragmentation and ipsec header */ + skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + + dst_exthdrlen); + + if (sk->sk_type == SOCK_DGRAM) + skb_shinfo(skb)->tx_flags = tx_flags; /* * Find where to start putting bytes */ data = skb_put(skb, fraglen); - skb->nh.raw = data + exthdrlen; + skb_set_network_header(skb, exthdrlen); data += fragheaderlen; - skb->h.raw = data + exthdrlen; - + skb->transport_header = (skb->network_header + + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, @@ -1024,9 +1418,10 @@ alloc_new_skb: skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; - skb_trim(skb_prev, maxfraglen); + pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap; + if (copy < 0) { err = -EINVAL; kfree_skb(skb); @@ -1041,7 +1436,7 @@ alloc_new_skb: length -= datalen - fraggap; transhdrlen = 0; exthdrlen = 0; - csummode = CHECKSUM_NONE; + dst_exthdrlen = 0; /* * Put the packet on the pending queue @@ -1053,7 +1448,7 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->u.dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG)) { unsigned int off; off = skb->len; @@ -1065,60 +1460,69 @@ alloc_new_skb: } } else { int i = skb_shinfo(skb)->nr_frags; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1]; - struct page *page = sk->sk_sndmsg_page; - int off = sk->sk_sndmsg_off; - unsigned int left; - - if (page && (left = PAGE_SIZE - off) > 0) { - if (copy >= left) - copy = left; - if (page != frag->page) { - if (i == MAX_SKB_FRAGS) { - err = -EMSGSIZE; - goto error; - } - get_page(page); - skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); - frag = &skb_shinfo(skb)->frags[i]; - } - } else if(i < MAX_SKB_FRAGS) { - if (copy > PAGE_SIZE) - copy = PAGE_SIZE; - page = alloc_pages(sk->sk_allocation, 0); - if (page == NULL) { - err = -ENOMEM; - goto error; - } - sk->sk_sndmsg_page = page; - sk->sk_sndmsg_off = 0; + struct page_frag *pfrag = sk_page_frag(sk); - skb_fill_page_desc(skb, i, page, 0, 0); - frag = &skb_shinfo(skb)->frags[i]; - skb->truesize += PAGE_SIZE; - atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc); - } else { - err = -EMSGSIZE; - goto error; - } - if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) { - err = -EFAULT; + err = -ENOMEM; + if (!sk_page_frag_refill(sk, pfrag)) goto error; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + err = -EMSGSIZE; + if (i == MAX_SKB_FRAGS) + goto error; + + __skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, 0); + skb_shinfo(skb)->nr_frags = ++i; + get_page(pfrag->page); } - sk->sk_sndmsg_off += copy; - frag->size += copy; + copy = min_t(int, copy, pfrag->size - pfrag->offset); + if (getfrag(from, + page_address(pfrag->page) + pfrag->offset, + offset, copy, skb->len, skb) < 0) + goto error_efault; + + pfrag->offset += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; + skb->truesize += copy; + atomic_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; } + return 0; + +error_efault: + err = -EFAULT; error: - inet->cork.length -= length; - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + cork->length -= length; + IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } +EXPORT_SYMBOL_GPL(ip6_append_data); + +static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np) +{ + if (np->cork.opt) { + kfree(np->cork.opt->dst0opt); + kfree(np->cork.opt->dst1opt); + kfree(np->cork.opt->hopopt); + kfree(np->cork.opt->srcrt); + kfree(np->cork.opt); + np->cork.opt = NULL; + } + + if (inet->cork.base.dst) { + dst_release(inet->cork.base.dst); + inet->cork.base.dst = NULL; + inet->cork.base.flags &= ~IPCORK_ALLFRAG; + } + memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); +} int ip6_push_pending_frames(struct sock *sk) { @@ -1127,11 +1531,12 @@ int ip6_push_pending_frames(struct sock *sk) struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); + struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = np->cork.opt; - struct rt6_info *rt = np->cork.rt; - struct flowi *fl = &inet->cork.fl; - unsigned char proto = fl->proto; + struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst; + struct flowi6 *fl6 = &inet->cork.fl.u.ip6; + unsigned char proto = fl6->flowi6_proto; int err = 0; if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL) @@ -1139,89 +1544,79 @@ int ip6_push_pending_frames(struct sock *sk) tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ - if (skb->data < skb->nh.raw) - __skb_pull(skb, skb->nh.raw - skb->data); + if (skb->data < skb_network_header(skb)) + __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { - __skb_pull(tmp_skb, skb->h.raw - skb->nh.raw); + __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; - __sock_put(tmp_skb->sk); tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } - ipv6_addr_copy(final_dst, &fl->fl6_dst); - __skb_pull(skb, skb->h.raw - skb->nh.raw); + /* Allow local fragmentation. */ + skb->ignore_df = ip6_sk_ignore_df(sk); + + *final_dst = fl6->daddr; + __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst); - skb->nh.ipv6h = hdr = (struct ipv6hdr*) skb_push(skb, sizeof(struct ipv6hdr)); - - *(u32*)hdr = fl->fl6_flowlabel | - htonl(0x60000000 | ((int)np->cork.tclass << 20)); + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); - if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) - hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); - else - hdr->payload_len = 0; + ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; - ipv6_addr_copy(&hdr->saddr, &fl->fl6_src); - ipv6_addr_copy(&hdr->daddr, final_dst); + hdr->saddr = fl6->saddr; + hdr->daddr = *final_dst; - skb->dst = dst_clone(&rt->u.dst); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output); + skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; + + skb_dst_set(skb, dst_clone(&rt->dst)); + IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + if (proto == IPPROTO_ICMPV6) { + struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + } + + err = ip6_local_out(skb); if (err) { if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; } out: - inet->cork.flags &= ~IPCORK_OPT; - if (np->cork.opt) { - kfree(np->cork.opt); - np->cork.opt = NULL; - } - if (np->cork.rt) { - dst_release(&np->cork.rt->u.dst); - np->cork.rt = NULL; - inet->cork.flags &= ~IPCORK_ALLFRAG; - } - memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); + ip6_cork_release(inet, np); return err; error: + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); goto out; } +EXPORT_SYMBOL_GPL(ip6_push_pending_frames); void ip6_flush_pending_frames(struct sock *sk) { - struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + if (skb_dst(skb)) + IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } - inet->cork.flags &= ~IPCORK_OPT; - - if (np->cork.opt) { - kfree(np->cork.opt); - np->cork.opt = NULL; - } - if (np->cork.rt) { - dst_release(&np->cork.rt->u.dst); - np->cork.rt = NULL; - inet->cork.flags &= ~IPCORK_ALLFRAG; - } - memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); + ip6_cork_release(inet_sk(sk), inet6_sk(sk)); } +EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cf94372d1af..afa08245836 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1,14 +1,13 @@ /* - * IPv6 over IPv6 tunnel device + * IPv6 tunneling device * Linux INET6 implementation * * Authors: - * Ville Nuorvala <vnuorval@tcs.hut.fi> - * - * $Id$ + * Ville Nuorvala <vnuorval@tcs.hut.fi> + * Yasuyuki Kozakai <kozakai@linux-ipv6.org> * * Based on: - * linux/net/ipv6/sit.c + * linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c * * RFC 2473 * @@ -19,15 +18,17 @@ * */ -#include <linux/config.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> +#include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> +#include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> -#include <linux/if_tunnel.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> @@ -37,61 +38,105 @@ #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> +#include <linux/slab.h> +#include <linux/hash.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> -#include <asm/atomic.h> +#include <linux/atomic.h> +#include <net/icmp.h> #include <net/ip.h> +#include <net/ip_tunnels.h> #include <net/ipv6.h> -#include <net/protocol.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/inet_ecn.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> MODULE_AUTHOR("Ville Nuorvala"); -MODULE_DESCRIPTION("IPv6-in-IPv6 tunnel"); +MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); - -#define IPV6_TLV_TEL_DST_SIZE 8 +MODULE_ALIAS_RTNL_LINK("ip6tnl"); +MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG -#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __FUNCTION__) +#define IP6_TNL_TRACE(x...) pr_debug("%s:" x "\n", __func__) #else #define IP6_TNL_TRACE(x...) do {;} while(0) #endif -#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) - -#define HASH_SIZE 32 +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) -#define HASH(addr) (((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \ - (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ - (HASH_SIZE - 1)) +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); -static int ip6ip6_fb_tnl_dev_init(struct net_device *dev); -static int ip6ip6_tnl_dev_init(struct net_device *dev); -static void ip6ip6_tnl_dev_setup(struct net_device *dev); +static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) +{ + u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); -/* the IPv6 tunnel fallback device */ -static struct net_device *ip6ip6_fb_tnl_dev; + return hash_32(hash, HASH_SIZE_SHIFT); +} +static int ip6_tnl_dev_init(struct net_device *dev); +static void ip6_tnl_dev_setup(struct net_device *dev); +static struct rtnl_link_ops ip6_link_ops __read_mostly; + +static int ip6_tnl_net_id __read_mostly; +struct ip6_tnl_net { + /* the IPv6 tunnel fallback device */ + struct net_device *fb_tnl_dev; + /* lists for storing tunnels in use */ + struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE]; + struct ip6_tnl __rcu *tnls_wc[1]; + struct ip6_tnl __rcu **tnls[2]; +}; -/* lists for storing tunnels in use */ -static struct ip6_tnl *tnls_r_l[HASH_SIZE]; -static struct ip6_tnl *tnls_wc[1]; -static struct ip6_tnl **tnls[2] = { tnls_wc, tnls_r_l }; +static struct net_device_stats *ip6_get_stats(struct net_device *dev) +{ + struct pcpu_sw_netstats tmp, sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + unsigned int start; + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + + do { + start = u64_stats_fetch_begin_irq(&tstats->syncp); + tmp.rx_packets = tstats->rx_packets; + tmp.rx_bytes = tstats->rx_bytes; + tmp.tx_packets = tstats->tx_packets; + tmp.tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); + + sum.rx_packets += tmp.rx_packets; + sum.rx_bytes += tmp.rx_bytes; + sum.tx_packets += tmp.tx_packets; + sum.tx_bytes += tmp.tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} -/* lock for the tunnel lists */ -static DEFINE_RWLOCK(ip6ip6_lock); +/* + * Locking : hash tables are protected by RCU and RTNL + */ -static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) +struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { struct dst_entry *dst = t->dst_cache; - if (dst && dst->obsolete && + if (dst && dst->obsolete && dst->ops->check(dst, t->dst_cookie) == NULL) { t->dst_cache = NULL; dst_release(dst); @@ -100,223 +145,251 @@ static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) return dst; } +EXPORT_SYMBOL_GPL(ip6_tnl_dst_check); -static inline void ip6_tnl_dst_reset(struct ip6_tnl *t) +void ip6_tnl_dst_reset(struct ip6_tnl *t) { dst_release(t->dst_cache); t->dst_cache = NULL; } +EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); -static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) +void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *) dst; t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; dst_release(t->dst_cache); t->dst_cache = dst; } +EXPORT_SYMBOL_GPL(ip6_tnl_dst_store); /** - * ip6ip6_tnl_lookup - fetch tunnel matching the end-point addresses - * @remote: the address of the tunnel exit-point - * @local: the address of the tunnel entry-point + * ip6_tnl_lookup - fetch tunnel matching the end-point addresses + * @remote: the address of the tunnel exit-point + * @local: the address of the tunnel entry-point * - * Return: + * Return: * tunnel matching given end-points if found, - * else fallback tunnel if its device is up, + * else fallback tunnel if its device is up, * else %NULL **/ +#define for_each_ip6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + static struct ip6_tnl * -ip6ip6_tnl_lookup(struct in6_addr *remote, struct in6_addr *local) +ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int hash = HASH(remote, local); struct ip6_tnl *t; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for (t = tnls_r_l[h0 ^ h1]; t; t = t->next) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } - if ((t = tnls_wc[0]) != NULL && (t->dev->flags & IFF_UP)) + t = rcu_dereference(ip6n->tnls_wc[0]); + if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** - * ip6ip6_bucket - get head of list matching given tunnel parameters - * @p: parameters containing tunnel end-points + * ip6_tnl_bucket - get head of list matching given tunnel parameters + * @p: parameters containing tunnel end-points * * Description: - * ip6ip6_bucket() returns the head of the list matching the + * ip6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * - * Return: head of IPv6 tunnel list + * Return: head of IPv6 tunnel list **/ -static struct ip6_tnl ** -ip6ip6_bucket(struct ip6_tnl_parm *p) +static struct ip6_tnl __rcu ** +ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { - struct in6_addr *remote = &p->raddr; - struct in6_addr *local = &p->laddr; - unsigned h = 0; + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; - h = HASH(remote) ^ HASH(local); + h = HASH(remote, local); } - return &tnls[prio][h]; + return &ip6n->tnls[prio][h]; } /** - * ip6ip6_tnl_link - add tunnel to hash table + * ip6_tnl_link - add tunnel to hash table * @t: tunnel to be added **/ static void -ip6ip6_tnl_link(struct ip6_tnl *t) +ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { - struct ip6_tnl **tp = ip6ip6_bucket(&t->parms); + struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); - t->next = *tp; - write_lock_bh(&ip6ip6_lock); - *tp = t; - write_unlock_bh(&ip6ip6_lock); + rcu_assign_pointer(t->next , rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); } /** - * ip6ip6_tnl_unlink - remove tunnel from hash table + * ip6_tnl_unlink - remove tunnel from hash table * @t: tunnel to be removed **/ static void -ip6ip6_tnl_unlink(struct ip6_tnl *t) +ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { - struct ip6_tnl **tp; - - for (tp = ip6ip6_bucket(&t->parms); *tp; tp = &(*tp)->next) { - if (t == *tp) { - write_lock_bh(&ip6ip6_lock); - *tp = t->next; - write_unlock_bh(&ip6ip6_lock); + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = ip6_tnl_bucket(ip6n, &t->parms); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } } +static void ip6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static int ip6_tnl_create2(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + t = netdev_priv(dev); + err = ip6_tnl_dev_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &ip6_link_ops; + + dev_hold(dev); + ip6_tnl_link(ip6n, t); + return 0; + +out: + return err; +} + /** - * ip6_tnl_create() - create a new tunnel + * ip6_tnl_create - create a new tunnel * @p: tunnel parameters * @pt: pointer to new tunnel * * Description: * Create tunnel matching given parameters. - * - * Return: - * 0 on success + * + * Return: + * created tunnel or NULL **/ -static int -ip6_tnl_create(struct ip6_tnl_parm *p, struct ip6_tnl **pt) +static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err; - if (p->name[0]) { + if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); - } else { - int i; - for (i = 1; i < IP6_TNL_MAX; i++) { - sprintf(name, "ip6tnl%d", i); - if (__dev_get_by_name(name) == NULL) - break; - } - if (i == IP6_TNL_MAX) - return -ENOBUFS; - } - dev = alloc_netdev(sizeof (*t), name, ip6ip6_tnl_dev_setup); + else + sprintf(name, "ip6tnl%%d"); + + dev = alloc_netdev(sizeof (*t), name, ip6_tnl_dev_setup); if (dev == NULL) - return -ENOMEM; + goto failed; + + dev_net_set(dev, net); - t = dev->priv; - dev->init = ip6ip6_tnl_dev_init; + t = netdev_priv(dev); t->parms = *p; + t->net = dev_net(dev); + err = ip6_tnl_create2(dev); + if (err < 0) + goto failed_free; - if ((err = register_netdevice(dev)) < 0) { - free_netdev(dev); - return err; - } - dev_hold(dev); + return t; - ip6ip6_tnl_link(t); - *pt = t; - return 0; +failed_free: + ip6_dev_free(dev); +failed: + return NULL; } /** - * ip6ip6_tnl_locate - find or create tunnel matching given parameters - * @p: tunnel parameters + * ip6_tnl_locate - find or create tunnel matching given parameters + * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: - * ip6ip6_tnl_locate() first tries to locate an existing tunnel + * ip6_tnl_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: - * 0 if tunnel located or created, - * -EINVAL if parameters incorrect, - * -ENODEV if no matching tunnel available + * matching tunnel or NULL **/ -static int -ip6ip6_tnl_locate(struct ip6_tnl_parm *p, struct ip6_tnl **pt, int create) +static struct ip6_tnl *ip6_tnl_locate(struct net *net, + struct __ip6_tnl_parm *p, int create) { - struct in6_addr *remote = &p->raddr; - struct in6_addr *local = &p->laddr; + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + struct ip6_tnl __rcu **tp; struct ip6_tnl *t; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - if (p->proto != IPPROTO_IPV6) - return -EINVAL; - - for (t = *ip6ip6_bucket(p); t; t = t->next) { + for (tp = ip6_tnl_bucket(ip6n, p); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && - ipv6_addr_equal(remote, &t->parms.raddr)) { - *pt = t; - return (create ? -EEXIST : 0); - } + ipv6_addr_equal(remote, &t->parms.raddr)) + return t; } if (!create) - return -ENODEV; - - return ip6_tnl_create(p, pt); + return NULL; + return ip6_tnl_create(net, p); } /** - * ip6ip6_tnl_dev_uninit - tunnel device uninitializer + * ip6_tnl_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed - * + * * Description: - * ip6ip6_tnl_dev_uninit() removes tunnel from its list + * ip6_tnl_dev_uninit() removes tunnel from its list **/ static void -ip6ip6_tnl_dev_uninit(struct net_device *dev) +ip6_tnl_dev_uninit(struct net_device *dev) { - struct ip6_tnl *t = dev->priv; + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - if (dev == ip6ip6_fb_tnl_dev) { - write_lock_bh(&ip6ip6_lock); - tnls_wc[0] = NULL; - write_unlock_bh(&ip6ip6_lock); - } else { - ip6ip6_tnl_unlink(t); - } + if (dev == ip6n->fb_tnl_dev) + RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); + else + ip6_tnl_unlink(ip6n, t); ip6_tnl_dst_reset(t); dev_put(dev); } @@ -325,15 +398,14 @@ ip6ip6_tnl_dev_uninit(struct net_device *dev) * parse_tvl_tnl_enc_lim - handle encapsulation limit option * @skb: received socket buffer * - * Return: - * 0 if none was found, + * Return: + * 0 if none was found, * else index to encapsulation limit **/ -static __u16 -parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) +__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { - struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; __u8 nexthdr = ipv6h->nexthdr; __u16 off = sizeof (*ipv6h); @@ -381,83 +453,83 @@ parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) } return 0; } +EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); /** - * ip6ip6_err - tunnel error handler + * ip6_tnl_err - tunnel error handler * * Description: - * ip6ip6_err() should handle errors in the tunnel according + * ip6_tnl_err() should handle errors in the tunnel according * to the specifications in RFC 2473. **/ -static void -ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) +static int +ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, + u8 *type, u8 *code, int *msg, __u32 *info, int offset) { - struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data; struct ip6_tnl *t; int rel_msg = 0; - int rel_type = ICMPV6_DEST_UNREACH; - int rel_code = ICMPV6_ADDR_UNREACH; + u8 rel_type = ICMPV6_DEST_UNREACH; + u8 rel_code = ICMPV6_ADDR_UNREACH; __u32 rel_info = 0; __u16 len; + int err = -ENOENT; - /* If the packet doesn't contain the original IPv6 header we are - in trouble since we might need the source address for further + /* If the packet doesn't contain the original IPv6 header we are + in trouble since we might need the source address for further processing of the error. */ - read_lock(&ip6ip6_lock); - if ((t = ip6ip6_tnl_lookup(&ipv6h->daddr, &ipv6h->saddr)) == NULL) + rcu_read_lock(); + if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, + &ipv6h->saddr)) == NULL) goto out; - switch (type) { + if (t->parms.proto != ipproto && t->parms.proto != 0) + goto out; + + err = 0; + + switch (*type) { __u32 teli; struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Path to destination invalid " - "or inactive!\n", t->parms.name); + net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: - if (code == ICMPV6_EXC_HOPLIMIT) { - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Too small hop limit or " - "routing loop in tunnel!\n", - t->parms.name); + if ((*code) == ICMPV6_EXC_HOPLIMIT) { + net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } break; case ICMPV6_PARAMPROB: - /* ignore if parameter problem not caused by a tunnel - encapsulation limit sub-option */ - if (code != ICMPV6_HDR_FIELD) { - break; - } - teli = parse_tlv_tnl_enc_lim(skb, skb->data); + teli = 0; + if ((*code) == ICMPV6_HDR_FIELD) + teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); - if (teli && teli == ntohl(info) - 2) { + if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Too small encapsulation " - "limit or routing loop in " - "tunnel!\n", t->parms.name); + net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } + } else { + net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: - mtu = ntohl(info) - offset; + mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; t->dev->mtu = mtu; - if ((len = sizeof (*ipv6h) + ipv6h->payload_len) > mtu) { + if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) { rel_type = ICMPV6_PKT_TOOBIG; rel_code = 0; rel_info = mtu; @@ -465,377 +537,675 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } break; } - if (rel_msg && pskb_may_pull(skb, offset + sizeof (*ipv6h))) { + + *type = rel_type; + *code = rel_code; + *info = rel_info; + *msg = rel_msg; + +out: + rcu_read_unlock(); + return err; +} + +static int +ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + int rel_msg = 0; + u8 rel_type = type; + u8 rel_code = code; + __u32 rel_info = ntohl(info); + int err; + struct sk_buff *skb2; + const struct iphdr *eiph; + struct rtable *rt; + struct flowi4 fl4; + + err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, + &rel_msg, &rel_info, offset); + if (err < 0) + return err; + + if (rel_msg == 0) + return 0; + + switch (rel_type) { + case ICMPV6_DEST_UNREACH: + if (rel_code != ICMPV6_ADDR_UNREACH) + return 0; + rel_type = ICMP_DEST_UNREACH; + rel_code = ICMP_HOST_UNREACH; + break; + case ICMPV6_PKT_TOOBIG: + if (rel_code != 0) + return 0; + rel_type = ICMP_DEST_UNREACH; + rel_code = ICMP_FRAG_NEEDED; + break; + case NDISC_REDIRECT: + rel_type = ICMP_REDIRECT; + rel_code = ICMP_REDIR_HOST; + default: + return 0; + } + + if (!pskb_may_pull(skb, offset + sizeof(struct iphdr))) + return 0; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + return 0; + + skb_dst_drop(skb2); + + skb_pull(skb2, offset); + skb_reset_network_header(skb2); + eiph = ip_hdr(skb2); + + /* Try to guess incoming interface */ + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, + eiph->saddr, 0, + 0, 0, + IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + if (IS_ERR(rt)) + goto out; + + skb2->dev = rt->dst.dev; + + /* route "incoming" packet */ + if (rt->rt_flags & RTCF_LOCAL) { + ip_rt_put(rt); + rt = NULL; + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, + eiph->daddr, eiph->saddr, + 0, 0, + IPPROTO_IPIP, + RT_TOS(eiph->tos), 0); + if (IS_ERR(rt) || + rt->dst.dev->type != ARPHRD_TUNNEL) { + if (!IS_ERR(rt)) + ip_rt_put(rt); + goto out; + } + skb_dst_set(skb2, &rt->dst); + } else { + ip_rt_put(rt); + if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, + skb2->dev) || + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) + goto out; + } + + /* change mtu on this route */ + if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { + if (rel_info > dst_mtu(skb_dst(skb2))) + goto out; + + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); + } + if (rel_type == ICMP_REDIRECT) + skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); + + icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); + +out: + kfree_skb(skb2); + return 0; +} + +static int +ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + int rel_msg = 0; + u8 rel_type = type; + u8 rel_code = code; + __u32 rel_info = ntohl(info); + int err; + + err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, + &rel_msg, &rel_info, offset); + if (err < 0) + return err; + + if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) { struct rt6_info *rt; struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) - goto out; + return 0; - dst_release(skb2->dst); - skb2->dst = NULL; + skb_dst_drop(skb2); skb_pull(skb2, offset); - skb2->nh.raw = skb2->data; + skb_reset_network_header(skb2); /* Try to guess incoming interface */ - rt = rt6_lookup(&skb2->nh.ipv6h->saddr, NULL, 0, 0); + 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, skb2->dev); + icmpv6_send(skb2, rel_type, rel_code, rel_info); - if (rt) - dst_release(&rt->u.dst); + ip6_rt_put(rt); kfree_skb(skb2); } -out: - read_unlock(&ip6ip6_lock); + + return 0; +} + +static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) +{ + __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; + + if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); + + return IP6_ECN_decapsulate(ipv6h, skb); } -static inline void ip6ip6_ecn_decapsulate(struct ipv6hdr *outer_iph, - struct sk_buff *skb) +static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb) { - struct ipv6hdr *inner_iph = skb->nh.ipv6h; + if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) + ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); + + return IP6_ECN_decapsulate(ipv6h, skb); +} - if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) - IP6_ECN_set_ce(inner_iph); +__u32 ip6_tnl_get_cap(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) +{ + struct __ip6_tnl_parm *p = &t->parms; + int ltype = ipv6_addr_type(laddr); + int rtype = ipv6_addr_type(raddr); + __u32 flags = 0; + + if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { + flags = IP6_TNL_F_CAP_PER_PACKET; + } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && + !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && + (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { + if (ltype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_XMIT; + if (rtype&IPV6_ADDR_UNICAST) + flags |= IP6_TNL_F_CAP_RCV; + } + return flags; } +EXPORT_SYMBOL(ip6_tnl_get_cap); + +/* called with rcu_read_lock() */ +int ip6_tnl_rcv_ctl(struct ip6_tnl *t, + const struct in6_addr *laddr, + const struct in6_addr *raddr) +{ + struct __ip6_tnl_parm *p = &t->parms; + int ret = 0; + struct net *net = t->net; + + if ((p->flags & IP6_TNL_F_CAP_RCV) || + ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && + (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { + struct net_device *ldev = NULL; + + if (p->link) + ldev = dev_get_by_index_rcu(net, p->link); + + if ((ipv6_addr_is_multicast(laddr) || + likely(ipv6_chk_addr(net, laddr, ldev, 0))) && + likely(!ipv6_chk_addr(net, raddr, NULL, 0))) + ret = 1; + } + return ret; +} +EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); /** - * ip6ip6_rcv - decapsulate IPv6 packet and retransmit it locally + * ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally * @skb: received socket buffer + * @protocol: ethernet protocol ID + * @dscp_ecn_decapsulate: the function to decapsulate DSCP code and ECN * * Return: 0 **/ -static int -ip6ip6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) +static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, + __u8 ipproto, + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb)) { - struct sk_buff *skb = *pskb; - struct ipv6hdr *ipv6h; struct ip6_tnl *t; + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int err; - if (!pskb_may_pull(skb, sizeof (*ipv6h))) - goto discard; + rcu_read_lock(); - ipv6h = skb->nh.ipv6h; + if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, + &ipv6h->daddr)) != NULL) { + struct pcpu_sw_netstats *tstats; - read_lock(&ip6ip6_lock); + if (t->parms.proto != ipproto && t->parms.proto != 0) { + rcu_read_unlock(); + goto discard; + } - if ((t = ip6ip6_tnl_lookup(&ipv6h->saddr, &ipv6h->daddr)) != NULL) { if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); - return 0; + rcu_read_unlock(); + goto discard; } - if (!(t->parms.flags & IP6_TNL_F_CAP_RCV)) { - t->stat.rx_dropped++; - read_unlock(&ip6ip6_lock); + if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { + t->dev->stats.rx_dropped++; + rcu_read_unlock(); goto discard; } - secpath_reset(skb); - skb->mac.raw = skb->nh.raw; - skb->nh.raw = skb->data; - skb->protocol = htons(ETH_P_IPV6); - skb->pkt_type = PACKET_HOST; + skb->mac_header = skb->network_header; + skb_reset_network_header(skb); + skb->protocol = htons(protocol); memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); - skb->dev = t->dev; - dst_release(skb->dst); - skb->dst = NULL; - if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) - ipv6_copy_dscp(ipv6h, skb->nh.ipv6h); - ip6ip6_ecn_decapsulate(ipv6h, skb); - t->stat.rx_packets++; - t->stat.rx_bytes += skb->len; + + __skb_tunnel_rx(skb, t->dev, t->net); + + err = dscp_ecn_decapsulate(t, ipv6h, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", + &ipv6h->saddr, + ipv6_get_dsfield(ipv6h)); + if (err > 1) { + ++t->dev->stats.rx_frame_errors; + ++t->dev->stats.rx_errors; + rcu_read_unlock(); + goto discard; + } + } + + tstats = this_cpu_ptr(t->dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + netif_rx(skb); - read_unlock(&ip6ip6_lock); + + rcu_read_unlock(); return 0; } - read_unlock(&ip6ip6_lock); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); -discard: + rcu_read_unlock(); return 1; + +discard: + kfree_skb(skb); + return 0; } -static inline struct ipv6_txoptions *create_tel(__u8 encap_limit) +static int ip4ip6_rcv(struct sk_buff *skb) { - struct ipv6_tlv_tnl_enc_lim *tel; - struct ipv6_txoptions *opt; - __u8 *raw; + return ip6_tnl_rcv(skb, ETH_P_IP, IPPROTO_IPIP, + ip4ip6_dscp_ecn_decapsulate); +} - int opt_len = sizeof(*opt) + 8; +static int ip6ip6_rcv(struct sk_buff *skb) +{ + return ip6_tnl_rcv(skb, ETH_P_IPV6, IPPROTO_IPV6, + ip6ip6_dscp_ecn_decapsulate); +} - if (!(opt = kmalloc(opt_len, GFP_ATOMIC))) { - return NULL; - } - memset(opt, 0, opt_len); - opt->tot_len = opt_len; - opt->dst0opt = (struct ipv6_opt_hdr *) (opt + 1); - opt->opt_nflen = 8; +struct ipv6_tel_txoption { + struct ipv6_txoptions ops; + __u8 dst_opt[8]; +}; - tel = (struct ipv6_tlv_tnl_enc_lim *) (opt->dst0opt + 1); - tel->type = IPV6_TLV_TNL_ENCAP_LIMIT; - tel->length = 1; - tel->encap_limit = encap_limit; +static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) +{ + memset(opt, 0, sizeof(struct ipv6_tel_txoption)); - raw = (__u8 *) opt->dst0opt; - raw[5] = IPV6_TLV_PADN; - raw[6] = 1; + opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; + opt->dst_opt[3] = 1; + opt->dst_opt[4] = encap_limit; + opt->dst_opt[5] = IPV6_TLV_PADN; + opt->dst_opt[6] = 1; - return opt; + opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt; + opt->ops.opt_nflen = 8; } /** - * ip6ip6_tnl_addr_conflict - compare packet addresses to tunnel's own + * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device - * @hdr: IPv6 header from the incoming packet + * @hdr: IPv6 header from the incoming packet * * Description: - * Avoid trivial tunneling loop by checking that tunnel exit-point + * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * - * Return: + * Return: * 1 if conflict, * 0 else **/ -static inline int -ip6ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr) +static inline bool +ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } +int ip6_tnl_xmit_ctl(struct ip6_tnl *t) +{ + struct __ip6_tnl_parm *p = &t->parms; + int ret = 0; + struct net *net = t->net; + + if (p->flags & IP6_TNL_F_CAP_XMIT) { + struct net_device *ldev = NULL; + + rcu_read_lock(); + if (p->link) + ldev = dev_get_by_index_rcu(net, p->link); + + if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0))) + pr_warn("%s xmit: Local address not yet configured!\n", + p->name); + else if (!ipv6_addr_is_multicast(&p->raddr) && + unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0))) + pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", + p->name); + else + ret = 1; + rcu_read_unlock(); + } + return ret; +} +EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); + /** - * ip6ip6_tnl_xmit - encapsulate packet and send + * ip6_tnl_xmit2 - encapsulate packet and send * @skb: the outgoing socket buffer - * @dev: the outgoing tunnel device + * @dev: the outgoing tunnel device + * @dsfield: dscp code for outer header + * @fl: flow of tunneled packet + * @encap_limit: encapsulation limit + * @pmtu: Path MTU is stored if packet is too big * * Description: * Build new header and do some sanity checks on the packet before sending * it. * - * Return: - * 0 + * Return: + * 0 on success + * -1 fail + * %-EMSGSIZE message too big. return mtu in this case. **/ -static int -ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) +static int ip6_tnl_xmit2(struct sk_buff *skb, + struct net_device *dev, + __u8 dsfield, + struct flowi6 *fl6, + int encap_limit, + __u32 *pmtu) { - struct ip6_tnl *t = (struct ip6_tnl *) dev->priv; - struct net_device_stats *stats = &t->stat; - struct ipv6hdr *ipv6h = skb->nh.ipv6h; - struct ipv6_txoptions *opt = NULL; - int encap_limit = -1; - __u16 offset; - struct flowi fl; - struct dst_entry *dst; + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; + struct net_device_stats *stats = &t->dev->stats; + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6_tel_txoption opt; + struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; - int max_headroom = sizeof(struct ipv6hdr); + unsigned int max_headroom = sizeof(struct ipv6hdr); u8 proto; - int err; - int pkt_len; - int dsfield; + int err = -1; - if (t->recursion++) { - stats->collisions++; - goto tx_err; - } - if (skb->protocol != htons(ETH_P_IPV6) || - !(t->parms.flags & IP6_TNL_F_CAP_XMIT) || - ip6ip6_tnl_addr_conflict(t, ipv6h)) { - goto tx_err; - } - if ((offset = parse_tlv_tnl_enc_lim(skb, skb->nh.raw)) > 0) { - struct ipv6_tlv_tnl_enc_lim *tel; - tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->nh.raw[offset]; - if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2, skb->dev); - goto tx_err; - } - encap_limit = tel->encap_limit - 1; - } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) { - encap_limit = t->parms.encap_limit; - } - memcpy(&fl, &t->fl, sizeof (fl)); - proto = fl.proto; + if (!fl6->flowi6_mark) + dst = ip6_tnl_dst_check(t); + if (!dst) { + ndst = ip6_route_output(net, NULL, fl6); - dsfield = ipv6_get_dsfield(ipv6h); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) - fl.fl6_flowlabel |= (*(__u32 *) ipv6h & IPV6_TCLASS_MASK); - if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)) - fl.fl6_flowlabel |= (*(__u32 *) ipv6h & IPV6_FLOWLABEL_MASK); - - if (encap_limit >= 0 && (opt = create_tel(encap_limit)) == NULL) - goto tx_err; - - if ((dst = ip6_tnl_dst_check(t)) != NULL) - dst_hold(dst); - else { - dst = ip6_route_output(NULL, &fl); - - if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0) < 0) + if (ndst->error) + goto tx_err_link_failure; + 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; if (tdev == dev) { stats->collisions++; - if (net_ratelimit()) - printk(KERN_WARNING - "%s: Local routing loop detected!\n", - t->parms.name); + net_warn_ratelimited("%s: Local routing loop detected!\n", + t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst) - sizeof (*ipv6h); - if (opt) { + if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (skb->dst && mtu < dst_mtu(skb->dst)) { - struct rt6_info *rt = (struct rt6_info *) skb->dst; - rt->rt6i_flags |= RTF_MODIFIED; - rt->u.dst.metrics[RTAX_MTU-1] = mtu; - } + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); + *pmtu = mtu; + err = -EMSGSIZE; goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom += LL_RESERVED_SPACE(tdev); - - if (skb_headroom(skb) < max_headroom || - skb_cloned(skb) || skb_shared(skb)) { + + if (skb_headroom(skb) < max_headroom || skb_shared(skb) || + (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb; - + if (!(new_skb = skb_realloc_headroom(skb, max_headroom))) goto tx_err_dst_release; if (skb->sk) skb_set_owner_w(new_skb, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = new_skb; } - dst_release(skb->dst); - skb->dst = 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; - skb->h.raw = skb->nh.raw; + proto = fl6->flowi6_proto; + if (encap_limit >= 0) { + init_tel_txopt(&opt, encap_limit); + ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); + } - if (opt) - ipv6_push_nfrag_opts(skb, opt, &proto, NULL); + if (likely(!skb->encapsulation)) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } - skb->nh.raw = skb_push(skb, sizeof(struct ipv6hdr)); - ipv6h = skb->nh.ipv6h; - *(u32*)ipv6h = fl.fl6_flowlabel | htonl(0x60000000); - dsfield = INET_ECN_encapsulate(0, dsfield); - ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); - ipv6h->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_push(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + ipv6h = ipv6_hdr(skb); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; - ipv6_addr_copy(&ipv6h->saddr, &fl.fl6_src); - ipv6_addr_copy(&ipv6h->daddr, &fl.fl6_dst); - nf_reset(skb); - pkt_len = skb->len; - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, - skb->dst->dev, dst_output); - - if (err == NET_XMIT_SUCCESS || err == NET_XMIT_CN) { - stats->tx_bytes += pkt_len; - stats->tx_packets++; - } else { - stats->tx_errors++; - stats->tx_aborted_errors++; - } - ip6_tnl_dst_store(t, dst); - - if (opt) - kfree(opt); - - t->recursion--; + ipv6h->saddr = fl6->saddr; + ipv6h->daddr = fl6->daddr; + ip6tunnel_xmit(skb, dev); + 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); - if (opt) - kfree(opt); -tx_err: - stats->tx_errors++; - stats->tx_dropped++; - kfree_skb(skb); - t->recursion--; - return 0; + dst_release(ndst); + return err; } -static void ip6_tnl_set_cap(struct ip6_tnl *t) +static inline int +ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ip6_tnl_parm *p = &t->parms; - struct in6_addr *laddr = &p->laddr; - struct in6_addr *raddr = &p->raddr; - int ltype = ipv6_addr_type(laddr); - int rtype = ipv6_addr_type(raddr); + struct ip6_tnl *t = netdev_priv(dev); + const struct iphdr *iph = ip_hdr(skb); + int encap_limit = -1; + struct flowi6 fl6; + __u8 dsfield; + __u32 mtu; + int err; - p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV); + if ((t->parms.proto != IPPROTO_IPIP && t->parms.proto != 0) || + !ip6_tnl_xmit_ctl(t)) + return -1; - if (ltype != IPV6_ADDR_ANY && rtype != IPV6_ADDR_ANY && - ((ltype|rtype) & - (IPV6_ADDR_UNICAST| - IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL| - IPV6_ADDR_MAPPED|IPV6_ADDR_RESERVED)) == IPV6_ADDR_UNICAST) { - struct net_device *ldev = NULL; - int l_ok = 1; - int r_ok = 1; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; - if (p->link) - ldev = dev_get_by_index(p->link); - - if (ltype&IPV6_ADDR_UNICAST && !ipv6_chk_addr(laddr, ldev, 0)) - l_ok = 0; - - if (rtype&IPV6_ADDR_UNICAST && ipv6_chk_addr(raddr, NULL, 0)) - r_ok = 0; - - if (l_ok && r_ok) { - if (ltype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_XMIT; - if (rtype&IPV6_ADDR_UNICAST) - p->flags |= IP6_TNL_F_CAP_RCV; + memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; + + dsfield = ipv4_get_dsfield(iph); + + 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) { + /* XXX: send ICMP error even if DF is not set. */ + if (err == -EMSGSIZE) + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + return -1; + } + + return 0; +} + +static inline int +ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + int encap_limit = -1; + __u16 offset; + struct flowi6 fl6; + __u8 dsfield; + __u32 mtu; + int err; + + if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || + !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h)) + return -1; + + offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + if (offset > 0) { + struct ipv6_tlv_tnl_enc_lim *tel; + tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; + if (tel->encap_limit == 0) { + icmpv6_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); + return -1; } - if (ldev) - dev_put(ldev); + encap_limit = tel->encap_limit - 1; + } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + encap_limit = t->parms.encap_limit; + + memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; + + dsfield = ipv6_get_dsfield(ipv6h); + 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) + fl6.flowlabel |= ip6_flowlabel(ipv6h); + 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) { + if (err == -EMSGSIZE) + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + return -1; + } + + return 0; +} + +static netdev_tx_t +ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + int ret; + + switch (skb->protocol) { + case htons(ETH_P_IP): + ret = ip4ip6_tnl_xmit(skb, dev); + break; + case htons(ETH_P_IPV6): + ret = ip6ip6_tnl_xmit(skb, dev); + break; + default: + goto tx_err; } + + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; } -static void ip6ip6_tnl_link_config(struct ip6_tnl *t) +static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; - struct ip6_tnl_parm *p = &t->parms; - struct flowi *fl = &t->fl; + struct __ip6_tnl_parm *p = &t->parms; + struct flowi6 *fl6 = &t->fl.u.ip6; - memcpy(&dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); - memcpy(&dev->broadcast, &p->raddr, sizeof(struct in6_addr)); + memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ - ipv6_addr_copy(&fl->fl6_src, &p->laddr); - ipv6_addr_copy(&fl->fl6_dst, &p->raddr); - fl->oif = p->link; - fl->fl6_flowlabel = 0; + fl6->saddr = p->laddr; + fl6->daddr = p->raddr; + fl6->flowi6_oif = p->link; + fl6->flowlabel = 0; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) - fl->fl6_flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; + fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) - fl->fl6_flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; + fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; - ip6_tnl_set_cap(t); + p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); + p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; @@ -845,58 +1215,107 @@ static void ip6ip6_tnl_link_config(struct ip6_tnl *t) dev->iflink = p->link; if (p->flags & IP6_TNL_F_CAP_XMIT) { - struct rt6_info *rt = rt6_lookup(&p->raddr, &p->laddr, - p->link, 0); + int strict = (ipv6_addr_type(&p->raddr) & + (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); + + struct rt6_info *rt = rt6_lookup(t->net, + &p->raddr, &p->laddr, + p->link, strict); 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; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } - dst_release(&rt->u.dst); + ip6_rt_put(rt); } } /** - * ip6ip6_tnl_change - update the tunnel parameters + * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters - * @active: != 0 if tunnel is ready for use * * Description: - * ip6ip6_tnl_change() updates the tunnel parameters + * ip6_tnl_change() updates the tunnel parameters **/ static int -ip6ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) +ip6_tnl_change(struct ip6_tnl *t, const 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; t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; - ip6ip6_tnl_link_config(t); + t->parms.proto = p->proto; + ip6_tnl_dst_reset(t); + ip6_tnl_link_config(t); return 0; } +static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = t->net; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + ip6_tnl_unlink(ip6n, t); + synchronize_net(); + err = ip6_tnl_change(t, p); + ip6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + +static void +ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) +{ + p->laddr = u->laddr; + p->raddr = u->raddr; + p->flags = u->flags; + p->hop_limit = u->hop_limit; + p->encap_limit = u->encap_limit; + p->flowinfo = u->flowinfo; + p->link = u->link; + p->proto = u->proto; + memcpy(p->name, u->name, sizeof(u->name)); +} + +static void +ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) +{ + u->laddr = p->laddr; + u->raddr = p->raddr; + u->flags = p->flags; + u->hop_limit = p->hop_limit; + u->encap_limit = p->encap_limit; + u->flowinfo = p->flowinfo; + u->link = p->link; + u->proto = p->proto; + memcpy(u->name, p->name, sizeof(u->name)); +} + /** - * ip6ip6_tnl_ioctl - configure ipv6 tunnels from userspace + * ip6_tnl_ioctl - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: parameters passed from userspace * @cmd: command to be performed * * Description: - * ip6ip6_tnl_ioctl() is used for managing IPv6 tunnels - * from userspace. + * ip6_tnl_ioctl() is used for managing IPv6 tunnels + * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device @@ -904,7 +1323,7 @@ ip6ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * - * The fallback device "ip6tnl0", created during module + * The fallback device "ip6tnl0", created during module * initialization, can be used for creating other tunnel devices. * * Return: @@ -917,30 +1336,30 @@ ip6ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) **/ static int -ip6ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; - int create; struct ip6_tnl_parm p; - struct ip6_tnl *t = NULL; + struct __ip6_tnl_parm p1; + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); switch (cmd) { case SIOCGETTUNNEL: - if (dev == ip6ip6_fb_tnl_dev) { - if (copy_from_user(&p, - ifr->ifr_ifru.ifru_data, - sizeof (p))) { + if (dev == ip6n->fb_tnl_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) { err = -EFAULT; break; } - if ((err = ip6ip6_tnl_locate(&p, &t, 0)) == -ENODEV) - t = (struct ip6_tnl *) dev->priv; - else if (err) - break; - } else - t = (struct ip6_tnl *) dev->priv; - - memcpy(&p, &t->parms, sizeof (p)); + ip6_tnl_parm_from_user(&p1, &p); + t = ip6_tnl_locate(net, &p1, 0); + if (t == NULL) + t = netdev_priv(dev); + } else { + memset(&p, 0, sizeof(p)); + } + ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) { err = -EFAULT; } @@ -948,58 +1367,58 @@ ip6ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - create = (cmd == SIOCADDTUNNEL); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) { - err = -EFAULT; + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) break; - } - if (!create && dev != ip6ip6_fb_tnl_dev) { - t = (struct ip6_tnl *) dev->priv; - } - if (!t && (err = ip6ip6_tnl_locate(&p, &t, create))) { + err = -EINVAL; + if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && + p.proto != 0) break; + ip6_tnl_parm_from_user(&p1, &p); + t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); + if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else + t = netdev_priv(dev); + + err = ip6_tnl_update(t, &p1); } - if (cmd == SIOCCHGTUNNEL) { - if (t->dev != dev) { - err = -EEXIST; - break; - } - ip6ip6_tnl_unlink(t); - err = ip6ip6_tnl_change(t, &p); - ip6ip6_tnl_link(t); - netdev_state_change(dev); - } - if (copy_to_user(ifr->ifr_ifru.ifru_data, - &t->parms, sizeof (p))) { - err = -EFAULT; - } else { + if (t) { err = 0; - } + ip6_tnl_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); break; case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; - if (dev == ip6ip6_fb_tnl_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, - sizeof (p))) { - err = -EFAULT; + if (dev == ip6n->fb_tnl_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) break; - } - err = ip6ip6_tnl_locate(&p, &t, 0); - if (err) + err = -ENOENT; + ip6_tnl_parm_from_user(&p1, &p); + t = ip6_tnl_locate(net, &p1, 0); + if (t == NULL) break; - if (t == ip6ip6_fb_tnl_dev->priv) { - err = -EPERM; + err = -EPERM; + if (t->dev == ip6n->fb_tnl_dev) break; - } - } else { - t = (struct ip6_tnl *) dev->priv; + dev = t->dev; } - err = unregister_netdevice(t->dev); + err = 0; + unregister_netdevice(dev); break; default: err = -EINVAL; @@ -1008,20 +1427,7 @@ ip6ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } /** - * ip6ip6_tnl_get_stats - return the stats for tunnel device - * @dev: virtual device associated with tunnel - * - * Return: stats for device - **/ - -static struct net_device_stats * -ip6ip6_tnl_get_stats(struct net_device *dev) -{ - return &(((struct ip6_tnl *) dev->priv)->stat); -} - -/** - * ip6ip6_tnl_change_mtu - change mtu manually for tunnel device + * ip6_tnl_change_mtu - change mtu manually for tunnel device * @dev: virtual device associated with tunnel * @new_mtu: the new mtu * @@ -1031,118 +1437,384 @@ ip6ip6_tnl_get_stats(struct net_device *dev) **/ static int -ip6ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) +ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < IPV6_MIN_MTU) { - return -EINVAL; + struct ip6_tnl *tnl = netdev_priv(dev); + + if (tnl->parms.proto == IPPROTO_IPIP) { + if (new_mtu < 68) + return -EINVAL; + } else { + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; } + if (new_mtu > 0xFFF8 - dev->hard_header_len) + return -EINVAL; dev->mtu = new_mtu; return 0; } + +static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_uninit = ip6_tnl_dev_uninit, + .ndo_start_xmit = ip6_tnl_xmit, + .ndo_do_ioctl = ip6_tnl_ioctl, + .ndo_change_mtu = ip6_tnl_change_mtu, + .ndo_get_stats = ip6_get_stats, +}; + + /** - * ip6ip6_tnl_dev_setup - setup virtual tunnel device + * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ -static void ip6ip6_tnl_dev_setup(struct net_device *dev) +static void ip6_tnl_dev_setup(struct net_device *dev) { - SET_MODULE_OWNER(dev); - dev->uninit = ip6ip6_tnl_dev_uninit; - dev->destructor = free_netdev; - dev->hard_start_xmit = ip6ip6_tnl_xmit; - dev->get_stats = ip6ip6_tnl_get_stats; - dev->do_ioctl = ip6ip6_tnl_ioctl; - dev->change_mtu = ip6ip6_tnl_change_mtu; + struct ip6_tnl *t; + + dev->netdev_ops = &ip6_tnl_netdev_ops; + dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr); + t = netdev_priv(dev); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu-=8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + /* This perm addr will be used as interface identifier by IPv6 */ + dev->addr_assign_type = NET_ADDR_RANDOM; + eth_random_addr(dev->perm_addr); } /** - * ip6ip6_tnl_dev_init_gen - general initializer for all tunnel devices + * ip6_tnl_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ -static inline void -ip6ip6_tnl_dev_init_gen(struct net_device *dev) +static inline int +ip6_tnl_dev_init_gen(struct net_device *dev) { - struct ip6_tnl *t = (struct ip6_tnl *) dev->priv; - t->fl.proto = IPPROTO_IPV6; + struct ip6_tnl *t = netdev_priv(dev); + t->dev = dev; - strcpy(t->parms.name, dev->name); + t->net = dev_net(dev); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } /** - * ip6ip6_tnl_dev_init - initializer for all non fallback tunnel devices + * ip6_tnl_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ -static int -ip6ip6_tnl_dev_init(struct net_device *dev) +static int ip6_tnl_dev_init(struct net_device *dev) { - struct ip6_tnl *t = (struct ip6_tnl *) dev->priv; - ip6ip6_tnl_dev_init_gen(dev); - ip6ip6_tnl_link_config(t); + struct ip6_tnl *t = netdev_priv(dev); + int err = ip6_tnl_dev_init_gen(dev); + + if (err) + return err; + ip6_tnl_link_config(t); return 0; } /** - * ip6ip6_fb_tnl_dev_init - initializer for fallback tunnel device + * ip6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ -static int -ip6ip6_fb_tnl_dev_init(struct net_device *dev) +static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { - struct ip6_tnl *t = dev->priv; - ip6ip6_tnl_dev_init_gen(dev); + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err = ip6_tnl_dev_init_gen(dev); + + if (err) + return err; + + t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - tnls_wc[0] = t; + + ip6_tnl_link_config(t); + + rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } -#ifdef CONFIG_INET6_TUNNEL -static struct xfrm6_tunnel ip6ip6_handler = { - .handler = ip6ip6_rcv, - .err_handler = ip6ip6_err, -}; +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data || !data[IFLA_IPTUN_PROTO]) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; -static inline int ip6ip6_register(void) + return 0; +} + +static void ip6_tnl_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) { - return xfrm6_tunnel_register(&ip6ip6_handler); + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); + + if (data[IFLA_IPTUN_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); + + if (data[IFLA_IPTUN_FLOWINFO]) + parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); + + if (data[IFLA_IPTUN_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); } -static inline int ip6ip6_unregister(void) +static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) { - return xfrm6_tunnel_deregister(&ip6ip6_handler); + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + ip6_tnl_netlink_parms(data, &nt->parms); + + if (ip6_tnl_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ip6_tnl_create2(dev); } -#else -static struct inet6_protocol xfrm6_tunnel_protocol = { + +static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct __ip6_tnl_parm p; + struct net *net = t->net; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + ip6_tnl_netlink_parms(data, &p); + + t = ip6_tnl_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return ip6_tnl_update(t, &p); +} + +static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + +static size_t ip6_tnl_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_IPTUN_FLOWINFO */ + nla_total_size(4) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(4) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + + 0; +} + +static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), + &parm->laddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || + nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || + nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || + nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ip6_link_ops __read_mostly = { + .kind = "ip6tnl", + .maxtype = IFLA_IPTUN_MAX, + .policy = ip6_tnl_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6_tnl_dev_setup, + .validate = ip6_tnl_validate, + .newlink = ip6_tnl_newlink, + .changelink = ip6_tnl_changelink, + .dellink = ip6_tnl_dellink, + .get_size = ip6_tnl_get_size, + .fill_info = ip6_tnl_fill_info, +}; + +static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { + .handler = ip4ip6_rcv, + .err_handler = ip4ip6_err, + .priority = 1, +}; + +static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .handler = ip6ip6_rcv, .err_handler = ip6ip6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, + .priority = 1, }; -static inline int ip6ip6_register(void) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) { - return inet6_add_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct net_device *dev, *aux; + int h; + struct ip6_tnl *t; + LIST_HEAD(list); + + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &ip6_link_ops) + unregister_netdevice_queue(dev, &list); + + for (h = 0; h < HASH_SIZE; h++) { + t = rtnl_dereference(ip6n->tnls_r_l[h]); + while (t != NULL) { + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, &list); + t = rtnl_dereference(t->next); + } + } + + unregister_netdevice_many(&list); } -static inline int ip6ip6_unregister(void) +static int __net_init ip6_tnl_init_net(struct net *net) { - return inet6_del_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6); + 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; + ip6n->tnls[1] = ip6n->tnls_r_l; + + err = -ENOMEM; + ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", + ip6_tnl_dev_setup); + + if (!ip6n->fb_tnl_dev) + goto err_alloc_dev; + dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; + + err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + if (err < 0) + goto err_register; + + 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: + ip6_dev_free(ip6n->fb_tnl_dev); +err_alloc_dev: + return err; +} + +static void __net_exit ip6_tnl_exit_net(struct net *net) +{ + rtnl_lock(); + ip6_tnl_destroy_tunnels(net); + rtnl_unlock(); } -#endif + +static struct pernet_operations ip6_tnl_net_ops = { + .init = ip6_tnl_init_net, + .exit = ip6_tnl_exit_net, + .id = &ip6_tnl_net_id, + .size = sizeof(struct ip6_tnl_net), +}; /** * ip6_tunnel_init - register protocol and reserve needed resources @@ -1154,26 +1826,34 @@ static int __init ip6_tunnel_init(void) { int err; - if (ip6ip6_register() < 0) { - printk(KERN_ERR "ip6ip6 init: can't register tunnel\n"); - return -EAGAIN; - } - ip6ip6_fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", - ip6ip6_tnl_dev_setup); + err = register_pernet_device(&ip6_tnl_net_ops); + if (err < 0) + goto out_pernet; - if (!ip6ip6_fb_tnl_dev) { - err = -ENOMEM; - goto fail; + err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); + if (err < 0) { + pr_err("%s: can't register ip4ip6\n", __func__); + goto out_ip4ip6; } - ip6ip6_fb_tnl_dev->init = ip6ip6_fb_tnl_dev_init; - if ((err = register_netdev(ip6ip6_fb_tnl_dev))) { - free_netdev(ip6ip6_fb_tnl_dev); - goto fail; + err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); + if (err < 0) { + pr_err("%s: can't register ip6ip6\n", __func__); + goto out_ip6ip6; } + err = rtnl_link_register(&ip6_link_ops); + if (err < 0) + goto rtnl_link_failed; + return 0; -fail: - ip6ip6_unregister(); + +rtnl_link_failed: + xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); +out_ip6ip6: + xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); +out_ip4ip6: + unregister_pernet_device(&ip6_tnl_net_ops); +out_pernet: return err; } @@ -1183,10 +1863,14 @@ fail: static void __exit ip6_tunnel_cleanup(void) { - if (ip6ip6_unregister() < 0) - printk(KERN_INFO "ip6ip6 close: can't deregister tunnel\n"); + rtnl_link_unregister(&ip6_link_ops); + if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) + pr_info("%s: can't deregister ip4ip6\n", __func__); + + if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) + pr_info("%s: can't deregister ip6ip6\n", __func__); - unregister_netdev(ip6ip6_fb_tnl_dev); + unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c new file mode 100644 index 00000000000..9aaa6bb229e --- /dev/null +++ b/net/ipv6/ip6_vti.c @@ -0,0 +1,1160 @@ +/* + * IPv6 virtual tunneling interface + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv6/ip6_tunnel.c + * + * 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. + */ + +#include <linux/module.h> +#include <linux/capability.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/sockios.h> +#include <linux/icmp.h> +#include <linux/if.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/net.h> +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/if_arp.h> +#include <linux/icmpv6.h> +#include <linux/init.h> +#include <linux/route.h> +#include <linux/rtnetlink.h> +#include <linux/netfilter_ipv6.h> +#include <linux/slab.h> +#include <linux/hash.h> + +#include <linux/uaccess.h> +#include <linux/atomic.h> + +#include <net/icmp.h> +#include <net/ip.h> +#include <net/ip_tunnels.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> +#include <net/ip6_tunnel.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> + +#define HASH_SIZE_SHIFT 5 +#define HASH_SIZE (1 << HASH_SIZE_SHIFT) + +static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) +{ + u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); + + return hash_32(hash, HASH_SIZE_SHIFT); +} + +static int vti6_dev_init(struct net_device *dev); +static void vti6_dev_setup(struct net_device *dev); +static struct rtnl_link_ops vti6_link_ops __read_mostly; + +static int vti6_net_id __read_mostly; +struct vti6_net { + /* the vti6 tunnel fallback device */ + struct net_device *fb_tnl_dev; + /* lists for storing tunnels in use */ + struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE]; + struct ip6_tnl __rcu *tnls_wc[1]; + struct ip6_tnl __rcu **tnls[2]; +}; + +#define for_each_vti6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + +/** + * vti6_tnl_lookup - fetch tunnel matching the end-point addresses + * @net: network namespace + * @remote: the address of the tunnel exit-point + * @local: the address of the tunnel entry-point + * + * Return: + * tunnel matching given end-points if found, + * else fallback tunnel if its device is up, + * else %NULL + **/ +static struct ip6_tnl * +vti6_tnl_lookup(struct net *net, const struct in6_addr *remote, + const struct in6_addr *local) +{ + unsigned int hash = HASH(remote, local); + struct ip6_tnl *t; + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { + if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_equal(remote, &t->parms.raddr) && + (t->dev->flags & IFF_UP)) + return t; + } + t = rcu_dereference(ip6n->tnls_wc[0]); + if (t && (t->dev->flags & IFF_UP)) + return t; + + return NULL; +} + +/** + * vti6_tnl_bucket - get head of list matching given tunnel parameters + * @p: parameters containing tunnel end-points + * + * Description: + * vti6_tnl_bucket() returns the head of the list matching the + * &struct in6_addr entries laddr and raddr in @p. + * + * Return: head of IPv6 tunnel list + **/ +static struct ip6_tnl __rcu ** +vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p) +{ + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + unsigned int h = 0; + int prio = 0; + + if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { + prio = 1; + h = HASH(remote, local); + } + return &ip6n->tnls[prio][h]; +} + +static void +vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms); + + rcu_assign_pointer(t->next , rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static void +vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) +{ + struct ip6_tnl __rcu **tp; + struct ip6_tnl *iter; + + for (tp = vti6_tnl_bucket(ip6n, &t->parms); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); + break; + } + } +} + +static void vti6_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + +static int vti6_tnl_create2(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + int err; + + err = vti6_dev_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &vti6_link_ops; + + dev_hold(dev); + vti6_tnl_link(ip6n, t); + + return 0; + +out: + return err; +} + +static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) +{ + struct net_device *dev; + struct ip6_tnl *t; + char name[IFNAMSIZ]; + int err; + + if (p->name[0]) + strlcpy(name, p->name, IFNAMSIZ); + else + sprintf(name, "ip6_vti%%d"); + + dev = alloc_netdev(sizeof(*t), name, vti6_dev_setup); + if (dev == NULL) + goto failed; + + dev_net_set(dev, net); + + t = netdev_priv(dev); + t->parms = *p; + t->net = dev_net(dev); + + err = vti6_tnl_create2(dev); + if (err < 0) + goto failed_free; + + return t; + +failed_free: + vti6_dev_free(dev); +failed: + return NULL; +} + +/** + * vti6_locate - find or create tunnel matching given parameters + * @net: network namespace + * @p: tunnel parameters + * @create: != 0 if allowed to create new tunnel if no match found + * + * Description: + * vti6_locate() first tries to locate an existing tunnel + * based on @parms. If this is unsuccessful, but @create is set a new + * tunnel device is created and registered for use. + * + * Return: + * matching tunnel or NULL + **/ +static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, + int create) +{ + const struct in6_addr *remote = &p->raddr; + const struct in6_addr *local = &p->laddr; + struct ip6_tnl __rcu **tp; + struct ip6_tnl *t; + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + for (tp = vti6_tnl_bucket(ip6n, p); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { + if (ipv6_addr_equal(local, &t->parms.laddr) && + ipv6_addr_equal(remote, &t->parms.raddr)) + return t; + } + if (!create) + return NULL; + return vti6_tnl_create(net, p); +} + +/** + * vti6_dev_uninit - tunnel device uninitializer + * @dev: the device to be destroyed + * + * Description: + * vti6_dev_uninit() removes tunnel from its list + **/ +static void vti6_dev_uninit(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev == ip6n->fb_tnl_dev) + RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); + else + vti6_tnl_unlink(ip6n, t); + dev_put(dev); +} + +static int vti6_rcv(struct sk_buff *skb) +{ + struct ip6_tnl *t; + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + + rcu_read_lock(); + if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, + &ipv6h->daddr)) != NULL) { + if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { + rcu_read_unlock(); + goto discard; + } + + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { + rcu_read_unlock(); + return 0; + } + + if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { + t->dev->stats.rx_dropped++; + rcu_read_unlock(); + goto discard; + } + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; + skb->mark = be32_to_cpu(t->parms.i_key); + + rcu_read_unlock(); + + return xfrm6_rcv(skb); + } + rcu_read_unlock(); + return -EINVAL; +discard: + kfree_skb(skb); + return 0; +} + +static int vti6_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; + + if (!t) + return 1; + + dev = t->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; + } + + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; +} + +/** + * vti6_addr_conflict - compare packet addresses to tunnel's own + * @t: the outgoing tunnel device + * @hdr: IPv6 header from the incoming packet + * + * Description: + * Avoid trivial tunneling loop by checking that tunnel exit-point + * doesn't match source of incoming packet. + * + * Return: + * 1 if conflict, + * 0 else + **/ +static inline bool +vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) +{ + return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); +} + +static bool vti6_state_check(const struct xfrm_state *x, + const struct in6_addr *dst, + const struct in6_addr *src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)dst; + xfrm_address_t *saddr = (xfrm_address_t *)src; + + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET6) + return false; + + if (ipv6_addr_any(dst)) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6)) + return false; + + return true; +} + +/** + * vti6_xmit - send a packet + * @skb: the outgoing socket buffer + * @dev: the outgoing tunnel device + * @fl: the flow informations for the xfrm_lookup + **/ +static int +vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + struct dst_entry *dst = skb_dst(skb); + struct net_device *tdev; + int err = -1; + + if (!dst) + goto tx_err_link_failure; + + dst_hold(dst); + dst = xfrm_lookup(t->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; + } + + if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr)) + goto tx_err_link_failure; + + tdev = dst->dev; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + t->parms.name); + goto tx_err_dst_release; + } + + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; + + err = dst_output(skb); + if (net_xmit_eval(err) == 0) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += skb->len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; + } + + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(dst); + return err; +} + +static netdev_tx_t +vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net_device_stats *stats = &t->dev->stats; + struct ipv6hdr *ipv6h; + struct flowi fl; + int ret; + + memset(&fl, 0, sizeof(fl)); + skb->mark = be32_to_cpu(t->parms.o_key); + + switch (skb->protocol) { + case htons(ETH_P_IPV6): + ipv6h = ipv6_hdr(skb); + + if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || + !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h)) + goto tx_err; + + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + default: + goto tx_err; + } + + ret = vti6_xmit(skb, dev, &fl); + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + __be32 spi; + __u32 mark; + struct xfrm_state *x; + struct ip6_tnl *t; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + int protocol = iph->nexthdr; + + t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr); + if (!t) + return -1; + + mark = be32_to_cpu(t->parms.o_key); + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data + offset); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data + offset); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data + offset); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; + + x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET6); + if (!x) + return 0; + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); + xfrm_state_put(x); + + return 0; +} + +static void vti6_link_config(struct ip6_tnl *t) +{ + struct net_device *dev = t->dev; + struct __ip6_tnl_parm *p = &t->parms; + + memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); + + p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | + IP6_TNL_F_CAP_PER_PACKET); + p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); + + if (p->flags & IP6_TNL_F_CAP_XMIT && p->flags & IP6_TNL_F_CAP_RCV) + dev->flags |= IFF_POINTOPOINT; + else + dev->flags &= ~IFF_POINTOPOINT; + + dev->iflink = p->link; +} + +/** + * vti6_tnl_change - update the tunnel parameters + * @t: tunnel to be changed + * @p: tunnel configuration parameters + * + * Description: + * vti6_tnl_change() updates the tunnel parameters + **/ +static int +vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) +{ + t->parms.laddr = p->laddr; + t->parms.raddr = p->raddr; + t->parms.link = p->link; + t->parms.i_key = p->i_key; + t->parms.o_key = p->o_key; + t->parms.proto = p->proto; + ip6_tnl_dst_reset(t); + vti6_link_config(t); + return 0; +} + +static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = dev_net(t->dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + int err; + + vti6_tnl_unlink(ip6n, t); + synchronize_net(); + err = vti6_tnl_change(t, p); + vti6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + +static void +vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u) +{ + p->laddr = u->laddr; + p->raddr = u->raddr; + p->link = u->link; + p->i_key = u->i_key; + p->o_key = u->o_key; + p->proto = u->proto; + + memcpy(p->name, u->name, sizeof(u->name)); +} + +static void +vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) +{ + u->laddr = p->laddr; + u->raddr = p->raddr; + u->link = p->link; + u->i_key = p->i_key; + u->o_key = p->o_key; + u->proto = p->proto; + + memcpy(u->name, p->name, sizeof(u->name)); +} + +/** + * vti6_tnl_ioctl - configure vti6 tunnels from userspace + * @dev: virtual device associated with tunnel + * @ifr: parameters passed from userspace + * @cmd: command to be performed + * + * Description: + * vti6_ioctl() is used for managing vti6 tunnels + * from userspace. + * + * The possible commands are the following: + * %SIOCGETTUNNEL: get tunnel parameters for device + * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters + * %SIOCCHGTUNNEL: change tunnel parameters to those given + * %SIOCDELTUNNEL: delete tunnel + * + * The fallback device "ip6_vti0", created during module + * initialization, can be used for creating other tunnel devices. + * + * Return: + * 0 on success, + * %-EFAULT if unable to copy data to or from userspace, + * %-EPERM if current process hasn't %CAP_NET_ADMIN set + * %-EINVAL if passed tunnel parameters are invalid, + * %-EEXIST if changing a tunnel's parameters would cause a conflict + * %-ENODEV if attempting to change or delete a nonexisting device + **/ +static int +vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + int err = 0; + struct ip6_tnl_parm2 p; + struct __ip6_tnl_parm p1; + struct ip6_tnl *t = NULL; + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + switch (cmd) { + case SIOCGETTUNNEL: + if (dev == ip6n->fb_tnl_dev) { + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + err = -EFAULT; + break; + } + vti6_parm_from_user(&p1, &p); + t = vti6_locate(net, &p1, 0); + } else { + memset(&p, 0, sizeof(p)); + } + if (t == NULL) + t = netdev_priv(dev); + vti6_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + break; + case SIOCADDTUNNEL: + case SIOCCHGTUNNEL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + break; + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + break; + err = -EINVAL; + if (p.proto != IPPROTO_IPV6 && p.proto != 0) + break; + vti6_parm_from_user(&p1, &p); + t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL); + if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else + t = netdev_priv(dev); + + err = vti6_update(t, &p1); + } + if (t) { + err = 0; + vti6_parm_to_user(&p, &t->parms); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + err = -EFAULT; + + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + break; + case SIOCDELTUNNEL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + break; + + if (dev == ip6n->fb_tnl_dev) { + err = -EFAULT; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + break; + err = -ENOENT; + vti6_parm_from_user(&p1, &p); + t = vti6_locate(net, &p1, 0); + if (t == NULL) + break; + err = -EPERM; + if (t->dev == ip6n->fb_tnl_dev) + break; + dev = t->dev; + } + err = 0; + unregister_netdevice(dev); + break; + default: + err = -EINVAL; + } + return err; +} + +/** + * vti6_tnl_change_mtu - change mtu manually for tunnel device + * @dev: virtual device associated with tunnel + * @new_mtu: the new mtu + * + * Return: + * 0 on success, + * %-EINVAL if mtu too small + **/ +static int vti6_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; + + dev->mtu = new_mtu; + return 0; +} + +static const struct net_device_ops vti6_netdev_ops = { + .ndo_uninit = vti6_dev_uninit, + .ndo_start_xmit = vti6_tnl_xmit, + .ndo_do_ioctl = vti6_ioctl, + .ndo_change_mtu = vti6_change_mtu, + .ndo_get_stats64 = ip_tunnel_get_stats64, +}; + +/** + * vti6_dev_setup - setup virtual tunnel device + * @dev: virtual device associated with tunnel + * + * Description: + * Initialize function pointers and device parameters + **/ +static void vti6_dev_setup(struct net_device *dev) +{ + dev->netdev_ops = &vti6_netdev_ops; + dev->destructor = vti6_dev_free; + + dev->type = ARPHRD_TUNNEL6; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr); + dev->mtu = ETH_DATA_LEN; + dev->flags |= IFF_NOARP; + dev->addr_len = sizeof(struct in6_addr); + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; +} + +/** + * vti6_dev_init_gen - general initializer for all tunnel devices + * @dev: virtual device associated with tunnel + **/ +static inline int vti6_dev_init_gen(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + + t->dev = dev; + t->net = dev_net(dev); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + return 0; +} + +/** + * vti6_dev_init - initializer for all non fallback tunnel devices + * @dev: virtual device associated with tunnel + **/ +static int vti6_dev_init(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + int err = vti6_dev_init_gen(dev); + + if (err) + return err; + vti6_link_config(t); + return 0; +} + +/** + * vti6_fb_tnl_dev_init - initializer for fallback tunnel device + * @dev: fallback device + * + * Return: 0 + **/ +static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + int err = vti6_dev_init_gen(dev); + + if (err) + return err; + + t->parms.proto = IPPROTO_IPV6; + dev_hold(dev); + + vti6_link_config(t); + + rcu_assign_pointer(ip6n->tnls_wc[0], t); + return 0; +} + +static int vti6_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + return 0; +} + +static void vti6_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_VTI_LINK]) + parms->link = nla_get_u32(data[IFLA_VTI_LINK]); + + if (data[IFLA_VTI_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_VTI_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_VTI_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_VTI_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_VTI_IKEY]) + parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); + + if (data[IFLA_VTI_OKEY]) + parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); +} + +static int vti6_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + vti6_netlink_parms(data, &nt->parms); + + nt->parms.proto = IPPROTO_IPV6; + + if (vti6_locate(net, &nt->parms, 0)) + return -EEXIST; + + return vti6_tnl_create2(dev); +} + +static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t; + struct __ip6_tnl_parm p; + struct net *net = dev_net(dev); + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + vti6_netlink_parms(data, &p); + + t = vti6_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return vti6_update(t, &p); +} + +static size_t vti6_get_size(const struct net_device *dev) +{ + return + /* IFLA_VTI_LINK */ + nla_total_size(4) + + /* IFLA_VTI_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_VTI_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_VTI_IKEY */ + nla_total_size(4) + + /* IFLA_VTI_OKEY */ + nla_total_size(4) + + 0; +} + +static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) || + nla_put(skb, IFLA_VTI_LOCAL, sizeof(struct in6_addr), + &parm->laddr) || + nla_put(skb, IFLA_VTI_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || + nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) || + nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = { + [IFLA_VTI_LINK] = { .type = NLA_U32 }, + [IFLA_VTI_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_VTI_IKEY] = { .type = NLA_U32 }, + [IFLA_VTI_OKEY] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops vti6_link_ops __read_mostly = { + .kind = "vti6", + .maxtype = IFLA_VTI_MAX, + .policy = vti6_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = vti6_dev_setup, + .validate = vti6_validate, + .newlink = vti6_newlink, + .changelink = vti6_changelink, + .get_size = vti6_get_size, + .fill_info = vti6_fill_info, +}; + +static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) +{ + int h; + struct ip6_tnl *t; + LIST_HEAD(list); + + for (h = 0; h < HASH_SIZE; h++) { + t = rtnl_dereference(ip6n->tnls_r_l[h]); + while (t != NULL) { + unregister_netdevice_queue(t->dev, &list); + t = rtnl_dereference(t->next); + } + } + + t = rtnl_dereference(ip6n->tnls_wc[0]); + unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_many(&list); +} + +static int __net_init vti6_init_net(struct net *net) +{ + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct ip6_tnl *t = NULL; + int err; + + ip6n->tnls[0] = ip6n->tnls_wc; + ip6n->tnls[1] = ip6n->tnls_r_l; + + err = -ENOMEM; + ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", + vti6_dev_setup); + + if (!ip6n->fb_tnl_dev) + goto err_alloc_dev; + dev_net_set(ip6n->fb_tnl_dev, net); + + err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + if (err < 0) + goto err_register; + + 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: + vti6_dev_free(ip6n->fb_tnl_dev); +err_alloc_dev: + return err; +} + +static void __net_exit vti6_exit_net(struct net *net) +{ + struct vti6_net *ip6n = net_generic(net, vti6_net_id); + + rtnl_lock(); + vti6_destroy_tunnels(ip6n); + rtnl_unlock(); +} + +static struct pernet_operations vti6_net_ops = { + .init = vti6_init_net, + .exit = vti6_exit_net, + .id = &vti6_net_id, + .size = sizeof(struct vti6_net), +}; + +static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +static struct xfrm6_protocol vti_ah6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +/** + * vti6_tunnel_init - register protocol and reserve needed resources + * + * Return: 0 on success + **/ +static int __init vti6_tunnel_init(void) +{ + int err; + + err = register_pernet_device(&vti6_net_ops); + if (err < 0) + goto out_pernet; + + err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); + if (err < 0) { + pr_err("%s: can't register vti6 protocol\n", __func__); + + goto out; + } + + err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); + if (err < 0) { + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); + pr_err("%s: can't register vti6 protocol\n", __func__); + + goto out; + } + + err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); + if (err < 0) { + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); + pr_err("%s: can't register vti6 protocol\n", __func__); + + goto out; + } + + err = rtnl_link_register(&vti6_link_ops); + if (err < 0) + goto rtnl_link_failed; + + return 0; + +rtnl_link_failed: + xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); +out: + unregister_pernet_device(&vti6_net_ops); +out_pernet: + return err; +} + +/** + * vti6_tunnel_cleanup - free resources and unregister protocol + **/ +static void __exit vti6_tunnel_cleanup(void) +{ + rtnl_link_unregister(&vti6_link_ops); + if (xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP)) + pr_info("%s: can't deregister protocol\n", __func__); + if (xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH)) + pr_info("%s: can't deregister protocol\n", __func__); + if (xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP)) + pr_info("%s: can't deregister protocol\n", __func__); + + unregister_pernet_device(&vti6_net_ops); +} + +module_init(vti6_tunnel_init); +module_exit(vti6_tunnel_cleanup); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("vti6"); +MODULE_ALIAS_NETDEV("ip6_vti0"); +MODULE_AUTHOR("Steffen Klassert"); +MODULE_DESCRIPTION("IPv6 virtual tunnel interface"); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c new file mode 100644 index 00000000000..8250474ab7d --- /dev/null +++ b/net/ipv6/ip6mr.c @@ -0,0 +1,2503 @@ +/* + * Linux IPv6 multicast routing support for BSD pim6sd + * Based on net/ipv4/ipmr.c. + * + * (c) 2004 Mickael Hoerdt, <hoerdt@clarinet.u-strasbg.fr> + * LSIIT Laboratory, Strasbourg, France + * (c) 2004 Jean-Philippe Andriot, <jean-philippe.andriot@6WIND.com> + * 6WIND, Paris, France + * Copyright (C)2007,2008 USAGI/WIDE Project + * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> + * + * 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. + * + */ + +#include <asm/uaccess.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/errno.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/kernel.h> +#include <linux/fcntl.h> +#include <linux/stat.h> +#include <linux/socket.h> +#include <linux/inet.h> +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/compat.h> +#include <net/protocol.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/raw.h> +#include <linux/notifier.h> +#include <linux/if_arp.h> +#include <net/checksum.h> +#include <net/netlink.h> +#include <net/fib_rules.h> + +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <linux/mroute6.h> +#include <linux/pim.h> +#include <net/addrconf.h> +#include <linux/netfilter_ipv6.h> +#include <linux/export.h> +#include <net/ip6_checksum.h> +#include <linux/netconf.h> + +struct mr6_table { + struct list_head list; +#ifdef CONFIG_NET_NS + struct net *net; +#endif + u32 id; + struct sock *mroute6_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc6_unres_queue; + struct list_head mfc6_cache_array[MFC6_LINES]; + struct mif_device vif6_table[MAXMIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + bool mroute_do_assert; + bool mroute_do_pim; +#ifdef CONFIG_IPV6_PIMSM_V2 + int mroute_reg_vif_num; +#endif +}; + +struct ip6mr_rule { + struct fib_rule common; +}; + +struct ip6mr_result { + struct mr6_table *mrt; +}; + +/* Big lock, protecting vif table, mrt cache and mroute socket state. + Note that the changes are semaphored via rtnl_lock. + */ + +static DEFINE_RWLOCK(mrt_lock); + +/* + * Multicast router control variables + */ + +#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL) + +/* Special spinlock for queue of unresolved entries */ +static DEFINE_SPINLOCK(mfc_unres_lock); + +/* We return to original Alan's scheme. Hash table of resolved + entries is changed only in process context and protected + with weak lock mrt_lock. Queue of unresolved entries is protected + with strong spinlock mfc_unres_lock. + + In this case data path is free of exclusive locks at all. + */ + +static struct kmem_cache *mrt_cachep __read_mostly; + +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); +static void ip6mr_free_table(struct mr6_table *mrt); + +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, + mifi_t mifi, int assert); +static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm); +static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, + int cmd); +static int ip6mr_rtm_dumproute(struct sk_buff *skb, + struct netlink_callback *cb); +static void mroute_clean_tables(struct mr6_table *mrt); +static void ipmr_expire_process(unsigned long arg); + +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES +#define ip6mr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + + ip6mr_for_each_table(mrt, net) { + if (mrt->id == id) + return mrt; + } + return NULL; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, + struct mr6_table **mrt) +{ + int err; + struct ip6mr_result res; + struct fib_lookup_arg arg = { + .result = &res, + .flags = FIB_LOOKUP_NOREF, + }; + + err = fib_rules_lookup(net->ipv6.mr6_rules_ops, + flowi6_to_flowi(flp6), 0, &arg); + if (err < 0) + return err; + *mrt = res.mrt; + return 0; +} + +static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct ip6mr_result *res = arg->result; + struct mr6_table *mrt; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + mrt = ip6mr_get_table(rule->fr_net, rule->table); + if (mrt == NULL) + return -EAGAIN; + res->mrt = mrt; + return 0; +} + +static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) +{ + return 1; +} + +static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { + FRA_GENERIC_POLICY, +}; + +static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, struct nlattr **tb) +{ + return 0; +} + +static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + return 1; +} + +static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + frh->dst_len = 0; + frh->src_len = 0; + frh->tos = 0; + return 0; +} + +static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { + .family = RTNL_FAMILY_IP6MR, + .rule_size = sizeof(struct ip6mr_rule), + .addr_size = sizeof(struct in6_addr), + .action = ip6mr_rule_action, + .match = ip6mr_rule_match, + .configure = ip6mr_rule_configure, + .compare = ip6mr_rule_compare, + .default_pref = fib_default_rule_pref, + .fill = ip6mr_rule_fill, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = ip6mr_rule_policy, + .owner = THIS_MODULE, +}; + +static int __net_init ip6mr_rules_init(struct net *net) +{ + struct fib_rules_ops *ops; + struct mr6_table *mrt; + int err; + + ops = fib_rules_register(&ip6mr_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + INIT_LIST_HEAD(&net->ipv6.mr6_tables); + + mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) { + err = -ENOMEM; + goto err1; + } + + err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0); + if (err < 0) + goto err2; + + net->ipv6.mr6_rules_ops = ops; + return 0; + +err2: + kfree(mrt); +err1: + fib_rules_unregister(ops); + return err; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + struct mr6_table *mrt, *next; + + rtnl_lock(); + list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { + list_del(&mrt->list); + ip6mr_free_table(mrt); + } + rtnl_unlock(); + fib_rules_unregister(net->ipv6.mr6_rules_ops); +} +#else +#define ip6mr_for_each_table(mrt, net) \ + for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + return net->ipv6.mrt6; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, + struct mr6_table **mrt) +{ + *mrt = net->ipv6.mrt6; + return 0; +} + +static int __net_init ip6mr_rules_init(struct net *net) +{ + net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT); + return net->ipv6.mrt6 ? 0 : -ENOMEM; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + rtnl_lock(); + ip6mr_free_table(net->ipv6.mrt6); + net->ipv6.mrt6 = NULL; + rtnl_unlock(); +} +#endif + +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + unsigned int i; + + mrt = ip6mr_get_table(net, id); + if (mrt != NULL) + return mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) + return NULL; + mrt->id = id; + write_pnet(&mrt->net, net); + + /* Forwarding cache */ + for (i = 0; i < MFC6_LINES; i++) + INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); + + INIT_LIST_HEAD(&mrt->mfc6_unres_queue); + + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); + +#ifdef CONFIG_IPV6_PIMSM_V2 + mrt->mroute_reg_vif_num = -1; +#endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); +#endif + return mrt; +} + +static void ip6mr_free_table(struct mr6_table *mrt) +{ + del_timer(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); +} + +#ifdef CONFIG_PROC_FS + +struct ipmr_mfc_iter { + struct seq_net_private p; + struct mr6_table *mrt; + struct list_head *cache; + int ct; +}; + + +static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, + struct ipmr_mfc_iter *it, loff_t pos) +{ + struct mr6_table *mrt = it->mrt; + struct mfc6_cache *mfc; + + read_lock(&mrt_lock); + for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { + it->cache = &mrt->mfc6_cache_array[it->ct]; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) + return mfc; + } + read_unlock(&mrt_lock); + + spin_lock_bh(&mfc_unres_lock); + it->cache = &mrt->mfc6_unres_queue; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) + return mfc; + spin_unlock_bh(&mfc_unres_lock); + + it->cache = NULL; + return NULL; +} + +/* + * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif + */ + +struct ipmr_vif_iter { + struct seq_net_private p; + struct mr6_table *mrt; + int ct; +}; + +static struct mif_device *ip6mr_vif_seq_idx(struct net *net, + struct ipmr_vif_iter *iter, + loff_t pos) +{ + struct mr6_table *mrt = iter->mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!MIF_EXISTS(mrt, iter->ct)) + continue; + if (pos-- == 0) + return &mrt->vif6_table[iter->ct]; + } + return NULL; +} + +static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(mrt_lock) +{ + struct ipmr_vif_iter *iter = seq->private; + struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + iter->mrt = mrt; + + read_lock(&mrt_lock); + return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) + : SEQ_START_TOKEN; +} + +static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct ipmr_vif_iter *iter = seq->private; + struct net *net = seq_file_net(seq); + struct mr6_table *mrt = iter->mrt; + + ++*pos; + if (v == SEQ_START_TOKEN) + return ip6mr_vif_seq_idx(net, iter, 0); + + while (++iter->ct < mrt->maxvif) { + if (!MIF_EXISTS(mrt, iter->ct)) + continue; + return &mrt->vif6_table[iter->ct]; + } + return NULL; +} + +static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) + __releases(mrt_lock) +{ + read_unlock(&mrt_lock); +} + +static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) +{ + struct ipmr_vif_iter *iter = seq->private; + struct mr6_table *mrt = iter->mrt; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, + "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); + } else { + const struct mif_device *vif = v; + const char *name = vif->dev ? vif->dev->name : "none"; + + seq_printf(seq, + "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", + vif - mrt->vif6_table, + name, vif->bytes_in, vif->pkt_in, + vif->bytes_out, vif->pkt_out, + vif->flags); + } + return 0; +} + +static const struct seq_operations ip6mr_vif_seq_ops = { + .start = ip6mr_vif_seq_start, + .next = ip6mr_vif_seq_next, + .stop = ip6mr_vif_seq_stop, + .show = ip6mr_vif_seq_show, +}; + +static int ip6mr_vif_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ip6mr_vif_seq_ops, + sizeof(struct ipmr_vif_iter)); +} + +static const struct file_operations ip6mr_vif_fops = { + .owner = THIS_MODULE, + .open = ip6mr_vif_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct ipmr_mfc_iter *it = seq->private; + struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + it->mrt = mrt; + return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) + : SEQ_START_TOKEN; +} + +static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct mfc6_cache *mfc = v; + struct ipmr_mfc_iter *it = seq->private; + struct net *net = seq_file_net(seq); + struct mr6_table *mrt = it->mrt; + + ++*pos; + + if (v == SEQ_START_TOKEN) + return ipmr_mfc_seq_idx(net, seq->private, 0); + + if (mfc->list.next != it->cache) + return list_entry(mfc->list.next, struct mfc6_cache, list); + + if (it->cache == &mrt->mfc6_unres_queue) + goto end_of_list; + + BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]); + + while (++it->ct < MFC6_LINES) { + it->cache = &mrt->mfc6_cache_array[it->ct]; + if (list_empty(it->cache)) + continue; + return list_first_entry(it->cache, struct mfc6_cache, list); + } + + /* exhausted cache_array, show unresolved */ + read_unlock(&mrt_lock); + it->cache = &mrt->mfc6_unres_queue; + it->ct = 0; + + spin_lock_bh(&mfc_unres_lock); + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mfc6_cache, list); + + end_of_list: + spin_unlock_bh(&mfc_unres_lock); + it->cache = NULL; + + return NULL; +} + +static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) +{ + struct ipmr_mfc_iter *it = seq->private; + struct mr6_table *mrt = it->mrt; + + if (it->cache == &mrt->mfc6_unres_queue) + spin_unlock_bh(&mfc_unres_lock); + else if (it->cache == mrt->mfc6_cache_array) + read_unlock(&mrt_lock); +} + +static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) +{ + int n; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, + "Group " + "Origin " + "Iif Pkts Bytes Wrong Oifs\n"); + } else { + const struct mfc6_cache *mfc = v; + const struct ipmr_mfc_iter *it = seq->private; + struct mr6_table *mrt = it->mrt; + + seq_printf(seq, "%pI6 %pI6 %-3hd", + &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, + mfc->mf6c_parent); + + if (it->cache != &mrt->mfc6_unres_queue) { + seq_printf(seq, " %8lu %8lu %8lu", + mfc->mfc_un.res.pkt, + mfc->mfc_un.res.bytes, + mfc->mfc_un.res.wrong_if); + for (n = mfc->mfc_un.res.minvif; + n < mfc->mfc_un.res.maxvif; n++) { + if (MIF_EXISTS(mrt, n) && + mfc->mfc_un.res.ttls[n] < 255) + seq_printf(seq, + " %2d:%-3d", + n, mfc->mfc_un.res.ttls[n]); + } + } else { + /* unresolved mfc_caches don't contain + * pkt, bytes and wrong_if values + */ + seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); + } + seq_putc(seq, '\n'); + } + return 0; +} + +static const struct seq_operations ipmr_mfc_seq_ops = { + .start = ipmr_mfc_seq_start, + .next = ipmr_mfc_seq_next, + .stop = ipmr_mfc_seq_stop, + .show = ipmr_mfc_seq_show, +}; + +static int ipmr_mfc_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ipmr_mfc_seq_ops, + sizeof(struct ipmr_mfc_iter)); +} + +static const struct file_operations ip6mr_mfc_fops = { + .owner = THIS_MODULE, + .open = ipmr_mfc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; +#endif + +#ifdef CONFIG_IPV6_PIMSM_V2 + +static int pim6_rcv(struct sk_buff *skb) +{ + struct pimreghdr *pim; + struct ipv6hdr *encap; + struct net_device *reg_dev = NULL; + struct net *net = dev_net(skb->dev); + struct mr6_table *mrt; + struct flowi6 fl6 = { + .flowi6_iif = skb->dev->ifindex, + .flowi6_mark = skb->mark, + }; + int reg_vif_num; + + if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) + goto drop; + + pim = (struct pimreghdr *)skb_transport_header(skb); + if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) || + (pim->flags & PIM_NULL_REGISTER) || + (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, + sizeof(*pim), IPPROTO_PIM, + csum_partial((void *)pim, sizeof(*pim), 0)) && + csum_fold(skb_checksum(skb, 0, skb->len, 0)))) + goto drop; + + /* check if the inner packet is destined to mcast group */ + encap = (struct ipv6hdr *)(skb_transport_header(skb) + + sizeof(*pim)); + + if (!ipv6_addr_is_multicast(&encap->daddr) || + encap->payload_len == 0 || + ntohs(encap->payload_len) + sizeof(*pim) > skb->len) + goto drop; + + if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) + goto drop; + reg_vif_num = mrt->mroute_reg_vif_num; + + read_lock(&mrt_lock); + if (reg_vif_num >= 0) + reg_dev = mrt->vif6_table[reg_vif_num].dev; + if (reg_dev) + dev_hold(reg_dev); + read_unlock(&mrt_lock); + + if (reg_dev == NULL) + goto drop; + + skb->mac_header = skb->network_header; + skb_pull(skb, (u8 *)encap - skb->data); + skb_reset_network_header(skb); + skb->protocol = htons(ETH_P_IPV6); + skb->ip_summed = CHECKSUM_NONE; + + skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); + + netif_rx(skb); + + dev_put(reg_dev); + return 0; + drop: + kfree_skb(skb); + return 0; +} + +static const struct inet6_protocol pim6_protocol = { + .handler = pim6_rcv, +}; + +/* Service routines creating virtual interfaces: PIMREG */ + +static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct mr6_table *mrt; + struct flowi6 fl6 = { + .flowi6_oif = dev->ifindex, + .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, + .flowi6_mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl6, &mrt); + if (err < 0) { + kfree_skb(skb); + return err; + } + + read_lock(&mrt_lock); + dev->stats.tx_bytes += skb->len; + dev->stats.tx_packets++; + ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT); + read_unlock(&mrt_lock); + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static const struct net_device_ops reg_vif_netdev_ops = { + .ndo_start_xmit = reg_vif_xmit, +}; + +static void reg_vif_setup(struct net_device *dev) +{ + dev->type = ARPHRD_PIMREG; + dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8; + dev->flags = IFF_NOARP; + dev->netdev_ops = ®_vif_netdev_ops; + dev->destructor = free_netdev; + dev->features |= NETIF_F_NETNS_LOCAL; +} + +static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) +{ + struct net_device *dev; + char name[IFNAMSIZ]; + + if (mrt->id == RT6_TABLE_DFLT) + sprintf(name, "pim6reg"); + else + sprintf(name, "pim6reg%u", mrt->id); + + dev = alloc_netdev(0, name, reg_vif_setup); + if (dev == NULL) + return NULL; + + dev_net_set(dev, net); + + if (register_netdevice(dev)) { + free_netdev(dev); + return NULL; + } + dev->iflink = 0; + + if (dev_open(dev)) + goto failure; + + dev_hold(dev); + return dev; + +failure: + /* allow the register to be completed before unregistering. */ + rtnl_unlock(); + rtnl_lock(); + + unregister_netdevice(dev); + return NULL; +} +#endif + +/* + * Delete a VIF entry + */ + +static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) +{ + struct mif_device *v; + struct net_device *dev; + struct inet6_dev *in6_dev; + + if (vifi < 0 || vifi >= mrt->maxvif) + return -EADDRNOTAVAIL; + + v = &mrt->vif6_table[vifi]; + + write_lock_bh(&mrt_lock); + dev = v->dev; + v->dev = NULL; + + if (!dev) { + write_unlock_bh(&mrt_lock); + return -EADDRNOTAVAIL; + } + +#ifdef CONFIG_IPV6_PIMSM_V2 + if (vifi == mrt->mroute_reg_vif_num) + mrt->mroute_reg_vif_num = -1; +#endif + + if (vifi + 1 == mrt->maxvif) { + int tmp; + for (tmp = vifi - 1; tmp >= 0; tmp--) { + if (MIF_EXISTS(mrt, tmp)) + break; + } + mrt->maxvif = tmp + 1; + } + + write_unlock_bh(&mrt_lock); + + dev_set_allmulti(dev, -1); + + in6_dev = __in6_dev_get(dev); + if (in6_dev) { + in6_dev->cnf.mc_forwarding--; + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in6_dev->cnf); + } + + if (v->flags & MIFF_REGISTER) + unregister_netdevice_queue(dev, head); + + dev_put(dev); + return 0; +} + +static inline void ip6mr_cache_free(struct mfc6_cache *c) +{ + kmem_cache_free(mrt_cachep, c); +} + +/* Destroy an unresolved cache entry, killing queued skbs + and reporting error to netlink readers. + */ + +static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) +{ + struct net *net = read_pnet(&mrt->net); + struct sk_buff *skb; + + atomic_dec(&mrt->cache_resolve_queue_len); + + while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { + if (ipv6_hdr(skb)->version == 0) { + struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + nlh->nlmsg_type = NLMSG_ERROR; + nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); + skb_trim(skb, nlh->nlmsg_len); + ((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT; + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); + } else + kfree_skb(skb); + } + + ip6mr_cache_free(c); +} + + +/* Timer process for all the unresolved queue. */ + +static void ipmr_do_expire_process(struct mr6_table *mrt) +{ + unsigned long now = jiffies; + unsigned long expires = 10 * HZ; + struct mfc6_cache *c, *next; + + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + if (time_after(c->mfc_un.unres.expires, now)) { + /* not yet... */ + unsigned long interval = c->mfc_un.unres.expires - now; + if (interval < expires) + expires = interval; + continue; + } + + list_del(&c->list); + mr6_netlink_event(mrt, c, RTM_DELROUTE); + ip6mr_destroy_unres(mrt, c); + } + + if (!list_empty(&mrt->mfc6_unres_queue)) + mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); +} + +static void ipmr_expire_process(unsigned long arg) +{ + struct mr6_table *mrt = (struct mr6_table *)arg; + + if (!spin_trylock(&mfc_unres_lock)) { + mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); + return; + } + + if (!list_empty(&mrt->mfc6_unres_queue)) + ipmr_do_expire_process(mrt); + + spin_unlock(&mfc_unres_lock); +} + +/* Fill oifs list. It is called under write locked mrt_lock. */ + +static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache, + unsigned char *ttls) +{ + int vifi; + + cache->mfc_un.res.minvif = MAXMIFS; + cache->mfc_un.res.maxvif = 0; + memset(cache->mfc_un.res.ttls, 255, MAXMIFS); + + for (vifi = 0; vifi < mrt->maxvif; vifi++) { + if (MIF_EXISTS(mrt, vifi) && + ttls[vifi] && ttls[vifi] < 255) { + cache->mfc_un.res.ttls[vifi] = ttls[vifi]; + if (cache->mfc_un.res.minvif > vifi) + cache->mfc_un.res.minvif = vifi; + if (cache->mfc_un.res.maxvif <= vifi) + cache->mfc_un.res.maxvif = vifi + 1; + } + } +} + +static int mif6_add(struct net *net, struct mr6_table *mrt, + struct mif6ctl *vifc, int mrtsock) +{ + int vifi = vifc->mif6c_mifi; + struct mif_device *v = &mrt->vif6_table[vifi]; + struct net_device *dev; + struct inet6_dev *in6_dev; + int err; + + /* Is vif busy ? */ + if (MIF_EXISTS(mrt, vifi)) + return -EADDRINUSE; + + switch (vifc->mif6c_flags) { +#ifdef CONFIG_IPV6_PIMSM_V2 + case MIFF_REGISTER: + /* + * Special Purpose VIF in PIM + * All the packets will be sent to the daemon + */ + if (mrt->mroute_reg_vif_num >= 0) + return -EADDRINUSE; + dev = ip6mr_reg_vif(net, mrt); + if (!dev) + return -ENOBUFS; + err = dev_set_allmulti(dev, 1); + if (err) { + unregister_netdevice(dev); + dev_put(dev); + return err; + } + break; +#endif + case 0: + dev = dev_get_by_index(net, vifc->mif6c_pifi); + if (!dev) + return -EADDRNOTAVAIL; + err = dev_set_allmulti(dev, 1); + if (err) { + dev_put(dev); + return err; + } + break; + default: + return -EINVAL; + } + + in6_dev = __in6_dev_get(dev); + if (in6_dev) { + in6_dev->cnf.mc_forwarding++; + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in6_dev->cnf); + } + + /* + * Fill in the VIF structures + */ + v->rate_limit = vifc->vifc_rate_limit; + v->flags = vifc->mif6c_flags; + if (!mrtsock) + v->flags |= VIFF_STATIC; + v->threshold = vifc->vifc_threshold; + v->bytes_in = 0; + v->bytes_out = 0; + v->pkt_in = 0; + v->pkt_out = 0; + v->link = dev->ifindex; + if (v->flags & MIFF_REGISTER) + v->link = dev->iflink; + + /* And finish update writing critical data */ + write_lock_bh(&mrt_lock); + v->dev = dev; +#ifdef CONFIG_IPV6_PIMSM_V2 + if (v->flags & MIFF_REGISTER) + mrt->mroute_reg_vif_num = vifi; +#endif + if (vifi + 1 > mrt->maxvif) + mrt->maxvif = vifi + 1; + write_unlock_bh(&mrt_lock); + return 0; +} + +static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, + const struct in6_addr *origin, + const struct in6_addr *mcastgrp) +{ + int line = MFC6_HASH(mcastgrp, origin); + struct mfc6_cache *c; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { + if (ipv6_addr_equal(&c->mf6c_origin, origin) && + ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) + return c; + } + return NULL; +} + +/* Look for a (*,*,oif) entry */ +static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt, + mifi_t mifi) +{ + int line = MFC6_HASH(&in6addr_any, &in6addr_any); + struct mfc6_cache *c; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp) && + (c->mfc_un.res.ttls[mifi] < 255)) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt, + struct in6_addr *mcastgrp, + mifi_t mifi) +{ + int line = MFC6_HASH(mcastgrp, &in6addr_any); + struct mfc6_cache *c, *proxy; + + if (ipv6_addr_any(mcastgrp)) + goto skip; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) { + if (c->mfc_un.res.ttls[mifi] < 255) + return c; + + /* It's ok if the mifi is part of the static tree */ + proxy = ip6mr_cache_find_any_parent(mrt, + c->mf6c_parent); + if (proxy && proxy->mfc_un.res.ttls[mifi] < 255) + return c; + } + +skip: + return ip6mr_cache_find_any_parent(mrt, mifi); +} + +/* + * Allocate a multicast cache entry + */ +static struct mfc6_cache *ip6mr_cache_alloc(void) +{ + struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); + if (c == NULL) + return NULL; + c->mfc_un.res.minvif = MAXMIFS; + return c; +} + +static struct mfc6_cache *ip6mr_cache_alloc_unres(void) +{ + struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); + if (c == NULL) + return NULL; + skb_queue_head_init(&c->mfc_un.unres.unresolved); + c->mfc_un.unres.expires = jiffies + 10 * HZ; + return c; +} + +/* + * A cache entry has gone into a resolved state from queued + */ + +static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, + struct mfc6_cache *uc, struct mfc6_cache *c) +{ + struct sk_buff *skb; + + /* + * Play the pending entries through our router + */ + + while((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { + if (ipv6_hdr(skb)->version == 0) { + struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + + if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { + nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; + } else { + nlh->nlmsg_type = NLMSG_ERROR; + nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); + skb_trim(skb, nlh->nlmsg_len); + ((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE; + } + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); + } else + ip6_mr_forward(net, mrt, skb, c); + } +} + +/* + * Bounce a cache query up to pim6sd. We could use netlink for this but pim6sd + * expects the following bizarre scheme. + * + * Called under mrt_lock. + */ + +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, + mifi_t mifi, int assert) +{ + struct sk_buff *skb; + struct mrt6msg *msg; + int ret; + +#ifdef CONFIG_IPV6_PIMSM_V2 + if (assert == MRT6MSG_WHOLEPKT) + skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt) + +sizeof(*msg)); + else +#endif + skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC); + + if (!skb) + return -ENOBUFS; + + /* I suppose that internal messages + * do not require checksums */ + + skb->ip_summed = CHECKSUM_UNNECESSARY; + +#ifdef CONFIG_IPV6_PIMSM_V2 + if (assert == MRT6MSG_WHOLEPKT) { + /* Ugly, but we have no choice with this interface. + Duplicate old header, fix length etc. + And all this only to mangle msg->im6_msgtype and + to set msg->im6_mbz to "mbz" :-) + */ + skb_push(skb, -skb_network_offset(pkt)); + + skb_push(skb, sizeof(*msg)); + skb_reset_transport_header(skb); + msg = (struct mrt6msg *)skb_transport_header(skb); + msg->im6_mbz = 0; + msg->im6_msgtype = MRT6MSG_WHOLEPKT; + msg->im6_mif = mrt->mroute_reg_vif_num; + msg->im6_pad = 0; + msg->im6_src = ipv6_hdr(pkt)->saddr; + msg->im6_dst = ipv6_hdr(pkt)->daddr; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else +#endif + { + /* + * Copy the IP header + */ + + skb_put(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr)); + + /* + * Add our header + */ + skb_put(skb, sizeof(*msg)); + skb_reset_transport_header(skb); + msg = (struct mrt6msg *)skb_transport_header(skb); + + msg->im6_mbz = 0; + msg->im6_msgtype = assert; + msg->im6_mif = mifi; + msg->im6_pad = 0; + 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; + } + + if (mrt->mroute6_sk == NULL) { + kfree_skb(skb); + return -EINVAL; + } + + /* + * Deliver to user space multicast routing algorithms + */ + ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); + if (ret < 0) { + net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); + kfree_skb(skb); + } + + return ret; +} + +/* + * Queue a packet for resolution. It gets locked cache entry! + */ + +static int +ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) +{ + bool found = false; + int err; + struct mfc6_cache *c; + + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(c, &mrt->mfc6_unres_queue, list) { + if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && + ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { + found = true; + break; + } + } + + if (!found) { + /* + * Create a new entry if allowable + */ + + if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || + (c = ip6mr_cache_alloc_unres()) == NULL) { + spin_unlock_bh(&mfc_unres_lock); + + kfree_skb(skb); + return -ENOBUFS; + } + + /* + * Fill in the new cache entry + */ + c->mf6c_parent = -1; + c->mf6c_origin = ipv6_hdr(skb)->saddr; + c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; + + /* + * Reflect first query at pim6sd + */ + err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); + if (err < 0) { + /* If the report failed throw the cache entry + out - Brad Parker + */ + spin_unlock_bh(&mfc_unres_lock); + + ip6mr_cache_free(c); + kfree_skb(skb); + return err; + } + + atomic_inc(&mrt->cache_resolve_queue_len); + list_add(&c->list, &mrt->mfc6_unres_queue); + mr6_netlink_event(mrt, c, RTM_NEWROUTE); + + ipmr_do_expire_process(mrt); + } + + /* + * See if we can append the packet + */ + if (c->mfc_un.unres.unresolved.qlen > 3) { + kfree_skb(skb); + err = -ENOBUFS; + } else { + skb_queue_tail(&c->mfc_un.unres.unresolved, skb); + err = 0; + } + + spin_unlock_bh(&mfc_unres_lock); + return err; +} + +/* + * MFC6 cache manipulation by user space + */ + +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, + int parent) +{ + int line; + struct mfc6_cache *c, *next; + + line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); + + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { + if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == c->mf6c_parent)) { + write_lock_bh(&mrt_lock); + list_del(&c->list); + write_unlock_bh(&mrt_lock); + + mr6_netlink_event(mrt, c, RTM_DELROUTE); + ip6mr_cache_free(c); + return 0; + } + } + return -ENOENT; +} + +static int ip6mr_device_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + struct mr6_table *mrt; + struct mif_device *v; + int ct; + LIST_HEAD(list); + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + ip6mr_for_each_table(mrt, net) { + v = &mrt->vif6_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { + if (v->dev == dev) + mif6_delete(mrt, ct, &list); + } + } + unregister_netdevice_many(&list); + + return NOTIFY_DONE; +} + +static struct notifier_block ip6_mr_notifier = { + .notifier_call = ip6mr_device_event +}; + +/* + * Setup for IP multicast routing + */ + +static int __net_init ip6mr_net_init(struct net *net) +{ + int err; + + err = ip6mr_rules_init(net); + if (err < 0) + goto fail; + +#ifdef CONFIG_PROC_FS + err = -ENOMEM; + if (!proc_create("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_fops)) + goto proc_vif_fail; + if (!proc_create("ip6_mr_cache", 0, net->proc_net, &ip6mr_mfc_fops)) + goto proc_cache_fail; +#endif + + return 0; + +#ifdef CONFIG_PROC_FS +proc_cache_fail: + remove_proc_entry("ip6_mr_vif", net->proc_net); +proc_vif_fail: + ip6mr_rules_exit(net); +#endif +fail: + return err; +} + +static void __net_exit ip6mr_net_exit(struct net *net) +{ +#ifdef CONFIG_PROC_FS + remove_proc_entry("ip6_mr_cache", net->proc_net); + remove_proc_entry("ip6_mr_vif", net->proc_net); +#endif + ip6mr_rules_exit(net); +} + +static struct pernet_operations ip6mr_net_ops = { + .init = ip6mr_net_init, + .exit = ip6mr_net_exit, +}; + +int __init ip6_mr_init(void) +{ + int err; + + mrt_cachep = kmem_cache_create("ip6_mrt_cache", + sizeof(struct mfc6_cache), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (!mrt_cachep) + return -ENOMEM; + + err = register_pernet_subsys(&ip6mr_net_ops); + if (err) + goto reg_pernet_fail; + + err = register_netdevice_notifier(&ip6_mr_notifier); + if (err) + goto reg_notif_fail; +#ifdef CONFIG_IPV6_PIMSM_V2 + if (inet6_add_protocol(&pim6_protocol, IPPROTO_PIM) < 0) { + pr_err("%s: can't add PIM protocol\n", __func__); + err = -EAGAIN; + goto add_proto_fail; + } +#endif + rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, + ip6mr_rtm_dumproute, NULL); + return 0; +#ifdef CONFIG_IPV6_PIMSM_V2 +add_proto_fail: + unregister_netdevice_notifier(&ip6_mr_notifier); +#endif +reg_notif_fail: + unregister_pernet_subsys(&ip6mr_net_ops); +reg_pernet_fail: + kmem_cache_destroy(mrt_cachep); + return err; +} + +void ip6_mr_cleanup(void) +{ + unregister_netdevice_notifier(&ip6_mr_notifier); + unregister_pernet_subsys(&ip6mr_net_ops); + kmem_cache_destroy(mrt_cachep); +} + +static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, + struct mf6cctl *mfc, int mrtsock, int parent) +{ + bool found = false; + int line; + struct mfc6_cache *uc, *c; + unsigned char ttls[MAXMIFS]; + int i; + + if (mfc->mf6cc_parent >= MAXMIFS) + return -ENFILE; + + memset(ttls, 255, MAXMIFS); + for (i = 0; i < MAXMIFS; i++) { + if (IF_ISSET(i, &mfc->mf6cc_ifset)) + ttls[i] = 1; + + } + + line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { + if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == mfc->mf6cc_parent)) { + found = true; + break; + } + } + + if (found) { + write_lock_bh(&mrt_lock); + c->mf6c_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(mrt, c, ttls); + if (!mrtsock) + c->mfc_flags |= MFC_STATIC; + write_unlock_bh(&mrt_lock); + mr6_netlink_event(mrt, c, RTM_NEWROUTE); + return 0; + } + + if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && + !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) + return -EINVAL; + + c = ip6mr_cache_alloc(); + if (c == NULL) + return -ENOMEM; + + c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; + c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; + c->mf6c_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(mrt, c, ttls); + if (!mrtsock) + c->mfc_flags |= MFC_STATIC; + + write_lock_bh(&mrt_lock); + list_add(&c->list, &mrt->mfc6_cache_array[line]); + write_unlock_bh(&mrt_lock); + + /* + * Check to see if we resolved a queued list. If so we + * need to send on the frames and tidy up. + */ + found = false; + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) { + if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && + ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { + list_del(&uc->list); + atomic_dec(&mrt->cache_resolve_queue_len); + found = true; + break; + } + } + if (list_empty(&mrt->mfc6_unres_queue)) + del_timer(&mrt->ipmr_expire_timer); + spin_unlock_bh(&mfc_unres_lock); + + if (found) { + ip6mr_cache_resolve(net, mrt, uc, c); + ip6mr_cache_free(uc); + } + mr6_netlink_event(mrt, c, RTM_NEWROUTE); + return 0; +} + +/* + * Close the multicast socket, and clear the vif tables etc + */ + +static void mroute_clean_tables(struct mr6_table *mrt) +{ + int i; + LIST_HEAD(list); + struct mfc6_cache *c, *next; + + /* + * Shut down all active vif entries + */ + for (i = 0; i < mrt->maxvif; i++) { + if (!(mrt->vif6_table[i].flags & VIFF_STATIC)) + mif6_delete(mrt, i, &list); + } + unregister_netdevice_many(&list); + + /* + * Wipe the cache + */ + for (i = 0; i < MFC6_LINES; i++) { + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { + if (c->mfc_flags & MFC_STATIC) + continue; + write_lock_bh(&mrt_lock); + list_del(&c->list); + write_unlock_bh(&mrt_lock); + + mr6_netlink_event(mrt, c, RTM_DELROUTE); + ip6mr_cache_free(c); + } + } + + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + list_del(&c->list); + mr6_netlink_event(mrt, c, RTM_DELROUTE); + ip6mr_destroy_unres(mrt, c); + } + spin_unlock_bh(&mfc_unres_lock); + } +} + +static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) +{ + int err = 0; + struct net *net = sock_net(sk); + + rtnl_lock(); + write_lock_bh(&mrt_lock); + if (likely(mrt->mroute6_sk == NULL)) { + mrt->mroute6_sk = sk; + net->ipv6.devconf_all->mc_forwarding++; + inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + } + else + err = -EADDRINUSE; + write_unlock_bh(&mrt_lock); + + rtnl_unlock(); + + return err; +} + +int ip6mr_sk_done(struct sock *sk) +{ + int err = -EACCES; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + rtnl_lock(); + ip6mr_for_each_table(mrt, net) { + if (sk == mrt->mroute6_sk) { + write_lock_bh(&mrt_lock); + mrt->mroute6_sk = NULL; + net->ipv6.devconf_all->mc_forwarding--; + inet6_netconf_notify_devconf(net, + NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + write_unlock_bh(&mrt_lock); + + mroute_clean_tables(mrt); + err = 0; + break; + } + } + rtnl_unlock(); + + return err; +} + +struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +{ + struct mr6_table *mrt; + struct flowi6 fl6 = { + .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, + .flowi6_oif = skb->dev->ifindex, + .flowi6_mark = skb->mark, + }; + + if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) + return NULL; + + return mrt->mroute6_sk; +} + +/* + * Socket options and virtual interface manipulation. The whole + * virtual interface system is a complete heap, but unfortunately + * that's how BSD mrouted happens to think. Maybe one day with a proper + * MOSPF/PIM router set up we can clean this up. + */ + +int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) +{ + int ret, parent = 0; + struct mif6ctl vif; + struct mf6cctl mfc; + mifi_t mifi; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + if (optname != MRT6_INIT) { + if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EACCES; + } + + switch (optname) { + case MRT6_INIT: + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + if (optlen < sizeof(int)) + return -EINVAL; + + return ip6mr_sk_init(mrt, sk); + + case MRT6_DONE: + return ip6mr_sk_done(sk); + + case MRT6_ADD_MIF: + if (optlen < sizeof(vif)) + return -EINVAL; + if (copy_from_user(&vif, optval, sizeof(vif))) + return -EFAULT; + if (vif.mif6c_mifi >= MAXMIFS) + return -ENFILE; + rtnl_lock(); + ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk); + rtnl_unlock(); + return ret; + + case MRT6_DEL_MIF: + if (optlen < sizeof(mifi_t)) + return -EINVAL; + if (copy_from_user(&mifi, optval, sizeof(mifi_t))) + return -EFAULT; + rtnl_lock(); + ret = mif6_delete(mrt, mifi, NULL); + rtnl_unlock(); + return ret; + + /* + * Manipulate the forwarding caches. These live + * in a sort of kernel/user symbiosis. + */ + case MRT6_ADD_MFC: + case MRT6_DEL_MFC: + parent = -1; + case MRT6_ADD_MFC_PROXY: + case MRT6_DEL_MFC_PROXY: + if (optlen < sizeof(mfc)) + return -EINVAL; + if (copy_from_user(&mfc, optval, sizeof(mfc))) + return -EFAULT; + if (parent == 0) + parent = mfc.mf6cc_parent; + rtnl_lock(); + if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) + ret = ip6mr_mfc_delete(mrt, &mfc, parent); + else + ret = ip6mr_mfc_add(net, mrt, &mfc, + sk == mrt->mroute6_sk, parent); + rtnl_unlock(); + return ret; + + /* + * Control PIM assert (to activate pim will activate assert) + */ + case MRT6_ASSERT: + { + int v; + + if (optlen != sizeof(v)) + return -EINVAL; + if (get_user(v, (int __user *)optval)) + return -EFAULT; + mrt->mroute_do_assert = v; + return 0; + } + +#ifdef CONFIG_IPV6_PIMSM_V2 + case MRT6_PIM: + { + int v; + + if (optlen != sizeof(v)) + return -EINVAL; + if (get_user(v, (int __user *)optval)) + return -EFAULT; + v = !!v; + rtnl_lock(); + ret = 0; + if (v != mrt->mroute_do_pim) { + mrt->mroute_do_pim = v; + mrt->mroute_do_assert = v; + } + rtnl_unlock(); + return ret; + } + +#endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + case MRT6_TABLE: + { + u32 v; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (get_user(v, (u32 __user *)optval)) + return -EFAULT; + /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (v != RT_TABLE_DEFAULT && v >= 100000000) + return -EINVAL; + if (sk == mrt->mroute6_sk) + return -EBUSY; + + rtnl_lock(); + ret = 0; + if (!ip6mr_new_table(net, v)) + ret = -ENOMEM; + raw6_sk(sk)->ip6mr_table = v; + rtnl_unlock(); + return ret; + } +#endif + /* + * Spurious command, or MRT6_VERSION which you cannot + * set. + */ + default: + return -ENOPROTOOPT; + } +} + +/* + * Getsock opt support for the multicast routing system. + */ + +int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen) +{ + int olr; + int val; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + switch (optname) { + case MRT6_VERSION: + val = 0x0305; + break; +#ifdef CONFIG_IPV6_PIMSM_V2 + case MRT6_PIM: + val = mrt->mroute_do_pim; + break; +#endif + case MRT6_ASSERT: + val = mrt->mroute_do_assert; + break; + default: + return -ENOPROTOOPT; + } + + if (get_user(olr, optlen)) + return -EFAULT; + + olr = min_t(int, olr, sizeof(int)); + if (olr < 0) + return -EINVAL; + + if (put_user(olr, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, olr)) + return -EFAULT; + return 0; +} + +/* + * The IP multicast ioctl support routines. + */ + +int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) +{ + struct sioc_sg_req6 sr; + struct sioc_mif_req6 vr; + struct mif_device *vif; + struct mfc6_cache *c; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + switch (cmd) { + case SIOCGETMIFCNT_IN6: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.mifi >= mrt->maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT_IN6: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + read_lock(&mrt_lock); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} + +#ifdef CONFIG_COMPAT +struct compat_sioc_sg_req6 { + struct sockaddr_in6 src; + struct sockaddr_in6 grp; + compat_ulong_t pktcnt; + compat_ulong_t bytecnt; + compat_ulong_t wrong_if; +}; + +struct compat_sioc_mif_req6 { + mifi_t mifi; + compat_ulong_t icount; + compat_ulong_t ocount; + compat_ulong_t ibytes; + compat_ulong_t obytes; +}; + +int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + struct compat_sioc_sg_req6 sr; + struct compat_sioc_mif_req6 vr; + struct mif_device *vif; + struct mfc6_cache *c; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + switch (cmd) { + case SIOCGETMIFCNT_IN6: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.mifi >= mrt->maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT_IN6: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + read_lock(&mrt_lock); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} +#endif + +static inline int ip6mr_forward2_finish(struct sk_buff *skb) +{ + IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTOCTETS, skb->len); + return dst_output(skb); +} + +/* + * Processing handlers for ip6mr_forward + */ + +static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *c, int vifi) +{ + struct ipv6hdr *ipv6h; + struct mif_device *vif = &mrt->vif6_table[vifi]; + struct net_device *dev; + struct dst_entry *dst; + struct flowi6 fl6; + + if (vif->dev == NULL) + goto out_free; + +#ifdef CONFIG_IPV6_PIMSM_V2 + if (vif->flags & MIFF_REGISTER) { + vif->pkt_out++; + vif->bytes_out += skb->len; + vif->dev->stats.tx_bytes += skb->len; + vif->dev->stats.tx_packets++; + ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); + goto out_free; + } +#endif + + ipv6h = ipv6_hdr(skb); + + fl6 = (struct flowi6) { + .flowi6_oif = vif->link, + .daddr = ipv6h->daddr, + }; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + dst_release(dst); + goto out_free; + } + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + /* + * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally + * not only before forwarding, but after forwarding on all output + * interfaces. It is clear, if mrouter runs a multicasting + * program, it should receive packets not depending to what interface + * program is joined. + * If we will not make it, the program will have to join on all + * interfaces. On the other hand, multihoming host (or router, but + * not mrouter) cannot join to more than one interface - it will + * result in receiving multiple packets. + */ + dev = vif->dev; + skb->dev = dev; + vif->pkt_out++; + vif->bytes_out += skb->len; + + /* We are about to write */ + /* XXX: extension headers? */ + if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(dev))) + goto out_free; + + ipv6h = ipv6_hdr(skb); + ipv6h->hop_limit--; + + IP6CB(skb)->flags |= IP6SKB_FORWARDED; + + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dev, + ip6mr_forward2_finish); + +out_free: + kfree_skb(skb); + return 0; +} + +static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) +{ + int ct; + + for (ct = mrt->maxvif - 1; ct >= 0; ct--) { + if (mrt->vif6_table[ct].dev == dev) + break; + } + return ct; +} + +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) +{ + int psend = -1; + int vif, ct; + int true_vifi = ip6mr_find_vif(mrt, skb->dev); + + vif = cache->mf6c_parent; + cache->mfc_un.res.pkt++; + cache->mfc_un.res.bytes += skb->len; + + if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) { + struct mfc6_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ip6mr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + + /* + * Wrong interface: drop packet and (maybe) send PIM assert. + */ + if (mrt->vif6_table[vif].dev != skb->dev) { + cache->mfc_un.res.wrong_if++; + + if (true_vifi >= 0 && mrt->mroute_do_assert && + /* pimsm uses asserts, when switching from RPT to SPT, + so that we cannot check that packet arrived on an oif. + It is bad, but otherwise we would need to move pretty + large chunk of pimd to kernel. Ough... --ANK + */ + (mrt->mroute_do_pim || + cache->mfc_un.res.ttls[true_vifi] < 255) && + time_after(jiffies, + cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { + cache->mfc_un.res.last_assert = jiffies; + ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); + } + goto dont_forward; + } + +forward: + mrt->vif6_table[vif].pkt_in++; + mrt->vif6_table[vif].bytes_in += skb->len; + + /* + * Forward the frame + */ + if (ipv6_addr_any(&cache->mf6c_origin) && + ipv6_addr_any(&cache->mf6c_mcastgrp)) { + if (true_vifi >= 0 && + true_vifi != cache->mf6c_parent && + ipv6_hdr(skb)->hop_limit > + cache->mfc_un.res.ttls[cache->mf6c_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mf6c_parent; + goto last_forward; + } + goto dont_forward; + } + for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) && + ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + if (psend != -1) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) + ip6mr_forward2(net, mrt, skb2, cache, psend); + } + psend = ct; + } + } +last_forward: + if (psend != -1) { + ip6mr_forward2(net, mrt, skb, cache, psend); + return; + } + +dont_forward: + kfree_skb(skb); +} + + +/* + * Multicast packets for forwarding arrive here + */ + +int ip6_mr_input(struct sk_buff *skb) +{ + struct mfc6_cache *cache; + struct net *net = dev_net(skb->dev); + struct mr6_table *mrt; + struct flowi6 fl6 = { + .flowi6_iif = skb->dev->ifindex, + .flowi6_mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl6, &mrt); + if (err < 0) { + kfree_skb(skb); + return err; + } + + read_lock(&mrt_lock); + cache = ip6mr_cache_find(mrt, + &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, + &ipv6_hdr(skb)->daddr, + vif); + } + + /* + * No usable cache entry + */ + if (cache == NULL) { + int vif; + + vif = ip6mr_find_vif(mrt, skb->dev); + if (vif >= 0) { + int err = ip6mr_cache_unresolved(mrt, vif, skb); + read_unlock(&mrt_lock); + + return err; + } + read_unlock(&mrt_lock); + kfree_skb(skb); + return -ENODEV; + } + + ip6_mr_forward(net, mrt, skb, cache); + + read_unlock(&mrt_lock); + + return 0; +} + + +static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm) +{ + int ct; + struct rtnexthop *nhp; + struct nlattr *mp_attr; + struct rta_mfc_stats mfcs; + + /* If cache is unresolved, don't try to parse IIF and OIF */ + if (c->mf6c_parent >= MAXMIFS) + return -ENOENT; + + if (MIF_EXISTS(mrt, c->mf6c_parent) && + nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) + return -EMSGSIZE; + mp_attr = nla_nest_start(skb, RTA_MULTIPATH); + if (mp_attr == NULL) + return -EMSGSIZE; + + for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { + if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { + nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); + if (nhp == NULL) { + nla_nest_cancel(skb, mp_attr); + return -EMSGSIZE; + } + + nhp->rtnh_flags = 0; + nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; + nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; + nhp->rtnh_len = sizeof(*nhp); + } + } + + nla_nest_end(skb, mp_attr); + + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0) + return -EMSGSIZE; + + rtm->rtm_type = RTN_MULTICAST; + return 1; +} + +int ip6mr_get_route(struct net *net, + struct sk_buff *skb, struct rtmsg *rtm, int nowait) +{ + int err; + struct mr6_table *mrt; + struct mfc6_cache *cache; + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + read_lock(&mrt_lock); + cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + if (!cache && skb->dev) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, + vif); + } + + if (!cache) { + struct sk_buff *skb2; + struct ipv6hdr *iph; + struct net_device *dev; + int vif; + + if (nowait) { + read_unlock(&mrt_lock); + return -EAGAIN; + } + + dev = skb->dev; + if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) { + read_unlock(&mrt_lock); + return -ENODEV; + } + + /* really correct? */ + skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); + if (!skb2) { + read_unlock(&mrt_lock); + return -ENOMEM; + } + + skb_reset_transport_header(skb2); + + skb_put(skb2, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb2); + + iph = ipv6_hdr(skb2); + iph->version = 0; + iph->priority = 0; + iph->flow_lbl[0] = 0; + iph->flow_lbl[1] = 0; + iph->flow_lbl[2] = 0; + iph->payload_len = 0; + iph->nexthdr = IPPROTO_NONE; + iph->hop_limit = 0; + iph->saddr = rt->rt6i_src.addr; + iph->daddr = rt->rt6i_dst.addr; + + err = ip6mr_cache_unresolved(mrt, vif, skb2); + read_unlock(&mrt_lock); + + return err; + } + + if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) + cache->mfc_flags |= MFC_NOTIFY; + + err = __ip6mr_fill_mroute(mrt, skb, cache, rtm); + read_unlock(&mrt_lock); + return err; +} + +static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mfc6_cache *c, int cmd, + int flags) +{ + struct nlmsghdr *nlh; + struct rtmsg *rtm; + int err; + + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); + rtm->rtm_family = RTNL_FAMILY_IP6MR; + rtm->rtm_dst_len = 128; + rtm->rtm_src_len = 128; + rtm->rtm_tos = 0; + rtm->rtm_table = mrt->id; + if (nla_put_u32(skb, RTA_TABLE, mrt->id)) + goto nla_put_failure; + rtm->rtm_type = RTN_MULTICAST; + rtm->rtm_scope = RT_SCOPE_UNIVERSE; + if (c->mfc_flags & MFC_STATIC) + rtm->rtm_protocol = RTPROT_STATIC; + else + rtm->rtm_protocol = RTPROT_MROUTED; + rtm->rtm_flags = 0; + + if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) || + nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp)) + goto nla_put_failure; + err = __ip6mr_fill_mroute(mrt, skb, c, rtm); + /* do not break the dump if cache is unresolved */ + if (err < 0 && err != -ENOENT) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mr6_msgsize(bool unresolved, int maxvif) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */ + + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */ + ; + + if (!unresolved) + len = len + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(0) /* RTA_MULTIPATH */ + + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) + /* RTA_MFC_STATS */ + + nla_total_size(sizeof(struct rta_mfc_stats)) + ; + + return len; +} + +static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, + int cmd) +{ + struct net *net = read_pnet(&mrt->net); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif), + GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); + if (err < 0) + goto errout; + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC); + return; + +errout: + kfree_skb(skb); + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); +} + +static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct mr6_table *mrt; + struct mfc6_cache *mfc; + unsigned int t = 0, s_t; + unsigned int h = 0, s_h; + unsigned int e = 0, s_e; + + s_t = cb->args[0]; + s_h = cb->args[1]; + s_e = cb->args[2]; + + read_lock(&mrt_lock); + ip6mr_for_each_table(mrt, net) { + if (t < s_t) + goto next_table; + if (t > s_t) + s_h = 0; + for (h = s_h; h < MFC6_LINES; h++) { + list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) { + if (e < s_e) + goto next_entry; + if (ip6mr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) + goto done; +next_entry: + e++; + } + e = s_e = 0; + } + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (ip6mr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { + spin_unlock_bh(&mfc_unres_lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(&mfc_unres_lock); + e = s_e = 0; + s_h = 0; +next_table: + t++; + } +done: + read_unlock(&mrt_lock); + + cb->args[2] = e; + cb->args[1] = h; + cb->args[0] = t; + + return skb->len; +} diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 85bfbc69b2c..d1c793cffcb 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -9,35 +9,35 @@ * 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. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * + * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ -/* +/* * [Memo] * * Outbound: - * The compression of IP datagram MUST be done before AH/ESP processing, - * fragmentation, and the addition of Hop-by-Hop/Routing header. + * The compression of IP datagram MUST be done before AH/ESP processing, + * fragmentation, and the addition of Hop-by-Hop/Routing header. * * Inbound: - * The decompression of IP datagram MUST be done after the reassembly, + * The decompression of IP datagram MUST be done after the reassembly, * AH/ESP processing. */ -#include <linux/config.h> + +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/module.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipcomp.h> -#include <asm/scatterlist.h> -#include <asm/semaphore.h> #include <linux/crypto.h> +#include <linux/err.h> #include <linux/pfkeyv2.h> #include <linux/random.h> #include <linux/percpu.h> @@ -45,194 +45,63 @@ #include <linux/list.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> +#include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> +#include <net/protocol.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> +#include <linux/mutex.h> -struct ipcomp6_tfms { - struct list_head list; - struct crypto_tfm **tfms; - int users; -}; - -static DECLARE_MUTEX(ipcomp6_resource_sem); -static void **ipcomp6_scratches; -static int ipcomp6_scratch_users; -static LIST_HEAD(ipcomp6_tfms_list); - -static int ipcomp6_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb) -{ - int err = 0; - u8 nexthdr = 0; - int hdr_len = skb->h.raw - skb->nh.raw; - unsigned char *tmp_hdr = NULL; - struct ipv6hdr *iph; - int plen, dlen; - struct ipcomp_data *ipcd = x->data; - u8 *start, *scratch; - struct crypto_tfm *tfm; - int cpu; - - if ((skb_is_nonlinear(skb) || skb_cloned(skb)) && - skb_linearize(skb, GFP_ATOMIC) != 0) { - err = -ENOMEM; - goto out; - } - - skb->ip_summed = CHECKSUM_NONE; - - /* Remove ipcomp header and decompress original payload */ - iph = skb->nh.ipv6h; - tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC); - if (!tmp_hdr) - goto out; - memcpy(tmp_hdr, iph, hdr_len); - nexthdr = *(u8 *)skb->data; - skb_pull(skb, sizeof(struct ipv6_comp_hdr)); - skb->nh.raw += sizeof(struct ipv6_comp_hdr); - memcpy(skb->nh.raw, tmp_hdr, hdr_len); - iph = skb->nh.ipv6h; - iph->payload_len = htons(ntohs(iph->payload_len) - sizeof(struct ipv6_comp_hdr)); - skb->h.raw = skb->data; - - /* decompression */ - plen = skb->len; - dlen = IPCOMP_SCRATCH_SIZE; - start = skb->data; - - cpu = get_cpu(); - scratch = *per_cpu_ptr(ipcomp6_scratches, cpu); - tfm = *per_cpu_ptr(ipcd->tfms, cpu); - - err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); - if (err) { - err = -EINVAL; - goto out_put_cpu; - } - - if (dlen < (plen + sizeof(struct ipv6_comp_hdr))) { - err = -EINVAL; - goto out_put_cpu; - } - - err = pskb_expand_head(skb, 0, dlen - plen, GFP_ATOMIC); - if (err) { - goto out_put_cpu; - } - - skb_put(skb, dlen - plen); - memcpy(skb->data, scratch, dlen); - - iph = skb->nh.ipv6h; - iph->payload_len = htons(skb->len); - -out_put_cpu: - put_cpu(); -out: - if (tmp_hdr) - kfree(tmp_hdr); - if (err) - goto error_out; - return nexthdr; -error_out: - return err; -} - -static int ipcomp6_output(struct xfrm_state *x, struct sk_buff *skb) +static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { - int err; - struct ipv6hdr *top_iph; - int hdr_len; - struct ipv6_comp_hdr *ipch; - struct ipcomp_data *ipcd = x->data; - int plen, dlen; - u8 *start, *scratch; - struct crypto_tfm *tfm; - int cpu; - - hdr_len = skb->h.raw - skb->data; - - /* check whether datagram len is larger than threshold */ - if ((skb->len - hdr_len) < ipcd->threshold) { - goto out_ok; - } - - if ((skb_is_nonlinear(skb) || skb_cloned(skb)) && - skb_linearize(skb, GFP_ATOMIC) != 0) { - goto out_ok; - } - - /* compression */ - plen = skb->len - hdr_len; - dlen = IPCOMP_SCRATCH_SIZE; - start = skb->h.raw; - - cpu = get_cpu(); - scratch = *per_cpu_ptr(ipcomp6_scratches, cpu); - tfm = *per_cpu_ptr(ipcd->tfms, cpu); - - err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); - if (err || (dlen + sizeof(struct ipv6_comp_hdr)) >= plen) { - put_cpu(); - goto out_ok; - } - memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); - put_cpu(); - pskb_trim(skb, hdr_len + dlen + sizeof(struct ip_comp_hdr)); - - /* insert ipcomp header and replace datagram */ - top_iph = (struct ipv6hdr *)skb->data; - - top_iph->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); - - ipch = (struct ipv6_comp_hdr *)start; - ipch->nexthdr = *skb->nh.raw; - ipch->flags = 0; - ipch->cpi = htons((u16 )ntohl(x->id.spi)); - *skb->nh.raw = IPPROTO_COMP; - -out_ok: - return 0; -} - -static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) -{ - u32 spi; - struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; - struct ipv6_comp_hdr *ipcomph = (struct ipv6_comp_hdr*)(skb->data+offset); + struct net *net = dev_net(skb->dev); + __be32 spi; + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + struct ip_comp_hdr *ipcomph = + (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && type != ICMPV6_PKT_TOOBIG) - return; + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; - spi = ntohl(ntohs(ipcomph->cpi)); - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); + spi = htonl(ntohs(ipcomph->cpi)); + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, IPPROTO_COMP, AF_INET6); if (!x) - return; + return 0; - printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - spi, NIP6(iph->daddr)); + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { + struct net *net = xs_net(x); struct xfrm_state *t = NULL; - t = xfrm_state_alloc(); + t = xfrm_state_alloc(net); if (!t) goto out; t->id.proto = IPPROTO_IPV6; - t->id.spi = xfrm6_tunnel_alloc_spi((xfrm_address_t *)&x->props.saddr); + t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr); + if (!t->id.spi) + goto error; + memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr)); memcpy(&t->sel, &x->sel, sizeof(t->sel)); t->props.family = AF_INET6; - t->props.mode = 1; + t->props.mode = x->props.mode; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); + memcpy(&t->mark, &x->mark, sizeof(t->mark)); if (xfrm_init_state(t)) goto error; @@ -243,19 +112,23 @@ out: return t; error: + t->km.state = XFRM_STATE_DEAD; xfrm_state_put(t); + t = NULL; goto out; } static int ipcomp6_tunnel_attach(struct xfrm_state *x) { + struct net *net = xs_net(x); int err = 0; struct xfrm_state *t = NULL; - u32 spi; + __be32 spi; + u32 mark = x->mark.m & x->mark.v; - spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr); + spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&x->props.saddr); if (spi) - t = xfrm_state_lookup((xfrm_address_t *)&x->id.daddr, + t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr, spi, IPPROTO_IPV6, AF_INET6); if (!t) { t = ipcomp6_tunnel_create(x); @@ -273,228 +146,69 @@ out: return err; } -static void ipcomp6_free_scratches(void) -{ - int i; - void **scratches; - - if (--ipcomp6_scratch_users) - return; - - scratches = ipcomp6_scratches; - if (!scratches) - return; - - for_each_cpu(i) { - void *scratch = *per_cpu_ptr(scratches, i); - if (scratch) - vfree(scratch); - } - - free_percpu(scratches); -} - -static void **ipcomp6_alloc_scratches(void) -{ - int i; - void **scratches; - - if (ipcomp6_scratch_users++) - return ipcomp6_scratches; - - scratches = alloc_percpu(void *); - if (!scratches) - return NULL; - - ipcomp6_scratches = scratches; - - for_each_cpu(i) { - void *scratch = vmalloc(IPCOMP_SCRATCH_SIZE); - if (!scratch) - return NULL; - *per_cpu_ptr(scratches, i) = scratch; - } - - return scratches; -} - -static void ipcomp6_free_tfms(struct crypto_tfm **tfms) -{ - struct ipcomp6_tfms *pos; - int cpu; - - list_for_each_entry(pos, &ipcomp6_tfms_list, list) { - if (pos->tfms == tfms) - break; - } - - BUG_TRAP(pos); - - if (--pos->users) - return; - - list_del(&pos->list); - kfree(pos); - - if (!tfms) - return; - - for_each_cpu(cpu) { - struct crypto_tfm *tfm = *per_cpu_ptr(tfms, cpu); - crypto_free_tfm(tfm); - } - free_percpu(tfms); -} - -static struct crypto_tfm **ipcomp6_alloc_tfms(const char *alg_name) -{ - struct ipcomp6_tfms *pos; - struct crypto_tfm **tfms; - int cpu; - - /* This can be any valid CPU ID so we don't need locking. */ - cpu = raw_smp_processor_id(); - - list_for_each_entry(pos, &ipcomp6_tfms_list, list) { - struct crypto_tfm *tfm; - - tfms = pos->tfms; - tfm = *per_cpu_ptr(tfms, cpu); - - if (!strcmp(crypto_tfm_alg_name(tfm), alg_name)) { - pos->users++; - return tfms; - } - } - - pos = kmalloc(sizeof(*pos), GFP_KERNEL); - if (!pos) - return NULL; - - pos->users = 1; - INIT_LIST_HEAD(&pos->list); - list_add(&pos->list, &ipcomp6_tfms_list); - - pos->tfms = tfms = alloc_percpu(struct crypto_tfm *); - if (!tfms) - goto error; - - for_each_cpu(cpu) { - struct crypto_tfm *tfm = crypto_alloc_tfm(alg_name, 0); - if (!tfm) - goto error; - *per_cpu_ptr(tfms, cpu) = tfm; - } - - return tfms; - -error: - ipcomp6_free_tfms(tfms); - return NULL; -} - -static void ipcomp6_free_data(struct ipcomp_data *ipcd) -{ - if (ipcd->tfms) - ipcomp6_free_tfms(ipcd->tfms); - ipcomp6_free_scratches(); -} - -static void ipcomp6_destroy(struct xfrm_state *x) -{ - struct ipcomp_data *ipcd = x->data; - if (!ipcd) - return; - xfrm_state_delete_tunnel(x); - down(&ipcomp6_resource_sem); - ipcomp6_free_data(ipcd); - up(&ipcomp6_resource_sem); - kfree(ipcd); - - xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr); -} - static int ipcomp6_init_state(struct xfrm_state *x) { - int err; - struct ipcomp_data *ipcd; - struct xfrm_algo_desc *calg_desc; - - err = -EINVAL; - if (!x->calg) - goto out; - - if (x->encap) - goto out; + int err = -EINVAL; - err = -ENOMEM; - ipcd = kmalloc(sizeof(*ipcd), GFP_KERNEL); - if (!ipcd) - goto out; - - memset(ipcd, 0, sizeof(*ipcd)); x->props.header_len = 0; - if (x->props.mode) + switch (x->props.mode) { + case XFRM_MODE_TRANSPORT: + break; + case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); - - down(&ipcomp6_resource_sem); - if (!ipcomp6_alloc_scratches()) - goto error; + break; + default: + goto out; + } - ipcd->tfms = ipcomp6_alloc_tfms(x->calg->alg_name); - if (!ipcd->tfms) - goto error; - up(&ipcomp6_resource_sem); + err = ipcomp_init_state(x); + if (err) + goto out; - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp6_tunnel_attach(x); if (err) - goto error_tunnel; + goto out; } - calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0); - BUG_ON(!calg_desc); - ipcd->threshold = calg_desc->uinfo.comp.threshold; - x->data = ipcd; err = 0; out: return err; -error_tunnel: - down(&ipcomp6_resource_sem); -error: - ipcomp6_free_data(ipcd); - up(&ipcomp6_resource_sem); - kfree(ipcd); +} - goto out; +static int ipcomp6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; } -static struct xfrm_type ipcomp6_type = +static const struct xfrm_type ipcomp6_type = { .description = "IPCOMP6", .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp6_init_state, - .destructor = ipcomp6_destroy, - .input = ipcomp6_input, - .output = ipcomp6_output, + .destructor = ipcomp_destroy, + .input = ipcomp_input, + .output = ipcomp_output, + .hdr_offset = xfrm6_find_1stfragopt, }; -static struct inet6_protocol ipcomp6_protocol = +static struct xfrm6_protocol ipcomp6_protocol = { .handler = xfrm6_rcv, + .cb_handler = ipcomp6_rcv_cb, .err_handler = ipcomp6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init ipcomp6_init(void) { if (xfrm_register_type(&ipcomp6_type, AF_INET6) < 0) { - printk(KERN_INFO "ipcomp6 init: can't add xfrm type\n"); + pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) { - printk(KERN_INFO "ipcomp6 init: can't add protocol\n"); + if (xfrm6_protocol_register(&ipcomp6_protocol, IPPROTO_COMP) < 0) { + pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp6_type, AF_INET6); return -EAGAIN; } @@ -503,10 +217,10 @@ static int __init ipcomp6_init(void) static void __exit ipcomp6_fini(void) { - if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) - printk(KERN_INFO "ipv6 ipcomp close: can't remove protocol\n"); + if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0) + pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0) - printk(KERN_INFO "ipv6 ipcomp close: can't remove xfrm type\n"); + pr_info("%s: can't remove xfrm type\n", __func__); } module_init(ipcomp6_init); @@ -515,4 +229,4 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) for IPv6 - RFC3173"); MODULE_AUTHOR("Mitsuru KANDA <mk@linux-ipv6.org>"); - +MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_COMP); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 8567873d0dd..edb58aff4ae 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1,14 +1,12 @@ /* * IPv6 BSD socket options interface - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_sockglue.c * - * $Id: ipv6_sockglue.c,v 1.41 2002/02/01 22:01:04 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 @@ -16,7 +14,6 @@ * * FIXME: Make the setsockopt code POSIX compliant: That is * - * o Return -EINVAL for setsockopt of short lengths * o Truncate getsockopt returns * o Return an optlen of the truncated length if need be * @@ -26,19 +23,20 @@ */ #include <linux/module.h> -#include <linux/config.h> +#include <linux/capability.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/mroute6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/sysctl.h> #include <linux/netfilter.h> +#include <linux/slab.h> #include <net/sock.h> #include <net/snmp.h> @@ -51,27 +49,22 @@ #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/udplite.h> #include <net/xfrm.h> +#include <net/compat.h> #include <asm/uaccess.h> -DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics) __read_mostly; - -static struct packet_type ipv6_packet_type = { - .type = __constant_htons(ETH_P_IPV6), - .func = ipv6_rcv, -}; - struct ip6_ra_chain *ip6_ra_chain; DEFINE_RWLOCK(ip6_ra_lock); -int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) +int ip6_ra_control(struct sock *sk, int sel) { struct ip6_ra_chain *ra, *new_ra, **rap; /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ - if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW) - return -EINVAL; + if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW) + return -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -80,16 +73,13 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) if (ra->sk == sk) { if (sel>=0) { write_unlock_bh(&ip6_ra_lock); - if (new_ra) - kfree(new_ra); + kfree(new_ra); return -EADDRINUSE; } *rap = ra->next; write_unlock_bh(&ip6_ra_lock); - if (ra->destructor) - ra->destructor(sk); sock_put(sk); kfree(ra); return 0; @@ -101,7 +91,6 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) } new_ra->sk = sk; new_ra->sel = sel; - new_ra->destructor = destructor; new_ra->next = ra; *rap = new_ra; sock_hold(sk); @@ -109,37 +98,74 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) return 0; } -int ipv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +static +struct ipv6_txoptions *ipv6_update_options(struct sock *sk, + struct ipv6_txoptions *opt) +{ + if (inet_sk(sk)->is_icsk) { + if (opt && + !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && + inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { + struct inet_connection_sock *icsk = inet_csk(sk); + icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; + icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); + } + opt = xchg(&inet6_sk(sk)->opt, opt); + } else { + spin_lock(&sk->sk_dst_lock); + opt = xchg(&inet6_sk(sk)->opt, opt); + spin_unlock(&sk->sk_dst_lock); + } + sk_dst_reset(sk); + + return opt; +} + +static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); + struct net *net = sock_net(sk); int val, valbool; int retv = -ENOPROTOOPT; - if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); - - if(level!=SOL_IPV6) - goto out; - if (optval == NULL) val=0; - else if (get_user(val, (int __user *) optval)) - return -EFAULT; + else { + if (optlen >= sizeof(int)) { + if (get_user(val, (int __user *) optval)) + return -EFAULT; + } else + val = 0; + } valbool = (val!=0); + if (ip6_mroute_opt(optname)) + return ip6_mroute_setsockopt(sk, optname, optval, optlen); + lock_sock(sk); switch (optname) { case IPV6_ADDRFORM: + if (optlen < sizeof(int)) + goto e_inval; if (val == PF_INET) { struct ipv6_txoptions *opt; struct sk_buff *pktopt; - if (sk->sk_protocol != IPPROTO_UDP && - sk->sk_protocol != IPPROTO_TCP) + if (sk->sk_type == SOCK_RAW) + break; + + if (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_UDPLITE) { + struct udp_sock *up = udp_sk(sk); + if (up->pending == AF_INET6) { + retv = -EBUSY; + break; + } + } else if (sk->sk_protocol != IPPROTO_TCP) break; if (sk->sk_state != TCP_ESTABLISHED) { @@ -148,7 +174,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, } if (ipv6_only_sock(sk) || - !(ipv6_addr_type(&np->daddr) & IPV6_ADDR_MAPPED)) { + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { retv = -EADDRNOTAVAIL; break; } @@ -164,23 +190,26 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sk_refcnt_debug_dec(sk); if (sk->sk_protocol == IPPROTO_TCP) { - struct tcp_sock *tp = tcp_sk(sk); - + struct inet_connection_sock *icsk = inet_csk(sk); local_bh_disable(); - sock_prot_dec_use(sk->sk_prot); - sock_prot_inc_use(&tcp_prot); + sock_prot_inuse_add(net, sk->sk_prot, -1); + sock_prot_inuse_add(net, &tcp_prot, 1); local_bh_enable(); sk->sk_prot = &tcp_prot; - tp->af_specific = &ipv4_specific; + icsk->icsk_af_ops = &ipv4_specific; sk->sk_socket->ops = &inet_stream_ops; sk->sk_family = PF_INET; - tcp_sync_mss(sk, tp->pmtu_cookie); + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { + struct proto *prot = &udp_prot; + + if (sk->sk_protocol == IPPROTO_UDPLITE) + prot = &udplite_prot; local_bh_disable(); - sock_prot_dec_use(sk->sk_prot); - sock_prot_inc_use(&udp_prot); + sock_prot_inuse_add(net, sk->sk_prot, -1); + sock_prot_inuse_add(net, prot, 1); local_bh_enable(); - sk->sk_prot = &udp_prot; + sk->sk_prot = prot; sk->sk_socket->ops = &inet_dgram_ops; sk->sk_family = PF_INET; } @@ -188,8 +217,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, if (opt) sock_kfree_s(sk, opt, opt->tot_len); pktopt = xchg(&np->pktoptions, NULL); - if (pktopt) - kfree_skb(pktopt); + kfree_skb(pktopt); sk->sk_destruct = inet_sock_destruct; /* @@ -204,99 +232,157 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, goto e_inval; case IPV6_V6ONLY: - if (inet_sk(sk)->num) + if (optlen < sizeof(int) || + inet_sk(sk)->inet_num) goto e_inval; np->ipv6only = valbool; retv = 0; break; case IPV6_RECVPKTINFO: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.rxinfo = valbool; retv = 0; break; - + case IPV6_2292PKTINFO: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.rxoinfo = valbool; retv = 0; break; case IPV6_RECVHOPLIMIT: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.rxhlim = valbool; retv = 0; break; case IPV6_2292HOPLIMIT: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.rxohlim = valbool; retv = 0; break; case IPV6_RECVRTHDR: - if (val < 0 || val > 2) + if (optlen < sizeof(int)) goto e_inval; - np->rxopt.bits.srcrt = val; + np->rxopt.bits.srcrt = valbool; retv = 0; break; case IPV6_2292RTHDR: - if (val < 0 || val > 2) + if (optlen < sizeof(int)) goto e_inval; - np->rxopt.bits.osrcrt = val; + np->rxopt.bits.osrcrt = valbool; retv = 0; break; case IPV6_RECVHOPOPTS: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.hopopts = valbool; retv = 0; break; case IPV6_2292HOPOPTS: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.ohopopts = valbool; retv = 0; break; case IPV6_RECVDSTOPTS: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.dstopts = valbool; retv = 0; break; case IPV6_2292DSTOPTS: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.odstopts = valbool; retv = 0; break; case IPV6_TCLASS: - if (val < 0 || val > 0xff) + if (optlen < sizeof(int)) + goto e_inval; + if (val < -1 || val > 0xff) goto e_inval; + /* RFC 3542, 6.5: default traffic class of 0x0 */ + if (val == -1) + val = 0; np->tclass = val; retv = 0; break; - + case IPV6_RECVTCLASS: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.rxtclass = valbool; retv = 0; break; case IPV6_FLOWINFO: + if (optlen < sizeof(int)) + goto e_inval; np->rxopt.bits.rxflow = valbool; retv = 0; break; + case IPV6_RECVPATHMTU: + if (optlen < sizeof(int)) + goto e_inval; + np->rxopt.bits.rxpmtu = valbool; + retv = 0; + break; + + case IPV6_TRANSPARENT: + if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) && + !ns_capable(net->user_ns, CAP_NET_RAW)) { + retv = -EPERM; + break; + } + if (optlen < sizeof(int)) + goto e_inval; + /* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */ + inet_sk(sk)->transparent = valbool; + retv = 0; + break; + + case IPV6_RECVORIGDSTADDR: + if (optlen < sizeof(int)) + goto e_inval; + np->rxopt.bits.rxorigdstaddr = valbool; + retv = 0; + break; + case IPV6_HOPOPTS: case IPV6_RTHDRDSTOPTS: case IPV6_RTHDR: case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + + /* remove any sticky options header with a zero option + * length, per RFC3542. + */ if (optlen == 0) - optval = 0; + optval = NULL; + else if (optval == NULL) + goto e_inval; + else if (optlen < sizeof(struct ipv6_opt_hdr) || + optlen & 0x7 || optlen > 8 * 255) + goto e_inval; /* hop-by-hop / destination options are privileged option */ retv = -EPERM; - if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) - break; - - retv = -EINVAL; - if (optlen & 0x7 || optlen > 8 * 255) + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; opt = ipv6_renew_options(sk, np->opt, optname, @@ -308,49 +394,63 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, } /* routing header option needs extra check */ - if (optname == IPV6_RTHDR && opt->srcrt) { + retv = -EINVAL; + if (optname == IPV6_RTHDR && opt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = opt->srcrt; - if (rthdr->type) - goto sticky_done; - if ((rthdr->hdrlen & 1) || - (rthdr->hdrlen >> 1) != rthdr->segments_left) + switch (rthdr->type) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_SRCRT_TYPE_2: + if (rthdr->hdrlen != 2 || + rthdr->segments_left != 1) + goto sticky_done; + + break; +#endif + default: goto sticky_done; + } } retv = 0; - if (sk->sk_type == SOCK_STREAM) { - if (opt) { - struct tcp_sock *tp = tcp_sk(sk); - if (!((1 << sk->sk_state) & - (TCPF_LISTEN | TCPF_CLOSE)) - && inet_sk(sk)->daddr != LOOPBACK4_IPV6) { - tp->ext_header_len = opt->opt_flen + opt->opt_nflen; - tcp_sync_mss(sk, tp->pmtu_cookie); - } - } - opt = xchg(&np->opt, opt); - sk_dst_reset(sk); - } else { - write_lock(&sk->sk_dst_lock); - opt = xchg(&np->opt, opt); - write_unlock(&sk->sk_dst_lock); - sk_dst_reset(sk); - } + opt = ipv6_update_options(sk, opt); sticky_done: if (opt) sock_kfree_s(sk, opt, opt->tot_len); break; } + case IPV6_PKTINFO: + { + struct in6_pktinfo pkt; + + if (optlen == 0) + goto e_inval; + else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL) + goto e_inval; + + if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) { + retv = -EFAULT; + break; + } + if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if) + goto e_inval; + + np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex; + np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr; + retv = 0; + break; + } + case IPV6_2292PKTOPTIONS: { struct ipv6_txoptions *opt = NULL; struct msghdr msg; - struct flowi fl; + struct flowi6 fl6; int junk; - fl.fl6_flowlabel = 0; - fl.oif = sk->sk_bound_dev_if; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = sk->sk_mark; if (optlen == 0) goto update; @@ -376,36 +476,21 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk); + retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, + &junk, &junk); if (retv) goto done; update: retv = 0; - if (sk->sk_type == SOCK_STREAM) { - if (opt) { - struct tcp_sock *tp = tcp_sk(sk); - if (!((1 << sk->sk_state) & - (TCPF_LISTEN | TCPF_CLOSE)) - && inet_sk(sk)->daddr != LOOPBACK4_IPV6) { - tp->ext_header_len = opt->opt_flen + opt->opt_nflen; - tcp_sync_mss(sk, tp->pmtu_cookie); - } - } - opt = xchg(&np->opt, opt); - sk_dst_reset(sk); - } else { - write_lock(&sk->sk_dst_lock); - opt = xchg(&np->opt, opt); - write_unlock(&sk->sk_dst_lock); - sk_dst_reset(sk); - } - + opt = ipv6_update_options(sk, opt); done: if (opt) sock_kfree_s(sk, opt, opt->tot_len); break; } case IPV6_UNICAST_HOPS: + if (optlen < sizeof(int)) + goto e_inval; if (val > 255 || val < -1) goto e_inval; np->hop_limit = val; @@ -414,27 +499,72 @@ done: case IPV6_MULTICAST_HOPS: if (sk->sk_type == SOCK_STREAM) + break; + if (optlen < sizeof(int)) 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; case IPV6_MULTICAST_LOOP: + if (optlen < sizeof(int)) + goto e_inval; + if (val != valbool) + goto e_inval; np->mc_loop = valbool; retv = 0; break; + case IPV6_UNICAST_IF: + { + struct net_device *dev = NULL; + int ifindex; + + if (optlen != sizeof(int)) + goto e_inval; + + ifindex = (__force int)ntohl((__force __be32)val); + if (ifindex == 0) { + np->ucast_oif = 0; + retv = 0; + break; + } + + dev = dev_get_by_index(net, ifindex); + retv = -EADDRNOTAVAIL; + if (!dev) + break; + dev_put(dev); + + retv = -EINVAL; + if (sk->sk_bound_dev_if) + break; + + np->ucast_oif = ifindex; + retv = 0; + break; + } + case IPV6_MULTICAST_IF: if (sk->sk_type == SOCK_STREAM) - goto e_inval; - if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val) + break; + if (optlen < sizeof(int)) goto e_inval; - if (__dev_get_by_index(val) == NULL) { - retv = -ENODEV; - break; + if (val) { + struct net_device *dev; + + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val) + goto e_inval; + + dev = dev_get_by_index(net, val); + if (!dev) { + retv = -ENODEV; + break; + } + dev_put(dev); } np->mcast_oif = val; retv = 0; @@ -444,6 +574,13 @@ done: { struct ipv6_mreq mreq; + if (optlen < sizeof(struct ipv6_mreq)) + goto e_inval; + + retv = -EPROTO; + if (inet_sk(sk)->is_icsk) + break; + retv = -EFAULT; if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq))) break; @@ -459,7 +596,7 @@ done: { struct ipv6_mreq mreq; - if (optlen != sizeof(struct ipv6_mreq)) + if (optlen < sizeof(struct ipv6_mreq)) goto e_inval; retv = -EFAULT; @@ -478,6 +615,9 @@ done: struct group_req greq; struct sockaddr_in6 *psin6; + if (optlen < sizeof(struct group_req)) + goto e_inval; + retv = -EFAULT; if (copy_from_user(&greq, optval, sizeof(struct group_req))) break; @@ -502,7 +642,7 @@ done: struct group_source_req greqs; int omode, add; - if (optlen != sizeof(struct group_source_req)) + if (optlen < sizeof(struct group_source_req)) goto e_inval; if (copy_from_user(&greqs, optval, sizeof(greqs))) { retv = -EFAULT; @@ -539,7 +679,6 @@ done: } case MCAST_MSFILTER: { - extern int sysctl_mld_max_msf; struct group_filter *gsf; if (optlen < GROUP_FILTER_SIZE(0)) @@ -548,8 +687,8 @@ done: retv = -ENOBUFS; break; } - gsf = (struct group_filter *)kmalloc(optlen,GFP_KERNEL); - if (gsf == 0) { + gsf = kmalloc(optlen,GFP_KERNEL); + if (!gsf) { retv = -ENOBUFS; break; } @@ -576,27 +715,37 @@ done: break; } case IPV6_ROUTER_ALERT: - retv = ip6_ra_control(sk, val, NULL); + if (optlen < sizeof(int)) + goto e_inval; + retv = ip6_ra_control(sk, val); break; case IPV6_MTU_DISCOVER: - if (val<0 || val>2) + if (optlen < sizeof(int)) + goto e_inval; + if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT) goto e_inval; np->pmtudisc = val; retv = 0; break; case IPV6_MTU: + if (optlen < sizeof(int)) + goto e_inval; if (val && val < IPV6_MIN_MTU) goto e_inval; np->frag_size = val; retv = 0; break; case IPV6_RECVERR: + if (optlen < sizeof(int)) + goto e_inval; np->recverr = valbool; if (!val) skb_queue_purge(&sk->sk_error_queue); retv = 0; break; case IPV6_FLOWINFO_SEND: + if (optlen < sizeof(int)) + goto e_inval; np->sndflow = valbool; retv = 0; break; @@ -606,22 +755,89 @@ done: case IPV6_IPSEC_POLICY: case IPV6_XFRM_POLICY: retv = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; retv = xfrm_user_policy(sk, optname, optval, optlen); break; -#ifdef CONFIG_NETFILTER - default: - retv = nf_setsockopt(sk, PF_INET6, optname, optval, - optlen); - break; -#endif + case IPV6_ADDR_PREFERENCES: + { + unsigned int pref = 0; + unsigned int prefmask = ~0; + + if (optlen < sizeof(int)) + goto e_inval; + + retv = -EINVAL; + + /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ + switch (val & (IPV6_PREFER_SRC_PUBLIC| + IPV6_PREFER_SRC_TMP| + IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { + case IPV6_PREFER_SRC_PUBLIC: + pref |= IPV6_PREFER_SRC_PUBLIC; + break; + case IPV6_PREFER_SRC_TMP: + pref |= IPV6_PREFER_SRC_TMP; + break; + case IPV6_PREFER_SRC_PUBTMP_DEFAULT: + break; + case 0: + goto pref_skip_pubtmp; + default: + goto e_inval; + } + + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC| + IPV6_PREFER_SRC_TMP); +pref_skip_pubtmp: + /* check HOME/COA conflicts */ + switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) { + case IPV6_PREFER_SRC_HOME: + break; + case IPV6_PREFER_SRC_COA: + pref |= IPV6_PREFER_SRC_COA; + case 0: + goto pref_skip_coa; + default: + goto e_inval; + } + + prefmask &= ~IPV6_PREFER_SRC_COA; +pref_skip_coa: + + /* check CGA/NONCGA conflicts */ + switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { + case IPV6_PREFER_SRC_CGA: + case IPV6_PREFER_SRC_NONCGA: + case 0: + break; + default: + goto e_inval; + } + + np->srcprefs = (np->srcprefs & prefmask) | pref; + retv = 0; + + break; + } + case IPV6_MINHOPCOUNT: + if (optlen < sizeof(int)) + goto e_inval; + if (val < 0 || val > 255) + goto e_inval; + np->min_hopcount = val; + retv = 0; + break; + case IPV6_DONTFRAG: + np->dontfrag = valbool; + retv = 0; + break; } + release_sock(sk); -out: return retv; e_inval: @@ -629,35 +845,122 @@ e_inval: return -EINVAL; } -int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_opt_hdr *hdr, - char __user *optval, int len) +int ipv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) +{ + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) + return udp_prot.setsockopt(sk, level, optname, optval, optlen); + + if (level != SOL_IPV6) + return -ENOPROTOOPT; + + err = do_ipv6_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY && + optname != IPV6_XFRM_POLICY) { + lock_sock(sk); + err = nf_setsockopt(sk, PF_INET6, optname, optval, + optlen); + release_sock(sk); + } +#endif + return err; +} + +EXPORT_SYMBOL(ipv6_setsockopt); + +#ifdef CONFIG_COMPAT +int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) { + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) { + if (udp_prot.compat_setsockopt != NULL) + return udp_prot.compat_setsockopt(sk, level, optname, + optval, optlen); + return udp_prot.setsockopt(sk, level, optname, optval, optlen); + } + + if (level != SOL_IPV6) + return -ENOPROTOOPT; + + if (optname >= MCAST_JOIN_GROUP && optname <= MCAST_MSFILTER) + return compat_mc_setsockopt(sk, level, optname, optval, optlen, + ipv6_setsockopt); + + err = do_ipv6_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY && + optname != IPV6_XFRM_POLICY) { + lock_sock(sk); + err = compat_nf_setsockopt(sk, PF_INET6, optname, + optval, optlen); + release_sock(sk); + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ipv6_setsockopt); +#endif + +static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, + int optname, char __user *optval, int len) +{ + struct ipv6_opt_hdr *hdr; + + if (!opt) + return 0; + + switch(optname) { + case IPV6_HOPOPTS: + hdr = opt->hopopt; + break; + case IPV6_RTHDRDSTOPTS: + hdr = opt->dst0opt; + break; + case IPV6_RTHDR: + hdr = (struct ipv6_opt_hdr *)opt->srcrt; + break; + case IPV6_DSTOPTS: + hdr = opt->dst1opt; + break; + default: + return -EINVAL; /* should not happen */ + } + if (!hdr) return 0; - len = min_t(int, len, ipv6_optlen(hdr)); - if (copy_to_user(optval, hdr, ipv6_optlen(hdr))) + + len = min_t(unsigned int, len, ipv6_optlen(hdr)); + if (copy_to_user(optval, hdr, len)) return -EFAULT; return len; } -int ipv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen, unsigned int flags) { struct ipv6_pinfo *np = inet6_sk(sk); int len; int val; - if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); - if(level!=SOL_IPV6) - return -ENOPROTOOPT; + if (ip6_mroute_opt(optname)) + return ip6_mroute_getsockopt(sk, optname, optval, optlen); + if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_ADDRFORM: if (sk->sk_protocol != IPPROTO_UDP && + sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) - return -EINVAL; + return -ENOPROTOOPT; if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; val = sk->sk_family; @@ -671,6 +974,8 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, return -EINVAL; if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) return -EFAULT; + if (gsf.gf_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; lock_sock(sk); err = ip6_mc_msfget(sk, &gsf, (struct group_filter __user *)optval, optlen); @@ -688,7 +993,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, msg.msg_control = optval; msg.msg_controllen = len; - msg.msg_flags = 0; + msg.msg_flags = flags; lock_sock(sk); skb = np->pktoptions; @@ -697,31 +1002,42 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, release_sock(sk); if (skb) { - int err = datagram_recv_ctl(sk, &msg, skb); + ip6_datagram_recv_ctl(sk, &msg, skb); kfree_skb(skb); - if (err) - return err; } else { if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif; - ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : + np->sticky_pktinfo.ipi6_ifindex; + src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { int hlim = np->mcast_hops; put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } + if (np->rxopt.bits.rxtclass) { + int tclass = (int)ip6_tclass(np->rcv_flowinfo); + + put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); + } if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif; - ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : + np->sticky_pktinfo.ipi6_ifindex; + src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : + np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { int hlim = np->mcast_hops; put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } + if (np->rxopt.bits.rxflow) { + __be32 flowinfo = np->rcv_flowinfo; + + put_cmsg(&msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); + } } len -= msg.msg_controllen; return put_user(len, optlen); @@ -729,14 +1045,13 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_MTU: { struct dst_entry *dst; - val = 0; - lock_sock(sk); - dst = sk_dst_get(sk); - if (dst) { + + val = 0; + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) val = dst_mtu(dst); - dst_release(dst); - } - release_sock(sk); + rcu_read_unlock(); if (!val) return -ENOTCONN; break; @@ -777,9 +1092,12 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, { lock_sock(sk); - len = ipv6_getsockopt_sticky(sk, np->opt->hopopt, - optval, len); + len = ipv6_getsockopt_sticky(sk, np->opt, + optname, optval, len); release_sock(sk); + /* check if ipv6_getsockopt_sticky() returns err code */ + if (len < 0) + return len; return put_user(len, optlen); } @@ -811,13 +1129,68 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->rxopt.bits.rxflow; break; - case IPV6_UNICAST_HOPS: - val = np->hop_limit; + case IPV6_RECVPATHMTU: + val = np->rxopt.bits.rxpmtu; + break; + + case IPV6_PATHMTU: + { + struct dst_entry *dst; + struct ip6_mtuinfo mtuinfo; + + if (len < sizeof(mtuinfo)) + return -EINVAL; + + len = sizeof(mtuinfo); + memset(&mtuinfo, 0, sizeof(mtuinfo)); + + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) + mtuinfo.ip6m_mtu = dst_mtu(dst); + rcu_read_unlock(); + if (!mtuinfo.ip6m_mtu) + return -ENOTCONN; + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &mtuinfo, len)) + return -EFAULT; + + return 0; + break; + } + + case IPV6_TRANSPARENT: + val = inet_sk(sk)->transparent; break; + case IPV6_RECVORIGDSTADDR: + val = np->rxopt.bits.rxorigdstaddr; + break; + + case IPV6_UNICAST_HOPS: case IPV6_MULTICAST_HOPS: - val = np->mcast_hops; + { + struct dst_entry *dst; + + if (optname == IPV6_UNICAST_HOPS) + val = np->hop_limit; + else + val = np->mcast_hops; + + if (val < 0) { + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) + val = ip6_dst_hoplimit(dst); + rcu_read_unlock(); + } + + if (val < 0) + val = sock_net(sk)->ipv6.devconf_all->hop_limit; break; + } case IPV6_MULTICAST_LOOP: val = np->mc_loop; @@ -827,6 +1200,10 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->mcast_oif; break; + case IPV6_UNICAST_IF: + val = (__force int)htonl((__u32) np->ucast_oif); + break; + case IPV6_MTU_DISCOVER: val = np->pmtudisc; break; @@ -839,18 +1216,65 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->sndflow; break; + case IPV6_FLOWLABEL_MGR: + { + struct in6_flowlabel_req freq; + int flags; + + if (len < sizeof(freq)) + return -EINVAL; + + if (copy_from_user(&freq, optval, sizeof(freq))) + return -EFAULT; + + if (freq.flr_action != IPV6_FL_A_GET) + return -EINVAL; + + len = sizeof(freq); + flags = freq.flr_flags; + + memset(&freq, 0, sizeof(freq)); + + val = ipv6_flowlabel_opt_get(sk, &freq, flags); + if (val < 0) + return val; + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &freq, len)) + return -EFAULT; + + return 0; + } + + case IPV6_ADDR_PREFERENCES: + val = 0; + + if (np->srcprefs & IPV6_PREFER_SRC_TMP) + val |= IPV6_PREFER_SRC_TMP; + else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC) + val |= IPV6_PREFER_SRC_PUBLIC; + else { + /* XXX: should we return system default? */ + val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT; + } + + if (np->srcprefs & IPV6_PREFER_SRC_COA) + val |= IPV6_PREFER_SRC_COA; + else + val |= IPV6_PREFER_SRC_HOME; + break; + + case IPV6_MINHOPCOUNT: + val = np->min_hopcount; + break; + + case IPV6_DONTFRAG: + val = np->dontfrag; + break; + default: -#ifdef CONFIG_NETFILTER - lock_sock(sk); - val = nf_getsockopt(sk, PF_INET6, optname, optval, - &len); - release_sock(sk); - if (val >= 0) - val = put_user(len, optlen); - return val; -#else - return -EINVAL; -#endif + return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if(put_user(len, optlen)) @@ -860,12 +1284,80 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, return 0; } -void __init ipv6_packet_init(void) +int ipv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - dev_add_pack(&ipv6_packet_type); + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) + return udp_prot.getsockopt(sk, level, optname, optval, optlen); + + if(level != SOL_IPV6) + return -ENOPROTOOPT; + + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + err = nf_getsockopt(sk, PF_INET6, optname, optval, + &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + } +#endif + return err; } -void ipv6_packet_cleanup(void) +EXPORT_SYMBOL(ipv6_getsockopt); + +#ifdef CONFIG_COMPAT +int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - dev_remove_pack(&ipv6_packet_type); + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) { + if (udp_prot.compat_getsockopt != NULL) + return udp_prot.compat_getsockopt(sk, level, optname, + optval, optlen); + return udp_prot.getsockopt(sk, level, optname, optval, optlen); + } + + if (level != SOL_IPV6) + return -ENOPROTOOPT; + + if (optname == MCAST_MSFILTER) + return compat_mc_getsockopt(sk, level, optname, optval, optlen, + ipv6_getsockopt); + + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, + MSG_CMSG_COMPAT); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET6, + optname, optval, &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + } +#endif + return err; } + +EXPORT_SYMBOL(compat_ipv6_getsockopt); +#endif + diff --git a/net/ipv6/ipv6_syms.c b/net/ipv6/ipv6_syms.c deleted file mode 100644 index 37a4a99c9fe..00000000000 --- a/net/ipv6/ipv6_syms.c +++ /dev/null @@ -1,37 +0,0 @@ - -#include <linux/config.h> -#include <linux/module.h> -#include <net/protocol.h> -#include <net/ipv6.h> -#include <net/addrconf.h> -#include <net/ip6_route.h> -#include <net/xfrm.h> - -EXPORT_SYMBOL(ipv6_addr_type); -EXPORT_SYMBOL(icmpv6_send); -EXPORT_SYMBOL(icmpv6_statistics); -EXPORT_SYMBOL(icmpv6_err_convert); -EXPORT_SYMBOL(ndisc_mc_map); -EXPORT_SYMBOL(register_inet6addr_notifier); -EXPORT_SYMBOL(unregister_inet6addr_notifier); -EXPORT_SYMBOL(ip6_route_output); -EXPORT_SYMBOL(addrconf_lock); -EXPORT_SYMBOL(ipv6_setsockopt); -EXPORT_SYMBOL(ipv6_getsockopt); -EXPORT_SYMBOL(inet6_register_protosw); -EXPORT_SYMBOL(inet6_unregister_protosw); -EXPORT_SYMBOL(inet6_add_protocol); -EXPORT_SYMBOL(inet6_del_protocol); -EXPORT_SYMBOL(ip6_xmit); -EXPORT_SYMBOL(inet6_release); -EXPORT_SYMBOL(inet6_bind); -EXPORT_SYMBOL(inet6_getname); -EXPORT_SYMBOL(inet6_ioctl); -EXPORT_SYMBOL(ipv6_get_saddr); -EXPORT_SYMBOL(ipv6_chk_addr); -EXPORT_SYMBOL(in6_dev_finish_destroy); -#ifdef CONFIG_XFRM -EXPORT_SYMBOL(xfrm6_rcv); -#endif -EXPORT_SYMBOL(rt6_lookup); -EXPORT_SYMBOL(ipv6_push_nfrag_opts); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index f15e04ad026..617f0958e16 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1,13 +1,11 @@ /* * Multicast support for IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * - * $Id: mcast.c,v 1.40 2002/02/08 03:57:19 davem Exp $ - * - * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c + * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -28,7 +26,6 @@ * - MLDv2 support */ -#include <linux/config.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> @@ -46,10 +43,14 @@ #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/pkt_sched.h> +#include <net/mld.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> +#include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> @@ -59,6 +60,7 @@ #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> +#include <net/inet_common.h> #include <net/ip6_checksum.h> @@ -71,64 +73,17 @@ #define MDBG(x) #endif -/* - * These header formats should be in a separate include file, but icmpv6.h - * doesn't have in6_addr defined in all cases, there is no __u128, and no - * other files reference these. - * - * +-DLS 4/14/03 - */ - -/* Multicast Listener Discovery version 2 headers */ - -struct mld2_grec { - __u8 grec_type; - __u8 grec_auxwords; - __u16 grec_nsrcs; - struct in6_addr grec_mca; - struct in6_addr grec_src[0]; -}; - -struct mld2_report { - __u8 type; - __u8 resv1; - __u16 csum; - __u16 resv2; - __u16 ngrec; - struct mld2_grec grec[0]; -}; - -struct mld2_query { - __u8 type; - __u8 code; - __u16 csum; - __u16 mrc; - __u16 resv1; - struct in6_addr mca; -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 qrv:3, - suppress:1, - resv2:4; -#elif defined(__BIG_ENDIAN_BITFIELD) - __u8 resv2:4, - suppress:1, - qrv:3; -#else -#error "Please fix <asm/byteorder.h>" -#endif - __u8 qqic; - __u16 nsrcs; - struct in6_addr srcs[0]; +/* Ensure that we have struct in6_addr aligned on 32bit word. */ +static void *__mld2_query_bugs[] __attribute__((__unused__)) = { + BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4), + BUILD_BUG_ON_NULL(offsetof(struct mld2_report, mld2r_grec) % 4), + BUILD_BUG_ON_NULL(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; /* Big mc list lock for all the sockets */ -static DEFINE_RWLOCK(ipv6_sk_mc_lock); - -static struct socket *igmp6_socket; - -int __ipv6_dev_mc_dec(struct inet6_dev *idev, struct in6_addr *addr); +static DEFINE_SPINLOCK(ipv6_sk_mc_lock); static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); @@ -138,65 +93,76 @@ static void mld_gq_timer_expire(unsigned long data); static void mld_ifc_timer_expire(unsigned long data); static void mld_ifc_event(struct inet6_dev *idev); static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc); -static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *addr); +static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr); static void mld_clear_delrec(struct inet6_dev *idev); +static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); -static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); -static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); - -#define IGMP6_UNSOLICITED_IVAL (10*HZ) #define MLD_QRV_DEFAULT 2 +/* RFC3810, 9.2. Query Interval */ +#define MLD_QI_DEFAULT (125 * HZ) +/* RFC3810, 9.3. Query Response Interval */ +#define MLD_QRI_DEFAULT (10 * HZ) -#define MLD_V1_SEEN(idev) (ipv6_devconf.force_mld_version == 1 || \ - (idev)->cnf.force_mld_version == 1 || \ - ((idev)->mc_v1_seen && \ - time_before(jiffies, (idev)->mc_v1_seen))) +/* RFC3810, 8.1 Query Version Distinctions */ +#define MLD_V1_QUERY_LEN 24 +#define MLD_V2_QUERY_LEN_MIN 28 -#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) -#define MLDV2_EXP(thresh, nbmant, nbexp, value) \ - ((value) < (thresh) ? (value) : \ - ((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \ - (MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp)))) +#define IPV6_MLD_MAX_MSF 64 -#define MLDV2_QQIC(value) MLDV2_EXP(0x80, 4, 3, value) -#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value) - -#define IPV6_MLD_MAX_MSF 10 - -int sysctl_mld_max_msf = IPV6_MLD_MAX_MSF; +int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; /* * socket join on multicast group */ -int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr) +#define for_each_pmc_rcu(np, pmc) \ + for (pmc = rcu_dereference(np->ipv6_mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next)) + +static int unsolicited_report_interval(struct inet6_dev *idev) +{ + int iv; + + if (mld_in_v1_mode(idev)) + iv = idev->cnf.mldv1_unsolicited_report_interval; + else + iv = idev->cnf.mldv2_unsolicited_report_interval; + + return iv > 0 ? iv : 1; +} + +int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; struct ipv6_pinfo *np = inet6_sk(sk); + struct net *net = sock_net(sk); int err; if (!ipv6_addr_is_multicast(addr)) return -EINVAL; - read_lock_bh(&ipv6_sk_mc_lock); - for (mc_lst=np->ipv6_mc_list; mc_lst; mc_lst=mc_lst->next) { + rcu_read_lock(); + for_each_pmc_rcu(np, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - read_unlock_bh(&ipv6_sk_mc_lock); + rcu_read_unlock(); return -EADDRINUSE; } } - read_unlock_bh(&ipv6_sk_mc_lock); + rcu_read_unlock(); mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); @@ -204,26 +170,28 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, 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(addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; - dev_hold(dev); - dst_release(&rt->u.dst); + dev = rt->dst.dev; + ip6_rt_put(rt); } } else - dev = dev_get_by_index(ifindex); + dev = dev_get_by_index_rcu(net, ifindex); if (dev == NULL) { + rcu_read_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = MCAST_EXCLUDE; + rwlock_init(&mc_lst->sflock); mc_lst->sflist = NULL; /* @@ -233,17 +201,17 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr) err = ipv6_dev_mc_inc(dev, addr); if (err) { + rcu_read_unlock(); sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); - dev_put(dev); return err; } - write_lock_bh(&ipv6_sk_mc_lock); + spin_lock(&ipv6_sk_mc_lock); mc_lst->next = np->ipv6_mc_list; - np->ipv6_mc_list = mc_lst; - write_unlock_bh(&ipv6_sk_mc_lock); + rcu_assign_pointer(np->ipv6_mc_list, mc_lst); + spin_unlock(&ipv6_sk_mc_lock); - dev_put(dev); + rcu_read_unlock(); return 0; } @@ -251,68 +219,75 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr) /* * socket leave on multicast group */ -int ipv6_sock_mc_drop(struct sock *sk, int ifindex, struct in6_addr *addr) +int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6_mc_socklist *mc_lst, **lnk; + struct ipv6_mc_socklist *mc_lst; + struct ipv6_mc_socklist __rcu **lnk; + struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_mc_lock); - for (lnk = &np->ipv6_mc_list; (mc_lst = *lnk) !=NULL ; lnk = &mc_lst->next) { + if (!ipv6_addr_is_multicast(addr)) + return -EINVAL; + + spin_lock(&ipv6_sk_mc_lock); + for (lnk = &np->ipv6_mc_list; + (mc_lst = rcu_dereference_protected(*lnk, + lockdep_is_held(&ipv6_sk_mc_lock))) !=NULL ; + lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); - if ((dev = dev_get_by_index(mc_lst->ifindex)) != NULL) { - struct inet6_dev *idev = in6_dev_get(dev); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, mc_lst->ifindex); + if (dev != NULL) { + struct inet6_dev *idev = __in6_dev_get(dev); - if (idev) { - (void) ip6_mc_leave_src(sk,mc_lst,idev); + (void) ip6_mc_leave_src(sk, mc_lst, idev); + if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); - in6_dev_put(idev); - } - dev_put(dev); - } - sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); + } else + (void) ip6_mc_leave_src(sk, mc_lst, NULL); + rcu_read_unlock(); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); + kfree_rcu(mc_lst, rcu); return 0; } } - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); return -EADDRNOTAVAIL; } -static struct inet6_dev *ip6_mc_find_dev(struct in6_addr *group, int ifindex) +/* called with rcu_read_lock() */ +static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, + const struct in6_addr *group, + int ifindex) { struct net_device *dev = NULL; struct inet6_dev *idev = NULL; if (ifindex == 0) { - struct rt6_info *rt; + struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, 0); - rt = rt6_lookup(group, NULL, 0, 0); if (rt) { - dev = rt->rt6i_dev; - dev_hold(dev); - dst_release(&rt->u.dst); + dev = rt->dst.dev; + ip6_rt_put(rt); } } else - dev = dev_get_by_index(ifindex); + dev = dev_get_by_index_rcu(net, ifindex); if (!dev) return NULL; - idev = in6_dev_get(dev); - if (!idev) { - dev_put(dev); + idev = __in6_dev_get(dev); + if (!idev) return NULL; - } read_lock_bh(&idev->lock); if (idev->dead) { read_unlock_bh(&idev->lock); - in6_dev_put(idev); - dev_put(dev); return NULL; } return idev; @@ -322,31 +297,37 @@ void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; + struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_mc_lock); - while ((mc_lst = np->ipv6_mc_list) != NULL) { + if (!rcu_access_pointer(np->ipv6_mc_list)) + return; + + spin_lock(&ipv6_sk_mc_lock); + while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list, + lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); - dev = dev_get_by_index(mc_lst->ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, mc_lst->ifindex); if (dev) { - struct inet6_dev *idev = in6_dev_get(dev); + struct inet6_dev *idev = __in6_dev_get(dev); - if (idev) { - (void) ip6_mc_leave_src(sk, mc_lst, idev); + (void) ip6_mc_leave_src(sk, mc_lst, idev); + if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); - in6_dev_put(idev); - } - dev_put(dev); - } + } else + (void) ip6_mc_leave_src(sk, mc_lst, NULL); + rcu_read_unlock(); - sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); + atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); + kfree_rcu(mc_lst, rcu); - write_lock_bh(&ipv6_sk_mc_lock); + spin_lock(&ipv6_sk_mc_lock); } - write_unlock_bh(&ipv6_sk_mc_lock); + spin_unlock(&ipv6_sk_mc_lock); } int ip6_mc_source(int add, int omode, struct sock *sk, @@ -354,33 +335,31 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct in6_addr *source, *group; struct ipv6_mc_socklist *pmc; - struct net_device *dev; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; + struct net *net = sock_net(sk); int i, j, rv; int leavegroup = 0; + int pmclocked = 0; int err; - if (pgsr->gsr_group.ss_family != AF_INET6 || - pgsr->gsr_source.ss_family != AF_INET6) - return -EINVAL; - source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; - idev = ip6_mc_find_dev(group, pgsr->gsr_interface); - if (!idev) + rcu_read_lock(); + idev = ip6_mc_find_dev_rcu(net, group, pgsr->gsr_interface); + if (!idev) { + rcu_read_unlock(); return -ENODEV; - dev = idev->dev; + } err = -EADDRNOTAVAIL; - read_lock_bh(&ipv6_sk_mc_lock); - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) @@ -403,14 +382,16 @@ int ip6_mc_source(int add, int omode, struct sock *sk, pmc->sfmode = omode; } + write_lock(&pmc->sflock); + pmclocked = 1; + psl = pmc->sflist; if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i=0; i<psl->sl_count; i++) { - rv = memcmp(&psl->sl_addr[i], source, - sizeof(struct in6_addr)); + rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } @@ -444,8 +425,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (psl) count += psl->sl_max; - newpsl = (struct ip6_sf_socklist *)sock_kmalloc(sk, - IP6_SFLSIZE(count), GFP_ATOMIC); + newpsl = sock_kmalloc(sk, IP6_SFLSIZE(count), GFP_ATOMIC); if (!newpsl) { err = -ENOBUFS; goto done; @@ -461,12 +441,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk, } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i=0; i<psl->sl_count; i++) { - rv = memcmp(&psl->sl_addr[i], source, sizeof(struct in6_addr)); - if (rv == 0) - break; + rv = !ipv6_addr_equal(&psl->sl_addr[i], source); + if (rv == 0) /* There is an error in the address. */ + goto done; } - if (rv == 0) /* address already there is an error */ - goto done; for (j=psl->sl_count-1; j>=i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; @@ -475,10 +453,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk, /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: - read_unlock_bh(&ipv6_sk_mc_lock); + if (pmclocked) + write_unlock(&pmc->sflock); read_unlock_bh(&idev->lock); - in6_dev_put(idev); - dev_put(dev); + rcu_read_unlock(); if (leavegroup) return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; @@ -486,12 +464,12 @@ done: int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) { - struct in6_addr *group; + const struct in6_addr *group; struct ipv6_mc_socklist *pmc; - struct net_device *dev; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; + struct net *net = sock_net(sk); int leavegroup = 0; int i, err; @@ -503,19 +481,22 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) gsf->gf_fmode != MCAST_EXCLUDE) return -EINVAL; - idev = ip6_mc_find_dev(group, gsf->gf_interface); + rcu_read_lock(); + idev = ip6_mc_find_dev_rcu(net, group, gsf->gf_interface); - if (!idev) + if (!idev) { + rcu_read_unlock(); return -ENODEV; - dev = idev->dev; + } err = 0; + if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) @@ -526,8 +507,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) goto done; } if (gsf->gf_numsrc) { - newpsl = (struct ip6_sf_socklist *)sock_kmalloc(sk, - IP6_SFLSIZE(gsf->gf_numsrc), GFP_ATOMIC); + newpsl = sock_kmalloc(sk, IP6_SFLSIZE(gsf->gf_numsrc), + GFP_ATOMIC); if (!newpsl) { err = -ENOBUFS; goto done; @@ -549,6 +530,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) newpsl = NULL; (void) ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); } + + write_lock(&pmc->sflock); psl = pmc->sflist; if (psl) { (void) ip6_mc_del_src(idev, group, pmc->sfmode, @@ -558,11 +541,11 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) (void) ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sflist = newpsl; pmc->sfmode = gsf->gf_fmode; + write_unlock(&pmc->sflock); err = 0; done: read_unlock_bh(&idev->lock); - in6_dev_put(idev); - dev_put(dev); + rcu_read_unlock(); if (leavegroup) err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; @@ -572,28 +555,34 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen) { int err, i, count, copycount; - struct in6_addr *group; + const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; - struct net_device *dev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; + struct net *net = sock_net(sk); group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; - idev = ip6_mc_find_dev(group, gsf->gf_interface); + rcu_read_lock(); + idev = ip6_mc_find_dev_rcu(net, group, gsf->gf_interface); - if (!idev) + if (!idev) { + rcu_read_unlock(); return -ENODEV; - - dev = idev->dev; + } err = -EADDRNOTAVAIL; + /* + * changes to the ipv6_mc_list require the socket lock and + * a read lock on ip6_sk_mc_lock. We have the socket lock, + * so reading the list is safe. + */ - for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(inet6, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) @@ -605,8 +594,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, psl = pmc->sflist; count = psl ? psl->sl_count : 0; read_unlock_bh(&idev->lock); - in6_dev_put(idev); - dev_put(dev); + rcu_read_unlock(); copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; @@ -614,6 +602,10 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) { return -EFAULT; } + /* changes to psl require the socket lock, a read lock on + * on ipv6_sk_mc_lock and a write lock on pmc->sflock. We + * have the socket lock, so reading here is safe. + */ for (i=0; i<copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; @@ -622,34 +614,34 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, memset(&ss, 0, sizeof(ss)); psin6->sin6_family = AF_INET6; psin6->sin6_addr = psl->sl_addr[i]; - if (copy_to_user(&optval->gf_slist[i], &ss, sizeof(ss))) + if (copy_to_user(&optval->gf_slist[i], &ss, sizeof(ss))) return -EFAULT; } return 0; done: read_unlock_bh(&idev->lock); - in6_dev_put(idev); - dev_put(dev); + rcu_read_unlock(); return err; } -int inet6_mc_check(struct sock *sk, struct in6_addr *mc_addr, - struct in6_addr *src_addr) +bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, + const struct in6_addr *src_addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc; struct ip6_sf_socklist *psl; - int rv = 1; + bool rv = true; - read_lock(&ipv6_sk_mc_lock); - for (mc = np->ipv6_mc_list; mc; mc = mc->next) { + rcu_read_lock(); + for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { - read_unlock(&ipv6_sk_mc_lock); - return 1; + rcu_read_unlock(); + return true; } + read_lock(&mc->sflock); psl = mc->sflist; if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; @@ -661,11 +653,12 @@ int inet6_mc_check(struct sock *sk, struct in6_addr *mc_addr, break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) - rv = 0; + rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) - rv = 0; + rv = false; } - read_unlock(&ipv6_sk_mc_lock); + read_unlock(&mc->sflock); + rcu_read_unlock(); return rv; } @@ -683,18 +676,22 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; + if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < + IPV6_ADDR_SCOPE_LINKLOCAL) + return; + spin_lock_bh(&mc->mca_lock); if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) - dev_mc_add(dev, buf, dev->addr_len, 0); + dev_mc_add(dev, buf); } spin_unlock_bh(&mc->mca_lock); if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; - if (MLD_V1_SEEN(mc->idev)) { + if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } @@ -709,11 +706,15 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; + if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < + IPV6_ADDR_SCOPE_LINKLOCAL) + return; + spin_lock_bh(&mc->mca_lock); if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) - dev_mc_delete(dev, buf, dev->addr_len, 0); + dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) @@ -744,10 +745,10 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ - pmc = (struct ifmcaddr6 *)kmalloc(sizeof(*pmc), GFP_ATOMIC); + pmc = kzalloc(sizeof(*pmc), GFP_ATOMIC); if (!pmc) return; - memset(pmc, 0, sizeof(*pmc)); + spin_lock_bh(&im->mca_lock); spin_lock_init(&pmc->mca_lock); pmc->idev = im->idev; @@ -766,18 +767,18 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) } spin_unlock_bh(&im->mca_lock); - write_lock_bh(&idev->mc_lock); + spin_lock_bh(&idev->mc_lock); pmc->next = idev->mc_tomb; idev->mc_tomb = pmc; - write_unlock_bh(&idev->mc_lock); + spin_unlock_bh(&idev->mc_lock); } -static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca) +static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca) { struct ifmcaddr6 *pmc, *pmc_prev; struct ip6_sf_list *psf, *psf_next; - write_lock_bh(&idev->mc_lock); + spin_lock_bh(&idev->mc_lock); pmc_prev = NULL; for (pmc=idev->mc_tomb; pmc; pmc=pmc->next) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) @@ -790,7 +791,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *pmca) else idev->mc_tomb = pmc->next; } - write_unlock_bh(&idev->mc_lock); + spin_unlock_bh(&idev->mc_lock); + if (pmc) { for (psf=pmc->mca_tomb; psf; psf=psf_next) { psf_next = psf->sf_next; @@ -805,10 +807,10 @@ static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; - write_lock_bh(&idev->mc_lock); + spin_lock_bh(&idev->mc_lock); pmc = idev->mc_tomb; idev->mc_tomb = NULL; - write_unlock_bh(&idev->mc_lock); + spin_unlock_bh(&idev->mc_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; @@ -838,11 +840,12 @@ static void mld_clear_delrec(struct inet6_dev *idev) /* * device multicast group inc (add if not found) */ -int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr) +int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { struct ifmcaddr6 *mc; struct inet6_dev *idev; + /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (idev == NULL) @@ -870,7 +873,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr) * not found: create a new one. */ - mc = kmalloc(sizeof(struct ifmcaddr6), GFP_ATOMIC); + mc = kzalloc(sizeof(struct ifmcaddr6), GFP_ATOMIC); if (mc == NULL) { write_unlock_bh(&idev->lock); @@ -878,13 +881,10 @@ int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr) return -ENOMEM; } - memset(mc, 0, sizeof(struct ifmcaddr6)); - init_timer(&mc->mca_timer); - mc->mca_timer.function = igmp6_timer_handler; - mc->mca_timer.data = (unsigned long) mc; + setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc); - ipv6_addr_copy(&mc->mca_addr, addr); - mc->idev = idev; + mc->mca_addr = *addr; + mc->idev = idev; /* (reference taken) */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; @@ -912,7 +912,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr) /* * device multicast group del */ -int __ipv6_dev_mc_dec(struct inet6_dev *idev, struct in6_addr *addr) +int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, **map; @@ -937,59 +937,35 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, struct in6_addr *addr) return -ENOENT; } -int ipv6_dev_mc_dec(struct net_device *dev, struct in6_addr *addr) +int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) { - struct inet6_dev *idev = in6_dev_get(dev); + struct inet6_dev *idev; int err; - if (!idev) - return -ENODEV; + rcu_read_lock(); - err = __ipv6_dev_mc_dec(idev, addr); - - in6_dev_put(idev); + idev = __in6_dev_get(dev); + if (!idev) + err = -ENODEV; + else + err = __ipv6_dev_mc_dec(idev, addr); + rcu_read_unlock(); return err; } /* - * identify MLD packets for MLD filter exceptions - */ -int ipv6_is_mld(struct sk_buff *skb, int nexthdr) -{ - struct icmp6hdr *pic; - - if (nexthdr != IPPROTO_ICMPV6) - return 0; - - if (!pskb_may_pull(skb, sizeof(struct icmp6hdr))) - return 0; - - pic = (struct icmp6hdr *)skb->h.raw; - - switch (pic->icmp6_type) { - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - case ICMPV6_MLD2_REPORT: - return 1; - default: - break; - } - return 0; -} - -/* * check if the interface/address pair is valid */ -int ipv6_chk_mcast_addr(struct net_device *dev, struct in6_addr *group, - struct in6_addr *src_addr) +bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, + const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; - int rv = 0; + bool rv = false; - idev = in6_dev_get(dev); + rcu_read_lock(); + idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); for (mc = idev->mc_list; mc; mc=mc->next) { @@ -1013,31 +989,59 @@ int ipv6_chk_mcast_addr(struct net_device *dev, struct in6_addr *group, rv = mc->mca_sfcount[MCAST_EXCLUDE] !=0; spin_unlock_bh(&mc->mca_lock); } else - rv = 1; /* don't filter unspecified source */ + rv = true; /* don't filter unspecified source */ } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } + rcu_read_unlock(); return rv; } static void mld_gq_start_timer(struct inet6_dev *idev) { - int tv = net_random() % idev->mc_maxdelay; + unsigned long tv = prandom_u32() % idev->mc_maxdelay; idev->mc_gq_running = 1; if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2)) in6_dev_hold(idev); } -static void mld_ifc_start_timer(struct inet6_dev *idev, int delay) +static void mld_gq_stop_timer(struct inet6_dev *idev) { - int tv = net_random() % delay; + idev->mc_gq_running = 0; + if (del_timer(&idev->mc_gq_timer)) + __in6_dev_put(idev); +} + +static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay) +{ + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2)) in6_dev_hold(idev); } +static void mld_ifc_stop_timer(struct inet6_dev *idev) +{ + idev->mc_ifc_count = 0; + if (del_timer(&idev->mc_ifc_timer)) + __in6_dev_put(idev); +} + +static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay) +{ + unsigned long tv = prandom_u32() % delay; + + if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2)) + in6_dev_hold(idev); +} + +static void mld_dad_stop_timer(struct inet6_dev *idev) +{ + if (del_timer(&idev->mc_dad_timer)) + __in6_dev_put(idev); +} + /* * IGMP handling (alias multicast ICMPv6 messages) */ @@ -1056,128 +1060,307 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) delay = ma->mca_timer.expires - jiffies; } - if (delay >= resptime) { - if (resptime) - delay = net_random() % resptime; - else - delay = 1; - } + if (delay >= resptime) + delay = prandom_u32() % resptime; + ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) atomic_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } -static void mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, - struct in6_addr *srcs) +/* mark EXCLUDE-mode sources */ +static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, + const struct in6_addr *srcs) +{ + struct ip6_sf_list *psf; + int i, scount; + + scount = 0; + for (psf=pmc->mca_sources; psf; psf=psf->sf_next) { + if (scount == nsrcs) + break; + for (i=0; i<nsrcs; i++) { + /* skip inactive filters */ + if (psf->sf_count[MCAST_INCLUDE] || + pmc->mca_sfcount[MCAST_EXCLUDE] != + psf->sf_count[MCAST_EXCLUDE]) + break; + if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { + scount++; + break; + } + } + } + pmc->mca_flags &= ~MAF_GSQUERY; + if (scount == nsrcs) /* all sources excluded */ + return false; + return true; +} + +static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, + const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; + if (pmc->mca_sfmode == MCAST_EXCLUDE) + return mld_xmarksources(pmc, nsrcs, srcs); + + /* mark INCLUDE-mode sources */ + scount = 0; for (psf=pmc->mca_sources; psf; psf=psf->sf_next) { if (scount == nsrcs) break; - for (i=0; i<nsrcs; i++) + for (i=0; i<nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } + } + } + if (!scount) { + pmc->mca_flags &= ~MAF_GSQUERY; + return false; } + pmc->mca_flags |= MAF_GSQUERY; + return true; } +static int mld_force_mld_version(const struct inet6_dev *idev) +{ + /* Normally, both are 0 here. If enforcement to a particular is + * being used, individual device enforcement will have a lower + * precedence over 'all' device (.../conf/all/force_mld_version). + */ + + if (dev_net(idev->dev)->ipv6.devconf_all->force_mld_version != 0) + return dev_net(idev->dev)->ipv6.devconf_all->force_mld_version; + else + return idev->cnf.force_mld_version; +} + +static bool mld_in_v2_mode_only(const struct inet6_dev *idev) +{ + return mld_force_mld_version(idev) == 2; +} + +static bool mld_in_v1_mode_only(const struct inet6_dev *idev) +{ + return mld_force_mld_version(idev) == 1; +} + +static bool mld_in_v1_mode(const struct inet6_dev *idev) +{ + if (mld_in_v2_mode_only(idev)) + return false; + if (mld_in_v1_mode_only(idev)) + return true; + if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) + return true; + + return false; +} + +static void mld_set_v1_mode(struct inet6_dev *idev) +{ + /* RFC3810, relevant sections: + * - 9.1. Robustness Variable + * - 9.2. Query Interval + * - 9.3. Query Response Interval + * - 9.12. Older Version Querier Present Timeout + */ + unsigned long switchback; + + switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; + + idev->mc_v1_seen = jiffies + switchback; +} + +static void mld_update_qrv(struct inet6_dev *idev, + const struct mld2_query *mlh2) +{ + /* RFC3810, relevant sections: + * - 5.1.8. QRV (Querier's Robustness Variable) + * - 9.1. Robustness Variable + */ + + /* The value of the Robustness Variable MUST NOT be zero, + * and SHOULD NOT be one. Catch this here if we ever run + * into such a case in future. + */ + WARN_ON(idev->mc_qrv == 0); + + if (mlh2->mld2q_qrv > 0) + idev->mc_qrv = mlh2->mld2q_qrv; + + if (unlikely(idev->mc_qrv < 2)) { + net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", + idev->mc_qrv, MLD_QRV_DEFAULT); + idev->mc_qrv = MLD_QRV_DEFAULT; + } +} + +static void mld_update_qi(struct inet6_dev *idev, + const struct mld2_query *mlh2) +{ + /* RFC3810, relevant sections: + * - 5.1.9. QQIC (Querier's Query Interval Code) + * - 9.2. Query Interval + * - 9.12. Older Version Querier Present Timeout + * (the [Query Interval] in the last Query received) + */ + unsigned long mc_qqi; + + if (mlh2->mld2q_qqic < 128) { + mc_qqi = mlh2->mld2q_qqic; + } else { + unsigned long mc_man, mc_exp; + + mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); + mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); + + mc_qqi = (mc_man | 0x10) << (mc_exp + 3); + } + + idev->mc_qi = mc_qqi * HZ; +} + +static void mld_update_qri(struct inet6_dev *idev, + const struct mld2_query *mlh2) +{ + /* RFC3810, relevant sections: + * - 5.1.3. Maximum Response Code + * - 9.3. Query Response Interval + */ + idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); +} + +static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, + unsigned long *max_delay) +{ + unsigned long mldv1_md; + + /* Ignore v1 queries */ + if (mld_in_v2_mode_only(idev)) + return -EINVAL; + + /* MLDv1 router present */ + mldv1_md = ntohs(mld->mld_maxdelay); + *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); + + mld_set_v1_mode(idev); + + /* cancel MLDv2 report timer */ + mld_gq_stop_timer(idev); + /* cancel the interface change timer */ + mld_ifc_stop_timer(idev); + /* clear deleted report items */ + mld_clear_delrec(idev); + + return 0; +} + +static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, + unsigned long *max_delay) +{ + /* hosts need to stay in MLDv1 mode, discard MLDv2 queries */ + if (mld_in_v1_mode(idev)) + return -EINVAL; + + *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); + + mld_update_qrv(idev, mld); + mld_update_qi(idev, mld); + mld_update_qri(idev, mld); + + idev->mc_maxdelay = *max_delay; + + return 0; +} + +/* called with rcu_read_lock() */ int igmp6_event_query(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; struct ifmcaddr6 *ma; - struct in6_addr *group; + const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; - struct icmp6hdr *hdr; + struct mld_msg *mld; int group_type; int mark = 0; - int len; + int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) return -EINVAL; /* compute payload length excluding extension headers */ - len = ntohs(skb->nh.ipv6h->payload_len) + sizeof(struct ipv6hdr); - len -= (char *)skb->h.raw - (char *)skb->nh.ipv6h; - - /* Drop queries with not link local source */ - if (!(ipv6_addr_type(&skb->nh.ipv6h->saddr)&IPV6_ADDR_LINKLOCAL)) + len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); + len -= skb_network_header_len(skb); + + /* RFC3810 6.2 + * Upon reception of an MLD message that contains a Query, the node + * checks if the source address of the message is a valid link-local + * address, if the Hop Limit is set to 1, and if the Router Alert + * option is present in the Hop-By-Hop Options header of the IPv6 + * packet. If any of these checks fails, the packet is dropped. + */ + if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || + ipv6_hdr(skb)->hop_limit != 1 || + !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || + IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) return -EINVAL; - idev = in6_dev_get(skb->dev); - + idev = __in6_dev_get(skb->dev); if (idev == NULL) return 0; - hdr = (struct icmp6hdr *) skb->h.raw; - group = (struct in6_addr *) (hdr + 1); + mld = (struct mld_msg *)icmp6_hdr(skb); + group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && - !(group_type&IPV6_ADDR_MULTICAST)) { - in6_dev_put(idev); + !(group_type&IPV6_ADDR_MULTICAST)) return -EINVAL; - } - if (len == 24) { - int switchback; - /* MLDv1 router present */ + if (len == MLD_V1_QUERY_LEN) { + err = mld_process_v1(idev, mld, &max_delay); + if (err < 0) + return err; + } else if (len >= MLD_V2_QUERY_LEN_MIN) { + int srcs_offset = sizeof(struct mld2_query) - + sizeof(struct icmp6hdr); - /* Translate milliseconds to jiffies */ - max_delay = (ntohs(hdr->icmp6_maxdelay)*HZ)/1000; + if (!pskb_may_pull(skb, srcs_offset)) + return -EINVAL; - switchback = (idev->mc_qrv + 1) * max_delay; - idev->mc_v1_seen = jiffies + switchback; + mlh2 = (struct mld2_query *)skb_transport_header(skb); + + err = mld_process_v2(idev, mlh2, &max_delay); + if (err < 0) + return err; - /* cancel the interface change timer */ - idev->mc_ifc_count = 0; - if (del_timer(&idev->mc_ifc_timer)) - __in6_dev_put(idev); - /* clear deleted report items */ - mld_clear_delrec(idev); - } else if (len >= 28) { - int srcs_offset = sizeof(struct mld2_query) - - sizeof(struct icmp6hdr); - if (!pskb_may_pull(skb, srcs_offset)) { - in6_dev_put(idev); - return -EINVAL; - } - mlh2 = (struct mld2_query *) skb->h.raw; - max_delay = (MLDV2_MRC(ntohs(mlh2->mrc))*HZ)/1000; - if (!max_delay) - max_delay = 1; - idev->mc_maxdelay = max_delay; - if (mlh2->qrv) - idev->mc_qrv = mlh2->qrv; if (group_type == IPV6_ADDR_ANY) { /* general query */ - if (mlh2->nsrcs) { - in6_dev_put(idev); + if (mlh2->mld2q_nsrcs) return -EINVAL; /* no sources allowed */ - } + mld_gq_start_timer(idev); - in6_dev_put(idev); return 0; } /* mark sources to include, if group & source-specific */ - if (mlh2->nsrcs != 0) { - if (!pskb_may_pull(skb, srcs_offset + - mlh2->nsrcs * sizeof(struct in6_addr))) { - in6_dev_put(idev); + if (mlh2->mld2q_nsrcs != 0) { + if (!pskb_may_pull(skb, srcs_offset + + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) return -EINVAL; - } - mlh2 = (struct mld2_query *) skb->h.raw; + + mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } - } else { - in6_dev_put(idev); + } else return -EINVAL; - } read_lock_bh(&idev->lock); if (group_type == IPV6_ADDR_ANY) { @@ -1188,8 +1371,7 @@ int igmp6_event_query(struct sk_buff *skb) } } else { for (ma = idev->mc_list; ma; ma=ma->next) { - if (group_type != IPV6_ADDR_ANY && - !ipv6_addr_equal(group, &ma->mca_addr)) + if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; spin_lock_bh(&ma->mca_lock); if (ma->mca_flags & MAF_TIMER_RUNNING) { @@ -1203,48 +1385,47 @@ int igmp6_event_query(struct sk_buff *skb) else ma->mca_flags &= ~MAF_GSQUERY; } - if (ma->mca_flags & MAF_GSQUERY) - mld_marksources(ma, ntohs(mlh2->nsrcs), - mlh2->srcs); - igmp6_group_queried(ma, max_delay); + if (!(ma->mca_flags & MAF_GSQUERY) || + mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) + igmp6_group_queried(ma, max_delay); spin_unlock_bh(&ma->mca_lock); - if (group_type != IPV6_ADDR_ANY) - break; + break; } } read_unlock_bh(&idev->lock); - in6_dev_put(idev); return 0; } - +/* called with rcu_read_lock() */ int igmp6_event_report(struct sk_buff *skb) { struct ifmcaddr6 *ma; - struct in6_addr *addrp; struct inet6_dev *idev; - struct icmp6hdr *hdr; + struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ if (skb->pkt_type == PACKET_LOOPBACK) return 0; - if (!pskb_may_pull(skb, sizeof(struct in6_addr))) + /* send our report if the MC router may not have heard this report */ + if (skb->pkt_type != PACKET_MULTICAST && + skb->pkt_type != PACKET_BROADCAST) + return 0; + + if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) return -EINVAL; - hdr = (struct icmp6hdr*) skb->h.raw; + mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ - addr_type = ipv6_addr_type(&skb->nh.ipv6h->saddr); - if (addr_type != IPV6_ADDR_ANY && + addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); + if (addr_type != IPV6_ADDR_ANY && !(addr_type&IPV6_ADDR_LINKLOCAL)) return -EINVAL; - addrp = (struct in6_addr *) (hdr + 1); - - idev = in6_dev_get(skb->dev); + idev = __in6_dev_get(skb->dev); if (idev == NULL) return -ENODEV; @@ -1254,7 +1435,7 @@ int igmp6_event_report(struct sk_buff *skb) read_lock_bh(&idev->lock); for (ma = idev->mc_list; ma; ma=ma->next) { - if (ipv6_addr_equal(&ma->mca_addr, addrp)) { + if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { spin_lock(&ma->mca_lock); if (del_timer(&ma->mca_timer)) atomic_dec(&ma->mca_refcnt); @@ -1264,41 +1445,51 @@ int igmp6_event_report(struct sk_buff *skb) } } read_unlock_bh(&idev->lock); - in6_dev_put(idev); return 0; } -static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, - int gdeleted, int sdeleted) +static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, + int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) - return 0; - return !((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp); + return false; + if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { + if (pmc->mca_sfmode == MCAST_INCLUDE) + return true; + /* don't include if this source is excluded + * in all filters + */ + if (psf->sf_count[MCAST_INCLUDE]) + return type == MLD2_MODE_IS_INCLUDE; + return pmc->mca_sfcount[MCAST_EXCLUDE] == + psf->sf_count[MCAST_EXCLUDE]; + } + return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) - return 0; + return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) - return 0; + return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) - return 0; + return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) - return 0; + return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } - return 0; + return false; } static int @@ -1315,97 +1506,142 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) return scount; } -static struct sk_buff *mld_newpack(struct net_device *dev, int size) +static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, + struct net_device *dev, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int proto, int len) { - struct sock *sk = igmp6_socket->sk; + struct ipv6hdr *hdr; + + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + + skb_reset_network_header(skb); + skb_put(skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(skb); + + ip6_flow_hdr(hdr, 0, 0); + + hdr->payload_len = htons(len); + hdr->nexthdr = proto; + hdr->hop_limit = inet6_sk(sk)->hop_limit; + + hdr->saddr = *saddr; + hdr->daddr = *daddr; +} + +static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) +{ + struct net_device *dev = idev->dev; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.igmp_sk; struct sk_buff *skb; 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 */ - skb = sock_alloc_send_skb(sk, size + LL_RESERVED_SPACE(dev), 1, &err); + 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); - if (skb == 0) + if (!skb) return NULL; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb->priority = TC_PRIO_CONTROL; + skb_reserve(skb, hlen); - if (ipv6_get_lladdr(dev, &addr_buf)) { + if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: - * use unspecified address as the source address + * use unspecified address as the source address * when a valid link-local address is not available. */ - memset(&addr_buf, 0, sizeof(addr_buf)); - } + saddr = &in6addr_any; + } else + saddr = &addr_buf; - ip6_nd_hdr(sk, skb, dev, &addr_buf, &mld2_all_mcr, NEXTHDR_HOP, 0); + ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); - pmr =(struct mld2_report *)skb_put(skb, sizeof(*pmr)); - skb->h.raw = (unsigned char *)pmr; - pmr->type = ICMPV6_MLD2_REPORT; - pmr->resv1 = 0; - pmr->csum = 0; - pmr->resv2 = 0; - pmr->ngrec = 0; + skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); + skb_put(skb, sizeof(*pmr)); + pmr = (struct mld2_report *)skb_transport_header(skb); + pmr->mld2r_type = ICMPV6_MLD2_REPORT; + pmr->mld2r_resv1 = 0; + pmr->mld2r_cksum = 0; + pmr->mld2r_resv2 = 0; + pmr->mld2r_ngrec = 0; return skb; } -static inline int mld_dev_queue_xmit2(struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - - if (dev->hard_header) { - unsigned char ha[MAX_ADDR_LEN]; - int err; - - ndisc_mc_map(&skb->nh.ipv6h->daddr, ha, dev, 1); - err = dev->hard_header(skb, dev, ETH_P_IPV6, ha, NULL, skb->len); - if (err < 0) { - kfree_skb(skb); - return err; - } - } - return dev_queue_xmit(skb); -} - -static inline int mld_dev_queue_xmit(struct sk_buff *skb) -{ - return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb, NULL, skb->dev, - mld_dev_queue_xmit2); -} - static void mld_sendpack(struct sk_buff *skb) { - struct ipv6hdr *pip6 = skb->nh.ipv6h; - struct mld2_report *pmr = (struct mld2_report *)skb->h.raw; + struct ipv6hdr *pip6 = ipv6_hdr(skb); + struct mld2_report *pmr = + (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; - struct inet6_dev *idev = in6_dev_get(skb->dev); + struct inet6_dev *idev; + struct net *net = dev_net(skb->dev); int err; + struct flowi6 fl6; + struct dst_entry *dst; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - payload_len = skb->tail - (unsigned char *)skb->nh.ipv6h - - sizeof(struct ipv6hdr); - mldlen = skb->tail - skb->h.raw; + payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - + sizeof(*pip6); + mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); - pmr->csum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, - IPPROTO_ICMPV6, csum_partial(skb->h.raw, mldlen, 0)); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dev, - mld_dev_queue_xmit); + pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, + IPPROTO_ICMPV6, + csum_partial(skb_transport_header(skb), + mldlen, 0)); + + 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, &fl6); + + err = 0; + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + } + skb_dst_set(skb, dst); + if (err) + goto err_out; + + payload_len = skb->len; + + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, + dst_output); +out: if (!err) { - ICMP6_INC_STATS(idev,ICMP6_MIB_OUTMSGS); - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); - } else - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); + } else { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + } - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); + return; + +err_out: + kfree_skb(skb); + goto out; } static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) @@ -1421,7 +1657,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr; if (!skb) - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(pmc->idev, dev->mtu); if (!skb) return NULL; pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); @@ -1429,8 +1665,8 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ - pmr = (struct mld2_report *)skb->h.raw; - pmr->ngrec = htons(ntohs(pmr->ngrec)+1); + pmr = (struct mld2_report *)skb_transport_header(skb); + pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } @@ -1439,13 +1675,14 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, skb_tailroom(skb)) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, - int type, int gdeleted, int sdeleted) + int type, int gdeleted, int sdeleted, int crsend) { - struct net_device *dev = pmc->idev->dev; + struct inet6_dev *idev = pmc->idev; + struct net_device *dev = idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; - int scount, first, isquery, truncate; + int scount, stotal, first, isquery, truncate; if (pmc->mca_flags & MAF_NOREPORT) return skb; @@ -1455,38 +1692,25 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; + stotal = scount = 0; + psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; - if (!*psf_list) { - if (type == MLD2_ALLOW_NEW_SOURCES || - type == MLD2_BLOCK_OLD_SOURCES) - return skb; - if (pmc->mca_crcount || isquery) { - /* make sure we have room for group header and at - * least one source. - */ - if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)+ - sizeof(struct in6_addr)) { - mld_sendpack(skb); - skb = NULL; /* add_grhead will get a new one */ - } - skb = add_grhead(skb, pmc, type, &pgr); - } - return skb; - } - pmr = skb ? (struct mld2_report *)skb->h.raw : NULL; + if (!*psf_list) + goto empty_source; + + pmr = skb ? (struct mld2_report *)skb_transport_header(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { - if (pmr && pmr->ngrec && + if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); } } first = 1; - scount = 0; psf_prev = NULL; for (psf=*psf_list; psf; psf=psf_next) { struct in6_addr *psrc; @@ -1510,7 +1734,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); first = 1; scount = 0; } @@ -1518,9 +1742,11 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, skb = add_grhead(skb, pmc, type, &pgr); first = 0; } + if (!skb) + return NULL; psrc = (struct in6_addr *)skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; - scount++; + scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { psf->sf_crcount--; @@ -1535,6 +1761,21 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, } psf_prev = psf; } + +empty_source: + if (!stotal) { + if (type == MLD2_ALLOW_NEW_SOURCES || + type == MLD2_BLOCK_OLD_SOURCES) + return skb; + if (pmc->mca_crcount || isquery || crsend) { + /* make sure we have room for group header */ + if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { + mld_sendpack(skb); + skb = NULL; /* add_grhead will get a new one */ + } + skb = add_grhead(skb, pmc, type, &pgr); + } + } if (pgr) pgr->grec_nsrcs = htons(scount); @@ -1548,8 +1789,8 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) struct sk_buff *skb = NULL; int type; + read_lock_bh(&idev->lock); if (!pmc) { - read_lock_bh(&idev->lock); for (pmc=idev->mc_list; pmc; pmc=pmc->next) { if (pmc->mca_flags & MAF_NOREPORT) continue; @@ -1558,19 +1799,19 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; - skb = add_grec(skb, pmc, type, 0, 0); + skb = add_grec(skb, pmc, type, 0, 0, 0); spin_unlock_bh(&pmc->mca_lock); } - read_unlock_bh(&idev->lock); } else { spin_lock_bh(&pmc->mca_lock); if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; - skb = add_grec(skb, pmc, type, 0, 0); + skb = add_grec(skb, pmc, type, 0, 0, 0); spin_unlock_bh(&pmc->mca_lock); } + read_unlock_bh(&idev->lock); if (skb) mld_sendpack(skb); } @@ -1603,7 +1844,7 @@ static void mld_send_cr(struct inet6_dev *idev) int type, dtype; read_lock_bh(&idev->lock); - write_lock_bh(&idev->mc_lock); + spin_lock(&idev->mc_lock); /* deleted MCA's */ pmc_prev = NULL; @@ -1612,15 +1853,15 @@ static void mld_send_cr(struct inet6_dev *idev) if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; - skb = add_grec(skb, pmc, type, 1, 0); - skb = add_grec(skb, pmc, dtype, 1, 1); + skb = add_grec(skb, pmc, type, 1, 0, 0); + skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { - pmc->mca_crcount--; if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; - skb = add_grec(skb, pmc, type, 1, 0); + skb = add_grec(skb, pmc, type, 1, 0, 0); } + pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb); mld_clear_zeros(&pmc->mca_sources); @@ -1637,7 +1878,7 @@ static void mld_send_cr(struct inet6_dev *idev) } else pmc_prev = pmc; } - write_unlock_bh(&idev->mc_lock); + spin_unlock(&idev->mc_lock); /* change recs */ for (pmc=idev->mc_list; pmc; pmc=pmc->next) { @@ -1649,17 +1890,17 @@ static void mld_send_cr(struct inet6_dev *idev) type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } - skb = add_grec(skb, pmc, type, 0, 0); - skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ + skb = add_grec(skb, pmc, type, 0, 0, 0); + skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { - pmc->mca_crcount--; if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; - skb = add_grec(skb, pmc, type, 0, 0); + skb = add_grec(skb, pmc, type, 0, 0, 0); + pmc->mca_crcount--; } spin_unlock_bh(&pmc->mca_lock); } @@ -1671,83 +1912,152 @@ static void mld_send_cr(struct inet6_dev *idev) static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { - struct sock *sk = igmp6_socket->sk; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; - struct sk_buff *skb; - struct icmp6hdr *hdr; - struct in6_addr *snd_addr; - struct in6_addr *addrp; + struct sk_buff *skb; + struct mld_msg *hdr; + const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; - struct in6_addr all_routers; + 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, IPV6_TLV_PADN, 0 }; + struct flowi6 fl6; + struct dst_entry *dst; - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - snd_addr = addr; - if (type == ICMPV6_MGM_REDUCTION) { - snd_addr = &all_routers; - ipv6_addr_all_routers(&all_routers); - } + if (type == ICMPV6_MGM_REDUCTION) + snd_addr = &in6addr_linklocal_allrouters; + else + snd_addr = addr; len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; - skb = sock_alloc_send_skb(sk, LL_RESERVED_SPACE(dev) + full_len, 1, &err); + rcu_read_lock(); + IP6_UPD_PO_STATS(net, __in6_dev_get(dev), + IPSTATS_MIB_OUT, full_len); + rcu_read_unlock(); + + skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (skb == NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + rcu_read_lock(); + IP6_INC_STATS(net, __in6_dev_get(dev), + IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return; } + skb->priority = TC_PRIO_CONTROL; + skb_reserve(skb, hlen); - skb_reserve(skb, LL_RESERVED_SPACE(dev)); - - if (ipv6_get_lladdr(dev, &addr_buf)) { + if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: - * use unspecified address as the source address + * use unspecified address as the source address * when a valid link-local address is not available. */ - memset(&addr_buf, 0, sizeof(addr_buf)); - } + saddr = &in6addr_any; + } else + saddr = &addr_buf; - ip6_nd_hdr(sk, skb, dev, &addr_buf, snd_addr, NEXTHDR_HOP, payload_len); + ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); - hdr = (struct icmp6hdr *) skb_put(skb, sizeof(struct icmp6hdr)); - memset(hdr, 0, sizeof(struct icmp6hdr)); - hdr->icmp6_type = type; + hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); + memset(hdr, 0, sizeof(struct mld_msg)); + hdr->mld_type = type; + hdr->mld_mca = *addr; - addrp = (struct in6_addr *) skb_put(skb, sizeof(struct in6_addr)); - ipv6_addr_copy(addrp, addr); + hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, + IPPROTO_ICMPV6, + csum_partial(hdr, len, 0)); - hdr->icmp6_cksum = csum_ipv6_magic(&addr_buf, snd_addr, len, - IPPROTO_ICMPV6, - csum_partial((__u8 *) hdr, len, 0)); + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); - idev = in6_dev_get(skb->dev); + icmpv6_flow_init(sk, &fl6, type, + &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, + skb->dev->ifindex); + dst = icmp6_dst_alloc(skb->dev, &fl6); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto err_out; + } - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dev, - mld_dev_queue_xmit); + skb_dst_set(skb, dst); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, skb->dev, + dst_output); +out: if (!err) { - if (type == ICMPV6_MGM_REDUCTION) - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTGROUPMEMBREDUCTIONS); - else - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTGROUPMEMBRESPONSES); - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); + ICMP6MSGOUT_INC_STATS(net, idev, type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len); } else - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); - if (likely(idev != NULL)) - in6_dev_put(idev); + rcu_read_unlock(); return; + +err_out: + kfree_skb(skb); + goto out; +} + +static void mld_send_initial_cr(struct inet6_dev *idev) +{ + struct sk_buff *skb; + struct ifmcaddr6 *pmc; + int type; + + if (mld_in_v1_mode(idev)) + return; + + skb = NULL; + read_lock_bh(&idev->lock); + for (pmc=idev->mc_list; pmc; pmc=pmc->next) { + spin_lock_bh(&pmc->mca_lock); + if (pmc->mca_sfcount[MCAST_EXCLUDE]) + type = MLD2_CHANGE_TO_EXCLUDE; + else + type = MLD2_CHANGE_TO_INCLUDE; + skb = add_grec(skb, pmc, type, 0, 0, 1); + spin_unlock_bh(&pmc->mca_lock); + } + read_unlock_bh(&idev->lock); + if (skb) + mld_sendpack(skb); +} + +void ipv6_mc_dad_complete(struct inet6_dev *idev) +{ + idev->mc_dad_count = idev->mc_qrv; + if (idev->mc_dad_count) { + mld_send_initial_cr(idev); + idev->mc_dad_count--; + if (idev->mc_dad_count) + mld_dad_start_timer(idev, idev->mc_maxdelay); + } +} + +static void mld_dad_timer_expire(unsigned long data) +{ + struct inet6_dev *idev = (struct inet6_dev *)data; + + mld_send_initial_cr(idev); + if (idev->mc_dad_count) { + idev->mc_dad_count--; + if (idev->mc_dad_count) + mld_dad_start_timer(idev, idev->mc_maxdelay); + } + in6_dev_put(idev); } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, - struct in6_addr *psfsrc) + const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; @@ -1772,7 +2082,7 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, else pmc->mca_sources = psf->sf_next; if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && - !MLD_V1_SEEN(idev)) { + !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; psf->sf_next = pmc->mca_tomb; pmc->mca_tomb = psf; @@ -1783,8 +2093,8 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, return rv; } -static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; @@ -1844,7 +2154,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca, * Add multicast single-source filter to the interface list */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, - struct in6_addr *psfsrc, int delta) + const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; @@ -1855,10 +2165,10 @@ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, psf_prev = psf; } if (!psf) { - psf = (struct ip6_sf_list *)kmalloc(sizeof(*psf), GFP_ATOMIC); + psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; - memset(psf, 0, sizeof(*psf)); + psf->sf_addr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; @@ -1885,7 +2195,7 @@ static void sf_markstate(struct ifmcaddr6 *pmc) static int sf_setstate(struct ifmcaddr6 *pmc) { - struct ip6_sf_list *psf; + struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; @@ -1897,8 +2207,47 @@ static int sf_setstate(struct ifmcaddr6 *pmc) !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; - if (new_in != psf->sf_oldin) { - psf->sf_crcount = qrv; + if (new_in) { + if (!psf->sf_oldin) { + struct ip6_sf_list *prev = NULL; + + for (dpsf=pmc->mca_tomb; dpsf; + dpsf=dpsf->sf_next) { + if (ipv6_addr_equal(&dpsf->sf_addr, + &psf->sf_addr)) + break; + prev = dpsf; + } + if (dpsf) { + if (prev) + prev->sf_next = dpsf->sf_next; + else + pmc->mca_tomb = dpsf->sf_next; + kfree(dpsf); + } + psf->sf_crcount = qrv; + rv++; + } + } else if (psf->sf_oldin) { + psf->sf_crcount = 0; + /* + * add or update "delete" records if an active filter + * is now inactive + */ + for (dpsf=pmc->mca_tomb; dpsf; dpsf=dpsf->sf_next) + if (ipv6_addr_equal(&dpsf->sf_addr, + &psf->sf_addr)) + break; + if (!dpsf) { + dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); + if (!dpsf) + continue; + *dpsf = *psf; + /* pmc->mca_lock held by callers */ + dpsf->sf_next = pmc->mca_tomb; + pmc->mca_tomb = dpsf; + } + dpsf->sf_crcount = qrv; rv++; } } @@ -1908,8 +2257,8 @@ static int sf_setstate(struct ifmcaddr6 *pmc) /* * Add multicast source filter list to the interface list */ -static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, - int sfmode, int sfcount, struct in6_addr *psfsrc, +static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, + int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; @@ -1936,7 +2285,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, 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; } @@ -1946,9 +2295,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca, if (!delta) pmc->mca_sfcount[sfmode]--; for (j=0; j<i; j++) - (void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); + ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { - struct inet6_dev *idev = pmc->idev; struct ip6_sf_list *psf; /* filter mode change */ @@ -1999,7 +2347,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = net_random() % IGMP6_UNSOLICITED_IVAL; + delay = prandom_u32() % unsolicited_report_interval(ma->idev); spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { @@ -2018,7 +2366,10 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, { int err; - if (iml->sflist == 0) { + /* callers have the socket lock and a write lock on ipv6_sk_mc_lock, + * so no other readers or writers of iml or its sflist + */ + if (!iml->sflist) { /* any-source empty exclude case */ return ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); } @@ -2031,7 +2382,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, static void igmp6_leave_group(struct ifmcaddr6 *ma) { - if (MLD_V1_SEEN(ma->idev)) { + if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); @@ -2047,7 +2398,7 @@ static void mld_gq_timer_expire(unsigned long data) idev->mc_gq_running = 0; mld_send_report(idev, NULL); - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_timer_expire(unsigned long data) @@ -2060,12 +2411,12 @@ static void mld_ifc_timer_expire(unsigned long data) if (idev->mc_ifc_count) mld_ifc_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) { - if (MLD_V1_SEEN(idev)) + if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_timer(idev, 1); @@ -2076,7 +2427,7 @@ static void igmp6_timer_handler(unsigned long data) { struct ifmcaddr6 *ma = (struct ifmcaddr6 *) data; - if (MLD_V1_SEEN(ma->idev)) + if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); @@ -2088,6 +2439,25 @@ static void igmp6_timer_handler(unsigned long data) ma_put(ma); } +/* Device changing type */ + +void ipv6_mc_unmap(struct inet6_dev *idev) +{ + struct ifmcaddr6 *i; + + /* Install multicast list, except for all-nodes (already installed) */ + + read_lock_bh(&idev->lock); + for (i = idev->mc_list; i; i = i->next) + igmp6_group_dropped(i); + read_unlock_bh(&idev->lock); +} + +void ipv6_mc_remap(struct inet6_dev *idev) +{ + ipv6_mc_up(idev); +} + /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) @@ -2097,12 +2467,9 @@ void ipv6_mc_down(struct inet6_dev *idev) /* Withdraw multicast list */ read_lock_bh(&idev->lock); - idev->mc_ifc_count = 0; - if (del_timer(&idev->mc_ifc_timer)) - __in6_dev_put(idev); - idev->mc_gq_running = 0; - if (del_timer(&idev->mc_gq_timer)) - __in6_dev_put(idev); + mld_ifc_stop_timer(idev); + mld_gq_stop_timer(idev); + mld_dad_stop_timer(idev); for (i = idev->mc_list; i; i=i->next) igmp6_group_dropped(i); @@ -2130,27 +2497,25 @@ void ipv6_mc_up(struct inet6_dev *idev) void ipv6_mc_init_dev(struct inet6_dev *idev) { - struct in6_addr maddr; - write_lock_bh(&idev->lock); - rwlock_init(&idev->mc_lock); + spin_lock_init(&idev->mc_lock); idev->mc_gq_running = 0; - init_timer(&idev->mc_gq_timer); - idev->mc_gq_timer.data = (unsigned long) idev; - idev->mc_gq_timer.function = &mld_gq_timer_expire; + setup_timer(&idev->mc_gq_timer, mld_gq_timer_expire, + (unsigned long)idev); idev->mc_tomb = NULL; idev->mc_ifc_count = 0; - init_timer(&idev->mc_ifc_timer); - idev->mc_ifc_timer.data = (unsigned long) idev; - idev->mc_ifc_timer.function = &mld_ifc_timer_expire; + setup_timer(&idev->mc_ifc_timer, mld_ifc_timer_expire, + (unsigned long)idev); + setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire, + (unsigned long)idev); + idev->mc_qrv = MLD_QRV_DEFAULT; - idev->mc_maxdelay = IGMP6_UNSOLICITED_IVAL; + idev->mc_qi = MLD_QI_DEFAULT; + idev->mc_qri = MLD_QRI_DEFAULT; + + idev->mc_maxdelay = unsolicited_report_interval(idev); idev->mc_v1_seen = 0; write_unlock_bh(&idev->lock); - - /* Add all-nodes address. */ - ipv6_addr_all_nodes(&maddr); - ipv6_dev_mc_inc(idev->dev, &maddr); } /* @@ -2160,24 +2525,19 @@ void ipv6_mc_init_dev(struct inet6_dev *idev) void ipv6_mc_destroy_dev(struct inet6_dev *idev) { struct ifmcaddr6 *i; - struct in6_addr maddr; /* Deactivate timers */ ipv6_mc_down(idev); /* Delete all-nodes address. */ - ipv6_addr_all_nodes(&maddr); - /* We cannot call ipv6_dev_mc_dec() directly, our caller in * addrconf.c has NULL'd out dev->ip6_ptr so in6_dev_get() will * fail. */ - __ipv6_dev_mc_dec(idev, &maddr); + __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allnodes); - if (idev->cnf.forwarding) { - ipv6_addr_all_routers(&maddr); - __ipv6_dev_mc_dec(idev, &maddr); - } + if (idev->cnf.forwarding) + __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allrouters); write_lock_bh(&idev->lock); while ((i = idev->mc_list) != NULL) { @@ -2194,6 +2554,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { + struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; @@ -2204,12 +2565,12 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) { struct ifmcaddr6 *im = NULL; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); + struct net *net = seq_file_net(seq); - for (state->dev = dev_base, state->idev = NULL; - state->dev; - state->dev = state->dev->next) { + state->idev = NULL; + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -2219,7 +2580,6 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) break; } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return im; } @@ -2230,16 +2590,15 @@ static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr im = im->next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = state->dev->next; + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -2258,29 +2617,31 @@ static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifmcaddr6 *im; - im = igmp6_mc_get_next(seq, v); + struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); + ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) @@ -2289,16 +2650,16 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, - "%-4d %-15s %04x%04x%04x%04x%04x%04x%04x%04x %5d %08X %ld\n", + "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, - NIP6(im->mca_addr), + &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags&MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_timer.expires-jiffies) : 0); return 0; } -static struct seq_operations igmp6_mc_seq_ops = { +static const struct seq_operations igmp6_mc_seq_ops = { .start = igmp6_mc_seq_start, .next = igmp6_mc_seq_next, .stop = igmp6_mc_seq_stop, @@ -2307,36 +2668,20 @@ static struct seq_operations igmp6_mc_seq_ops = { static int igmp6_mc_seq_open(struct inode *inode, struct file *file) { - struct seq_file *seq; - int rc = -ENOMEM; - struct igmp6_mc_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); - - if (!s) - goto out; - - rc = seq_open(file, &igmp6_mc_seq_ops); - if (rc) - goto out_kfree; - - seq = file->private_data; - seq->private = s; - memset(s, 0, sizeof(*s)); -out: - return rc; -out_kfree: - kfree(s); - goto out; + return seq_open_net(inode, file, &igmp6_mc_seq_ops, + sizeof(struct igmp6_mc_iter_state)); } -static struct file_operations igmp6_mc_seq_fops = { +static const struct file_operations igmp6_mc_seq_fops = { .owner = THIS_MODULE, .open = igmp6_mc_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; struct igmp6_mcf_iter_state { + struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; struct ifmcaddr6 *im; @@ -2349,12 +2694,13 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) struct ip6_sf_list *psf = NULL; struct ifmcaddr6 *im = NULL; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); + struct net *net = seq_file_net(seq); - for (state->dev = dev_base, state->idev = NULL, state->im = NULL; - state->dev; - state->dev = state->dev->next) { + state->idev = NULL; + state->im = NULL; + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; read_lock_bh(&idev->lock); @@ -2370,7 +2716,6 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) spin_unlock_bh(&im->mca_lock); } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return psf; } @@ -2384,16 +2729,15 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s spin_unlock_bh(&state->im->mca_lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = state->dev->next; + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -2418,8 +2762,9 @@ static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2435,6 +2780,7 @@ static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im != NULL)) { @@ -2443,11 +2789,10 @@ static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) } if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) @@ -2456,27 +2801,24 @@ static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { - seq_printf(seq, + seq_printf(seq, "%3s %6s " "%32s %32s %6s %6s\n", "Idx", "Device", "Multicast Address", "Source Address", "INC", "EXC"); } else { seq_printf(seq, - "%3d %6.6s " - "%04x%04x%04x%04x%04x%04x%04x%04x " - "%04x%04x%04x%04x%04x%04x%04x%04x " - "%6lu %6lu\n", + "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, - NIP6(state->im->mca_addr), - NIP6(psf->sf_addr), + &state->im->mca_addr, + &psf->sf_addr, psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } -static struct seq_operations igmp6_mcf_seq_ops = { +static const struct seq_operations igmp6_mcf_seq_ops = { .start = igmp6_mcf_seq_start, .next = igmp6_mcf_seq_next, .stop = igmp6_mcf_seq_stop, @@ -2485,73 +2827,95 @@ static struct seq_operations igmp6_mcf_seq_ops = { static int igmp6_mcf_seq_open(struct inode *inode, struct file *file) { - struct seq_file *seq; - int rc = -ENOMEM; - struct igmp6_mcf_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); - - if (!s) - goto out; - - rc = seq_open(file, &igmp6_mcf_seq_ops); - if (rc) - goto out_kfree; - - seq = file->private_data; - seq->private = s; - memset(s, 0, sizeof(*s)); -out: - return rc; -out_kfree: - kfree(s); - goto out; + return seq_open_net(inode, file, &igmp6_mcf_seq_ops, + sizeof(struct igmp6_mcf_iter_state)); } -static struct file_operations igmp6_mcf_seq_fops = { +static const struct file_operations igmp6_mcf_seq_fops = { .owner = THIS_MODULE, .open = igmp6_mcf_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; + +static int __net_init igmp6_proc_init(struct net *net) +{ + int err; + + err = -ENOMEM; + if (!proc_create("igmp6", S_IRUGO, net->proc_net, &igmp6_mc_seq_fops)) + goto out; + if (!proc_create("mcfilter6", S_IRUGO, net->proc_net, + &igmp6_mcf_seq_fops)) + goto out_proc_net_igmp6; + + err = 0; +out: + return err; + +out_proc_net_igmp6: + remove_proc_entry("igmp6", net->proc_net); + goto out; +} + +static void __net_exit igmp6_proc_exit(struct net *net) +{ + remove_proc_entry("mcfilter6", net->proc_net); + remove_proc_entry("igmp6", net->proc_net); +} +#else +static inline int igmp6_proc_init(struct net *net) +{ + return 0; +} +static inline void igmp6_proc_exit(struct net *net) +{ +} #endif -int __init igmp6_init(struct net_proto_family *ops) +static int __net_init igmp6_net_init(struct net *net) { - struct ipv6_pinfo *np; - struct sock *sk; int err; - err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, &igmp6_socket); + err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, + SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - printk(KERN_ERR - "Failed to initialize the IGMP6 control socket (err %d).\n", + pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); - igmp6_socket = NULL; /* For safety. */ - return err; + goto out; } - sk = igmp6_socket->sk; - sk->sk_allocation = GFP_ATOMIC; - sk->sk_prot->unhash(sk); + inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; - np = inet6_sk(sk); - np->hop_limit = 1; + err = igmp6_proc_init(net); + if (err) + goto out_sock_create; +out: + return err; -#ifdef CONFIG_PROC_FS - proc_net_fops_create("igmp6", S_IRUGO, &igmp6_mc_seq_fops); - proc_net_fops_create("mcfilter6", S_IRUGO, &igmp6_mcf_seq_fops); -#endif +out_sock_create: + inet_ctl_sock_destroy(net->ipv6.igmp_sk); + goto out; +} - return 0; +static void __net_exit igmp6_net_exit(struct net *net) +{ + inet_ctl_sock_destroy(net->ipv6.igmp_sk); + igmp6_proc_exit(net); } -void igmp6_cleanup(void) +static struct pernet_operations igmp6_net_ops = { + .init = igmp6_net_init, + .exit = igmp6_net_exit, +}; + +int __init igmp6_init(void) { - sock_release(igmp6_socket); - igmp6_socket = NULL; /* for safety */ + return register_pernet_subsys(&igmp6_net_ops); +} -#ifdef CONFIG_PROC_FS - proc_net_remove("mcfilter6"); - proc_net_remove("igmp6"); -#endif +void igmp6_cleanup(void) +{ + unregister_pernet_subsys(&igmp6_net_ops); } diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c new file mode 100644 index 00000000000..db9b6cbc9db --- /dev/null +++ b/net/ipv6/mip6.c @@ -0,0 +1,528 @@ +/* + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ +/* + * Authors: + * Noriaki TAKAMIYA @USAGI + * Masahide NAKAMURA @USAGI + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/time.h> +#include <linux/ipv6.h> +#include <linux/icmpv6.h> +#include <net/sock.h> +#include <net/ipv6.h> +#include <net/ip6_checksum.h> +#include <net/rawv6.h> +#include <net/xfrm.h> +#include <net/mip6.h> + +static inline unsigned int calc_padlen(unsigned int len, unsigned int n) +{ + return (n - len + 16) & 0x7; +} + +static inline void *mip6_padn(__u8 *data, __u8 padlen) +{ + if (!data) + return NULL; + if (padlen == 1) { + data[0] = IPV6_TLV_PAD1; + } else if (padlen > 1) { + data[0] = IPV6_TLV_PADN; + data[1] = padlen - 2; + if (padlen > 2) + memset(data+2, 0, data[1]); + } + return data + padlen; +} + +static inline void mip6_param_prob(struct sk_buff *skb, u8 code, int pos) +{ + icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos); +} + +static int mip6_mh_len(int type) +{ + int len = 0; + + switch (type) { + case IP6_MH_TYPE_BRR: + len = 0; + break; + case IP6_MH_TYPE_HOTI: + case IP6_MH_TYPE_COTI: + case IP6_MH_TYPE_BU: + case IP6_MH_TYPE_BACK: + len = 1; + break; + case IP6_MH_TYPE_HOT: + case IP6_MH_TYPE_COT: + case IP6_MH_TYPE_BERROR: + len = 2; + break; + } + return len; +} + +static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb) +{ + struct ip6_mh _hdr; + const struct ip6_mh *mh; + + mh = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (!mh) + return -1; + + if (((mh->ip6mh_hdrlen + 1) << 3) > skb->len) + return -1; + + if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) { + LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n", + mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type)); + mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_hdrlen) + + skb_network_header_len(skb)); + return -1; + } + + if (mh->ip6mh_proto != IPPROTO_NONE) { + LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n", + mh->ip6mh_proto); + mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_proto) + + skb_network_header_len(skb)); + return -1; + } + + return 0; +} + +struct mip6_report_rate_limiter { + spinlock_t lock; + struct timeval stamp; + int iif; + struct in6_addr src; + struct in6_addr dst; +}; + +static struct mip6_report_rate_limiter mip6_report_rl = { + .lock = __SPIN_LOCK_UNLOCKED(mip6_report_rl.lock) +}; + +static int mip6_destopt_input(struct xfrm_state *x, struct sk_buff *skb) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6_destopt_hdr *destopt = (struct ipv6_destopt_hdr *)skb->data; + int err = destopt->nexthdr; + + spin_lock(&x->lock); + if (!ipv6_addr_equal(&iph->saddr, (struct in6_addr *)x->coaddr) && + !ipv6_addr_any((struct in6_addr *)x->coaddr)) + err = -ENOENT; + spin_unlock(&x->lock); + + return err; +} + +/* Destination Option Header is inserted. + * IP Header's src address is replaced with Home Address Option in + * Destination Option Header. + */ +static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + struct ipv6_destopt_hdr *dstopt; + struct ipv6_destopt_hao *hao; + u8 nexthdr; + int len; + + skb_push(skb, -skb_network_offset(skb)); + iph = ipv6_hdr(skb); + + nexthdr = *skb_mac_header(skb); + *skb_mac_header(skb) = IPPROTO_DSTOPTS; + + dstopt = (struct ipv6_destopt_hdr *)skb_transport_header(skb); + dstopt->nexthdr = nexthdr; + + hao = mip6_padn((char *)(dstopt + 1), + calc_padlen(sizeof(*dstopt), 6)); + + hao->type = IPV6_TLV_HAO; + BUILD_BUG_ON(sizeof(*hao) != 18); + hao->length = sizeof(*hao) - 2; + + len = ((char *)hao - (char *)dstopt) + sizeof(*hao); + + memcpy(&hao->addr, &iph->saddr, sizeof(hao->addr)); + spin_lock_bh(&x->lock); + memcpy(&iph->saddr, x->coaddr, sizeof(iph->saddr)); + spin_unlock_bh(&x->lock); + + WARN_ON(len != x->props.header_len); + dstopt->hdrlen = (x->props.header_len >> 3) - 1; + + return 0; +} + +static inline int mip6_report_rl_allow(struct timeval *stamp, + const struct in6_addr *dst, + const struct in6_addr *src, int iif) +{ + int allow = 0; + + spin_lock_bh(&mip6_report_rl.lock); + if (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_equal(&mip6_report_rl.src, src) || + !ipv6_addr_equal(&mip6_report_rl.dst, dst)) { + mip6_report_rl.stamp.tv_sec = stamp->tv_sec; + mip6_report_rl.stamp.tv_usec = stamp->tv_usec; + mip6_report_rl.iif = iif; + mip6_report_rl.src = *src; + mip6_report_rl.dst = *dst; + allow = 1; + } + spin_unlock_bh(&mip6_report_rl.lock); + return allow; +} + +static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, + const struct flowi *fl) +{ + struct net *net = xs_net(x); + struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb; + const struct flowi6 *fl6 = &fl->u.ip6; + struct ipv6_destopt_hao *hao = NULL; + struct xfrm_selector sel; + int offset; + struct timeval stamp; + int err = 0; + + if (unlikely(fl6->flowi6_proto == IPPROTO_MH && + fl6->fl6_mh_type <= IP6_MH_TYPE_MAX)) + goto out; + + if (likely(opt->dsthao)) { + offset = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); + if (likely(offset >= 0)) + hao = (struct ipv6_destopt_hao *) + (skb_network_header(skb) + offset); + } + + skb_get_timestamp(skb, &stamp); + + if (!mip6_report_rl_allow(&stamp, &ipv6_hdr(skb)->daddr, + hao ? &hao->addr : &ipv6_hdr(skb)->saddr, + opt->iif)) + goto out; + + memset(&sel, 0, sizeof(sel)); + memcpy(&sel.daddr, (xfrm_address_t *)&ipv6_hdr(skb)->daddr, + sizeof(sel.daddr)); + sel.prefixlen_d = 128; + memcpy(&sel.saddr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, + sizeof(sel.saddr)); + sel.prefixlen_s = 128; + sel.family = AF_INET6; + sel.proto = fl6->flowi6_proto; + sel.dport = xfrm_flowi_dport(fl, &fl6->uli); + if (sel.dport) + sel.dport_mask = htons(~0); + sel.sport = xfrm_flowi_sport(fl, &fl6->uli); + if (sel.sport) + sel.sport_mask = htons(~0); + sel.ifindex = fl6->flowi6_oif; + + err = km_report(net, IPPROTO_DSTOPTS, &sel, + (hao ? (xfrm_address_t *)&hao->addr : NULL)); + + out: + return err; +} + +static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, + u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + const unsigned char *nh = skb_network_header(skb); + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); + int found_rhdr = 0; + + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + found_rhdr = 1; + break; + case NEXTHDR_DEST: + /* + * HAO MUST NOT appear more than once. + * XXX: It is better to try to find by the end of + * XXX: packet if HAO exists. + */ + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { + LIMIT_NETDEBUG(KERN_WARNING "mip6: hao exists already, override\n"); + return offset; + } + + if (found_rhdr) + return offset; + + break; + default: + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr *)(nh + offset); + } + + return offset; +} + +static int mip6_destopt_init_state(struct xfrm_state *x) +{ + if (x->id.spi) { + pr_info("%s: spi is not 0: %u\n", __func__, x->id.spi); + return -EINVAL; + } + if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) { + pr_info("%s: state's mode is not %u: %u\n", + __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); + return -EINVAL; + } + + x->props.header_len = sizeof(struct ipv6_destopt_hdr) + + calc_padlen(sizeof(struct ipv6_destopt_hdr), 6) + + sizeof(struct ipv6_destopt_hao); + WARN_ON(x->props.header_len != 24); + + return 0; +} + +/* + * Do nothing about destroying since it has no specific operation for + * destination options header unlike IPsec protocols. + */ +static void mip6_destopt_destroy(struct xfrm_state *x) +{ +} + +static const struct xfrm_type mip6_destopt_type = +{ + .description = "MIP6DESTOPT", + .owner = THIS_MODULE, + .proto = IPPROTO_DSTOPTS, + .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR, + .init_state = mip6_destopt_init_state, + .destructor = mip6_destopt_destroy, + .input = mip6_destopt_input, + .output = mip6_destopt_output, + .reject = mip6_destopt_reject, + .hdr_offset = mip6_destopt_offset, +}; + +static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data; + int err = rt2->rt_hdr.nexthdr; + + spin_lock(&x->lock); + if (!ipv6_addr_equal(&iph->daddr, (struct in6_addr *)x->coaddr) && + !ipv6_addr_any((struct in6_addr *)x->coaddr)) + err = -ENOENT; + spin_unlock(&x->lock); + + return err; +} + +/* Routing Header type 2 is inserted. + * IP Header's dst address is replaced with Routing Header's Home Address. + */ +static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + struct rt2_hdr *rt2; + u8 nexthdr; + + skb_push(skb, -skb_network_offset(skb)); + iph = ipv6_hdr(skb); + + nexthdr = *skb_mac_header(skb); + *skb_mac_header(skb) = IPPROTO_ROUTING; + + rt2 = (struct rt2_hdr *)skb_transport_header(skb); + rt2->rt_hdr.nexthdr = nexthdr; + rt2->rt_hdr.hdrlen = (x->props.header_len >> 3) - 1; + rt2->rt_hdr.type = IPV6_SRCRT_TYPE_2; + rt2->rt_hdr.segments_left = 1; + memset(&rt2->reserved, 0, sizeof(rt2->reserved)); + + WARN_ON(rt2->rt_hdr.hdrlen != 2); + + memcpy(&rt2->addr, &iph->daddr, sizeof(rt2->addr)); + spin_lock_bh(&x->lock); + memcpy(&iph->daddr, x->coaddr, sizeof(iph->daddr)); + spin_unlock_bh(&x->lock); + + return 0; +} + +static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, + u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + const unsigned char *nh = skb_network_header(skb); + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); + int found_rhdr = 0; + + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + if (offset + 3 <= packet_len) { + struct ipv6_rt_hdr *rt; + rt = (struct ipv6_rt_hdr *)(nh + offset); + if (rt->type != 0) + return offset; + } + found_rhdr = 1; + break; + case NEXTHDR_DEST: + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + return offset; + + if (found_rhdr) + return offset; + + break; + default: + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr *)(nh + offset); + } + + return offset; +} + +static int mip6_rthdr_init_state(struct xfrm_state *x) +{ + if (x->id.spi) { + pr_info("%s: spi is not 0: %u\n", __func__, x->id.spi); + return -EINVAL; + } + if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) { + pr_info("%s: state's mode is not %u: %u\n", + __func__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); + return -EINVAL; + } + + x->props.header_len = sizeof(struct rt2_hdr); + + return 0; +} + +/* + * Do nothing about destroying since it has no specific operation for routing + * header type 2 unlike IPsec protocols. + */ +static void mip6_rthdr_destroy(struct xfrm_state *x) +{ +} + +static const struct xfrm_type mip6_rthdr_type = +{ + .description = "MIP6RT", + .owner = THIS_MODULE, + .proto = IPPROTO_ROUTING, + .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR, + .init_state = mip6_rthdr_init_state, + .destructor = mip6_rthdr_destroy, + .input = mip6_rthdr_input, + .output = mip6_rthdr_output, + .hdr_offset = mip6_rthdr_offset, +}; + +static int __init mip6_init(void) +{ + pr_info("Mobile IPv6\n"); + + if (xfrm_register_type(&mip6_destopt_type, AF_INET6) < 0) { + pr_info("%s: can't add xfrm type(destopt)\n", __func__); + goto mip6_destopt_xfrm_fail; + } + if (xfrm_register_type(&mip6_rthdr_type, AF_INET6) < 0) { + pr_info("%s: can't add xfrm type(rthdr)\n", __func__); + goto mip6_rthdr_xfrm_fail; + } + if (rawv6_mh_filter_register(mip6_mh_filter) < 0) { + pr_info("%s: can't add rawv6 mh filter\n", __func__); + goto mip6_rawv6_mh_fail; + } + + + return 0; + + mip6_rawv6_mh_fail: + xfrm_unregister_type(&mip6_rthdr_type, AF_INET6); + mip6_rthdr_xfrm_fail: + xfrm_unregister_type(&mip6_destopt_type, AF_INET6); + mip6_destopt_xfrm_fail: + return -EAGAIN; +} + +static void __exit mip6_fini(void) +{ + if (rawv6_mh_filter_unregister(mip6_mh_filter) < 0) + pr_info("%s: can't remove rawv6 mh filter\n", __func__); + if (xfrm_unregister_type(&mip6_rthdr_type, AF_INET6) < 0) + pr_info("%s: can't remove xfrm type(rthdr)\n", __func__); + if (xfrm_unregister_type(&mip6_destopt_type, AF_INET6) < 0) + pr_info("%s: can't remove xfrm type(destopt)\n", __func__); +} + +module_init(mip6_init); +module_exit(mip6_fini); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS); +MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 305d9ee6d7d..ca8d4ea48a5 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1,9 +1,9 @@ /* * Neighbour Discovery for IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> * * This program is free software; you can redistribute it and/or @@ -15,9 +15,11 @@ /* * Changes: * + * Alexey I. Froloff : RFC6106 (DNSSL) support + * Pierre Ynard : export userland ND options + * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt * of an RA. - * * Janos Farkas : kmalloc failure checks * Alexey Kuznetsov : state machine reworked * and moved to net/core. @@ -25,30 +27,9 @@ * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ -/* Set to 3 to get tracing... */ -#define ND_DEBUG 1 - -#define ND_PRINTK(fmt, args...) do { if (net_ratelimit()) { printk(fmt, ## args); } } while(0) -#define ND_NOPRINTK(x...) do { ; } while(0) -#define ND_PRINTK0 ND_PRINTK -#define ND_PRINTK1 ND_NOPRINTK -#define ND_PRINTK2 ND_NOPRINTK -#define ND_PRINTK3 ND_NOPRINTK -#if ND_DEBUG >= 1 -#undef ND_PRINTK1 -#define ND_PRINTK1 ND_PRINTK -#endif -#if ND_DEBUG >= 2 -#undef ND_PRINTK2 -#define ND_PRINTK2 ND_PRINTK -#endif -#if ND_DEBUG >= 3 -#undef ND_PRINTK3 -#define ND_PRINTK3 ND_PRINTK -#endif +#define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> -#include <linux/config.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -59,10 +40,12 @@ #include <linux/route.h> #include <linux/init.h> #include <linux/rcupdate.h> +#include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif +#include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> @@ -78,16 +61,29 @@ #include <net/addrconf.h> #include <net/icmp.h> +#include <net/netlink.h> +#include <linux/rtnetlink.h> + #include <net/flow.h> #include <net/ip6_checksum.h> +#include <net/inet_common.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> -static struct socket *ndisc_socket; +/* Set to 3 to get tracing... */ +#define ND_DEBUG 1 + +#define ND_PRINTK(val, level, fmt, ...) \ +do { \ + if (val <= ND_DEBUG) \ + net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ +} while (0) -static u32 ndisc_hash(const void *pkey, const struct net_device *dev); +static u32 ndisc_hash(const void *pkey, + const struct net_device *dev, + __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); @@ -95,38 +91,31 @@ static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); -static struct neigh_ops ndisc_generic_ops = { +static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; -static struct neigh_ops ndisc_hh_ops = { +static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; -static struct neigh_ops ndisc_direct_ops = { +static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, - .output = dev_queue_xmit, - .connected_output = dev_queue_xmit, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, + .output = neigh_direct_output, + .connected_output = neigh_direct_output, }; 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, @@ -135,18 +124,20 @@ struct neigh_table nd_tbl = { .proxy_redo = pndisc_redo, .id = "ndisc_cache", .parms = { - .tbl = &nd_tbl, - .base_reachable_time = 30 * HZ, - .retrans_time = 1 * HZ, - .gc_staletime = 60 * HZ, - .reachable_time = 30 * HZ, - .delay_probe_time = 5 * HZ, - .queue_len = 3, - .ucast_probes = 3, - .mcast_probes = 3, - .anycast_delay = 1 * HZ, - .proxy_delay = (8 * HZ) / 10, - .proxy_qlen = 64, + .tbl = &nd_tbl, + .reachable_time = ND_REACHABLE_TIME, + .data = { + [NEIGH_VAR_MCAST_PROBES] = 3, + [NEIGH_VAR_UCAST_PROBES] = 3, + [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, + [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, + [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_GC_STALETIME] = 60 * HZ, + [NEIGH_VAR_QUEUE_LEN_BYTES] = 64 * 1024, + [NEIGH_VAR_PROXY_QLEN] = 64, + [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, + [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, + }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, @@ -154,44 +145,12 @@ struct neigh_table nd_tbl = { .gc_thresh3 = 1024, }; -/* ND options */ -struct ndisc_options { - struct nd_opt_hdr *nd_opt_array[__ND_OPT_MAX]; -}; - -#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] -#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] -#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] -#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] -#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] -#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] - -#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) - -/* - * Return the padding between the option length and the start of the - * link addr. Currently only IP-over-InfiniBand needs this, although - * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may - * also need a pad of 2. - */ -static int ndisc_addr_option_pad(unsigned short type) -{ - switch (type) { - case ARPHRD_INFINIBAND: return 2; - default: return 0; - } -} - -static inline int ndisc_opt_addr_space(struct net_device *dev) -{ - return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type)); -} - -static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, - unsigned short addr_type) +static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) { - int space = NDISC_OPT_SPACE(data_len); - int pad = ndisc_addr_option_pad(addr_type); + int pad = ndisc_addr_option_pad(skb->dev->type); + int data_len = skb->dev->addr_len; + int space = ndisc_opt_addr_space(skb->dev); + u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; @@ -205,7 +164,6 @@ static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, opt += data_len; if ((space -= data_len) > 0) memset(opt, 0, space); - return opt + space; } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, @@ -218,11 +176,28 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while(cur < end && cur->nd_opt_type != type); - return (cur <= end && cur->nd_opt_type == type ? cur : NULL); + return cur <= end && cur->nd_opt_type == type ? cur : NULL; } -static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, - struct ndisc_options *ndopts) +static inline int ndisc_is_useropt(struct nd_opt_hdr *opt) +{ + return opt->nd_opt_type == ND_OPT_RDNSS || + opt->nd_opt_type == ND_OPT_DNSSL; +} + +static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur, + struct nd_opt_hdr *end) +{ + if (!cur || !end || cur >= end) + return NULL; + do { + cur = ((void *)cur) + (cur->nd_opt_len << 3); + } while(cur < end && !ndisc_is_useropt(cur)); + return cur <= end && ndisc_is_useropt(cur) ? cur : NULL; +} + +struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, + struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; @@ -242,28 +217,42 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, case ND_OPT_MTU: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { - ND_PRINTK2(KERN_WARNING - "%s(): duplicated ND6 option found: type=%d\n", - __FUNCTION__, - nd_opt->nd_opt_type); + ND_PRINTK(2, warn, + "%s: duplicated ND6 option found: type=%d\n", + __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } break; case ND_OPT_PREFIX_INFO: ndopts->nd_opts_pi_end = nd_opt; - if (ndopts->nd_opt_array[nd_opt->nd_opt_type] == 0) + if (!ndopts->nd_opt_array[nd_opt->nd_opt_type]) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; +#ifdef CONFIG_IPV6_ROUTE_INFO + case ND_OPT_ROUTE_INFO: + ndopts->nd_opts_ri_end = nd_opt; + if (!ndopts->nd_opts_ri) + ndopts->nd_opts_ri = nd_opt; + break; +#endif default: - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the protocol. - */ - ND_PRINTK2(KERN_NOTICE - "%s(): ignored unsupported option; type=%d, len=%d\n", - __FUNCTION__, - nd_opt->nd_opt_type, nd_opt->nd_opt_len); + if (ndisc_is_useropt(nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); + } } opt_len -= l; nd_opt = ((void *)nd_opt) + l; @@ -271,18 +260,7 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, return ndopts; } -static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, - struct net_device *dev) -{ - u8 *lladdr = (u8 *)(p + 1); - int lladdrlen = p->nd_opt_len << 3; - int prepad = ndisc_addr_option_pad(dev->type); - if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad)) - return NULL; - return (lladdr + prepad); -} - -int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir) +int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: @@ -290,15 +268,14 @@ int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int d case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; - case ARPHRD_IEEE802_TR: - ipv6_tr_mc_map(addr,buf); - return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; case ARPHRD_INFINIBAND: - ipv6_ib_mc_map(addr, buf); + ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; + case ARPHRD_IPGRE: + return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); @@ -308,16 +285,13 @@ int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int d return -EINVAL; } -static u32 ndisc_hash(const void *pkey, const struct net_device *dev) -{ - 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++; +EXPORT_SYMBOL(ndisc_mc_map); - return jhash_2words(addr_hash, dev->ifindex, nd_tbl.hash_rnd); +static u32 ndisc_hash(const void *pkey, + const struct net_device *dev, + __u32 *hash_rnd) +{ + return ndisc_hashfn(pkey, dev, hash_rnd); } static int ndisc_constructor(struct neighbour *neigh) @@ -326,25 +300,22 @@ static int ndisc_constructor(struct neighbour *neigh) struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; - int is_multicast = ipv6_addr_is_multicast(addr); + bool 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->hard_header == NULL) { + if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; - neigh->output = neigh->ops->queue_xmit; + neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; @@ -358,7 +329,7 @@ static int ndisc_constructor(struct neighbour *neigh) neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } - if (dev->hard_header_cache) + if (dev->header_ops->cache) neigh->ops = &ndisc_hh_ops; else neigh->ops = &ndisc_generic_ops; @@ -396,274 +367,273 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -/* - * Send a Neighbour Advertisement - */ +static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, + int len) +{ + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; + struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; + struct sk_buff *skb; + + skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); + if (!skb) { + ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", + __func__); + return NULL; + } + + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + + skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); + skb_reset_transport_header(skb); -static inline void ndisc_flow_init(struct flowi *fl, u8 type, - struct in6_addr *saddr, struct in6_addr *daddr) + /* Manually assign socket ownership as we avoid calling + * sock_alloc_send_pskb() to bypass wmem buffer limits + */ + skb_set_owner_w(skb, sk); + + return skb; +} + +static void ip6_nd_hdr(struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int hop_limit, int len) { - memset(fl, 0, sizeof(*fl)); - ipv6_addr_copy(&fl->fl6_src, saddr); - ipv6_addr_copy(&fl->fl6_dst, daddr); - fl->proto = IPPROTO_ICMPV6; - fl->fl_icmp_type = type; - fl->fl_icmp_code = 0; + struct ipv6hdr *hdr; + + skb_push(skb, sizeof(*hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); + + ip6_flow_hdr(hdr, 0, 0); + + hdr->payload_len = htons(len); + hdr->nexthdr = IPPROTO_ICMPV6; + hdr->hop_limit = hop_limit; + + hdr->saddr = *saddr; + hdr->daddr = *daddr; } -static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - struct in6_addr *daddr, struct in6_addr *solicited_addr, - int router, int solicited, int override, int inc_opt) +static void ndisc_send_skb(struct sk_buff *skb, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { - struct in6_addr tmpaddr; - struct inet6_ifaddr *ifp; + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(skb->dev); + struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; - struct flowi fl; - struct dst_entry* dst; - struct sock *sk = ndisc_socket->sk; - struct in6_addr *src_addr; - struct nd_msg *msg; - int len; - struct sk_buff *skb; int err; + struct icmp6hdr *icmp6h = icmp6_hdr(skb); + u8 type; + + type = icmp6h->icmp6_type; + + if (!dst) { + struct flowi6 fl6; - len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); + dst = icmp6_dst_alloc(skb->dev, &fl6); + if (IS_ERR(dst)) { + kfree_skb(skb); + return; + } + + skb_dst_set(skb, dst); + } + + icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, + IPPROTO_ICMPV6, + csum_partial(icmp6h, + skb->len, 0)); + + ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len); + + 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, + dst_output); + if (!err) { + ICMP6MSGOUT_INC_STATS(net, idev, type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + } + + rcu_read_unlock(); +} + +void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *solicited_addr, + bool router, bool solicited, bool override, bool inc_opt) +{ + struct sk_buff *skb; + struct in6_addr tmpaddr; + struct inet6_ifaddr *ifp; + const struct in6_addr *src_addr; + struct nd_msg *msg; + int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ - ifp = ipv6_get_ifaddr(solicited_addr, dev, 1); - if (ifp) { + ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); + if (ifp) { src_addr = solicited_addr; + if (ifp->flags & IFA_F_OPTIMISTIC) + override = false; + inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { - if (ipv6_dev_get_saddr(dev, daddr, &tmpaddr)) + if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, + inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, + &tmpaddr)) return; src_addr = &tmpaddr; } - ndisc_flow_init(&fl, NDISC_NEIGHBOUR_ADVERTISEMENT, src_addr, daddr); - - dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output); - if (!dst) - return; + if (!dev->addr_len) + inc_opt = 0; + if (inc_opt) + optlen += ndisc_opt_addr_space(dev); - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) return; - if (inc_opt) { - if (dev->addr_len) - len += ndisc_opt_addr_space(dev); - else - inc_opt = 0; - } - - skb = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), - 1, &err); - - if (skb == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 NA: %s() failed to allocate an skb.\n", - __FUNCTION__); - dst_release(dst); - return; - } + msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct nd_msg) { + .icmph = { + .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, + .icmp6_router = router, + .icmp6_solicited = solicited, + .icmp6_override = override, + }, + .target = *solicited_addr, + }; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); - ip6_nd_hdr(sk, skb, dev, src_addr, daddr, IPPROTO_ICMPV6, len); + if (inc_opt) + ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, + dev->dev_addr); - msg = (struct nd_msg *)skb_put(skb, len); - skb->h.raw = (unsigned char*)msg; - msg->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; - msg->icmph.icmp6_code = 0; - msg->icmph.icmp6_cksum = 0; + ndisc_send_skb(skb, daddr, src_addr); +} - msg->icmph.icmp6_unused = 0; - msg->icmph.icmp6_router = router; - msg->icmph.icmp6_solicited = solicited; - msg->icmph.icmp6_override = !!override; +static void ndisc_send_unsol_na(struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; - /* Set the target address. */ - ipv6_addr_copy(&msg->target, solicited_addr); + idev = in6_dev_get(dev); + if (!idev) + return; - if (inc_opt) - ndisc_fill_addr_option(msg->opt, ND_OPT_TARGET_LL_ADDR, dev->dev_addr, - dev->addr_len, dev->type); - - /* checksum */ - msg->icmph.icmp6_cksum = csum_ipv6_magic(src_addr, daddr, len, - IPPROTO_ICMPV6, - csum_partial((__u8 *) msg, - len, 0)); - - skb->dst = dst; - idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); - if (!err) { - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTNEIGHBORADVERTISEMENTS); - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, + /*router=*/ !!idev->cnf.forwarding, + /*solicited=*/ false, /*override=*/ true, + /*inc_opt=*/ true); } + read_unlock_bh(&idev->lock); - if (likely(idev != NULL)) - in6_dev_put(idev); -} + in6_dev_put(idev); +} void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - struct in6_addr *solicit, - struct in6_addr *daddr, struct in6_addr *saddr) + const struct in6_addr *solicit, + const struct in6_addr *daddr, const struct in6_addr *saddr) { - struct flowi fl; - struct dst_entry* dst; - struct inet6_dev *idev; - struct sock *sk = ndisc_socket->sk; - struct sk_buff *skb; - struct nd_msg *msg; + struct sk_buff *skb; struct in6_addr addr_buf; - int len; - int err; - int send_llinfo; + int inc_opt = dev->addr_len; + int optlen = 0; + struct nd_msg *msg; if (saddr == NULL) { - if (ipv6_get_lladdr(dev, &addr_buf)) + if (ipv6_get_lladdr(dev, &addr_buf, + (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))) return; saddr = &addr_buf; } - ndisc_flow_init(&fl, NDISC_NEIGHBOUR_SOLICITATION, saddr, daddr); - - dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output); - if (!dst) - return; + if (ipv6_addr_any(saddr)) + inc_opt = false; + if (inc_opt) + optlen += ndisc_opt_addr_space(dev); - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) return; - len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); - send_llinfo = dev->addr_len && !ipv6_addr_any(saddr); - if (send_llinfo) - len += ndisc_opt_addr_space(dev); - - skb = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), - 1, &err); - if (skb == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 NA: %s() failed to allocate an skb.\n", - __FUNCTION__); - dst_release(dst); - return; - } + msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct nd_msg) { + .icmph = { + .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, + }, + .target = *solicit, + }; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); - ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); - - msg = (struct nd_msg *)skb_put(skb, len); - skb->h.raw = (unsigned char*)msg; - msg->icmph.icmp6_type = NDISC_NEIGHBOUR_SOLICITATION; - msg->icmph.icmp6_code = 0; - msg->icmph.icmp6_cksum = 0; - msg->icmph.icmp6_unused = 0; - - /* Set the target address. */ - ipv6_addr_copy(&msg->target, solicit); - - if (send_llinfo) - ndisc_fill_addr_option(msg->opt, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, - dev->addr_len, dev->type); - - /* checksum */ - msg->icmph.icmp6_cksum = csum_ipv6_magic(&skb->nh.ipv6h->saddr, - daddr, len, - IPPROTO_ICMPV6, - csum_partial((__u8 *) msg, - len, 0)); - /* send it! */ - skb->dst = dst; - idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); - if (!err) { - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTNEIGHBORSOLICITS); - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); - } + if (inc_opt) + ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, + dev->dev_addr); - if (likely(idev != NULL)) - in6_dev_put(idev); + ndisc_send_skb(skb, daddr, saddr); } -void ndisc_send_rs(struct net_device *dev, struct in6_addr *saddr, - struct in6_addr *daddr) +void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, + const struct in6_addr *daddr) { - struct flowi fl; - struct dst_entry* dst; - struct inet6_dev *idev; - struct sock *sk = ndisc_socket->sk; - struct sk_buff *skb; - struct icmp6hdr *hdr; - __u8 * opt; - int len; - int err; - - ndisc_flow_init(&fl, NDISC_ROUTER_SOLICITATION, saddr, daddr); - - dst = ndisc_dst_alloc(dev, NULL, daddr, ip6_output); - if (!dst) - return; - - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) - return; - - len = sizeof(struct icmp6hdr); - if (dev->addr_len) - len += ndisc_opt_addr_space(dev); + struct sk_buff *skb; + struct rs_msg *msg; + int send_sllao = dev->addr_len; + int optlen = 0; - skb = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), - 1, &err); - if (skb == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RS: %s() failed to allocate an skb.\n", - __FUNCTION__); - dst_release(dst); - return; +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + /* + * According to section 2.2 of RFC 4429, we must not + * send router solicitations with a sllao from + * optimistic addresses, but we may send the solicitation + * if we don't include the sllao. So here we check + * if our address is optimistic, and if so, we + * suppress the inclusion of the sllao. + */ + if (send_sllao) { + struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, + dev, 1); + if (ifp) { + if (ifp->flags & IFA_F_OPTIMISTIC) { + send_sllao = 0; + } + in6_ifa_put(ifp); + } else { + send_sllao = 0; + } } +#endif + if (send_sllao) + optlen += ndisc_opt_addr_space(dev); - skb_reserve(skb, LL_RESERVED_SPACE(dev)); - ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); - - hdr = (struct icmp6hdr *)skb_put(skb, len); - skb->h.raw = (unsigned char*)hdr; - hdr->icmp6_type = NDISC_ROUTER_SOLICITATION; - hdr->icmp6_code = 0; - hdr->icmp6_cksum = 0; - hdr->icmp6_unused = 0; - - opt = (u8*) (hdr + 1); - - if (dev->addr_len) - ndisc_fill_addr_option(opt, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, - dev->addr_len, dev->type); + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; - /* checksum */ - hdr->icmp6_cksum = csum_ipv6_magic(&skb->nh.ipv6h->saddr, daddr, len, - IPPROTO_ICMPV6, - csum_partial((__u8 *) hdr, len, 0)); + msg = (struct rs_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct rs_msg) { + .icmph = { + .icmp6_type = NDISC_ROUTER_SOLICITATION, + }, + }; - /* send it! */ - skb->dst = dst; - idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); - if (!err) { - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTROUTERSOLICITS); - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); - } + if (send_sllao) + ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, + dev->dev_addr); - if (likely(idev != NULL)) - in6_dev_put(idev); + ndisc_send_skb(skb, daddr, saddr); } - + static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) { @@ -685,46 +655,63 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); - if (skb && ipv6_chk_addr(&skb->nh.ipv6h->saddr, dev, 1)) - saddr = &skb->nh.ipv6h->saddr; + if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1)) + saddr = &ipv6_hdr(skb)->saddr; - if ((probes -= neigh->parms->ucast_probes) < 0) { + if ((probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES)) < 0) { if (!(neigh->nud_state & NUD_VALID)) { - ND_PRINTK1(KERN_DEBUG - "%s(): trying to ucast probe in NUD_INVALID: " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - __FUNCTION__, - NIP6(*target)); + ND_PRINTK(1, dbg, + "%s: trying to ucast probe in NUD_INVALID: %pI6\n", + __func__, target); } ndisc_send_ns(dev, neigh, target, target, saddr); - } else if ((probes -= neigh->parms->app_probes) < 0) { -#ifdef CONFIG_ARPD + } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); -#endif } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, NULL, target, &mcaddr, saddr); } } +static int pndisc_is_router(const void *pkey, + struct net_device *dev) +{ + struct pneigh_entry *n; + int ret = -1; + + read_lock_bh(&nd_tbl.lock); + n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); + if (n) + ret = !!(n->flags & NTF_ROUTER); + read_unlock_bh(&nd_tbl.lock); + + return ret; +} + static void ndisc_recv_ns(struct sk_buff *skb) { - struct nd_msg *msg = (struct nd_msg *)skb->h.raw; - struct in6_addr *saddr = &skb->nh.ipv6h->saddr; - struct in6_addr *daddr = &skb->nh.ipv6h->daddr; + struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); + const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - msg->opt; + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); - int inc; + bool inc; + int is_router = -1; + + if (skb->len < sizeof(struct nd_msg)) { + ND_PRINTK(2, warn, "NS: packet too short\n"); + return; + } if (ipv6_addr_is_multicast(&msg->target)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: multicast target address"); + ND_PRINTK(2, warn, "NS: multicast target address\n"); return; } @@ -732,88 +719,84 @@ static void ndisc_recv_ns(struct sk_buff *skb) * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ - if (dad && - !(daddr->s6_addr32[0] == htonl(0xff020000) && - daddr->s6_addr32[1] == htonl(0x00000000) && - daddr->s6_addr32[2] == htonl(0x00000001) && - daddr->s6_addr [12] == 0xff )) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: bad DAD packet (wrong destination)\n"); + if (dad && !ipv6_addr_is_solict_mult(daddr)) { + ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return; } if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: invalid ND options\n"); + ND_PRINTK(2, warn, "NS: invalid ND options\n"); return; } if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "NS: invalid link-layer address length\n"); return; } /* RFC2461 7.1.1: - * If the IP source address is the unspecified address, - * there MUST NOT be source link-layer address option + * If the IP source address is the unspecified address, + * there MUST NOT be source link-layer address option * in the message. */ if (dad) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: bad DAD packet (link-layer address option)\n"); + ND_PRINTK(2, warn, + "NS: bad DAD packet (link-layer address option)\n"); return; } } inc = ipv6_addr_is_multicast(daddr); - if ((ifp = ipv6_get_ifaddr(&msg->target, dev, 1)) != NULL) { - if (ifp->flags & IFA_F_TENTATIVE) { - /* Address is tentative. If the source - is unspecified address, it is someone - does DAD, otherwise we ignore solicitations - until DAD timer expires. - */ - if (!dad) - goto out; - if (dev->type == ARPHRD_IEEE802_TR) { - unsigned char *sadr = skb->mac.raw; - if (((sadr[8] ^ dev->dev_addr[0]) & 0x7f) == 0 && - sadr[9] == dev->dev_addr[1] && - sadr[10] == dev->dev_addr[2] && - sadr[11] == dev->dev_addr[3] && - sadr[12] == dev->dev_addr[4] && - sadr[13] == dev->dev_addr[5]) { - /* looped-back to us */ + ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); + if (ifp) { + + if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { + if (dad) { + /* + * We are colliding with another node + * who is doing DAD + * so fail our DAD process + */ + addrconf_dad_failure(ifp); + return; + } else { + /* + * This is not a dad solicitation. + * If we are an optimistic node, + * we should respond. + * Otherwise, we should ignore it. + */ + if (!(ifp->flags & IFA_F_OPTIMISTIC)) goto out; - } } - addrconf_dad_failure(ifp); - return; } idev = ifp->idev; } else { + struct net *net = dev_net(dev); + idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ return; } - if (ipv6_chk_acast_addr(dev, &msg->target) || - (idev->cnf.forwarding && - pneigh_lookup(&nd_tbl, &msg->target, dev, 0))) { + if (ipv6_chk_acast_addr(net, dev, &msg->target) || + (idev->cnf.forwarding && + (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) && + (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && - inc != 0 && - idev->nd_parms->proxy_delay != 0) { + inc && + NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, - * sender should delay its response - * by a random time between 0 and + * sender should delay its response + * by a random time between 0 and * MAX_ANYCAST_DELAY_TIME seconds. * (RFC2461) -- yoshfuji */ @@ -826,12 +809,12 @@ static void ndisc_recv_ns(struct sk_buff *skb) goto out; } - if (dad) { - struct in6_addr maddr; + if (is_router < 0) + is_router = idev->cnf.forwarding; - ipv6_addr_all_nodes(&maddr); - ndisc_send_na(dev, NULL, &maddr, &msg->target, - idev->cnf.forwarding, 0, (ifp != NULL), 1); + if (dad) { + ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target, + !!is_router, false, (ifp != NULL), true); goto out; } @@ -840,20 +823,20 @@ static void ndisc_recv_ns(struct sk_buff *skb) else NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast); - /* + /* * update / create cache entry * for the source address */ neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) - neigh_update(neigh, lladdr, NUD_STALE, + neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE); - if (neigh || !dev->hard_header) { + if (neigh || !dev->header_ops) { ndisc_send_na(dev, neigh, saddr, &msg->target, - idev->cnf.forwarding, - 1, (ifp != NULL && inc), inc); + !!is_router, + true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); } @@ -863,67 +846,69 @@ out: in6_ifa_put(ifp); else in6_dev_put(idev); - - return; } static void ndisc_recv_na(struct sk_buff *skb) { - struct nd_msg *msg = (struct nd_msg *)skb->h.raw; - struct in6_addr *saddr = &skb->nh.ipv6h->saddr; - struct in6_addr *daddr = &skb->nh.ipv6h->daddr; + struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); + struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; - u32 ndoptlen = skb->tail - msg->opt; + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct neighbour *neigh; if (skb->len < sizeof(struct nd_msg)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: packet too short\n"); + ND_PRINTK(2, warn, "NA: packet too short\n"); return; } if (ipv6_addr_is_multicast(&msg->target)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: target address is multicast.\n"); + ND_PRINTK(2, warn, "NA: target address is multicast\n"); return; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: solicited NA is multicasted.\n"); + ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); return; } - + if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NS: invalid ND option\n"); + ND_PRINTK(2, warn, "NS: invalid ND option\n"); return; } if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NA: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "NA: invalid link-layer address length\n"); return; } } - if ((ifp = ipv6_get_ifaddr(&msg->target, dev, 1))) { - if (ifp->flags & IFA_F_TENTATIVE) { - addrconf_dad_failure(ifp); - return; + ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); + if (ifp) { + if (skb->pkt_type != PACKET_LOOPBACK + && (ifp->flags & IFA_F_TENTATIVE)) { + addrconf_dad_failure(ifp); + return; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) + + We should not print the error if NA has been + received from loopback - it is just our own + unsolicited advertisement. */ - ND_PRINTK1(KERN_WARNING - "ICMPv6 NA: someone advertises our address on %s!\n", - ifp->idev->dev->name); + if (skb->pkt_type != PACKET_LOOPBACK) + ND_PRINTK(1, warn, + "NA: someone advertises our address %pI6 on %s!\n", + &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } @@ -931,10 +916,23 @@ static void ndisc_recv_na(struct sk_buff *skb) if (neigh) { u8 old_flags = neigh->flags; + struct net *net = dev_net(dev); if (neigh->nud_state & NUD_FAILED) goto out; + /* + * Don't update the neighbor cache entry on a proxy NA from + * ourselves because either the proxied node is off link or it + * has already sent a NA to us. + */ + if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && + net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && + pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { + /* XXX: idev->cnf.proxy_ndp */ + goto out; + } + neigh_update(neigh, lladdr, msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| @@ -946,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb) /* * Change: router to host */ - struct rt6_info *rt; - rt = rt6_get_dflt_router(saddr, dev); - if (rt) - ip6_del_rt(rt, NULL, NULL, NULL); + rt6_clean_tohost(dev_net(dev), saddr); } out: @@ -959,21 +954,20 @@ out: static void ndisc_recv_rs(struct sk_buff *skb) { - struct rs_msg *rs_msg = (struct rs_msg *) skb->h.raw; + struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; - struct in6_addr *saddr = &skb->nh.ipv6h->saddr; + const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; 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"); + ND_PRINTK(1, err, "RS: can't find in6 device\n"); return; } @@ -990,8 +984,7 @@ static void ndisc_recv_rs(struct sk_buff *skb) /* Parse ND options */ if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) { - if (net_ratelimit()) - ND_PRINTK2("ICMP6 NS: invalid ND option, ignored\n"); + ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n"); goto out; } @@ -1011,57 +1004,113 @@ 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) +{ + struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra); + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct nduseroptmsg *ndmsg; + struct net *net = dev_net(ra->dev); + int err; + int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + + (opt->nd_opt_len << 3)); + size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); + + skb = nlmsg_new(msg_size, GFP_ATOMIC); + if (skb == NULL) { + err = -ENOBUFS; + goto errout; + } + + nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); + if (nlh == NULL) { + goto nla_put_failure; + } + + ndmsg = nlmsg_data(nlh); + ndmsg->nduseropt_family = AF_INET6; + ndmsg->nduseropt_ifindex = ra->dev->ifindex; + ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; + ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; + ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; + + memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); + + if (nla_put(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr), + &ipv6_hdr(ra)->saddr)) + goto nla_put_failure; + nlmsg_end(skb, nlh); + + rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); + return; + +nla_put_failure: + nlmsg_free(skb); + err = -EMSGSIZE; +errout: + rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } static void ndisc_router_discovery(struct sk_buff *skb) { - struct ra_msg *ra_msg = (struct ra_msg *) skb->h.raw; + struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; - struct rt6_info *rt; + struct rt6_info *rt = NULL; int lifetime; struct ndisc_options ndopts; int optlen; + unsigned int pref = 0; __u8 * opt = (__u8 *)(ra_msg + 1); - optlen = (skb->tail - skb->h.raw) - sizeof(struct ra_msg); + optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - + sizeof(struct ra_msg); - if (!(ipv6_addr_type(&skb->nh.ipv6h->saddr) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: source address is not link-local.\n"); + if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { + ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return; } if (optlen < 0) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: packet too short\n"); + ND_PRINTK(2, warn, "RA: packet too short\n"); return; } +#ifdef CONFIG_IPV6_NDISC_NODETYPE + if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { + ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); + return; + } +#endif + /* * 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", - skb->dev->name); - return; - } - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra) { - in6_dev_put(in6_dev); + ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", + skb->dev->name); return; } if (!ndisc_parse_options(opt, optlen, &ndopts)) { - in6_dev_put(in6_dev); - ND_PRINTK2(KERN_WARNING - "ICMP6 RA: invalid ND options\n"); + ND_PRINTK(2, warn, "RA: invalid ND options\n"); return; } + if (!ipv6_accept_ra(in6_dev)) + goto skip_linkparms; + +#ifdef CONFIG_IPV6_NDISC_NODETYPE + /* skip link-specific parameters from interior routers */ + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + goto skip_linkparms; +#endif + if (in6_dev->if_flags & IF_RS_SENT) { /* * flag that an RA was received after an RS was sent @@ -1081,53 +1130,74 @@ static void ndisc_router_discovery(struct sk_buff *skb) (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); + 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); - rt = rt6_get_dflt_router(&skb->nh.ipv6h->saddr, skb->dev); +#ifdef CONFIG_IPV6_ROUTER_PREF + pref = ra_msg->icmph.icmp6_router_pref; + /* 10b is handled as if it were 00b (medium) */ + if (pref == ICMPV6_ROUTER_PREF_INVALID || + !in6_dev->cnf.accept_ra_rtr_pref) + pref = ICMPV6_ROUTER_PREF_MEDIUM; +#endif - if (rt) - neigh = rt->rt6i_nexthop; + rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); + if (rt) { + neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + if (!neigh) { + ND_PRINTK(0, err, + "RA: %s got default router without neighbour\n", + __func__); + ip6_rt_put(rt); + return; + } + } if (rt && lifetime == 0) { - neigh_clone(neigh); - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } if (rt == NULL && lifetime) { - ND_PRINTK3(KERN_DEBUG - "ICMPv6 RA: adding default router.\n"); + ND_PRINTK(3, dbg, "RA: adding default router\n"); - rt = rt6_add_dflt_router(&skb->nh.ipv6h->saddr, skb->dev); + rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); if (rt == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RA: %s() failed to add default route.\n", - __FUNCTION__); - in6_dev_put(in6_dev); + ND_PRINTK(0, err, + "RA: %s failed to add default route\n", + __func__); return; } - neigh = rt->rt6i_nexthop; + neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); if (neigh == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 RA: %s() got default router without neighbour.\n", - __FUNCTION__); - dst_release(&rt->u.dst); - in6_dev_put(in6_dev); + ND_PRINTK(0, err, + "RA: %s got default router without neighbour\n", + __func__); + ip6_rt_put(rt); return; } neigh->flags |= NTF_ROUTER; + } else if (rt) { + rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); } if (rt) - rt->rt6i_expires = jiffies + (HZ * lifetime); - + rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = ra_msg->icmph.icmp6_hop_limit; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } +skip_defrtr: + /* * Update Reachable Time and Retrans Timer */ @@ -1139,7 +1209,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; - in6_dev->nd_parms->retrans_time = rtime; + NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); } @@ -1151,9 +1221,11 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rtime < HZ/10) rtime = HZ/10; - if (rtime != in6_dev->nd_parms->base_reachable_time) { - in6_dev->nd_parms->base_reachable_time = rtime; - in6_dev->nd_parms->gc_staletime = 3 * rtime; + if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { + NEIGH_VAR_SET(in6_dev->nd_parms, + BASE_REACHABLE_TIME, rtime); + NEIGH_VAR_SET(in6_dev->nd_parms, + GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); @@ -1161,12 +1233,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) } } +skip_linkparms: + /* * Process options. */ if (!neigh) - neigh = __neigh_lookup(&nd_tbl, &skb->nh.ipv6h->saddr, + neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr, skb->dev, 1); if (neigh) { u8 *lladdr = NULL; @@ -1174,8 +1248,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: invalid link-layer address length\n"); + ND_PRINTK(2, warn, + "RA: invalid link-layer address length\n"); goto out; } } @@ -1186,266 +1260,261 @@ static void ndisc_router_discovery(struct sk_buff *skb) NEIGH_UPDATE_F_ISROUTER); } - if (ndopts.nd_opts_pi) { + if (!ipv6_accept_ra(in6_dev)) + 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; + p; + p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { + struct route_info *ri = (struct route_info *)p; +#ifdef CONFIG_IPV6_NDISC_NODETYPE + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT && + ri->prefix_len == 0) + continue; +#endif + if (ri->prefix_len == 0 && + !in6_dev->cnf.accept_ra_defrtr) + continue; + if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) + continue; + rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3, + &ipv6_hdr(skb)->saddr); + } + } + +skip_routeinfo: +#endif + +#ifdef CONFIG_IPV6_NDISC_NODETYPE + /* skip link-specific ndopts from interior routers */ + if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) + goto out; +#endif + + if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; 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); } } if (ndopts.nd_opts_mtu) { + __be32 n; u32 mtu; - memcpy(&mtu, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); - mtu = ntohl(mtu); + memcpy(&n, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); + mtu = ntohl(n); if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: invalid mtu: %d\n", - mtu); + ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (in6_dev->cnf.mtu6 != mtu) { in6_dev->cnf.mtu6 = mtu; if (rt) - rt->u.dst.metrics[RTAX_MTU-1] = mtu; + dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } - + + if (ndopts.nd_useropts) { + struct nd_opt_hdr *p; + for (p = ndopts.nd_useropts; + p; + p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) { + ndisc_ra_useropt(skb, p); + } + } + if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 RA: invalid RA options"); + ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: - if (rt) - dst_release(&rt->u.dst); - else if (neigh) + ip6_rt_put(rt); + if (neigh) neigh_release(neigh); - in6_dev_put(in6_dev); } static void ndisc_redirect_rcv(struct sk_buff *skb) { - struct inet6_dev *in6_dev; - struct icmp6hdr *icmph; - struct in6_addr *dest; - struct in6_addr *target; /* new first hop to destination */ - struct neighbour *neigh; - int on_link = 0; + u8 *hdr; struct ndisc_options ndopts; - int optlen; - u8 *lladdr = NULL; - - if (!(ipv6_addr_type(&skb->nh.ipv6h->saddr) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: source address is not link-local.\n"); + struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); + u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + + offsetof(struct rd_msg, opt)); + +#ifdef CONFIG_IPV6_NDISC_NODETYPE + switch (skb->ndisc_nodetype) { + case NDISC_NODETYPE_HOST: + case NDISC_NODETYPE_NODEFAULT: + ND_PRINTK(2, warn, + "Redirect: from host or unauthorized router\n"); return; } +#endif - optlen = skb->tail - skb->h.raw; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); - - if (optlen < 0) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: packet too short\n"); + if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { + ND_PRINTK(2, warn, + "Redirect: source address is not link-local\n"); return; } - icmph = (struct icmp6hdr *) skb->h.raw; - target = (struct in6_addr *) (icmph + 1); - dest = target + 1; - - if (ipv6_addr_is_multicast(dest)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: destination address is multicast.\n"); + if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) return; - } - if (ipv6_addr_equal(dest, target)) { - on_link = 1; - } else if (!(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: target address is not link-local.\n"); + if (!ndopts.nd_opts_rh) { + ip6_redirect_no_header(skb, dev_net(skb->dev), + skb->dev->ifindex, 0); return; } - 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); + hdr = (u8 *)ndopts.nd_opts_rh; + hdr += 8; + if (!pskb_pull(skb, hdr - skb_transport_header(skb))) return; - } - /* RFC2461 8.1: - * The IP source address of the Redirect MUST be the same as the current - * first-hop router for the specified ICMP Destination Address. - */ - - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: invalid ND options\n"); - in6_dev_put(in6_dev); - return; - } - if (ndopts.nd_opts_tgt_lladdr) { - lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, - skb->dev); - if (!lladdr) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: invalid link-layer address length\n"); - in6_dev_put(in6_dev); - return; - } - } + icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); +} - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); - if (neigh) { - rt6_redirect(dest, &skb->nh.ipv6h->saddr, neigh, lladdr, - on_link); - neigh_release(neigh); - } - in6_dev_put(in6_dev); +static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, + struct sk_buff *orig_skb, + int rd_len) +{ + u8 *opt = skb_put(skb, rd_len); + + memset(opt, 0, 8); + *(opt++) = ND_OPT_REDIRECT_HDR; + *(opt++) = (rd_len >> 3); + opt += 6; + + memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); } -void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, - struct in6_addr *target) +void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { - struct sock *sk = ndisc_socket->sk; - int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.ndisc_sk; + int optlen = 0; + struct inet_peer *peer; struct sk_buff *buff; - struct icmp6hdr *icmph; + struct rd_msg *msg; struct in6_addr saddr_buf; - struct in6_addr *addrp; - struct net_device *dev; struct rt6_info *rt; struct dst_entry *dst; - struct inet6_dev *idev; - struct flowi fl; - u8 *opt; + struct flowi6 fl6; int rd_len; - int err; - int hlen; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; + bool ret; - dev = skb->dev; - - if (ipv6_get_lladdr(dev, &saddr_buf)) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: no link-local address on %s\n", - dev->name); - return; - } - - ndisc_flow_init(&fl, NDISC_REDIRECT, &saddr_buf, &skb->nh.ipv6h->saddr); - - dst = ip6_route_output(NULL, &fl); - if (dst == NULL) + if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { + ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", + dev->name); return; + } - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err) + if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && + ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { + ND_PRINTK(2, warn, + "Redirect: target address is not link-local unicast\n"); return; + } - rt = (struct rt6_info *) dst; + icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, + &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); - if (rt->rt6i_flags & RTF_GATEWAY) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: destination is not a neighbour.\n"); + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { dst_release(dst); return; } - if (!xrlim_allow(dst, 1*HZ)) { - dst_release(dst); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) return; + + rt = (struct rt6_info *) dst; + + if (rt->rt6i_flags & RTF_GATEWAY) { + ND_PRINTK(2, warn, + "Redirect: destination is not a neighbour\n"); + goto release; } + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + ret = inet_peer_xrlim_allow(peer, 1*HZ); + if (peer) + inet_putpeer(peer); + if (!ret) + goto release; if (dev->addr_len) { + struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); + if (!neigh) { + ND_PRINTK(2, warn, + "Redirect: no neigh for target address\n"); + goto release; + } + read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; - len += ndisc_opt_addr_space(dev); + optlen += ndisc_opt_addr_space(dev); } else read_unlock_bh(&neigh->lock); + + neigh_release(neigh); } rd_len = min_t(unsigned int, - IPV6_MIN_MTU-sizeof(struct ipv6hdr)-len, skb->len + 8); + IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, + skb->len + 8); rd_len &= ~0x7; - len += rd_len; - - buff = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), - 1, &err); - if (buff == NULL) { - ND_PRINTK0(KERN_ERR - "ICMPv6 Redirect: %s() failed to allocate an skb.\n", - __FUNCTION__); - dst_release(dst); - return; - } - - hlen = 0; - - skb_reserve(buff, LL_RESERVED_SPACE(dev)); - ip6_nd_hdr(sk, buff, dev, &saddr_buf, &skb->nh.ipv6h->saddr, - IPPROTO_ICMPV6, len); - - icmph = (struct icmp6hdr *)skb_put(buff, len); - buff->h.raw = (unsigned char*)icmph; - - memset(icmph, 0, sizeof(struct icmp6hdr)); - icmph->icmp6_type = NDISC_REDIRECT; - - /* - * copy target and destination addresses - */ - - addrp = (struct in6_addr *)(icmph + 1); - ipv6_addr_copy(addrp, target); - addrp++; - ipv6_addr_copy(addrp, &skb->nh.ipv6h->daddr); - - opt = (u8*) (addrp + 1); + optlen += rd_len; + + buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!buff) + goto release; + + msg = (struct rd_msg *)skb_put(buff, sizeof(*msg)); + *msg = (struct rd_msg) { + .icmph = { + .icmp6_type = NDISC_REDIRECT, + }, + .target = *target, + .dest = ipv6_hdr(skb)->daddr, + }; /* * include target_address option */ if (ha) - opt = ndisc_fill_addr_option(opt, ND_OPT_TARGET_LL_ADDR, ha, - dev->addr_len, dev->type); + ndisc_fill_addr_option(buff, ND_OPT_TARGET_LL_ADDR, ha); /* * build redirect option and copy skb over to the new packet. */ - memset(opt, 0, 8); - *(opt++) = ND_OPT_REDIRECT_HDR; - *(opt++) = (rd_len >> 3); - opt += 6; - - memcpy(opt, skb->nh.ipv6h, rd_len - 8); + if (rd_len) + ndisc_fill_redirect_hdr_option(buff, skb, rd_len); - icmph->icmp6_cksum = csum_ipv6_magic(&saddr_buf, &skb->nh.ipv6h->saddr, - len, IPPROTO_ICMPV6, - csum_partial((u8 *) icmph, len, 0)); - - buff->dst = dst; - idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, buff, NULL, dst->dev, dst_output); - if (!err) { - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTREDIRECTS); - ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); - } + skb_dst_set(buff, dst); + ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); + return; - if (likely(idev != NULL)) - in6_dev_put(idev); +release: + dst_release(dst); } static void pndisc_redo(struct sk_buff *skb) @@ -1454,28 +1523,43 @@ static void pndisc_redo(struct sk_buff *skb) kfree_skb(skb); } +static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) +{ + struct inet6_dev *idev = __in6_dev_get(skb->dev); + + if (!idev) + return true; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && + idev->cnf.suppress_frag_ndisc) { + net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); + return true; + } + return false; +} + int ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; - if (!pskb_may_pull(skb, skb->len)) + if (ndisc_suppress_frag_ndisc(skb)) + return 0; + + if (skb_linearize(skb)) return 0; - msg = (struct nd_msg *) skb->h.raw; + msg = (struct nd_msg *)skb_transport_header(skb); - __skb_push(skb, skb->data-skb->h.raw); + __skb_push(skb, skb->data - skb_transport_header(skb)); - if (skb->nh.ipv6h->hop_limit != 255) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NDISC: invalid hop-limit: %d\n", - skb->nh.ipv6h->hop_limit); + if (ipv6_hdr(skb)->hop_limit != 255) { + ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", + ipv6_hdr(skb)->hop_limit); return 0; } if (msg->icmph.icmp6_code != 0) { - ND_PRINTK2(KERN_WARNING - "ICMPv6 NDISC: invalid ICMPv6 code: %d\n", - msg->icmph.icmp6_code); + ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", + msg->icmph.icmp6_code); return 0; } @@ -1501,23 +1585,34 @@ int ndisc_rcv(struct sk_buff *skb) case NDISC_REDIRECT: ndisc_redirect_rcv(skb); break; - }; + } return 0; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + struct inet6_dev *idev; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); - fib6_run_gc(~0UL); + fib6_run_gc(0, net, false); + idev = in6_dev_get(dev); + if (!idev) + break; + if (idev->cnf.ndisc_notify) + ndisc_send_unsol_na(dev); + in6_dev_put(idev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); - fib6_run_gc(~0UL); + fib6_run_gc(0, net, false); + break; + case NETDEV_NOTIFY_PEERS: + ndisc_send_unsol_na(dev); break; default: break; @@ -1538,11 +1633,7 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strcpy(warncomm, current->comm); - printk(KERN_WARNING - "process `%s' is using deprecated sysctl (%s) " - "net.ipv6.neigh.%s.%s; " - "Use net.ipv6.neigh.%s.%s_ms " - "instead.\n", + pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); @@ -1550,37 +1641,34 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, } } -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos) +int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; int ret; - if (ctl->ctl_name == NET_NEIGH_RETRANS_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME) + if ((strcmp(ctl->procname, "retrans_time") == 0) || + (strcmp(ctl->procname, "base_reachable_time") == 0)) ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); - switch (ctl->ctl_name) { - case NET_NEIGH_RETRANS_TIME: - ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - break; - case NET_NEIGH_REACHABLE_TIME: - ret = proc_dointvec_jiffies(ctl, write, - filp, buffer, lenp, ppos); - break; - case NET_NEIGH_RETRANS_TIME_MS: - case NET_NEIGH_REACHABLE_TIME_MS: - ret = proc_dointvec_ms_jiffies(ctl, write, - filp, buffer, lenp, ppos); - break; - default: + if (strcmp(ctl->procname, "retrans_time") == 0) + ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); + + else if (strcmp(ctl->procname, "base_reachable_time") == 0) + ret = neigh_proc_dointvec_jiffies(ctl, write, + buffer, lenp, ppos); + + else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || + (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) + ret = neigh_proc_dointvec_ms_jiffies(ctl, write, + buffer, lenp, ppos); + else ret = -1; - } if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->ctl_name == NET_NEIGH_REACHABLE_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME_MS) - idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time); + if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) + idev->nd_parms->reachable_time = + neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); idev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); @@ -1588,89 +1676,80 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, struct file * f return ret; } -static int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl, int __user *name, - int nlen, void __user *oldval, - size_t __user *oldlenp, - void __user *newval, size_t newlen, - void **context) -{ - struct net_device *dev = ctl->extra1; - struct inet6_dev *idev; - int ret; - - if (ctl->ctl_name == NET_NEIGH_RETRANS_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME) - ndisc_warn_deprecated_sysctl(ctl, "procfs", dev ? dev->name : "default"); - - switch (ctl->ctl_name) { - case NET_NEIGH_REACHABLE_TIME: - ret = sysctl_jiffies(ctl, name, nlen, - oldval, oldlenp, newval, newlen, - context); - break; - case NET_NEIGH_RETRANS_TIME_MS: - case NET_NEIGH_REACHABLE_TIME_MS: - ret = sysctl_ms_jiffies(ctl, name, nlen, - oldval, oldlenp, newval, newlen, - context); - break; - default: - ret = 0; - } - - if (newval && newlen && ret > 0 && - dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->ctl_name == NET_NEIGH_REACHABLE_TIME || - ctl->ctl_name == NET_NEIGH_REACHABLE_TIME_MS) - idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time); - idev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, idev); - in6_dev_put(idev); - } - - return ret; -} #endif -int __init ndisc_init(struct net_proto_family *ops) +static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; - int err; + int err; - err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, &ndisc_socket); + err = inet_ctl_sock_create(&sk, PF_INET6, + SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { - ND_PRINTK0(KERN_ERR - "ICMPv6 NDISC: Failed to initialize the control socket (err %d).\n", - err); - ndisc_socket = NULL; /* For safety. */ + ND_PRINTK(0, err, + "NDISC: Failed to initialize the control socket (err %d)\n", + err); return err; } - sk = ndisc_socket->sk; + net->ipv6.ndisc_sk = sk; + np = inet6_sk(sk); - sk->sk_allocation = GFP_ATOMIC; np->hop_limit = 255; /* Do not loopback ndisc messages */ np->mc_loop = 0; - sk->sk_prot->unhash(sk); - /* - * Initialize the neighbour table - */ - + return 0; +} + +static void __net_exit ndisc_net_exit(struct net *net) +{ + inet_ctl_sock_destroy(net->ipv6.ndisc_sk); +} + +static struct pernet_operations ndisc_net_ops = { + .init = ndisc_net_init, + .exit = ndisc_net_exit, +}; + +int __init ndisc_init(void) +{ + int err; + + err = register_pernet_subsys(&ndisc_net_ops); + if (err) + return err; + /* + * Initialize the neighbour table + */ neigh_table_init(&nd_tbl); #ifdef CONFIG_SYSCTL - neigh_sysctl_register(NULL, &nd_tbl.parms, NET_IPV6, NET_IPV6_NEIGH, - "ipv6", - &ndisc_ifinfo_sysctl_change, - &ndisc_ifinfo_sysctl_strategy); + err = neigh_sysctl_register(NULL, &nd_tbl.parms, + &ndisc_ifinfo_sysctl_change); + if (err) + goto out_unregister_pernet; +out: #endif + return err; - register_netdevice_notifier(&ndisc_netdev_notifier); - return 0; +#ifdef CONFIG_SYSCTL +out_unregister_pernet: + unregister_pernet_subsys(&ndisc_net_ops); + goto out; +#endif +} + +int __init ndisc_late_init(void) +{ + return register_netdevice_notifier(&ndisc_netdev_notifier); +} + +void ndisc_late_cleanup(void) +{ + unregister_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_cleanup(void) @@ -1679,6 +1758,5 @@ void ndisc_cleanup(void) neigh_sysctl_unregister(&nd_tbl.parms); #endif neigh_table_clear(&nd_tbl); - sock_release(ndisc_socket); - ndisc_socket = NULL; /* For safety. */ + unregister_pernet_subsys(&ndisc_net_ops); } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index f8626ebf90f..d38e6a8d8b9 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -1,42 +1,69 @@ -#include <linux/config.h> -#include <linux/init.h> - -#ifdef CONFIG_NETFILTER - +/* + * IPv6 specific functions of netfilter core + * + * Rusty Russell (C) 2000 -- This code is GPL. + * Patrick McHardy (C) 2006-2012 + */ #include <linux/kernel.h> +#include <linux/init.h> #include <linux/ipv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> +#include <linux/export.h> +#include <net/addrconf.h> #include <net/dst.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/xfrm.h> +#include <net/ip6_checksum.h> +#include <net/netfilter/nf_queue.h> int ip6_route_me_harder(struct sk_buff *skb) { - struct ipv6hdr *iph = skb->nh.ipv6h; + struct net *net = dev_net(skb_dst(skb)->dev); + const struct ipv6hdr *iph = ipv6_hdr(skb); + unsigned int hh_len; struct dst_entry *dst; - struct flowi fl = { - .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, - .nl_u = - { .ip6_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, } }, - .proto = iph->nexthdr, + struct flowi6 fl6 = { + .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_mark = skb->mark, + .daddr = iph->daddr, + .saddr = iph->saddr, }; + int err; - dst = ip6_route_output(skb->sk, &fl); - - if (dst->error) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); + dst = ip6_route_output(net, skb->sk, &fl6); + err = dst->error; + if (err) { + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); - return -EINVAL; + return err; } /* Drop old route. */ - dst_release(skb->dst); + skb_dst_drop(skb); + + skb_dst_set(skb, dst); + +#ifdef CONFIG_XFRM + if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { + skb_dst_set(skb, NULL); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + if (IS_ERR(dst)) + return PTR_ERR(dst); + skb_dst_set(skb, dst); + } +#endif + + /* Change in oif may mean change in hh_len. */ + hh_len = skb_dst(skb)->dev->hard_header_len; + if (skb_headroom(skb) < hh_len && + pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), + 0, GFP_ATOMIC)) + return -ENOMEM; - skb->dst = dst; return 0; } EXPORT_SYMBOL(ip6_route_me_harder); @@ -49,56 +76,144 @@ EXPORT_SYMBOL(ip6_route_me_harder); struct ip6_rt_info { struct in6_addr daddr; struct in6_addr saddr; + u_int32_t mark; }; -static void save(const struct sk_buff *skb, struct nf_info *info) +static void nf_ip6_saveroute(const struct sk_buff *skb, + struct nf_queue_entry *entry) { - struct ip6_rt_info *rt_info = nf_info_reroute(info); + struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); - if (info->hook == NF_IP6_LOCAL_OUT) { - struct ipv6hdr *iph = skb->nh.ipv6h; + if (entry->hook == NF_INET_LOCAL_OUT) { + const struct ipv6hdr *iph = ipv6_hdr(skb); rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; + rt_info->mark = skb->mark; } } -static int reroute(struct sk_buff **pskb, const struct nf_info *info) +static int nf_ip6_reroute(struct sk_buff *skb, + const struct nf_queue_entry *entry) { - struct ip6_rt_info *rt_info = nf_info_reroute(info); + struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); - if (info->hook == NF_IP6_LOCAL_OUT) { - struct ipv6hdr *iph = (*pskb)->nh.ipv6h; + if (entry->hook == NF_INET_LOCAL_OUT) { + const struct ipv6hdr *iph = ipv6_hdr(skb); if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || - !ipv6_addr_equal(&iph->saddr, &rt_info->saddr)) - return ip6_route_me_harder(*pskb); + !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || + skb->mark != rt_info->mark) + return ip6_route_me_harder(skb); } return 0; } -static struct nf_queue_rerouter ip6_reroute = { - .rer_size = sizeof(struct ip6_rt_info), - .save = &save, - .reroute = &reroute, -}; - -int __init ipv6_netfilter_init(void) +static int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl, bool strict) { - return nf_register_queue_rerouter(PF_INET6, &ip6_reroute); + static const struct ipv6_pinfo fake_pinfo; + static const struct inet_sock fake_sk = { + /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */ + .sk.sk_bound_dev_if = 1, + .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, + }; + const void *sk = strict ? &fake_sk : NULL; + 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; } -void ipv6_netfilter_fini(void) +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol) { - nf_unregister_queue_rerouter(PF_INET6); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + __sum16 csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN) + break; + if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - dataoff, protocol, + csum_sub(skb->csum, + skb_checksum(skb, 0, + dataoff, 0)))) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + /* fall through */ + case CHECKSUM_NONE: + skb->csum = ~csum_unfold( + csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - dataoff, + protocol, + csum_sub(0, + skb_checksum(skb, 0, + dataoff, 0)))); + csum = __skb_checksum_complete(skb); + } + return csum; } +EXPORT_SYMBOL(nf_ip6_checksum); + +static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, unsigned int len, + u_int8_t protocol) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + __wsum hsum; + __sum16 csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (len == skb->len - dataoff) + return nf_ip6_checksum(skb, hook, dataoff, protocol); + /* fall through */ + case CHECKSUM_NONE: + hsum = skb_checksum(skb, 0, dataoff, 0); + skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, + &ip6h->daddr, + skb->len - dataoff, + protocol, + csum_sub(0, hsum))); + skb->ip_summed = CHECKSUM_NONE; + return __skb_checksum_complete_head(skb, dataoff + len); + } + return csum; +}; + +static const struct nf_ipv6_ops ipv6ops = { + .chk_addr = ipv6_chk_addr, +}; + +static const struct nf_afinfo nf_ip6_afinfo = { + .family = AF_INET6, + .checksum = nf_ip6_checksum, + .checksum_partial = nf_ip6_checksum_partial, + .route = nf_ip6_route, + .saveroute = nf_ip6_saveroute, + .reroute = nf_ip6_reroute, + .route_key_size = sizeof(struct ip6_rt_info), +}; -#else /* CONFIG_NETFILTER */ int __init ipv6_netfilter_init(void) { - return 0; + RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops); + return nf_register_afinfo(&nf_ip6_afinfo); } +/* This can be called from inet6_init() on errors, so it cannot + * be marked __exit. -DaveM + */ void ipv6_netfilter_fini(void) { + RCU_INIT_POINTER(nf_ipv6_ops, NULL); + nf_unregister_afinfo(&nf_ip6_afinfo); } -#endif /* CONFIG_NETFILTER */ diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index bb7ccfe33f2..4bff1f297e3 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -2,35 +2,64 @@ # IP netfilter configuration # -menu "IPv6: Netfilter Configuration (EXPERIMENTAL)" - depends on INET && IPV6 && NETFILTER && EXPERIMENTAL - -#tristate 'Connection tracking (required for masq/NAT)' CONFIG_IP6_NF_CONNTRACK -#if [ "$CONFIG_IP6_NF_CONNTRACK" != "n" ]; then -# dep_tristate ' FTP protocol support' CONFIG_IP6_NF_FTP $CONFIG_IP6_NF_CONNTRACK -#fi -config IP6_NF_QUEUE - tristate "IP6 Userspace queueing via NETLINK (OBSOLETE)" +menu "IPv6: Netfilter Configuration" + depends on INET && IPV6 && NETFILTER + +config NF_DEFRAG_IPV6 + tristate + default n + +config NF_CONNTRACK_IPV6 + tristate "IPv6 connection tracking support" + depends on INET && IPV6 && NF_CONNTRACK + default m if NETFILTER_ADVANCED=n + select NF_DEFRAG_IPV6 ---help--- + Connection tracking keeps a record of what packets have passed + through your machine, in order to figure out how they are related + into connections. - This option adds a queue handler to the kernel for IPv6 - packets which enables users to receive the filtered packets - with QUEUE target using libipq. + This is IPv6 support on Layer 3 independent connection tracking. + Layer 3 independent connection tracking is experimental scheme + which generalize ip_conntrack to support other layer 3 protocols. - THis option enables the old IPv6-only "ip6_queue" implementation - which has been obsoleted by the new "nfnetlink_queue" code (see - CONFIG_NETFILTER_NETLINK_QUEUE). + To compile it as a module, choose M here. If unsure, say N. - (C) Fernando Anton 2001 - IPv64 Project - Work based in IPv64 draft by Arturo Azcorra. - Universidad Carlos III de Madrid - Universidad Politecnica de Alcala de Henares - email: <fanton@it.uc3m.es>. +config NF_TABLES_IPV6 + depends on NF_TABLES + tristate "IPv6 nf_tables support" + help + This option enables the IPv6 support for nf_tables. - To compile it as a module, choose M here. If unsure, say N. +config NFT_CHAIN_ROUTE_IPV6 + depends on NF_TABLES_IPV6 + tristate "IPv6 nf_tables route chain support" + help + This option enables the "route" chain for IPv6 in nf_tables. This + chain type is used to force packet re-routing after mangling header + fields such as the source, destination, flowlabel, hop-limit and + the packet mark. + +config NFT_CHAIN_NAT_IPV6 + depends on NF_TABLES_IPV6 + depends on NF_NAT_IPV6 && NFT_NAT + tristate "IPv6 nf_tables nat chain support" + help + This option enables the "nat" chain for IPv6 in nf_tables. This + chain type is used to perform Network Address Translation (NAT) + packet transformations such as the source, destination address and + source and destination ports. + +config NFT_REJECT_IPV6 + depends on NF_TABLES_IPV6 + default NFT_REJECT + tristate config IP6_NF_IPTABLES - tristate "IP6 tables support (required for filtering/masq/NAT)" + tristate "IP6 tables support (required for filtering)" + depends on INET && IPV6 + select NETFILTER_XTABLES + default m if NETFILTER_ADVANCED=n help ip6tables is a general, extensible packet identification framework. Currently only the packet filtering and packet mangling subsystem @@ -39,150 +68,103 @@ config IP6_NF_IPTABLES To compile it as a module, choose M here. If unsure, say N. +if IP6_NF_IPTABLES + # The simple matches. -config IP6_NF_MATCH_LIMIT - tristate "limit match support" - depends on IP6_NF_IPTABLES +config IP6_NF_MATCH_AH + tristate '"ah" match support' + depends on NETFILTER_ADVANCED help - limit matching allows you to control the rate at which a rule can be - matched: mainly useful in combination with the LOG target ("LOG - target support", below) and to avoid some Denial of Service attacks. + This module allows one to match AH packets. To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_MAC - tristate "MAC address match support" - depends on IP6_NF_IPTABLES +config IP6_NF_MATCH_EUI64 + tristate '"eui64" address check' + depends on NETFILTER_ADVANCED help - mac matching allows you to match packets based on the source - Ethernet address of the packet. + This module performs checking on the IPv6 source address + Compares the last 64 bits with the EUI64 (delivered + from the MAC address) address To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_RT - tristate "Routing header match support" - depends on IP6_NF_IPTABLES +config IP6_NF_MATCH_FRAG + tristate '"frag" Fragmentation header match support' + depends on NETFILTER_ADVANCED help - rt matching allows you to match packets based on the routing + frag matching allows you to match packets based on the fragmentation header of the packet. To compile it as a module, choose M here. If unsure, say N. config IP6_NF_MATCH_OPTS - tristate "Hop-by-hop and Dst opts header match support" - depends on IP6_NF_IPTABLES + tristate '"hbh" hop-by-hop and "dst" opts header match support' + depends on NETFILTER_ADVANCED help This allows one to match packets based on the hop-by-hop and destination options headers of a packet. To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_FRAG - tristate "Fragmentation header match support" - depends on IP6_NF_IPTABLES - help - frag matching allows you to match packets based on the fragmentation - header of the packet. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_MATCH_HL - tristate "HL match support" - depends on IP6_NF_IPTABLES - help - HL matching allows you to match packets based on the hop - limit of the packet. - - To compile it as a module, choose M here. If unsure, say N. - -config IP6_NF_MATCH_MULTIPORT - tristate "Multiple port match support" - depends on IP6_NF_IPTABLES - help - Multiport matching allows you to match TCP or UDP packets based on - a series of source or destination ports: normally a rule can only - match a single range of ports. - - To compile it as a module, choose M here. If unsure, say N. - -config IP6_NF_MATCH_OWNER - tristate "Owner match support" - depends on IP6_NF_IPTABLES - help - Packet owner matching allows you to match locally-generated packets - based on who created them: the user, group, process or session. - - To compile it as a module, choose M here. If unsure, say N. - -# dep_tristate ' MAC address match support' CONFIG_IP6_NF_MATCH_MAC $CONFIG_IP6_NF_IPTABLES -config IP6_NF_MATCH_MARK - tristate "netfilter MARK match support" - depends on IP6_NF_IPTABLES - help - Netfilter mark matching allows you to match packets based on the - `nfmark' value in the packet. This can be set by the MARK target - (see below). - - To compile it as a module, choose M here. If unsure, say N. + tristate '"hl" hoplimit match support' + depends on NETFILTER_ADVANCED + select NETFILTER_XT_MATCH_HL + ---help--- + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_MATCH_HL. config IP6_NF_MATCH_IPV6HEADER - tristate "IPv6 Extension Headers Match" - depends on IP6_NF_IPTABLES + tristate '"ipv6header" IPv6 Extension Headers Match' + default m if NETFILTER_ADVANCED=n help This module allows one to match packets based upon the ipv6 extension headers. To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_AHESP - tristate "AH/ESP match support" - depends on IP6_NF_IPTABLES +config IP6_NF_MATCH_MH + tristate '"mh" match support' + depends on NETFILTER_ADVANCED help - This module allows one to match AH and ESP packets. + This module allows one to match MH packets. To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_LENGTH - tristate "Packet Length match support" - depends on IP6_NF_IPTABLES - help - This option allows you to match the length of a packet against a - specific value or range of values. - - To compile it as a module, choose M here. If unsure, say N. - -config IP6_NF_MATCH_EUI64 - tristate "EUI64 address check" - depends on IP6_NF_IPTABLES - help - This module performs checking on the IPv6 source address - Compares the last 64 bits with the EUI64 (delivered - from the MAC address) address +config IP6_NF_MATCH_RPFILTER + tristate '"rpfilter" reverse path filter match support' + depends on NETFILTER_ADVANCED && (IP6_NF_MANGLE || IP6_NF_RAW) + ---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_PHYSDEV - tristate "Physdev match support" - depends on IP6_NF_IPTABLES && BRIDGE_NETFILTER +config IP6_NF_MATCH_RT + tristate '"rt" Routing header match support' + depends on NETFILTER_ADVANCED help - Physdev packet matching matches against the physical bridge ports - the IP packet arrived on or will leave by. + rt matching allows you to match packets based on the routing + header of the packet. To compile it as a module, choose M here. If unsure, say N. -# dep_tristate ' Multiple port match support' CONFIG_IP6_NF_MATCH_MULTIPORT $CONFIG_IP6_NF_IPTABLES -# dep_tristate ' TOS match support' CONFIG_IP6_NF_MATCH_TOS $CONFIG_IP6_NF_IPTABLES -# if [ "$CONFIG_IP6_NF_CONNTRACK" != "n" ]; then -# dep_tristate ' Connection state match support' CONFIG_IP6_NF_MATCH_STATE $CONFIG_IP6_NF_CONNTRACK $CONFIG_IP6_NF_IPTABLES -# fi -# if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then -# dep_tristate ' Unclean match support (EXPERIMENTAL)' CONFIG_IP6_NF_MATCH_UNCLEAN $CONFIG_IP6_NF_IPTABLES -# dep_tristate ' Owner match support (EXPERIMENTAL)' CONFIG_IP6_NF_MATCH_OWNER $CONFIG_IP6_NF_IPTABLES -# fi # The targets +config IP6_NF_TARGET_HL + tristate '"HL" hoplimit target support' + depends on NETFILTER_ADVANCED && IP6_NF_MANGLE + select NETFILTER_XT_TARGET_HL + ---help--- + This is a backwards-compatible option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_TARGET_HL. + config IP6_NF_FILTER tristate "Packet filtering" - depends on IP6_NF_IPTABLES + default m if NETFILTER_ADVANCED=n help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -190,18 +172,10 @@ config IP6_NF_FILTER To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_LOG - tristate "LOG target support" - depends on IP6_NF_FILTER - help - This option adds a `LOG' target, which allows you to create rules in - any iptables table which records the packet header to the syslog. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_TARGET_REJECT tristate "REJECT target support" depends on IP6_NF_FILTER + default m if NETFILTER_ADVANCED=n help The REJECT target allows a filtering rule to specify that an ICMPv6 error should be issued in response to an incoming packet, rather @@ -209,26 +183,22 @@ config IP6_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_NFQUEUE - tristate "NFQUEUE Target Support" - depends on IP_NF_IPTABLES +config IP6_NF_TARGET_SYNPROXY + tristate "SYNPROXY target support" + depends on NF_CONNTRACK && NETFILTER_ADVANCED + select NETFILTER_SYNPROXY + select SYN_COOKIES help - This Target replaced the old obsolete QUEUE target. + The SYNPROXY target allows you to intercept TCP connections and + establish them using syncookies before they are passed on to the + server. This allows to avoid conntrack and server resource usage + during SYN-flood attacks. - As opposed to QUEUE, it supports 65535 different queues, - not just one. - - To compile it as a module, choose M here. If unsure, say N. + To compile it as a module, choose M here. If unsure, say N. -# if [ "$CONFIG_IP6_NF_FILTER" != "n" ]; then -# dep_tristate ' REJECT target support' CONFIG_IP6_NF_TARGET_REJECT $CONFIG_IP6_NF_FILTER -# if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then -# dep_tristate ' MIRROR target support (EXPERIMENTAL)' CONFIG_IP6_NF_TARGET_MIRROR $CONFIG_IP6_NF_FILTER -# fi -# fi config IP6_NF_MANGLE tristate "Packet mangling" - depends on IP6_NF_IPTABLES + default m if NETFILTER_ADVANCED=n help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -236,47 +206,63 @@ config IP6_NF_MANGLE To compile it as a module, choose M here. If unsure, say N. -# dep_tristate ' TOS target support' CONFIG_IP6_NF_TARGET_TOS $CONFIG_IP_NF_MANGLE -config IP6_NF_TARGET_MARK - tristate "MARK target support" - depends on IP6_NF_MANGLE +config IP6_NF_RAW + tristate 'raw table support (required for TRACE)' + 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 + and OUTPUT chains. + + If you want to compile it as a module, say M here and read + <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. + +# security table for MAC policy +config IP6_NF_SECURITY + tristate "Security table" + depends on SECURITY + depends on NETFILTER_ADVANCED + help + This option adds a `security' table to iptables, for use + with Mandatory Access Control (MAC) policy. + + If unsure, say N. + +config NF_NAT_IPV6 + tristate "IPv6 NAT" + depends on NF_CONNTRACK_IPV6 + depends on NETFILTER_ADVANCED + select NF_NAT help - This option adds a `MARK' target, which allows you to create rules - in the `mangle' table which alter the netfilter mark (nfmark) field - associated with the packet packet prior to routing. This can change - the routing method (see `Use netfilter MARK value as routing - key') and can also be used by other subsystems to change their - behavior. + The IPv6 NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. It is controlled by + the `nat' table in ip6tables, see the man page for ip6tables(8). To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_HL - tristate 'HL (hoplimit) target support' - depends on IP6_NF_MANGLE +if NF_NAT_IPV6 + +config IP6_NF_TARGET_MASQUERADE + tristate "MASQUERADE target support" help - This option adds a `HL' target, which enables the user to decrement - the hoplimit value of the IPv6 header or set it to a given (lower) - value. - - While it is safe to decrement the hoplimit value, this option also - enables functionality to increment and set the hoplimit value of the - IPv6 header to arbitrary values. This is EXTREMELY DANGEROUS since - you can easily create immortal packets that loop forever on the - network. + Masquerading is a special case of NAT: all outgoing connections are + changed to seem to come from a particular interface's address, and + if the interface goes down, those connections are lost. This is + only useful for dialup accounts with dynamic IP address (ie. your IP + address will be different on next dialup). To compile it as a module, choose M here. If unsure, say N. -#dep_tristate ' LOG target support' CONFIG_IP6_NF_TARGET_LOG $CONFIG_IP6_NF_IPTABLES -config IP6_NF_RAW - tristate 'raw table support (required for TRACE)' - depends on IP6_NF_IPTABLES +config IP6_NF_TARGET_NPT + tristate "NPT (Network Prefix translation) target support" help - This option adds a `raw' table to ip6tables. This table is the very - first in the netfilter framework and hooks in at the PREROUTING - and OUTPUT chains. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. + This option adds the `SNPT' and `DNPT' target, which perform + stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296. + + To compile it as a module, choose M here. If unsure, say N. + +endif # NF_NAT_IPV6 + +endif # IP6_NF_IPTABLES endmenu diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 2b2c370e8b1..70d3dd66f2c 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -4,26 +4,43 @@ # Link order matters here. obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o -obj-$(CONFIG_IP6_NF_MATCH_LIMIT) += ip6t_limit.o -obj-$(CONFIG_IP6_NF_MATCH_MARK) += ip6t_mark.o -obj-$(CONFIG_IP6_NF_MATCH_LENGTH) += ip6t_length.o -obj-$(CONFIG_IP6_NF_MATCH_MAC) += ip6t_mac.o -obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o -obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o ip6t_dst.o -obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o -obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o -obj-$(CONFIG_IP6_NF_MATCH_AHESP) += ip6t_esp.o ip6t_ah.o -obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o -obj-$(CONFIG_IP6_NF_MATCH_MULTIPORT) += ip6t_multiport.o -obj-$(CONFIG_IP6_NF_MATCH_OWNER) += ip6t_owner.o -obj-$(CONFIG_IP6_NF_MATCH_PHYSDEV) += ip6t_physdev.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o -obj-$(CONFIG_IP6_NF_TARGET_MARK) += ip6t_MARK.o -obj-$(CONFIG_IP6_NF_TARGET_HL) += ip6t_HL.o -obj-$(CONFIG_IP6_NF_TARGET_NFQUEUE) += ip6t_NFQUEUE.o -obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o -obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o -obj-$(CONFIG_IP6_NF_MATCH_HL) += ip6t_hl.o +obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o +obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o + +# objects for l3 independent conntrack +nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o + +# l3 independent conntrack +obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o + +nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o +obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o + +# defrag +nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o +obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o + +# nf_tables +obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o +obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o +obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o +obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o + +# matches +obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o +obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o +obj-$(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-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o + +# targets +obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o +obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o +obj-$(CONFIG_IP6_NF_TARGET_SYNPROXY) += ip6t_SYNPROXY.o diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c deleted file mode 100644 index 5027bbe6415..00000000000 --- a/net/ipv6/netfilter/ip6_queue.c +++ /dev/null @@ -1,730 +0,0 @@ -/* - * This is a module which is used for queueing IPv6 packets and - * communicating with userspace via netlink. - * - * (C) 2001 Fernando Anton, this code is GPL. - * IPv64 Project - Work based in IPv64 draft by Arturo Azcorra. - * Universidad Carlos III de Madrid - Leganes (Madrid) - Spain - * Universidad Politecnica de Alcala de Henares - Alcala de H. (Madrid) - Spain - * email: fanton@it.uc3m.es - * - * 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. - * - * 2001-11-06: First try. Working with ip_queue.c for IPv4 and trying - * to adapt it to IPv6 - * HEAVILY based in ipqueue.c by James Morris. It's just - * a little modified version of it, so he's nearly the - * real coder of this. - * Few changes needed, mainly the hard_routing code and - * the netlink socket protocol (we're NETLINK_IP6_FW). - * 2002-06-25: Code cleanup. [JM: ported cleanup over from ip_queue.c] - * 2005-02-04: Added /proc counter for dropped packets; fixed so - * packets aren't delivered to user space if they're going - * to be dropped. - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <linux/ipv6.h> -#include <linux/notifier.h> -#include <linux/netdevice.h> -#include <linux/netfilter.h> -#include <linux/netlink.h> -#include <linux/spinlock.h> -#include <linux/sysctl.h> -#include <linux/proc_fs.h> -#include <net/sock.h> -#include <net/ipv6.h> -#include <net/ip6_route.h> -#include <linux/netfilter_ipv4/ip_queue.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -#define IPQ_QMAX_DEFAULT 1024 -#define IPQ_PROC_FS_NAME "ip6_queue" -#define NET_IPQ_QMAX 2088 -#define NET_IPQ_QMAX_NAME "ip6_queue_maxlen" - -struct ipq_queue_entry { - struct list_head list; - struct nf_info *info; - struct sk_buff *skb; -}; - -typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long); - -static unsigned char copy_mode = IPQ_COPY_NONE; -static unsigned int queue_maxlen = IPQ_QMAX_DEFAULT; -static DEFINE_RWLOCK(queue_lock); -static int peer_pid; -static unsigned int copy_range; -static unsigned int queue_total; -static unsigned int queue_dropped = 0; -static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl; -static LIST_HEAD(queue_list); -static DECLARE_MUTEX(ipqnl_sem); - -static void -ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict) -{ - local_bh_disable(); - nf_reinject(entry->skb, entry->info, verdict); - local_bh_enable(); - kfree(entry); -} - -static inline void -__ipq_enqueue_entry(struct ipq_queue_entry *entry) -{ - list_add(&entry->list, &queue_list); - queue_total++; -} - -/* - * Find and return a queued entry matched by cmpfn, or return the last - * entry if cmpfn is NULL. - */ -static inline struct ipq_queue_entry * -__ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data) -{ - struct list_head *p; - - list_for_each_prev(p, &queue_list) { - struct ipq_queue_entry *entry = (struct ipq_queue_entry *)p; - - if (!cmpfn || cmpfn(entry, data)) - return entry; - } - return NULL; -} - -static inline void -__ipq_dequeue_entry(struct ipq_queue_entry *entry) -{ - list_del(&entry->list); - queue_total--; -} - -static inline struct ipq_queue_entry * -__ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data) -{ - struct ipq_queue_entry *entry; - - entry = __ipq_find_entry(cmpfn, data); - if (entry == NULL) - return NULL; - - __ipq_dequeue_entry(entry); - return entry; -} - - -static inline void -__ipq_flush(int verdict) -{ - struct ipq_queue_entry *entry; - - while ((entry = __ipq_find_dequeue_entry(NULL, 0))) - ipq_issue_verdict(entry, verdict); -} - -static inline int -__ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status = 0; - - switch(mode) { - case IPQ_COPY_NONE: - case IPQ_COPY_META: - copy_mode = mode; - copy_range = 0; - break; - - case IPQ_COPY_PACKET: - copy_mode = mode; - copy_range = range; - if (copy_range > 0xFFFF) - copy_range = 0xFFFF; - break; - - default: - status = -EINVAL; - - } - return status; -} - -static inline void -__ipq_reset(void) -{ - peer_pid = 0; - net_disable_timestamp(); - __ipq_set_mode(IPQ_COPY_NONE, 0); - __ipq_flush(NF_DROP); -} - -static struct ipq_queue_entry * -ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data) -{ - struct ipq_queue_entry *entry; - - write_lock_bh(&queue_lock); - entry = __ipq_find_dequeue_entry(cmpfn, data); - write_unlock_bh(&queue_lock); - return entry; -} - -static void -ipq_flush(int verdict) -{ - write_lock_bh(&queue_lock); - __ipq_flush(verdict); - write_unlock_bh(&queue_lock); -} - -static struct sk_buff * -ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) -{ - unsigned char *old_tail; - size_t size = 0; - size_t data_len = 0; - struct sk_buff *skb; - struct ipq_packet_msg *pmsg; - struct nlmsghdr *nlh; - - read_lock_bh(&queue_lock); - - switch (copy_mode) { - case IPQ_COPY_META: - case IPQ_COPY_NONE: - size = NLMSG_SPACE(sizeof(*pmsg)); - data_len = 0; - break; - - case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entry->skb, - entry->info->outdev == NULL))) { - read_unlock_bh(&queue_lock); - return NULL; - } - if (copy_range == 0 || copy_range > entry->skb->len) - data_len = entry->skb->len; - else - data_len = copy_range; - - size = NLMSG_SPACE(sizeof(*pmsg) + data_len); - break; - - default: - *errp = -EINVAL; - read_unlock_bh(&queue_lock); - return NULL; - } - - read_unlock_bh(&queue_lock); - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - goto nlmsg_failure; - - old_tail= skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh)); - pmsg = NLMSG_DATA(nlh); - memset(pmsg, 0, sizeof(*pmsg)); - - pmsg->packet_id = (unsigned long )entry; - pmsg->data_len = data_len; - pmsg->timestamp_sec = entry->skb->tstamp.off_sec; - pmsg->timestamp_usec = entry->skb->tstamp.off_usec; - pmsg->mark = entry->skb->nfmark; - pmsg->hook = entry->info->hook; - pmsg->hw_protocol = entry->skb->protocol; - - if (entry->info->indev) - strcpy(pmsg->indev_name, entry->info->indev->name); - else - pmsg->indev_name[0] = '\0'; - - if (entry->info->outdev) - strcpy(pmsg->outdev_name, entry->info->outdev->name); - else - pmsg->outdev_name[0] = '\0'; - - if (entry->info->indev && entry->skb->dev) { - pmsg->hw_type = entry->skb->dev->type; - if (entry->skb->dev->hard_header_parse) - pmsg->hw_addrlen = - entry->skb->dev->hard_header_parse(entry->skb, - pmsg->hw_addr); - } - - if (data_len) - if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len)) - BUG(); - - nlh->nlmsg_len = skb->tail - old_tail; - return skb; - -nlmsg_failure: - if (skb) - kfree_skb(skb); - *errp = -EINVAL; - printk(KERN_ERR "ip6_queue: error creating packet message\n"); - return NULL; -} - -static int -ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info, - unsigned int queuenum, void *data) -{ - int status = -EINVAL; - struct sk_buff *nskb; - struct ipq_queue_entry *entry; - - if (copy_mode == IPQ_COPY_NONE) - return -EAGAIN; - - entry = kmalloc(sizeof(*entry), GFP_ATOMIC); - if (entry == NULL) { - printk(KERN_ERR "ip6_queue: OOM in ipq_enqueue_packet()\n"); - return -ENOMEM; - } - - entry->info = info; - entry->skb = skb; - - nskb = ipq_build_packet_message(entry, &status); - if (nskb == NULL) - goto err_out_free; - - write_lock_bh(&queue_lock); - - if (!peer_pid) - goto err_out_free_nskb; - - if (queue_total >= queue_maxlen) { - queue_dropped++; - status = -ENOSPC; - if (net_ratelimit()) - printk (KERN_WARNING "ip6_queue: fill at %d entries, " - "dropping packet(s). Dropped: %d\n", queue_total, - queue_dropped); - goto err_out_free_nskb; - } - - /* netlink_unicast will either free the nskb or attach it to a socket */ - status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT); - if (status < 0) { - queue_user_dropped++; - goto err_out_unlock; - } - - __ipq_enqueue_entry(entry); - - write_unlock_bh(&queue_lock); - return status; - -err_out_free_nskb: - kfree_skb(nskb); - -err_out_unlock: - write_unlock_bh(&queue_lock); - -err_out_free: - kfree(entry); - return status; -} - -static int -ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct ipq_queue_entry *e) -{ - int diff; - struct ipv6hdr *user_iph = (struct ipv6hdr *)v->payload; - - if (v->data_len < sizeof(*user_iph)) - return 0; - diff = v->data_len - e->skb->len; - if (diff < 0) - skb_trim(e->skb, v->data_len); - else if (diff > 0) { - if (v->data_len > 0xFFFF) - return -EINVAL; - if (diff > skb_tailroom(e->skb)) { - struct sk_buff *newskb; - - newskb = skb_copy_expand(e->skb, - skb_headroom(e->skb), - diff, - GFP_ATOMIC); - if (newskb == NULL) { - printk(KERN_WARNING "ip6_queue: OOM " - "in mangle, dropping packet\n"); - return -ENOMEM; - } - if (e->skb->sk) - skb_set_owner_w(newskb, e->skb->sk); - kfree_skb(e->skb); - e->skb = newskb; - } - skb_put(e->skb, diff); - } - if (!skb_make_writable(&e->skb, v->data_len)) - return -ENOMEM; - memcpy(e->skb->data, v->payload, v->data_len); - e->skb->ip_summed = CHECKSUM_NONE; - - return 0; -} - -static inline int -id_cmp(struct ipq_queue_entry *e, unsigned long id) -{ - return (id == (unsigned long )e); -} - -static int -ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len) -{ - struct ipq_queue_entry *entry; - - if (vmsg->value > NF_MAX_VERDICT) - return -EINVAL; - - entry = ipq_find_dequeue_entry(id_cmp, vmsg->id); - if (entry == NULL) - return -ENOENT; - else { - int verdict = vmsg->value; - - if (vmsg->data_len && vmsg->data_len == len) - if (ipq_mangle_ipv6(vmsg, entry) < 0) - verdict = NF_DROP; - - ipq_issue_verdict(entry, verdict); - return 0; - } -} - -static int -ipq_set_mode(unsigned char mode, unsigned int range) -{ - int status; - - write_lock_bh(&queue_lock); - status = __ipq_set_mode(mode, range); - write_unlock_bh(&queue_lock); - return status; -} - -static int -ipq_receive_peer(struct ipq_peer_msg *pmsg, - unsigned char type, unsigned int len) -{ - int status = 0; - - if (len < sizeof(*pmsg)) - return -EINVAL; - - switch (type) { - case IPQM_MODE: - status = ipq_set_mode(pmsg->msg.mode.value, - pmsg->msg.mode.range); - break; - - case IPQM_VERDICT: - if (pmsg->msg.verdict.value > NF_MAX_VERDICT) - status = -EINVAL; - else - status = ipq_set_verdict(&pmsg->msg.verdict, - len - sizeof(*pmsg)); - break; - default: - status = -EINVAL; - } - return status; -} - -static int -dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex) -{ - if (entry->info->indev) - if (entry->info->indev->ifindex == ifindex) - return 1; - - if (entry->info->outdev) - if (entry->info->outdev->ifindex == ifindex) - return 1; - - return 0; -} - -static void -ipq_dev_drop(int ifindex) -{ - struct ipq_queue_entry *entry; - - while ((entry = ipq_find_dequeue_entry(dev_cmp, ifindex)) != NULL) - ipq_issue_verdict(entry, NF_DROP); -} - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0) - -static inline void -ipq_rcv_skb(struct sk_buff *skb) -{ - int status, type, pid, flags, nlmsglen, skblen; - struct nlmsghdr *nlh; - - skblen = skb->len; - if (skblen < sizeof(*nlh)) - return; - - nlh = (struct nlmsghdr *)skb->data; - nlmsglen = nlh->nlmsg_len; - if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen) - return; - - pid = nlh->nlmsg_pid; - flags = nlh->nlmsg_flags; - - if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI) - RCV_SKB_FAIL(-EINVAL); - - if (flags & MSG_TRUNC) - RCV_SKB_FAIL(-ECOMM); - - type = nlh->nlmsg_type; - if (type < NLMSG_NOOP || type >= IPQM_MAX) - RCV_SKB_FAIL(-EINVAL); - - if (type <= IPQM_BASE) - return; - - if (security_netlink_recv(skb)) - RCV_SKB_FAIL(-EPERM); - - write_lock_bh(&queue_lock); - - if (peer_pid) { - if (peer_pid != pid) { - write_unlock_bh(&queue_lock); - RCV_SKB_FAIL(-EBUSY); - } - } else { - net_enable_timestamp(); - peer_pid = pid; - } - - write_unlock_bh(&queue_lock); - - status = ipq_receive_peer(NLMSG_DATA(nlh), type, - skblen - NLMSG_LENGTH(0)); - if (status < 0) - RCV_SKB_FAIL(status); - - if (flags & NLM_F_ACK) - netlink_ack(skb, nlh, 0); - return; -} - -static void -ipq_rcv_sk(struct sock *sk, int len) -{ - struct sk_buff *skb; - unsigned int qlen; - - down(&ipqnl_sem); - - for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) { - skb = skb_dequeue(&sk->sk_receive_queue); - ipq_rcv_skb(skb); - kfree_skb(skb); - } - - up(&ipqnl_sem); -} - -static int -ipq_rcv_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - - /* Drop any packets associated with the downed device */ - if (event == NETDEV_DOWN) - ipq_dev_drop(dev->ifindex); - return NOTIFY_DONE; -} - -static struct notifier_block ipq_dev_notifier = { - .notifier_call = ipq_rcv_dev_event, -}; - -static int -ipq_rcv_nl_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct netlink_notify *n = ptr; - - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_IP6_FW && n->pid) { - write_lock_bh(&queue_lock); - if (n->pid == peer_pid) - __ipq_reset(); - write_unlock_bh(&queue_lock); - } - return NOTIFY_DONE; -} - -static struct notifier_block ipq_nl_notifier = { - .notifier_call = ipq_rcv_nl_event, -}; - -static struct ctl_table_header *ipq_sysctl_header; - -static ctl_table ipq_table[] = { - { - .ctl_name = NET_IPQ_QMAX, - .procname = NET_IPQ_QMAX_NAME, - .data = &queue_maxlen, - .maxlen = sizeof(queue_maxlen), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .ctl_name = 0 } -}; - -static ctl_table ipq_dir_table[] = { - { - .ctl_name = NET_IPV6, - .procname = "ipv6", - .mode = 0555, - .child = ipq_table - }, - { .ctl_name = 0 } -}; - -static ctl_table ipq_root_table[] = { - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, - .child = ipq_dir_table - }, - { .ctl_name = 0 } -}; - -static int -ipq_get_info(char *buffer, char **start, off_t offset, int length) -{ - int len; - - read_lock_bh(&queue_lock); - - len = sprintf(buffer, - "Peer PID : %d\n" - "Copy mode : %hu\n" - "Copy range : %u\n" - "Queue length : %u\n" - "Queue max. length : %u\n" - "Queue dropped : %u\n" - "Netfilter dropped : %u\n", - peer_pid, - copy_mode, - copy_range, - queue_total, - queue_maxlen, - queue_dropped, - queue_user_dropped); - - read_unlock_bh(&queue_lock); - - *start = buffer + offset; - len -= offset; - if (len > length) - len = length; - else if (len < 0) - len = 0; - return len; -} - -static struct nf_queue_handler nfqh = { - .name = "ip6_queue", - .outfn = &ipq_enqueue_packet, -}; - -static int -init_or_cleanup(int init) -{ - int status = -ENOMEM; - struct proc_dir_entry *proc; - - if (!init) - goto cleanup; - - netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(NETLINK_IP6_FW, 0, ipq_rcv_sk, - THIS_MODULE); - if (ipqnl == NULL) { - printk(KERN_ERR "ip6_queue: failed to create netlink socket\n"); - goto cleanup_netlink_notifier; - } - - proc = proc_net_create(IPQ_PROC_FS_NAME, 0, ipq_get_info); - if (proc) - proc->owner = THIS_MODULE; - else { - printk(KERN_ERR "ip6_queue: failed to create proc entry\n"); - goto cleanup_ipqnl; - } - - register_netdevice_notifier(&ipq_dev_notifier); - ipq_sysctl_header = register_sysctl_table(ipq_root_table, 0); - - status = nf_register_queue_handler(PF_INET6, &nfqh); - if (status < 0) { - printk(KERN_ERR "ip6_queue: failed to register queue handler\n"); - goto cleanup_sysctl; - } - return status; - -cleanup: - nf_unregister_queue_handlers(&nfqh); - synchronize_net(); - ipq_flush(NF_DROP); - -cleanup_sysctl: - unregister_sysctl_table(ipq_sysctl_header); - unregister_netdevice_notifier(&ipq_dev_notifier); - proc_net_remove(IPQ_PROC_FS_NAME); - -cleanup_ipqnl: - sock_release(ipqnl->sk_socket); - down(&ipqnl_sem); - up(&ipqnl_sem); - -cleanup_netlink_notifier: - netlink_unregister_notifier(&ipq_nl_notifier); - return status; -} - -static int __init init(void) -{ - - return init_or_cleanup(1); -} - -static void __exit fini(void) -{ - init_or_cleanup(0); -} - -MODULE_DESCRIPTION("IPv6 packet queue handler"); -MODULE_LICENSE("GPL"); - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7d492226c16..e080fbbbc0e 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -3,75 +3,60 @@ * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> + * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> * * 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. - * - * 19 Jan 2002 Harald Welte <laforge@gnumonks.org> - * - increase module usage count as soon as we have rules inside - * a table - * 06 Jun 2002 Andras Kis-Szabo <kisza@sch.bme.hu> - * - new extension header parser code */ -#include <linux/config.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/capability.h> +#include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> -#include <linux/tcp.h> -#include <linux/udp.h> +#include <linux/poison.h> #include <linux/icmpv6.h> #include <net/ipv6.h> +#include <net/compat.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include <linux/proc_fs.h> +#include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_log.h> +#include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); -#define IPV6_HDR_LEN (sizeof(struct ipv6hdr)) -#define IPV6_OPTHDR_LEN (sizeof(struct ipv6_opt_hdr)) - /*#define DEBUG_IP_FIREWALL*/ /*#define DEBUG_ALLOW_ALL*/ /* Useful for remote debugging */ /*#define DEBUG_IP_FIREWALL_USER*/ #ifdef DEBUG_IP_FIREWALL -#define dprintf(format, args...) printk(format , ## args) +#define dprintf(format, args...) pr_info(format , ## args) #else #define dprintf(format, args...) #endif #ifdef DEBUG_IP_FIREWALL_USER -#define duprintf(format, args...) printk(format , ## args) +#define duprintf(format, args...) pr_info(format , ## args) #else #define duprintf(format, args...) #endif #ifdef CONFIG_NETFILTER_DEBUG -#define IP_NF_ASSERT(x) \ -do { \ - if (!(x)) \ - printk("IP_NF_ASSERT: %s:%s:%u\n", \ - __FUNCTION__, __FILE__, __LINE__); \ -} while(0) +#define IP_NF_ASSERT(x) WARN_ON(!(x)) #else #define IP_NF_ASSERT(x) #endif -#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) - -static DECLARE_MUTEX(ip6t_mutex); - -/* Must have mutex */ -#define ASSERT_READ_LOCK(x) IP_NF_ASSERT(down_trylock(&ip6t_mutex) != 0) -#define ASSERT_WRITE_LOCK(x) IP_NF_ASSERT(down_trylock(&ip6t_mutex) != 0) -#include <linux/netfilter_ipv4/listhelp.h> #if 0 /* All the better to debug you with... */ @@ -79,6 +64,12 @@ static DECLARE_MUTEX(ip6t_mutex); #define inline #endif +void *ip6t_alloc_initial_table(const struct xt_table *info) +{ + return xt_alloc_initial_table(ip6t, IP6T); +} +EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); + /* We keep a set of rules for each CPU, so we can avoid write-locking them in the softirq when updating the counters and therefore @@ -86,92 +77,27 @@ static DECLARE_MUTEX(ip6t_mutex); context stops packets coming through and allows user context to read the counters or update the rules. - To be cache friendly on SMP, we arrange them like so: - [ n-entries ] - ... cache-align padding ... - [ n-entries ] - Hence the start of any table is given by get_table() below. */ -/* The table itself */ -struct ip6t_table_info -{ - /* Size per table */ - unsigned int size; - /* Number of entries: FIXME. --RR */ - unsigned int number; - /* Initial number of entries. Needed for module usage count */ - unsigned int initial_entries; - - /* Entry points and underflows */ - unsigned int hook_entry[NF_IP6_NUMHOOKS]; - unsigned int underflow[NF_IP6_NUMHOOKS]; - - /* ip6t_entry tables: one per CPU */ - char entries[0] ____cacheline_aligned; -}; - -static LIST_HEAD(ip6t_target); -static LIST_HEAD(ip6t_match); -static LIST_HEAD(ip6t_tables); -#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) - -#ifdef CONFIG_SMP -#define TABLE_OFFSET(t,p) (SMP_ALIGN((t)->size)*(p)) -#else -#define TABLE_OFFSET(t,p) 0 -#endif - -#if 0 -#define down(x) do { printk("DOWN:%u:" #x "\n", __LINE__); down(x); } while(0) -#define down_interruptible(x) ({ int __r; printk("DOWNi:%u:" #x "\n", __LINE__); __r = down_interruptible(x); if (__r != 0) printk("ABORT-DOWNi:%u\n", __LINE__); __r; }) -#define up(x) do { printk("UP:%u:" #x "\n", __LINE__); up(x); } while(0) -#endif - -static int ip6_masked_addrcmp(struct in6_addr addr1, struct in6_addr mask, - struct in6_addr addr2) -{ - int i; - for( i = 0; i < 16; i++){ - if((addr1.s6_addr[i] & mask.s6_addr[i]) != - (addr2.s6_addr[i] & mask.s6_addr[i])) - return 1; - } - return 0; -} - -/* Check for an extension */ -int -ip6t_ext_hdr(u8 nexthdr) -{ - return ( (nexthdr == IPPROTO_HOPOPTS) || - (nexthdr == IPPROTO_ROUTING) || - (nexthdr == IPPROTO_FRAGMENT) || - (nexthdr == IPPROTO_ESP) || - (nexthdr == IPPROTO_AH) || - (nexthdr == IPPROTO_NONE) || - (nexthdr == IPPROTO_DSTOPTS) ); -} - /* Returns whether matches rule or not. */ -static inline int +/* Performance critical - called for every packet */ +static inline bool ip6_packet_match(const struct sk_buff *skb, const char *indev, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, - int *fragoff) + int *fragoff, bool *hotdrop) { - size_t i; unsigned long ret; - const struct ipv6hdr *ipv6 = skb->nh.ipv6h; + const struct ipv6hdr *ipv6 = ipv6_hdr(skb); -#define FWINV(bool,invflg) ((bool) ^ !!(ip6info->invflags & invflg)) +#define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg))) - if (FWINV(ip6_masked_addrcmp(ipv6->saddr,ip6info->smsk,ip6info->src), - IP6T_INV_SRCIP) - || FWINV(ip6_masked_addrcmp(ipv6->daddr,ip6info->dmsk,ip6info->dst), - IP6T_INV_DSTIP)) { + if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, + &ip6info->src), IP6T_INV_SRCIP) || + FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst), IP6T_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); /* dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr, @@ -180,189 +106,228 @@ ip6_packet_match(const struct sk_buff *skb, dprintf("DST: %u. Mask: %u. Target: %u.%s\n", ip->daddr, ipinfo->dmsk.s_addr, ipinfo->dst.s_addr, ipinfo->invflags & IP6T_INV_DSTIP ? " (INV)" : "");*/ - return 0; + return false; } - /* Look for ifname matches; this should unroll nicely. */ - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) { - ret |= (((const unsigned long *)indev)[i] - ^ ((const unsigned long *)ip6info->iniface)[i]) - & ((const unsigned long *)ip6info->iniface_mask)[i]; - } + ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (FWINV(ret != 0, IP6T_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", indev, ip6info->iniface, ip6info->invflags&IP6T_INV_VIA_IN ?" (INV)":""); - return 0; + return false; } - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) { - ret |= (((const unsigned long *)outdev)[i] - ^ ((const unsigned long *)ip6info->outiface)[i]) - & ((const unsigned long *)ip6info->outiface_mask)[i]; - } + ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (FWINV(ret != 0, IP6T_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", outdev, ip6info->outiface, ip6info->invflags&IP6T_INV_VIA_OUT ?" (INV)":""); - return 0; + return false; } /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ if((ip6info->flags & IP6T_F_PROTO)) { - u_int8_t currenthdr = ipv6->nexthdr; - struct ipv6_opt_hdr _hdr, *hp; - u_int16_t ptr; /* Header offset in skb */ - u_int16_t hdrlen; /* Header */ - u_int16_t _fragoff = 0, *fp = NULL; - - ptr = IPV6_HDR_LEN; - - while (ip6t_ext_hdr(currenthdr)) { - /* Is there enough space for the next ext header? */ - if (skb->len - ptr < IPV6_OPTHDR_LEN) - return 0; - - /* NONE or ESP: there isn't protocol part */ - /* If we want to count these packets in '-p all', - * we will change the return 0 to 1*/ - if ((currenthdr == IPPROTO_NONE) || - (currenthdr == IPPROTO_ESP)) - break; - - hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); - BUG_ON(hp == NULL); - - /* Size calculation */ - if (currenthdr == IPPROTO_FRAGMENT) { - fp = skb_header_pointer(skb, - ptr+offsetof(struct frag_hdr, - frag_off), - sizeof(_fragoff), - &_fragoff); - if (fp == NULL) - return 0; - - _fragoff = ntohs(*fp) & ~0x7; - hdrlen = 8; - } else if (currenthdr == IPPROTO_AH) - hdrlen = (hp->hdrlen+2)<<2; - else - hdrlen = ipv6_optlen(hp); - - currenthdr = hp->nexthdr; - ptr += hdrlen; - /* ptr is too large */ - if ( ptr > skb->len ) - return 0; - if (_fragoff) { - if (ip6t_ext_hdr(currenthdr)) - return 0; - break; - } + int protohdr; + unsigned short _frag_off; + + protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); + if (protohdr < 0) { + if (_frag_off == 0) + *hotdrop = true; + return false; } - - *protoff = ptr; - *fragoff = _fragoff; - - /* currenthdr contains the protocol header */ + *fragoff = _frag_off; dprintf("Packet protocol %hi ?= %s%hi.\n", - currenthdr, + protohdr, ip6info->invflags & IP6T_INV_PROTO ? "!":"", ip6info->proto); - if (ip6info->proto == currenthdr) { + if (ip6info->proto == protohdr) { if(ip6info->invflags & IP6T_INV_PROTO) { - return 0; + return false; } - return 1; + return true; } /* We need match for the '-p all', too! */ if ((ip6info->proto != 0) && !(ip6info->invflags & IP6T_INV_PROTO)) - return 0; + return false; } - return 1; + return true; } /* should be ip6 safe */ -static inline int +static bool ip6_checkentry(const struct ip6t_ip6 *ipv6) { if (ipv6->flags & ~IP6T_F_MASK) { duprintf("Unknown flag bits set: %08X\n", ipv6->flags & ~IP6T_F_MASK); - return 0; + return false; } if (ipv6->invflags & ~IP6T_INV_MASK) { duprintf("Unknown invflag bits set: %08X\n", ipv6->invflags & ~IP6T_INV_MASK); - return 0; + return false; } - return 1; + return true; } static unsigned int -ip6t_error(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) +ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { - if (net_ratelimit()) - printk("ip6_tables: error: `%s'\n", (char *)targinfo); + net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } -static inline -int do_match(struct ip6t_entry_match *m, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int offset, - unsigned int protoff, - int *hotdrop) +static inline struct ip6t_entry * +get_entry(const void *base, unsigned int offset) { - /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, in, out, m->data, - offset, protoff, hotdrop)) + return (struct ip6t_entry *)(base + offset); +} + +/* All zeroes == unconditional rule. */ +/* Mildly perf critical (only if packet tracing is on) */ +static inline bool unconditional(const struct ip6t_ip6 *ipv6) +{ + static const struct ip6t_ip6 uncond; + + return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; +} + +static inline const struct xt_entry_target * +ip6t_get_target_c(const struct ip6t_entry *e) +{ + return ip6t_get_target((struct ip6t_entry *)e); +} + +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +/* This cries for unification! */ +static const char *const hooknames[] = { + [NF_INET_PRE_ROUTING] = "PREROUTING", + [NF_INET_LOCAL_IN] = "INPUT", + [NF_INET_FORWARD] = "FORWARD", + [NF_INET_LOCAL_OUT] = "OUTPUT", + [NF_INET_POST_ROUTING] = "POSTROUTING", +}; + +enum nf_ip_trace_comments { + NF_IP6_TRACE_COMMENT_RULE, + NF_IP6_TRACE_COMMENT_RETURN, + NF_IP6_TRACE_COMMENT_POLICY, +}; + +static const char *const comments[] = { + [NF_IP6_TRACE_COMMENT_RULE] = "rule", + [NF_IP6_TRACE_COMMENT_RETURN] = "return", + [NF_IP6_TRACE_COMMENT_POLICY] = "policy", +}; + +static struct nf_loginfo trace_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 4, + .logflags = NF_LOG_MASK, + }, + }, +}; + +/* Mildly perf critical (only if packet tracing is on) */ +static inline int +get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, + const char *hookname, const char **chainname, + const char **comment, unsigned int *rulenum) +{ + const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); + + if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { + /* Head of user chain: ERROR target with chainname */ + *chainname = t->target.data; + (*rulenum) = 0; + } else if (s == e) { + (*rulenum)++; + + if (s->target_offset == sizeof(struct ip6t_entry) && + strcmp(t->target.u.kernel.target->name, + XT_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ipv6)) { + /* Tail of chains: STANDARD target (return/policy) */ + *comment = *chainname == hookname + ? comments[NF_IP6_TRACE_COMMENT_POLICY] + : comments[NF_IP6_TRACE_COMMENT_RETURN]; + } return 1; - else - return 0; + } else + (*rulenum)++; + + return 0; } -static inline struct ip6t_entry * -get_entry(void *base, unsigned int offset) +static void trace_packet(const struct sk_buff *skb, + unsigned int hook, + const struct net_device *in, + const struct net_device *out, + const char *tablename, + const struct xt_table_info *private, + const struct ip6t_entry *e) { - return (struct ip6t_entry *)(base + offset); + const void *table_base; + const struct ip6t_entry *root; + const char *hookname, *chainname, *comment; + const struct ip6t_entry *iter; + unsigned int rulenum = 0; + struct net *net = dev_net(in ? in : out); + + table_base = private->entries[smp_processor_id()]; + root = get_entry(table_base, private->hook_entry[hook]); + + hookname = chainname = hooknames[hook]; + comment = comments[NF_IP6_TRACE_COMMENT_RULE]; + + xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) + if (get_chainname_rulenum(iter, e, hookname, + &chainname, &comment, &rulenum) != 0) + break; + + nf_log_packet(net, AF_INET6, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); +} +#endif + +static inline __pure struct ip6t_entry * +ip6t_next_entry(const struct ip6t_entry *entry) +{ + return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int -ip6t_do_table(struct sk_buff **pskb, +ip6t_do_table(struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, - struct ip6t_table *table, - void *userdata) + struct xt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); - int offset = 0; - unsigned int protoff = 0; - int hotdrop = 0; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; - void *table_base; - struct ip6t_entry *e, *back; + const void *table_base; + struct ip6t_entry *e, **jumpstack; + unsigned int *stackptr, origptr, cpu; + const struct xt_table_info *private; + struct xt_action_param acpar; + unsigned int addend; /* Initialization */ indev = in ? in->name : nulldevname; @@ -373,292 +338,130 @@ ip6t_do_table(struct sk_buff **pskb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ + acpar.hotdrop = false; + acpar.in = in; + acpar.out = out; + acpar.family = NFPROTO_IPV6; + acpar.hooknum = hook; - read_lock_bh(&table->lock); IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - table_base = (void *)table->private->entries - + TABLE_OFFSET(table->private, smp_processor_id()); - e = get_entry(table_base, table->private->hook_entry[hook]); - -#ifdef CONFIG_NETFILTER_DEBUG - /* Check noone else using our table */ - if (((struct ip6t_entry *)table_base)->comefrom != 0xdead57ac - && ((struct ip6t_entry *)table_base)->comefrom != 0xeeeeeeec) { - printk("ASSERT: CPU #%u, %s comefrom(%p) = %X\n", - smp_processor_id(), - table->name, - &((struct ip6t_entry *)table_base)->comefrom, - ((struct ip6t_entry *)table_base)->comefrom); - } - ((struct ip6t_entry *)table_base)->comefrom = 0x57acc001; -#endif - /* For return from builtin chain */ - back = get_entry(table_base, table->private->underflow[hook]); + local_bh_disable(); + addend = xt_write_recseq_begin(); + private = table->private; + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); + cpu = smp_processor_id(); + table_base = private->entries[cpu]; + jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; + stackptr = per_cpu_ptr(private->stackptr, cpu); + origptr = *stackptr; + + e = get_entry(table_base, private->hook_entry[hook]); do { + const struct xt_entry_target *t; + const struct xt_entry_match *ematch; + IP_NF_ASSERT(e); - IP_NF_ASSERT(back); - if (ip6_packet_match(*pskb, indev, outdev, &e->ipv6, - &protoff, &offset)) { - struct ip6t_entry_target *t; - - if (IP6T_MATCH_ITERATE(e, do_match, - *pskb, in, out, - offset, protoff, &hotdrop) != 0) + acpar.thoff = 0; + if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, + &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { + no_match: + e = ip6t_next_entry(e); + continue; + } + + xt_ematch_foreach(ematch, e) { + acpar.match = ematch->u.kernel.match; + acpar.matchinfo = ematch->data; + if (!acpar.match->match(skb, &acpar)) goto no_match; + } - ADD_COUNTER(e->counters, - ntohs((*pskb)->nh.ipv6h->payload_len) - + IPV6_HDR_LEN, - 1); - - t = ip6t_get_target(e); - IP_NF_ASSERT(t->u.kernel.target); - /* Standard target? */ - if (!t->u.kernel.target->target) { - int v; - - v = ((struct ip6t_standard_target *)t)->verdict; - if (v < 0) { - /* Pop from stack? */ - if (v != IP6T_RETURN) { - verdict = (unsigned)(-v) - 1; - break; - } - e = back; - back = get_entry(table_base, - back->comefrom); - continue; - } - if (table_base + v != (void *)e + e->next_offset - && !(e->ipv6.flags & IP6T_F_GOTO)) { - /* Save old back ptr in next entry */ - struct ip6t_entry *next - = (void *)e + e->next_offset; - next->comefrom - = (void *)back - table_base; - /* set back pointer to next entry */ - back = next; - } + ADD_COUNTER(e->counters, skb->len, 1); - e = get_entry(table_base, v); - } else { - /* Targets which reenter must return - abs. verdicts */ -#ifdef CONFIG_NETFILTER_DEBUG - ((struct ip6t_entry *)table_base)->comefrom - = 0xeeeeeeec; -#endif - verdict = t->u.kernel.target->target(pskb, - in, out, - hook, - t->data, - userdata); + t = ip6t_get_target_c(e); + IP_NF_ASSERT(t->u.kernel.target); -#ifdef CONFIG_NETFILTER_DEBUG - if (((struct ip6t_entry *)table_base)->comefrom - != 0xeeeeeeec - && verdict == IP6T_CONTINUE) { - printk("Target %s reentered!\n", - t->u.kernel.target->name); - verdict = NF_DROP; - } - ((struct ip6t_entry *)table_base)->comefrom - = 0x57acc001; +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) + /* The packet is traced: log it */ + if (unlikely(skb->nf_trace)) + trace_packet(skb, hook, in, out, + table->name, private, e); #endif - if (verdict == IP6T_CONTINUE) - e = (void *)e + e->next_offset; + /* Standard target? */ + if (!t->u.kernel.target->target) { + int v; + + v = ((struct xt_standard_target *)t)->verdict; + if (v < 0) { + /* Pop from stack? */ + if (v != XT_RETURN) { + verdict = (unsigned int)(-v) - 1; + break; + } + if (*stackptr <= origptr) + e = get_entry(table_base, + private->underflow[hook]); else - /* Verdict */ + e = ip6t_next_entry(jumpstack[--*stackptr]); + continue; + } + if (table_base + v != ip6t_next_entry(e) && + !(e->ipv6.flags & IP6T_F_GOTO)) { + if (*stackptr >= private->stacksize) { + verdict = NF_DROP; break; + } + jumpstack[(*stackptr)++] = e; } - } else { - no_match: - e = (void *)e + e->next_offset; + e = get_entry(table_base, v); + continue; } - } while (!hotdrop); -#ifdef CONFIG_NETFILTER_DEBUG - ((struct ip6t_entry *)table_base)->comefrom = 0xdead57ac; -#endif - read_unlock_bh(&table->lock); + acpar.target = t->u.kernel.target; + acpar.targinfo = t->data; + + verdict = t->u.kernel.target->target(skb, &acpar); + if (verdict == XT_CONTINUE) + e = ip6t_next_entry(e); + else + /* Verdict */ + break; + } while (!acpar.hotdrop); + + *stackptr = origptr; + + xt_write_recseq_end(addend); + local_bh_enable(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; #else - if (hotdrop) + if (acpar.hotdrop) return NF_DROP; else return verdict; #endif } -/* - * These are weird, but module loading must not be done with mutex - * held (since they will register), and we have to have a single - * function to use try_then_request_module(). - */ - -/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -static inline struct ip6t_table *find_table_lock(const char *name) -{ - struct ip6t_table *t; - - if (down_interruptible(&ip6t_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ip6t_tables, list) - if (strcmp(t->name, name) == 0 && try_module_get(t->me)) - return t; - up(&ip6t_mutex); - return NULL; -} - -/* Find match, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ip6t_match *find_match(const char *name, u8 revision) -{ - struct ip6t_match *m; - int err = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(m, &ip6t_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision == revision) { - if (try_module_get(m->me)) { - up(&ip6t_mutex); - return m; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ip6t_mutex); - return ERR_PTR(err); -} - -/* Find target, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ip6t_target *find_target(const char *name, u8 revision) -{ - struct ip6t_target *t; - int err = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ip6t_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision == revision) { - if (try_module_get(t->me)) { - up(&ip6t_mutex); - return t; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ip6t_mutex); - return ERR_PTR(err); -} - -struct ip6t_target *ip6t_find_target(const char *name, u8 revision) -{ - struct ip6t_target *target; - - target = try_then_request_module(find_target(name, revision), - "ip6t_%s", name); - if (IS_ERR(target) || !target) - return NULL; - return target; -} - -static int match_revfn(const char *name, u8 revision, int *bestp) -{ - struct ip6t_match *m; - int have_rev = 0; - - list_for_each_entry(m, &ip6t_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision > *bestp) - *bestp = m->revision; - if (m->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -static int target_revfn(const char *name, u8 revision, int *bestp) -{ - struct ip6t_target *t; - int have_rev = 0; - - list_for_each_entry(t, &ip6t_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision > *bestp) - *bestp = t->revision; - if (t->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -/* Returns true or fals (if no such extension at all) */ -static inline int find_revision(const char *name, u8 revision, - int (*revfn)(const char *, u8, int *), - int *err) -{ - int have_rev, best = -1; - - if (down_interruptible(&ip6t_mutex) != 0) { - *err = -EINTR; - return 1; - } - have_rev = revfn(name, revision, &best); - up(&ip6t_mutex); - - /* Nothing at all? Return 0 to try loading module. */ - if (best == -1) { - *err = -ENOENT; - return 0; - } - - *err = best; - if (!have_rev) - *err = -EPROTONOSUPPORT; - return 1; -} - - -/* All zeroes == unconditional rule. */ -static inline int -unconditional(const struct ip6t_ip6 *ipv6) -{ - unsigned int i; - - for (i = 0; i < sizeof(*ipv6); i++) - if (((char *)ipv6)[i]) - break; - - return (i == sizeof(*ipv6)); -} - /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) +mark_source_chains(const struct xt_table_info *newinfo, + unsigned int valid_hooks, void *entry0) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ - for (hook = 0; hook < NF_IP6_NUMHOOKS; hook++) { + for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; - struct ip6t_entry *e - = (struct ip6t_entry *)(newinfo->entries + pos); + struct ip6t_entry *e = (struct ip6t_entry *)(entry0 + pos); if (!(valid_hooks & (1 << hook))) continue; @@ -667,32 +470,41 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) e->counters.pcnt = pos; for (;;) { - struct ip6t_standard_target *t - = (void *)ip6t_get_target(e); + const struct xt_standard_target *t + = (void *)ip6t_get_target_c(e); + int visited = e->comefrom & (1 << hook); - if (e->comefrom & (1 << NF_IP6_NUMHOOKS)) { - printk("iptables: loop hook %u pos %u %08X.\n", + if (e->comefrom & (1 << NF_INET_NUMHOOKS)) { + pr_err("iptables: loop hook %u pos %u %08X.\n", hook, pos, e->comefrom); return 0; } - e->comefrom - |= ((1 << hook) | (1 << NF_IP6_NUMHOOKS)); + e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if (e->target_offset == sizeof(struct ip6t_entry) - && (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ipv6)) { + if ((e->target_offset == sizeof(struct ip6t_entry) && + (strcmp(t->target.u.user.name, + XT_STANDARD_TARGET) == 0) && + t->verdict < 0 && + unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; + if ((strcmp(t->target.u.user.name, + XT_STANDARD_TARGET) == 0) && + t->verdict < -NF_MAX_VERDICT - 1) { + duprintf("mark_source_chains: bad " + "negative verdict (%i)\n", + t->verdict); + return 0; + } + /* Return: backtrack through the last big jump. */ do { - e->comefrom ^= (1<<NF_IP6_NUMHOOKS); + e->comefrom ^= (1<<NF_INET_NUMHOOKS); #ifdef DEBUG_IP_FIREWALL_USER if (e->comefrom - & (1 << NF_IP6_NUMHOOKS)) { + & (1 << NF_INET_NUMHOOKS)) { duprintf("Back unset " "on hook %u " "rule %u\n", @@ -708,21 +520,28 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) goto next; e = (struct ip6t_entry *) - (newinfo->entries + pos); + (entry0 + pos); } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = (struct ip6t_entry *) - (newinfo->entries + pos + size); + (entry0 + pos + size); e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0 - && newpos >= 0) { + XT_STANDARD_TARGET) == 0 && + newpos >= 0) { + if (newpos > newinfo->size - + sizeof(struct ip6t_entry)) { + duprintf("mark_source_chains: " + "bad verdict (%i)\n", + newpos); + return 0; + } /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); @@ -731,7 +550,7 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) newpos = pos + e->next_offset; } e = (struct ip6t_entry *) - (newinfo->entries + newpos); + (entry0 + newpos); e->counters.pcnt = pos; pos = newpos; } @@ -742,218 +561,257 @@ mark_source_chains(struct ip6t_table_info *newinfo, unsigned int valid_hooks) return 1; } -static inline int -cleanup_match(struct ip6t_entry_match *m, unsigned int *i) +static void cleanup_match(struct xt_entry_match *m, struct net *net) { - if (i && (*i)-- == 0) - return 1; - - if (m->u.kernel.match->destroy) - m->u.kernel.match->destroy(m->data, - m->u.match_size - sizeof(*m)); - module_put(m->u.kernel.match->me); - return 0; + struct xt_mtdtor_param par; + + par.net = net; + par.match = m->u.kernel.match; + par.matchinfo = m->data; + par.family = NFPROTO_IPV6; + if (par.match->destroy != NULL) + par.match->destroy(&par); + module_put(par.match->me); } -static inline int -standard_check(const struct ip6t_entry_target *t, - unsigned int max_offset) +static int +check_entry(const struct ip6t_entry *e, const char *name) { - struct ip6t_standard_target *targ = (void *)t; + const struct xt_entry_target *t; - /* Check standard info. */ - if (t->u.target_size - != IP6T_ALIGN(sizeof(struct ip6t_standard_target))) { - duprintf("standard_check: target size %u != %u\n", - t->u.target_size, - IP6T_ALIGN(sizeof(struct ip6t_standard_target))); - return 0; + if (!ip6_checkentry(&e->ipv6)) { + duprintf("ip_tables: ip check failed %p %s.\n", e, name); + return -EINVAL; } - if (targ->verdict >= 0 - && targ->verdict > max_offset - sizeof(struct ip6t_entry)) { - duprintf("ip6t_standard_check: bad verdict (%i)\n", - targ->verdict); - return 0; - } + if (e->target_offset + sizeof(struct xt_entry_target) > + e->next_offset) + return -EINVAL; + + t = ip6t_get_target_c(e); + if (e->target_offset + t->u.target_size > e->next_offset) + return -EINVAL; + + return 0; +} + +static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) +{ + const struct ip6t_ip6 *ipv6 = par->entryinfo; + int ret; + + par->match = m->u.kernel.match; + par->matchinfo = m->data; - if (targ->verdict < -NF_MAX_VERDICT - 1) { - duprintf("ip6t_standard_check: bad negative verdict (%i)\n", - targ->verdict); - return 0; + ret = xt_check_match(par, m->u.match_size - sizeof(*m), + ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); + if (ret < 0) { + duprintf("ip_tables: check failed for `%s'.\n", + par.match->name); + return ret; } - return 1; + return 0; } -static inline int -check_match(struct ip6t_entry_match *m, - const char *name, - const struct ip6t_ip6 *ipv6, - unsigned int hookmask, - unsigned int *i) +static int +find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { - struct ip6t_match *match; + struct xt_match *match; + int ret; - match = try_then_request_module(find_match(m->u.user.name, - m->u.user.revision), - "ip6t_%s", m->u.user.name); - if (IS_ERR(match) || !match) { - duprintf("check_match: `%s' not found\n", m->u.user.name); - return match ? PTR_ERR(match) : -ENOENT; + match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) { + duprintf("find_check_match: `%s' not found\n", m->u.user.name); + return PTR_ERR(match); } m->u.kernel.match = match; - if (m->u.kernel.match->checkentry - && !m->u.kernel.match->checkentry(name, ipv6, m->data, - m->u.match_size - sizeof(*m), - hookmask)) { - module_put(m->u.kernel.match->me); - duprintf("ip_tables: check failed for `%s'.\n", - m->u.kernel.match->name); - return -EINVAL; - } + ret = check_match(m, par); + if (ret) + goto err; - (*i)++; return 0; +err: + module_put(m->u.kernel.match->me); + return ret; } -static struct ip6t_target ip6t_standard_target; +static int check_target(struct ip6t_entry *e, struct net *net, const char *name) +{ + struct xt_entry_target *t = ip6t_get_target(e); + struct xt_tgchk_param par = { + .net = net, + .table = name, + .entryinfo = e, + .target = t->u.kernel.target, + .targinfo = t->data, + .hook_mask = e->comefrom, + .family = NFPROTO_IPV6, + }; + int ret; -static inline int -check_entry(struct ip6t_entry *e, const char *name, unsigned int size, - unsigned int *i) + t = ip6t_get_target(e); + ret = xt_check_target(&par, t->u.target_size - sizeof(*t), + e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); + if (ret < 0) { + duprintf("ip_tables: check failed for `%s'.\n", + t->u.kernel.target->name); + return ret; + } + return 0; +} + +static int +find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, + unsigned int size) { - struct ip6t_entry_target *t; - struct ip6t_target *target; + struct xt_entry_target *t; + struct xt_target *target; int ret; unsigned int j; + struct xt_mtchk_param mtpar; + struct xt_entry_match *ematch; - if (!ip6_checkentry(&e->ipv6)) { - duprintf("ip_tables: ip check failed %p %s.\n", e, name); - return -EINVAL; - } + ret = check_entry(e, name); + if (ret) + return ret; j = 0; - ret = IP6T_MATCH_ITERATE(e, check_match, name, &e->ipv6, e->comefrom, &j); - if (ret != 0) - goto cleanup_matches; + mtpar.net = net; + mtpar.table = name; + mtpar.entryinfo = &e->ipv6; + mtpar.hook_mask = e->comefrom; + mtpar.family = NFPROTO_IPV6; + xt_ematch_foreach(ematch, e) { + ret = find_check_match(ematch, &mtpar); + if (ret != 0) + goto cleanup_matches; + ++j; + } t = ip6t_get_target(e); - target = try_then_request_module(find_target(t->u.user.name, - t->u.user.revision), - "ip6t_%s", t->u.user.name); - if (IS_ERR(target) || !target) { - duprintf("check_entry: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { + duprintf("find_check_entry: `%s' not found\n", t->u.user.name); + ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; - if (t->u.kernel.target == &ip6t_standard_target) { - if (!standard_check(t, size)) { - ret = -EINVAL; - goto cleanup_matches; - } - } else if (t->u.kernel.target->checkentry - && !t->u.kernel.target->checkentry(name, e, t->data, - t->u.target_size - - sizeof(*t), - e->comefrom)) { - module_put(t->u.kernel.target->me); - duprintf("ip_tables: check failed for `%s'.\n", - t->u.kernel.target->name); - ret = -EINVAL; - goto cleanup_matches; - } - - (*i)++; + ret = check_target(e, net, name); + if (ret) + goto err; return 0; - + err: + module_put(t->u.kernel.target->me); cleanup_matches: - IP6T_MATCH_ITERATE(e, cleanup_match, &j); + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + cleanup_match(ematch, net); + } return ret; } -static inline int +static bool check_underflow(const struct ip6t_entry *e) +{ + const struct xt_entry_target *t; + unsigned int verdict; + + if (!unconditional(&e->ipv6)) + return false; + t = ip6t_get_target_c(e); + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) + return false; + verdict = ((struct xt_standard_target *)t)->verdict; + verdict = -verdict - 1; + return verdict == NF_DROP || verdict == NF_ACCEPT; +} + +static int check_entry_size_and_hooks(struct ip6t_entry *e, - struct ip6t_table_info *newinfo, - unsigned char *base, - unsigned char *limit, + struct xt_table_info *newinfo, + const unsigned char *base, + const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, - unsigned int *i) + unsigned int valid_hooks) { unsigned int h; - if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } if (e->next_offset - < sizeof(struct ip6t_entry) + sizeof(struct ip6t_entry_target)) { + < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; } /* Check hooks & underflows */ - for (h = 0; h < NF_IP6_NUMHOOKS; h++) { + for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if (!(valid_hooks & (1 << h))) + continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) + if ((unsigned char *)e - base == underflows[h]) { + if (!check_underflow(e)) { + pr_err("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); + return -EINVAL; + } newinfo->underflow[h] = underflows[h]; + } } - /* FIXME: underflows must be unconditional, standard verdicts - < 0 (not IP6T_RETURN). --RR */ - /* Clear counters and comefrom */ - e->counters = ((struct ip6t_counters) { 0, 0 }); + e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; - - (*i)++; return 0; } -static inline int -cleanup_entry(struct ip6t_entry *e, unsigned int *i) +static void cleanup_entry(struct ip6t_entry *e, struct net *net) { - struct ip6t_entry_target *t; - - if (i && (*i)-- == 0) - return 1; + struct xt_tgdtor_param par; + struct xt_entry_target *t; + struct xt_entry_match *ematch; /* Cleanup all matches */ - IP6T_MATCH_ITERATE(e, cleanup_match, NULL); + xt_ematch_foreach(ematch, e) + cleanup_match(ematch, net); t = ip6t_get_target(e); - if (t->u.kernel.target->destroy) - t->u.kernel.target->destroy(t->data, - t->u.target_size - sizeof(*t)); - module_put(t->u.kernel.target->me); - return 0; + + par.net = net; + par.target = t->u.kernel.target; + par.targinfo = t->data; + par.family = NFPROTO_IPV6; + if (par.target->destroy != NULL) + par.target->destroy(&par); + module_put(par.target->me); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int -translate_table(const char *name, - unsigned int valid_hooks, - struct ip6t_table_info *newinfo, - unsigned int size, - unsigned int number, - const unsigned int *hook_entries, - const unsigned int *underflows) +translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, + const struct ip6t_replace *repl) { + struct ip6t_entry *iter; unsigned int i; - int ret; + int ret = 0; - newinfo->size = size; - newinfo->number = number; + newinfo->size = repl->size; + newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ - for (i = 0; i < NF_IP6_NUMHOOKS; i++) { + for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } @@ -961,161 +819,143 @@ translate_table(const char *name, duprintf("translate_table: size %u\n", newinfo->size); i = 0; /* Walk through entries, checking offsets. */ - ret = IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, - check_entry_size_and_hooks, - newinfo, - newinfo->entries, - newinfo->entries + size, - hook_entries, underflows, &i); - if (ret != 0) - return ret; - - if (i != number) { + xt_entry_foreach(iter, entry0, newinfo->size) { + ret = check_entry_size_and_hooks(iter, newinfo, entry0, + entry0 + repl->size, + repl->hook_entry, + repl->underflow, + repl->valid_hooks); + if (ret != 0) + return ret; + ++i; + if (strcmp(ip6t_get_target(iter)->u.user.name, + XT_ERROR_TARGET) == 0) + ++newinfo->stacksize; + } + + if (i != repl->num_entries) { duprintf("translate_table: %u not %u entries\n", - i, number); + i, repl->num_entries); return -EINVAL; } /* Check hooks all assigned */ - for (i = 0; i < NF_IP6_NUMHOOKS; i++) { + for (i = 0; i < NF_INET_NUMHOOKS; i++) { /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) + if (!(repl->valid_hooks & (1 << i))) continue; if (newinfo->hook_entry[i] == 0xFFFFFFFF) { duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); + i, repl->hook_entry[i]); return -EINVAL; } if (newinfo->underflow[i] == 0xFFFFFFFF) { duprintf("Invalid underflow %u %u\n", - i, underflows[i]); + i, repl->underflow[i]); return -EINVAL; } } - if (!mark_source_chains(newinfo, valid_hooks)) + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) return -ELOOP; /* Finally, each sanity check must pass */ i = 0; - ret = IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, - check_entry, name, size, &i); + xt_entry_foreach(iter, entry0, newinfo->size) { + ret = find_check_entry(iter, net, repl->name, repl->size); + if (ret != 0) + break; + ++i; + } if (ret != 0) { - IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, - cleanup_entry, &i); + xt_entry_foreach(iter, entry0, newinfo->size) { + if (i-- == 0) + break; + cleanup_entry(iter, net); + } return ret; } /* And one copy for every other CPU */ - for_each_cpu(i) { - if (i == 0) - continue; - memcpy(newinfo->entries + SMP_ALIGN(newinfo->size) * i, - newinfo->entries, - SMP_ALIGN(newinfo->size)); + for_each_possible_cpu(i) { + if (newinfo->entries[i] && newinfo->entries[i] != entry0) + memcpy(newinfo->entries[i], entry0, newinfo->size); } return ret; } -static struct ip6t_table_info * -replace_table(struct ip6t_table *table, - unsigned int num_counters, - struct ip6t_table_info *newinfo, - int *error) -{ - struct ip6t_table_info *oldinfo; - -#ifdef CONFIG_NETFILTER_DEBUG - { - struct ip6t_entry *table_base; - unsigned int i; - - for_each_cpu(i) { - table_base = - (void *)newinfo->entries - + TABLE_OFFSET(newinfo, i); - - table_base->comefrom = 0xdead57ac; - } - } -#endif - - /* Do the substitution. */ - write_lock_bh(&table->lock); - /* Check inside lock: is the old number correct? */ - if (num_counters != table->private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", - num_counters, table->private->number); - write_unlock_bh(&table->lock); - *error = -EAGAIN; - return NULL; - } - oldinfo = table->private; - table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - - return oldinfo; -} - -/* Gets counters. */ -static inline int -add_entry_to_counter(const struct ip6t_entry *e, - struct ip6t_counters total[], - unsigned int *i) -{ - ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); - - (*i)++; - return 0; -} - static void -get_counters(const struct ip6t_table_info *t, - struct ip6t_counters counters[]) +get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) { + struct ip6t_entry *iter; unsigned int cpu; unsigned int i; - for_each_cpu(cpu) { + for_each_possible_cpu(cpu) { + seqcount_t *s = &per_cpu(xt_recseq, cpu); + i = 0; - IP6T_ENTRY_ITERATE(t->entries + TABLE_OFFSET(t, cpu), - t->size, - add_entry_to_counter, - counters, - &i); + xt_entry_foreach(iter, t->entries[cpu], t->size) { + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqcount_begin(s); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqcount_retry(s, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); + ++i; + } } } -static int -copy_entries_to_user(unsigned int total_size, - struct ip6t_table *table, - void __user *userptr) +static struct xt_counters *alloc_counters(const struct xt_table *table) { - unsigned int off, num, countersize; - struct ip6t_entry *e; - struct ip6t_counters *counters; - int ret = 0; + unsigned int countersize; + struct xt_counters *counters; + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ - countersize = sizeof(struct ip6t_counters) * table->private->number; - counters = vmalloc(countersize); + countersize = sizeof(struct xt_counters) * private->number; + counters = vzalloc(countersize); if (counters == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - /* First, sum counters... */ - memset(counters, 0, countersize); - write_lock_bh(&table->lock); - get_counters(table->private, counters); - write_unlock_bh(&table->lock); + get_counters(private, counters); - /* ... then copy entire thing from CPU 0... */ - if (copy_to_user(userptr, table->private->entries, total_size) != 0) { + return counters; +} + +static int +copy_entries_to_user(unsigned int total_size, + const struct xt_table *table, + void __user *userptr) +{ + unsigned int off, num; + const struct ip6t_entry *e; + struct xt_counters *counters; + const struct xt_table_info *private = table->private; + int ret = 0; + const void *loc_cpu_entry; + + counters = alloc_counters(table); + if (IS_ERR(counters)) + return PTR_ERR(counters); + + /* choose the copy that is on our node/cpu, ... + * This choice is lazy (because current thread is + * allowed to migrate to another cpu) + */ + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; goto free_counters; } @@ -1124,10 +964,10 @@ copy_entries_to_user(unsigned int total_size, /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; - struct ip6t_entry_match *m; - struct ip6t_entry_target *t; + const struct xt_entry_match *m; + const struct xt_entry_target *t; - e = (struct ip6t_entry *)(table->private->entries + off); + e = (struct ip6t_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], @@ -1142,7 +982,7 @@ copy_entries_to_user(unsigned int total_size, m = (void *)e + i; if (copy_to_user(userptr + off + i - + offsetof(struct ip6t_entry_match, + + offsetof(struct xt_entry_match, u.user.name), m->u.kernel.match->name, strlen(m->u.kernel.match->name)+1) @@ -1152,9 +992,9 @@ copy_entries_to_user(unsigned int total_size, } } - t = ip6t_get_target(e); + t = ip6t_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct ip6t_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -1168,196 +1008,389 @@ copy_entries_to_user(unsigned int total_size, return ret; } -static int -get_entries(const struct ip6t_get_entries *entries, - struct ip6t_get_entries __user *uptr) +#ifdef CONFIG_COMPAT +static void compat_standard_from_user(void *dst, const void *src) +{ + int v = *(compat_int_t *)src; + + if (v > 0) + v += xt_compat_calc_jump(AF_INET6, v); + memcpy(dst, &v, sizeof(v)); +} + +static int compat_standard_to_user(void __user *dst, const void *src) +{ + compat_int_t cv = *(int *)src; + + if (cv > 0) + cv -= xt_compat_calc_jump(AF_INET6, cv); + return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; +} + +static int compat_calc_entry(const struct ip6t_entry *e, + const struct xt_table_info *info, + const void *base, struct xt_table_info *newinfo) { + const struct xt_entry_match *ematch; + const struct xt_entry_target *t; + unsigned int entry_offset; + int off, i, ret; + + off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + entry_offset = (void *)e - base; + xt_ematch_foreach(ematch, e) + off += xt_compat_match_offset(ematch->u.kernel.match); + t = ip6t_get_target_c(e); + off += xt_compat_target_offset(t->u.kernel.target); + newinfo->size -= off; + ret = xt_compat_add_offset(AF_INET6, entry_offset, off); + if (ret) + return ret; + + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + if (info->hook_entry[i] && + (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) + newinfo->hook_entry[i] -= off; + if (info->underflow[i] && + (e < (struct ip6t_entry *)(base + info->underflow[i]))) + newinfo->underflow[i] -= off; + } + return 0; +} + +static int compat_table_info(const struct xt_table_info *info, + struct xt_table_info *newinfo) +{ + struct ip6t_entry *iter; + void *loc_cpu_entry; int ret; - struct ip6t_table *t; - - t = find_table_lock(entries->name); - if (t && !IS_ERR(t)) { - duprintf("t->private->number = %u\n", - t->private->number); - if (entries->size == t->private->size) - ret = copy_entries_to_user(t->private->size, - t, uptr->entrytable); - else { - duprintf("get_entries: I've got %u not %u!\n", - t->private->size, - entries->size); - ret = -EINVAL; + + if (!newinfo || !info) + return -EINVAL; + + /* we dont care about newinfo->entries[] */ + memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); + newinfo->initial_entries = 0; + loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET6, info->number); + xt_entry_foreach(iter, loc_cpu_entry, info->size) { + ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); + if (ret != 0) + return ret; + } + return 0; +} +#endif + +static int get_info(struct net *net, void __user *user, + const int *len, int compat) +{ + char name[XT_TABLE_MAXNAMELEN]; + struct xt_table *t; + int ret; + + if (*len != sizeof(struct ip6t_getinfo)) { + duprintf("length %u != %zu\n", *len, + sizeof(struct ip6t_getinfo)); + return -EINVAL; + } + + if (copy_from_user(name, user, sizeof(name)) != 0) + return -EFAULT; + + name[XT_TABLE_MAXNAMELEN-1] = '\0'; +#ifdef CONFIG_COMPAT + if (compat) + xt_compat_lock(AF_INET6); +#endif + t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name), + "ip6table_%s", name); + if (!IS_ERR_OR_NULL(t)) { + struct ip6t_getinfo info; + const struct xt_table_info *private = t->private; +#ifdef CONFIG_COMPAT + struct xt_table_info tmp; + + if (compat) { + ret = compat_table_info(private, &tmp); + xt_compat_flush_offsets(AF_INET6); + private = &tmp; } +#endif + memset(&info, 0, sizeof(info)); + info.valid_hooks = t->valid_hooks; + memcpy(info.hook_entry, private->hook_entry, + sizeof(info.hook_entry)); + memcpy(info.underflow, private->underflow, + sizeof(info.underflow)); + info.num_entries = private->number; + info.size = private->size; + strcpy(info.name, name); + + if (copy_to_user(user, &info, *len) != 0) + ret = -EFAULT; + else + ret = 0; + + xt_table_unlock(t); module_put(t->me); - up(&ip6t_mutex); } else ret = t ? PTR_ERR(t) : -ENOENT; - +#ifdef CONFIG_COMPAT + if (compat) + xt_compat_unlock(AF_INET6); +#endif return ret; } static int -do_replace(void __user *user, unsigned int len) +get_entries(struct net *net, struct ip6t_get_entries __user *uptr, + const int *len) { int ret; - struct ip6t_replace tmp; - struct ip6t_table *t; - struct ip6t_table_info *newinfo, *oldinfo; - struct ip6t_counters *counters; + struct ip6t_get_entries get; + struct xt_table *t; - if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + if (*len < sizeof(get)) { + duprintf("get_entries: %u < %zu\n", *len, sizeof(get)); + return -EINVAL; + } + if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; + if (*len != sizeof(struct ip6t_get_entries) + get.size) { + duprintf("get_entries: %u != %zu\n", + *len, sizeof(get) + get.size); + return -EINVAL; + } - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) - return -ENOMEM; - - newinfo = vmalloc(sizeof(struct ip6t_table_info) - + SMP_ALIGN(tmp.size) * - (highest_possible_processor_id()+1)); - if (!newinfo) - return -ENOMEM; + t = xt_find_table_lock(net, AF_INET6, get.name); + if (!IS_ERR_OR_NULL(t)) { + struct xt_table_info *private = t->private; + duprintf("t->private->number = %u\n", private->number); + if (get.size == private->size) + ret = copy_entries_to_user(private->size, + t, uptr->entrytable); + else { + duprintf("get_entries: I've got %u not %u!\n", + private->size, get.size); + ret = -EAGAIN; + } + module_put(t->me); + xt_table_unlock(t); + } else + ret = t ? PTR_ERR(t) : -ENOENT; - if (copy_from_user(newinfo->entries, user + sizeof(tmp), - tmp.size) != 0) { - ret = -EFAULT; - goto free_newinfo; - } + return ret; +} - counters = vmalloc(tmp.num_counters * sizeof(struct ip6t_counters)); +static int +__do_replace(struct net *net, const char *name, unsigned int valid_hooks, + struct xt_table_info *newinfo, unsigned int num_counters, + void __user *counters_ptr) +{ + int ret; + struct xt_table *t; + struct xt_table_info *oldinfo; + struct xt_counters *counters; + const void *loc_cpu_old_entry; + struct ip6t_entry *iter; + + ret = 0; + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; - goto free_newinfo; + goto out; } - memset(counters, 0, tmp.num_counters * sizeof(struct ip6t_counters)); - ret = translate_table(tmp.name, tmp.valid_hooks, - newinfo, tmp.size, tmp.num_entries, - tmp.hook_entry, tmp.underflow); - if (ret != 0) - goto free_newinfo_counters; - - duprintf("ip_tables: Translated table\n"); - - t = try_then_request_module(find_table_lock(tmp.name), - "ip6table_%s", tmp.name); - if (!t || IS_ERR(t)) { + t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name), + "ip6table_%s", name); + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } /* You lied! */ - if (tmp.valid_hooks != t->valid_hooks) { + if (valid_hooks != t->valid_hooks) { duprintf("Valid hook crap: %08X vs %08X\n", - tmp.valid_hooks, t->valid_hooks); + valid_hooks, t->valid_hooks); ret = -EINVAL; goto put_module; } - oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret); + oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ duprintf("do_replace: oldnum=%u, initnum=%u, newnum=%u\n", oldinfo->number, oldinfo->initial_entries, newinfo->number); - if ((oldinfo->number > oldinfo->initial_entries) || - (newinfo->number <= oldinfo->initial_entries)) + if ((oldinfo->number > oldinfo->initial_entries) || + (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ - IP6T_ENTRY_ITERATE(oldinfo->entries, oldinfo->size, cleanup_entry,NULL); - vfree(oldinfo); - if (copy_to_user(tmp.counters, counters, - sizeof(struct ip6t_counters) * tmp.num_counters) != 0) - ret = -EFAULT; + loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; + xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) + cleanup_entry(iter, net); + + xt_free_table_info(oldinfo); + if (copy_to_user(counters_ptr, counters, + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); + } vfree(counters); - up(&ip6t_mutex); + xt_table_unlock(t); return ret; put_module: module_put(t->me); - up(&ip6t_mutex); + xt_table_unlock(t); free_newinfo_counters_untrans: - IP6T_ENTRY_ITERATE(newinfo->entries, newinfo->size, cleanup_entry,NULL); - free_newinfo_counters: vfree(counters); - free_newinfo: - vfree(newinfo); + out: return ret; } -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static inline int -add_counter_to_entry(struct ip6t_entry *e, - const struct ip6t_counters addme[], - unsigned int *i) +static int +do_replace(struct net *net, const void __user *user, unsigned int len) { -#if 0 - duprintf("add_counter: Entry %u %lu/%lu + %lu/%lu\n", - *i, - (long unsigned int)e->counters.pcnt, - (long unsigned int)e->counters.bcnt, - (long unsigned int)addme[*i].pcnt, - (long unsigned int)addme[*i].bcnt); -#endif + int ret; + struct ip6t_replace tmp; + struct xt_table_info *newinfo; + void *loc_cpu_entry; + struct ip6t_entry *iter; + + if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + return -EFAULT; + + /* overflow check */ + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + tmp.name[sizeof(tmp.name)-1] = 0; + + newinfo = xt_alloc_table_info(tmp.size); + if (!newinfo) + return -ENOMEM; - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + /* choose the copy that is on our node/cpu */ + loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; + if (copy_from_user(loc_cpu_entry, user + sizeof(tmp), + tmp.size) != 0) { + ret = -EFAULT; + goto free_newinfo; + } + + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); + if (ret != 0) + goto free_newinfo; - (*i)++; + duprintf("ip_tables: Translated table\n"); + + ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, + tmp.num_counters, tmp.counters); + if (ret) + goto free_newinfo_untrans; return 0; + + free_newinfo_untrans: + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); + free_newinfo: + xt_free_table_info(newinfo); + return ret; } static int -do_add_counters(void __user *user, unsigned int len) +do_add_counters(struct net *net, const void __user *user, unsigned int len, + int compat) { - unsigned int i; - struct ip6t_counters_info tmp, *paddc; - struct ip6t_table *t; + unsigned int i, curcpu; + struct xt_counters_info tmp; + struct xt_counters *paddc; + unsigned int num_counters; + char *name; + int size; + void *ptmp; + struct xt_table *t; + const struct xt_table_info *private; int ret = 0; + const void *loc_cpu_entry; + struct ip6t_entry *iter; + unsigned int addend; +#ifdef CONFIG_COMPAT + struct compat_xt_counters_info compat_tmp; + + if (compat) { + ptmp = &compat_tmp; + size = sizeof(struct compat_xt_counters_info); + } else +#endif + { + ptmp = &tmp; + size = sizeof(struct xt_counters_info); + } - if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + if (copy_from_user(ptmp, user, size) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct ip6t_counters)) +#ifdef CONFIG_COMPAT + if (compat) { + num_counters = compat_tmp.num_counters; + name = compat_tmp.name; + } else +#endif + { + num_counters = tmp.num_counters; + name = tmp.name; + } + + if (len != size + num_counters * sizeof(struct xt_counters)) return -EINVAL; - paddc = vmalloc(len); + paddc = vmalloc(len - size); if (!paddc) return -ENOMEM; - if (copy_from_user(paddc, user, len) != 0) { + if (copy_from_user(paddc, user + size, len - size) != 0) { ret = -EFAULT; goto free; } - t = find_table_lock(tmp.name); - if (!t || IS_ERR(t)) { + t = xt_find_table_lock(net, AF_INET6, name); + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } - write_lock_bh(&t->lock); - if (t->private->number != paddc->num_counters) { + + local_bh_disable(); + private = t->private; + if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; - IP6T_ENTRY_ITERATE(t->private->entries, - t->private->size, - add_counter_to_entry, - paddc->counters, - &i); + /* Choose the copy that is on our node */ + curcpu = smp_processor_id(); + addend = xt_write_recseq_begin(); + loc_cpu_entry = private->entries[curcpu]; + xt_entry_foreach(iter, loc_cpu_entry, private->size) { + ADD_COUNTER(iter->counters, paddc[i].bcnt, paddc[i].pcnt); + ++i; + } + xt_write_recseq_end(addend); + unlock_up_free: - write_unlock_bh(&t->lock); - up(&ip6t_mutex); + local_bh_enable(); + xt_table_unlock(t); module_put(t->me); free: vfree(paddc); @@ -1365,469 +1398,764 @@ do_add_counters(void __user *user, unsigned int len) return ret; } +#ifdef CONFIG_COMPAT +struct compat_ip6t_replace { + char name[XT_TABLE_MAXNAMELEN]; + u32 valid_hooks; + u32 num_entries; + u32 size; + u32 hook_entry[NF_INET_NUMHOOKS]; + u32 underflow[NF_INET_NUMHOOKS]; + u32 num_counters; + compat_uptr_t counters; /* struct xt_counters * */ + struct compat_ip6t_entry entries[0]; +}; + static int -do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) +compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, + unsigned int *size, struct xt_counters *counters, + unsigned int i) { - int ret; + struct xt_entry_target *t; + struct compat_ip6t_entry __user *ce; + u_int16_t target_offset, next_offset; + compat_uint_t origsize; + const struct xt_entry_match *ematch; + int ret = 0; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; + origsize = *size; + ce = (struct compat_ip6t_entry __user *)*dstptr; + if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || + copy_to_user(&ce->counters, &counters[i], + sizeof(counters[i])) != 0) + return -EFAULT; - switch (cmd) { - case IP6T_SO_SET_REPLACE: - ret = do_replace(user, len); - break; + *dstptr += sizeof(struct compat_ip6t_entry); + *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); - case IP6T_SO_SET_ADD_COUNTERS: - ret = do_add_counters(user, len); - break; + xt_ematch_foreach(ematch, e) { + ret = xt_compat_match_to_user(ematch, dstptr, size); + if (ret != 0) + return ret; + } + target_offset = e->target_offset - (origsize - *size); + t = ip6t_get_target(e); + ret = xt_compat_target_to_user(t, dstptr, size); + if (ret) + return ret; + next_offset = e->next_offset - (origsize - *size); + if (put_user(target_offset, &ce->target_offset) != 0 || + put_user(next_offset, &ce->next_offset) != 0) + return -EFAULT; + return 0; +} - default: - duprintf("do_ip6t_set_ctl: unknown request %i\n", cmd); - ret = -EINVAL; +static int +compat_find_calc_match(struct xt_entry_match *m, + const char *name, + const struct ip6t_ip6 *ipv6, + unsigned int hookmask, + int *size) +{ + struct xt_match *match; + + match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) { + duprintf("compat_check_calc_match: `%s' not found\n", + m->u.user.name); + return PTR_ERR(match); } + m->u.kernel.match = match; + *size += xt_compat_match_offset(match); + return 0; +} - return ret; +static void compat_release_entry(struct compat_ip6t_entry *e) +{ + struct xt_entry_target *t; + struct xt_entry_match *ematch; + + /* Cleanup all matches */ + xt_ematch_foreach(ematch, e) + module_put(ematch->u.kernel.match->me); + t = compat_ip6t_get_target(e); + module_put(t->u.kernel.target->me); } static int -do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) +check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, + struct xt_table_info *newinfo, + unsigned int *size, + const unsigned char *base, + const unsigned char *limit, + const unsigned int *hook_entries, + const unsigned int *underflows, + const char *name) { - int ret; + struct xt_entry_match *ematch; + struct xt_entry_target *t; + struct xt_target *target; + unsigned int entry_offset; + unsigned int j; + int ret, off, h; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; + duprintf("check_compat_entry_size_and_hooks %p\n", e); + if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + duprintf("Bad offset %p, limit = %p\n", e, limit); + return -EINVAL; + } - switch (cmd) { - case IP6T_SO_GET_INFO: { - char name[IP6T_TABLE_MAXNAMELEN]; - struct ip6t_table *t; + if (e->next_offset < sizeof(struct compat_ip6t_entry) + + sizeof(struct compat_xt_entry_target)) { + duprintf("checking: element %p size %u\n", + e, e->next_offset); + return -EINVAL; + } - if (*len != sizeof(struct ip6t_getinfo)) { - duprintf("length %u != %u\n", *len, - sizeof(struct ip6t_getinfo)); - ret = -EINVAL; - break; - } + /* For purposes of check_entry casting the compat entry is fine */ + ret = check_entry((struct ip6t_entry *)e, name); + if (ret) + return ret; - if (copy_from_user(name, user, sizeof(name)) != 0) { - ret = -EFAULT; - break; - } - name[IP6T_TABLE_MAXNAMELEN-1] = '\0'; - - t = try_then_request_module(find_table_lock(name), - "ip6table_%s", name); - if (t && !IS_ERR(t)) { - struct ip6t_getinfo info; - - info.valid_hooks = t->valid_hooks; - memcpy(info.hook_entry, t->private->hook_entry, - sizeof(info.hook_entry)); - memcpy(info.underflow, t->private->underflow, - sizeof(info.underflow)); - info.num_entries = t->private->number; - info.size = t->private->size; - memcpy(info.name, name, sizeof(info.name)); - - if (copy_to_user(user, &info, *len) != 0) - ret = -EFAULT; - else - ret = 0; - up(&ip6t_mutex); - module_put(t->me); - } else - ret = t ? PTR_ERR(t) : -ENOENT; + off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + entry_offset = (void *)e - (void *)base; + j = 0; + xt_ematch_foreach(ematch, e) { + ret = compat_find_calc_match(ematch, name, + &e->ipv6, e->comefrom, &off); + if (ret != 0) + goto release_matches; + ++j; + } + + t = compat_ip6t_get_target(e); + target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { + duprintf("check_compat_entry_size_and_hooks: `%s' not found\n", + t->u.user.name); + ret = PTR_ERR(target); + goto release_matches; } - break; + t->u.kernel.target = target; - case IP6T_SO_GET_ENTRIES: { - struct ip6t_get_entries get; + off += xt_compat_target_offset(target); + *size += off; + ret = xt_compat_add_offset(AF_INET6, entry_offset, off); + if (ret) + goto out; - if (*len < sizeof(get)) { - duprintf("get_entries: %u < %u\n", *len, sizeof(get)); - ret = -EINVAL; - } else if (copy_from_user(&get, user, sizeof(get)) != 0) { - ret = -EFAULT; - } else if (*len != sizeof(struct ip6t_get_entries) + get.size) { - duprintf("get_entries: %u != %u\n", *len, - sizeof(struct ip6t_get_entries) + get.size); - ret = -EINVAL; - } else - ret = get_entries(&get, user); - break; + /* Check hooks & underflows */ + for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if ((unsigned char *)e - base == hook_entries[h]) + newinfo->hook_entry[h] = hook_entries[h]; + if ((unsigned char *)e - base == underflows[h]) + newinfo->underflow[h] = underflows[h]; } - case IP6T_SO_GET_REVISION_MATCH: - case IP6T_SO_GET_REVISION_TARGET: { - struct ip6t_get_revision rev; - int (*revfn)(const char *, u8, int *); + /* Clear counters and comefrom */ + memset(&e->counters, 0, sizeof(e->counters)); + e->comefrom = 0; + return 0; - if (*len != sizeof(rev)) { - ret = -EINVAL; - break; - } - if (copy_from_user(&rev, user, sizeof(rev)) != 0) { - ret = -EFAULT; +out: + module_put(t->u.kernel.target->me); +release_matches: + xt_ematch_foreach(ematch, e) { + if (j-- == 0) break; - } - - if (cmd == IP6T_SO_GET_REVISION_TARGET) - revfn = target_revfn; - else - revfn = match_revfn; - - try_then_request_module(find_revision(rev.name, rev.revision, - revfn, &ret), - "ip6t_%s", rev.name); - break; + module_put(ematch->u.kernel.match->me); } + return ret; +} - default: - duprintf("do_ip6t_get_ctl: unknown request %i\n", cmd); - ret = -EINVAL; +static int +compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, + unsigned int *size, const char *name, + struct xt_table_info *newinfo, unsigned char *base) +{ + struct xt_entry_target *t; + struct ip6t_entry *de; + unsigned int origsize; + int ret, h; + struct xt_entry_match *ematch; + + ret = 0; + origsize = *size; + de = (struct ip6t_entry *)*dstptr; + memcpy(de, e, sizeof(struct ip6t_entry)); + memcpy(&de->counters, &e->counters, sizeof(e->counters)); + + *dstptr += sizeof(struct ip6t_entry); + *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + + xt_ematch_foreach(ematch, e) { + ret = xt_compat_match_from_user(ematch, dstptr, size); + if (ret != 0) + return ret; + } + de->target_offset = e->target_offset - (origsize - *size); + t = compat_ip6t_get_target(e); + xt_compat_target_from_user(t, dstptr, size); + + de->next_offset = e->next_offset - (origsize - *size); + for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if ((unsigned char *)de - base < newinfo->hook_entry[h]) + newinfo->hook_entry[h] -= origsize - *size; + if ((unsigned char *)de - base < newinfo->underflow[h]) + newinfo->underflow[h] -= origsize - *size; } - return ret; } -/* Registration hooks for targets. */ -int -ip6t_register_target(struct ip6t_target *target) +static int compat_check_entry(struct ip6t_entry *e, struct net *net, + const char *name) { - int ret; + unsigned int j; + int ret = 0; + struct xt_mtchk_param mtpar; + struct xt_entry_match *ematch; - ret = down_interruptible(&ip6t_mutex); - if (ret != 0) - return ret; - list_add(&target->list, &ip6t_target); - up(&ip6t_mutex); + j = 0; + mtpar.net = net; + mtpar.table = name; + mtpar.entryinfo = &e->ipv6; + mtpar.hook_mask = e->comefrom; + mtpar.family = NFPROTO_IPV6; + xt_ematch_foreach(ematch, e) { + ret = check_match(ematch, &mtpar); + if (ret != 0) + goto cleanup_matches; + ++j; + } + + ret = check_target(e, net, name); + if (ret) + goto cleanup_matches; + return 0; + + cleanup_matches: + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + cleanup_match(ematch, net); + } return ret; } -void -ip6t_unregister_target(struct ip6t_target *target) +static int +translate_compat_table(struct net *net, + const char *name, + unsigned int valid_hooks, + struct xt_table_info **pinfo, + void **pentry0, + unsigned int total_size, + unsigned int number, + unsigned int *hook_entries, + unsigned int *underflows) { - down(&ip6t_mutex); - LIST_DELETE(&ip6t_target, target); - up(&ip6t_mutex); -} + unsigned int i, j; + struct xt_table_info *newinfo, *info; + void *pos, *entry0, *entry1; + struct compat_ip6t_entry *iter0; + struct ip6t_entry *iter1; + unsigned int size; + int ret = 0; -int -ip6t_register_match(struct ip6t_match *match) -{ - int ret; + info = *pinfo; + entry0 = *pentry0; + size = total_size; + info->number = number; - ret = down_interruptible(&ip6t_mutex); - if (ret != 0) + /* Init all hooks to impossible value. */ + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + info->hook_entry[i] = 0xFFFFFFFF; + info->underflow[i] = 0xFFFFFFFF; + } + + duprintf("translate_compat_table: size %u\n", info->size); + j = 0; + xt_compat_lock(AF_INET6); + xt_compat_init_offsets(AF_INET6, number); + /* Walk through entries, checking offsets. */ + xt_entry_foreach(iter0, entry0, total_size) { + ret = check_compat_entry_size_and_hooks(iter0, info, &size, + entry0, + entry0 + total_size, + hook_entries, + underflows, + name); + if (ret != 0) + goto out_unlock; + ++j; + } + + ret = -EINVAL; + if (j != number) { + duprintf("translate_compat_table: %u not %u entries\n", + j, number); + goto out_unlock; + } + + /* Check hooks all assigned */ + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + /* Only hooks which are valid */ + if (!(valid_hooks & (1 << i))) + continue; + if (info->hook_entry[i] == 0xFFFFFFFF) { + duprintf("Invalid hook entry %u %u\n", + i, hook_entries[i]); + goto out_unlock; + } + if (info->underflow[i] == 0xFFFFFFFF) { + duprintf("Invalid underflow %u %u\n", + i, underflows[i]); + goto out_unlock; + } + } + + ret = -ENOMEM; + newinfo = xt_alloc_table_info(size); + if (!newinfo) + goto out_unlock; + + newinfo->number = number; + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + newinfo->hook_entry[i] = info->hook_entry[i]; + newinfo->underflow[i] = info->underflow[i]; + } + entry1 = newinfo->entries[raw_smp_processor_id()]; + pos = entry1; + size = total_size; + xt_entry_foreach(iter0, entry0, total_size) { + ret = compat_copy_entry_from_user(iter0, &pos, &size, + name, newinfo, entry1); + if (ret != 0) + break; + } + xt_compat_flush_offsets(AF_INET6); + xt_compat_unlock(AF_INET6); + if (ret) + goto free_newinfo; + + ret = -ELOOP; + if (!mark_source_chains(newinfo, valid_hooks, entry1)) + goto free_newinfo; + + i = 0; + xt_entry_foreach(iter1, entry1, newinfo->size) { + ret = compat_check_entry(iter1, net, name); + if (ret != 0) + break; + ++i; + if (strcmp(ip6t_get_target(iter1)->u.user.name, + XT_ERROR_TARGET) == 0) + ++newinfo->stacksize; + } + if (ret) { + /* + * The first i matches need cleanup_entry (calls ->destroy) + * because they had called ->check already. The other j-i + * entries need only release. + */ + int skip = i; + j -= i; + xt_entry_foreach(iter0, entry0, newinfo->size) { + if (skip-- > 0) + continue; + if (j-- == 0) + break; + compat_release_entry(iter0); + } + xt_entry_foreach(iter1, entry1, newinfo->size) { + if (i-- == 0) + break; + cleanup_entry(iter1, net); + } + xt_free_table_info(newinfo); return ret; + } - list_add(&match->list, &ip6t_match); - up(&ip6t_mutex); + /* And one copy for every other CPU */ + for_each_possible_cpu(i) + if (newinfo->entries[i] && newinfo->entries[i] != entry1) + memcpy(newinfo->entries[i], entry1, newinfo->size); - return ret; -} + *pinfo = newinfo; + *pentry0 = entry1; + xt_free_table_info(info); + return 0; -void -ip6t_unregister_match(struct ip6t_match *match) -{ - down(&ip6t_mutex); - LIST_DELETE(&ip6t_match, match); - up(&ip6t_mutex); +free_newinfo: + xt_free_table_info(newinfo); +out: + xt_entry_foreach(iter0, entry0, total_size) { + if (j-- == 0) + break; + compat_release_entry(iter0); + } + return ret; +out_unlock: + xt_compat_flush_offsets(AF_INET6); + xt_compat_unlock(AF_INET6); + goto out; } -int ip6t_register_table(struct ip6t_table *table, - const struct ip6t_replace *repl) +static int +compat_do_replace(struct net *net, void __user *user, unsigned int len) { int ret; - struct ip6t_table_info *newinfo; - static struct ip6t_table_info bootstrap - = { 0, 0, 0, { 0 }, { 0 }, { } }; + struct compat_ip6t_replace tmp; + struct xt_table_info *newinfo; + void *loc_cpu_entry; + struct ip6t_entry *iter; - newinfo = vmalloc(sizeof(struct ip6t_table_info) - + SMP_ALIGN(repl->size) * - (highest_possible_processor_id()+1)); - if (!newinfo) + if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) + return -EFAULT; + + /* overflow check */ + if (tmp.size >= INT_MAX / num_possible_cpus()) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + tmp.name[sizeof(tmp.name)-1] = 0; - memcpy(newinfo->entries, repl->entries, repl->size); + newinfo = xt_alloc_table_info(tmp.size); + if (!newinfo) + return -ENOMEM; - ret = translate_table(table->name, table->valid_hooks, - newinfo, repl->size, - repl->num_entries, - repl->hook_entry, - repl->underflow); - if (ret != 0) { - vfree(newinfo); - return ret; + /* choose the copy that is on our node/cpu */ + loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; + if (copy_from_user(loc_cpu_entry, user + sizeof(tmp), + tmp.size) != 0) { + ret = -EFAULT; + goto free_newinfo; } - ret = down_interruptible(&ip6t_mutex); - if (ret != 0) { - vfree(newinfo); - return ret; - } + ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, + &newinfo, &loc_cpu_entry, tmp.size, + tmp.num_entries, tmp.hook_entry, + tmp.underflow); + if (ret != 0) + goto free_newinfo; - /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&ip6t_tables, table->name)) { - ret = -EEXIST; - goto free_unlock; - } + duprintf("compat_do_replace: Translated table\n"); - /* Simplifies replace_table code. */ - table->private = &bootstrap; - if (!replace_table(table, 0, newinfo, &ret)) - goto free_unlock; + ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, + tmp.num_counters, compat_ptr(tmp.counters)); + if (ret) + goto free_newinfo_untrans; + return 0; - duprintf("table->private->number = %u\n", - table->private->number); + free_newinfo_untrans: + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); + free_newinfo: + xt_free_table_info(newinfo); + return ret; +} - /* save number of initial entries */ - table->private->initial_entries = table->private->number; +static int +compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, + unsigned int len) +{ + int ret; - rwlock_init(&table->lock); - list_prepend(&ip6t_tables, table); + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; - unlock: - up(&ip6t_mutex); - return ret; + switch (cmd) { + case IP6T_SO_SET_REPLACE: + ret = compat_do_replace(sock_net(sk), user, len); + break; - free_unlock: - vfree(newinfo); - goto unlock; -} + case IP6T_SO_SET_ADD_COUNTERS: + ret = do_add_counters(sock_net(sk), user, len, 1); + break; -void ip6t_unregister_table(struct ip6t_table *table) -{ - down(&ip6t_mutex); - LIST_DELETE(&ip6t_tables, table); - up(&ip6t_mutex); + default: + duprintf("do_ip6t_set_ctl: unknown request %i\n", cmd); + ret = -EINVAL; + } - /* Decrease module usage counts and free resources */ - IP6T_ENTRY_ITERATE(table->private->entries, table->private->size, - cleanup_entry, NULL); - vfree(table->private); + return ret; } -/* Returns 1 if the port is matched by the range, 0 otherwise */ -static inline int -port_match(u_int16_t min, u_int16_t max, u_int16_t port, int invert) +struct compat_ip6t_get_entries { + char name[XT_TABLE_MAXNAMELEN]; + compat_uint_t size; + struct compat_ip6t_entry entrytable[0]; +}; + +static int +compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, + void __user *userptr) { - int ret; + struct xt_counters *counters; + const struct xt_table_info *private = table->private; + void __user *pos; + unsigned int size; + int ret = 0; + const void *loc_cpu_entry; + unsigned int i = 0; + struct ip6t_entry *iter; + + counters = alloc_counters(table); + if (IS_ERR(counters)) + return PTR_ERR(counters); + + /* choose the copy that is on our node/cpu, ... + * This choice is lazy (because current thread is + * allowed to migrate to another cpu) + */ + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + pos = userptr; + size = total_size; + xt_entry_foreach(iter, loc_cpu_entry, total_size) { + ret = compat_copy_entry_to_user(iter, &pos, + &size, counters, i++); + if (ret != 0) + break; + } - ret = (port >= min && port <= max) ^ invert; + vfree(counters); return ret; } static int -tcp_find_option(u_int8_t option, - const struct sk_buff *skb, - unsigned int tcpoff, - unsigned int optlen, - int invert, - int *hotdrop) +compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, + int *len) { - /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ - u_int8_t _opt[60 - sizeof(struct tcphdr)], *op; - unsigned int i; + int ret; + struct compat_ip6t_get_entries get; + struct xt_table *t; - duprintf("tcp_match: finding option\n"); - if (!optlen) - return invert; - /* If we don't have the whole header, drop packet. */ - op = skb_header_pointer(skb, tcpoff + sizeof(struct tcphdr), optlen, - _opt); - if (op == NULL) { - *hotdrop = 1; - return 0; + if (*len < sizeof(get)) { + duprintf("compat_get_entries: %u < %zu\n", *len, sizeof(get)); + return -EINVAL; } - for (i = 0; i < optlen; ) { - if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; + if (copy_from_user(&get, uptr, sizeof(get)) != 0) + return -EFAULT; + + if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) { + duprintf("compat_get_entries: %u != %zu\n", + *len, sizeof(get) + get.size); + return -EINVAL; } - return invert; + xt_compat_lock(AF_INET6); + t = xt_find_table_lock(net, AF_INET6, get.name); + if (!IS_ERR_OR_NULL(t)) { + const struct xt_table_info *private = t->private; + struct xt_table_info info; + duprintf("t->private->number = %u\n", private->number); + ret = compat_table_info(private, &info); + if (!ret && get.size == info.size) { + ret = compat_copy_entries_to_user(private->size, + t, uptr->entrytable); + } else if (!ret) { + duprintf("compat_get_entries: I've got %u not %u!\n", + private->size, get.size); + ret = -EAGAIN; + } + xt_compat_flush_offsets(AF_INET6); + module_put(t->me); + xt_table_unlock(t); + } else + ret = t ? PTR_ERR(t) : -ENOENT; + + xt_compat_unlock(AF_INET6); + return ret; } +static int do_ip6t_get_ctl(struct sock *, int, void __user *, int *); + static int -tcp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +compat_do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { - struct tcphdr _tcph, *th; - const struct ip6t_tcp *tcpinfo = matchinfo; - - if (offset) { - /* To quote Alan: - - Don't allow a fragment of TCP 8 bytes in. Nobody normal - causes this. Its a cracker trying to break in by doing a - flag overwrite to pass the direction checks. - */ - if (offset == 1) { - duprintf("Dropping evil TCP offset=1 frag.\n"); - *hotdrop = 1; - } - /* Must not be a fragment. */ - return 0; - } + int ret; -#define FWINVTCP(bool,invflg) ((bool) ^ !!(tcpinfo->invflags & invflg)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; - th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph); - if (th == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil TCP offset=0 tinygram.\n"); - *hotdrop = 1; - return 0; - } - - if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1], - ntohs(th->source), - !!(tcpinfo->invflags & IP6T_TCP_INV_SRCPT))) - return 0; - if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1], - ntohs(th->dest), - !!(tcpinfo->invflags & IP6T_TCP_INV_DSTPT))) - return 0; - if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask) - == tcpinfo->flg_cmp, - IP6T_TCP_INV_FLAGS)) - return 0; - if (tcpinfo->option) { - if (th->doff * 4 < sizeof(_tcph)) { - *hotdrop = 1; - return 0; - } - if (!tcp_find_option(tcpinfo->option, skb, protoff, - th->doff*4 - sizeof(*th), - tcpinfo->invflags & IP6T_TCP_INV_OPTION, - hotdrop)) - return 0; + switch (cmd) { + case IP6T_SO_GET_INFO: + ret = get_info(sock_net(sk), user, len, 1); + break; + case IP6T_SO_GET_ENTRIES: + ret = compat_get_entries(sock_net(sk), user, len); + break; + default: + ret = do_ip6t_get_ctl(sk, cmd, user, len); } - return 1; + return ret; } +#endif -/* Called when user tries to insert an entry of this type. */ static int -tcp_checkentry(const char *tablename, - const struct ip6t_ip6 *ipv6, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) +do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { - const struct ip6t_tcp *tcpinfo = matchinfo; + int ret; + + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + switch (cmd) { + case IP6T_SO_SET_REPLACE: + ret = do_replace(sock_net(sk), user, len); + break; + + case IP6T_SO_SET_ADD_COUNTERS: + ret = do_add_counters(sock_net(sk), user, len, 0); + break; - /* Must specify proto == TCP, and no unknown invflags */ - return ipv6->proto == IPPROTO_TCP - && !(ipv6->invflags & IP6T_INV_PROTO) - && matchsize == IP6T_ALIGN(sizeof(struct ip6t_tcp)) - && !(tcpinfo->invflags & ~IP6T_TCP_INV_MASK); + default: + duprintf("do_ip6t_set_ctl: unknown request %i\n", cmd); + ret = -EINVAL; + } + + return ret; } static int -udp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { - struct udphdr _udph, *uh; - const struct ip6t_udp *udpinfo = matchinfo; + int ret; - /* Must not be a fragment. */ - if (offset) - return 0; + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; - uh = skb_header_pointer(skb, protoff, sizeof(_udph), &_udph); - if (uh == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil UDP tinygram.\n"); - *hotdrop = 1; - return 0; - } - - return port_match(udpinfo->spts[0], udpinfo->spts[1], - ntohs(uh->source), - !!(udpinfo->invflags & IP6T_UDP_INV_SRCPT)) - && port_match(udpinfo->dpts[0], udpinfo->dpts[1], - ntohs(uh->dest), - !!(udpinfo->invflags & IP6T_UDP_INV_DSTPT)); + switch (cmd) { + case IP6T_SO_GET_INFO: + ret = get_info(sock_net(sk), user, len, 0); + break; + + case IP6T_SO_GET_ENTRIES: + ret = get_entries(sock_net(sk), user, len); + break; + + case IP6T_SO_GET_REVISION_MATCH: + case IP6T_SO_GET_REVISION_TARGET: { + struct xt_get_revision rev; + int target; + + if (*len != sizeof(rev)) { + ret = -EINVAL; + break; + } + if (copy_from_user(&rev, user, sizeof(rev)) != 0) { + ret = -EFAULT; + break; + } + rev.name[sizeof(rev.name)-1] = 0; + + if (cmd == IP6T_SO_GET_REVISION_TARGET) + target = 1; + else + target = 0; + + try_then_request_module(xt_find_revision(AF_INET6, rev.name, + rev.revision, + target, &ret), + "ip6t_%s", rev.name); + break; + } + + default: + duprintf("do_ip6t_get_ctl: unknown request %i\n", cmd); + ret = -EINVAL; + } + + return ret; } -/* Called when user tries to insert an entry of this type. */ -static int -udp_checkentry(const char *tablename, - const struct ip6t_ip6 *ipv6, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) +struct xt_table *ip6t_register_table(struct net *net, + const struct xt_table *table, + const struct ip6t_replace *repl) { - const struct ip6t_udp *udpinfo = matchinfo; + int ret; + struct xt_table_info *newinfo; + struct xt_table_info bootstrap = {0}; + void *loc_cpu_entry; + struct xt_table *new_table; - /* Must specify proto == UDP, and no unknown invflags */ - if (ipv6->proto != IPPROTO_UDP || (ipv6->invflags & IP6T_INV_PROTO)) { - duprintf("ip6t_udp: Protocol %u != %u\n", ipv6->proto, - IPPROTO_UDP); - return 0; - } - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_udp))) { - duprintf("ip6t_udp: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_udp))); - return 0; + newinfo = xt_alloc_table_info(repl->size); + if (!newinfo) { + ret = -ENOMEM; + goto out; } - if (udpinfo->invflags & ~IP6T_UDP_INV_MASK) { - duprintf("ip6t_udp: unknown flags %X\n", - udpinfo->invflags); - return 0; + + /* choose the copy on our node/cpu, but dont care about preemption */ + loc_cpu_entry = newinfo->entries[raw_smp_processor_id()]; + memcpy(loc_cpu_entry, repl->entries, repl->size); + + ret = translate_table(net, newinfo, loc_cpu_entry, repl); + if (ret != 0) + goto out_free; + + new_table = xt_register_table(net, table, &bootstrap, newinfo); + if (IS_ERR(new_table)) { + ret = PTR_ERR(new_table); + goto out_free; } + return new_table; - return 1; +out_free: + xt_free_table_info(newinfo); +out: + return ERR_PTR(ret); +} + +void ip6t_unregister_table(struct net *net, struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct ip6t_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ -static inline int +static inline bool icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code, u_int8_t type, u_int8_t code, - int invert) + bool invert) { return (type == test_type && code >= min_code && code <= max_code) ^ invert; } -static int -icmp6_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static bool +icmp6_match(const struct sk_buff *skb, struct xt_action_param *par) { - struct icmp6hdr _icmp, *ic; - const struct ip6t_icmp *icmpinfo = matchinfo; + const struct icmp6hdr *ic; + struct icmp6hdr _icmph; + const struct ip6t_icmp *icmpinfo = par->matchinfo; /* Must not be a fragment. */ - if (offset) - return 0; + if (par->fragoff != 0) + return false; - ic = skb_header_pointer(skb, protoff, sizeof(_icmp), &_icmp); + ic = skb_header_pointer(skb, par->thoff, sizeof(_icmph), &_icmph); if (ic == NULL) { /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ + * can't. Hence, no choice but to drop. + */ duprintf("Dropping evil ICMP tinygram.\n"); - *hotdrop = 1; - return 0; + par->hotdrop = true; + return false; } return icmp6_type_code_match(icmpinfo->type, @@ -1838,30 +2166,32 @@ icmp6_match(const struct sk_buff *skb, } /* Called when user tries to insert an entry of this type. */ -static int -icmp6_checkentry(const char *tablename, - const struct ip6t_ip6 *ipv6, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) +static int icmp6_checkentry(const struct xt_mtchk_param *par) { - const struct ip6t_icmp *icmpinfo = matchinfo; + const struct ip6t_icmp *icmpinfo = par->matchinfo; - /* Must specify proto == ICMP, and no unknown invflags */ - return ipv6->proto == IPPROTO_ICMPV6 - && !(ipv6->invflags & IP6T_INV_PROTO) - && matchsize == IP6T_ALIGN(sizeof(struct ip6t_icmp)) - && !(icmpinfo->invflags & ~IP6T_ICMP_INV); + /* Must specify no unknown invflags */ + return (icmpinfo->invflags & ~IP6T_ICMP_INV) ? -EINVAL : 0; } /* The built-in targets: standard (NULL) and error. */ -static struct ip6t_target ip6t_standard_target = { - .name = IP6T_STANDARD_TARGET, -}; - -static struct ip6t_target ip6t_error_target = { - .name = IP6T_ERROR_TARGET, - .target = ip6t_error, +static struct xt_target ip6t_builtin_tg[] __read_mostly = { + { + .name = XT_STANDARD_TARGET, + .targetsize = sizeof(int), + .family = NFPROTO_IPV6, +#ifdef CONFIG_COMPAT + .compatsize = sizeof(compat_int_t), + .compat_from_user = compat_standard_from_user, + .compat_to_user = compat_standard_to_user, +#endif + }, + { + .name = XT_ERROR_TARGET, + .target = ip6t_error, + .targetsize = XT_FUNCTION_MAXNAMELEN, + .family = NFPROTO_IPV6, + }, }; static struct nf_sockopt_ops ip6t_sockopts = { @@ -1869,231 +2199,90 @@ static struct nf_sockopt_ops ip6t_sockopts = { .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, +#ifdef CONFIG_COMPAT + .compat_set = compat_do_ip6t_set_ctl, +#endif .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, +#ifdef CONFIG_COMPAT + .compat_get = compat_do_ip6t_get_ctl, +#endif + .owner = THIS_MODULE, }; -static struct ip6t_match tcp_matchstruct = { - .name = "tcp", - .match = &tcp_match, - .checkentry = &tcp_checkentry, -}; - -static struct ip6t_match udp_matchstruct = { - .name = "udp", - .match = &udp_match, - .checkentry = &udp_checkentry, -}; - -static struct ip6t_match icmp6_matchstruct = { - .name = "icmp6", - .match = &icmp6_match, - .checkentry = &icmp6_checkentry, +static struct xt_match ip6t_builtin_mt[] __read_mostly = { + { + .name = "icmp6", + .match = icmp6_match, + .matchsize = sizeof(struct ip6t_icmp), + .checkentry = icmp6_checkentry, + .proto = IPPROTO_ICMPV6, + .family = NFPROTO_IPV6, + }, }; -#ifdef CONFIG_PROC_FS -static inline int print_name(const char *i, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if ((*count)++ >= start_offset) { - unsigned int namelen; - - namelen = sprintf(buffer + *pos, "%s\n", - i + sizeof(struct list_head)); - if (*pos + namelen > length) { - /* Stop iterating */ - return 1; - } - *pos += namelen; - } - return 0; -} - -static inline int print_target(const struct ip6t_target *t, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) +static int __net_init ip6_tables_net_init(struct net *net) { - if (t == &ip6t_standard_target || t == &ip6t_error_target) - return 0; - return print_name((char *)t, start_offset, buffer, length, pos, count); + return xt_proto_init(net, NFPROTO_IPV6); } -static int ip6t_get_tables(char *buffer, char **start, off_t offset, int length) +static void __net_exit ip6_tables_net_exit(struct net *net) { - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return 0; - - LIST_FIND(&ip6t_tables, print_name, char *, - offset, buffer, length, &pos, &count); - - up(&ip6t_mutex); - - /* `start' hack - see fs/proc/generic.c line ~105 */ - *start=(char *)((unsigned long)count-offset); - return pos; + xt_proto_fini(net, NFPROTO_IPV6); } -static int ip6t_get_targets(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return 0; - - LIST_FIND(&ip6t_target, print_target, struct ip6t_target *, - offset, buffer, length, &pos, &count); - - up(&ip6t_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static int ip6t_get_matches(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return 0; - - LIST_FIND(&ip6t_match, print_name, char *, - offset, buffer, length, &pos, &count); - - up(&ip6t_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static struct { char *name; get_info_t *get_info; } ip6t_proc_entry[] = -{ { "ip6_tables_names", ip6t_get_tables }, - { "ip6_tables_targets", ip6t_get_targets }, - { "ip6_tables_matches", ip6t_get_matches }, - { NULL, NULL} }; -#endif /*CONFIG_PROC_FS*/ +static struct pernet_operations ip6_tables_net_ops = { + .init = ip6_tables_net_init, + .exit = ip6_tables_net_exit, +}; -static int __init init(void) +static int __init ip6_tables_init(void) { int ret; - /* Noone else will be downing sem now, so we won't sleep */ - down(&ip6t_mutex); - list_append(&ip6t_target, &ip6t_standard_target); - list_append(&ip6t_target, &ip6t_error_target); - list_append(&ip6t_match, &tcp_matchstruct); - list_append(&ip6t_match, &udp_matchstruct); - list_append(&ip6t_match, &icmp6_matchstruct); - up(&ip6t_mutex); + ret = register_pernet_subsys(&ip6_tables_net_ops); + if (ret < 0) + goto err1; + + /* No one else will be downing sem now, so we won't sleep */ + ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); + if (ret < 0) + goto err2; + ret = xt_register_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); + if (ret < 0) + goto err4; /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); - if (ret < 0) { - duprintf("Unable to register sockopts.\n"); - return ret; - } - -#ifdef CONFIG_PROC_FS - { - struct proc_dir_entry *proc; - int i; - - for (i = 0; ip6t_proc_entry[i].name; i++) { - proc = proc_net_create(ip6t_proc_entry[i].name, 0, - ip6t_proc_entry[i].get_info); - if (!proc) { - while (--i >= 0) - proc_net_remove(ip6t_proc_entry[i].name); - nf_unregister_sockopt(&ip6t_sockopts); - return -ENOMEM; - } - proc->owner = THIS_MODULE; - } - } -#endif + if (ret < 0) + goto err5; - printk("ip6_tables: (C) 2000-2002 Netfilter core team\n"); + pr_info("(C) 2000-2006 Netfilter Core Team\n"); return 0; -} -static void __exit fini(void) -{ - nf_unregister_sockopt(&ip6t_sockopts); -#ifdef CONFIG_PROC_FS - { - int i; - for (i = 0; ip6t_proc_entry[i].name; i++) - proc_net_remove(ip6t_proc_entry[i].name); - } -#endif +err5: + xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); +err4: + xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); +err2: + unregister_pernet_subsys(&ip6_tables_net_ops); +err1: + return ret; } -/* - * find specified header up to transport protocol header. - * If found target header, the offset to the header is set to *offset - * and return 0. otherwise, return -1. - * - * Notes: - non-1st Fragment Header isn't skipped. - * - ESP header isn't skipped. - * - The target header may be trancated. - */ -int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, u8 target) +static void __exit ip6_tables_fini(void) { - unsigned int start = (u8*)(skb->nh.ipv6h + 1) - skb->data; - u8 nexthdr = skb->nh.ipv6h->nexthdr; - unsigned int len = skb->len - start; - - while (nexthdr != target) { - struct ipv6_opt_hdr _hdr, *hp; - unsigned int hdrlen; - - if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) - return -1; - hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); - if (hp == NULL) - return -1; - if (nexthdr == NEXTHDR_FRAGMENT) { - unsigned short _frag_off, *fp; - fp = skb_header_pointer(skb, - start+offsetof(struct frag_hdr, - frag_off), - sizeof(_frag_off), - &_frag_off); - if (fp == NULL) - return -1; - - if (ntohs(*fp) & ~0x7) - return -1; - hdrlen = 8; - } else if (nexthdr == NEXTHDR_AUTH) - hdrlen = (hp->hdrlen + 2) << 2; - else - hdrlen = ipv6_optlen(hp); - - nexthdr = hp->nexthdr; - len -= hdrlen; - start += hdrlen; - } + nf_unregister_sockopt(&ip6t_sockopts); - *offset = start; - return 0; + xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); + xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); + unregister_pernet_subsys(&ip6_tables_net_ops); } EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ip6t_register_match); -EXPORT_SYMBOL(ip6t_unregister_match); -EXPORT_SYMBOL(ip6t_register_target); -EXPORT_SYMBOL(ip6t_unregister_target); -EXPORT_SYMBOL(ip6t_ext_hdr); -EXPORT_SYMBOL(ipv6_find_hdr); - -module_init(init); -module_exit(fini); + +module_init(ip6_tables_init); +module_exit(ip6_tables_fini); diff --git a/net/ipv6/netfilter/ip6t_HL.c b/net/ipv6/netfilter/ip6t_HL.c deleted file mode 100644 index 8f5549b7272..00000000000 --- a/net/ipv6/netfilter/ip6t_HL.c +++ /dev/null @@ -1,118 +0,0 @@ -/* - * Hop Limit modification target for ip6tables - * Maciej Soltysiak <solt@dns.toxicfilms.tv> - * Based on HW's TTL module - * - * This software is distributed under the terms of GNU GPL - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_HL.h> - -MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>"); -MODULE_DESCRIPTION("IP tables Hop Limit modification module"); -MODULE_LICENSE("GPL"); - -static unsigned int ip6t_hl_target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, void *userinfo) -{ - struct ipv6hdr *ip6h; - const struct ip6t_HL_info *info = targinfo; - u_int16_t diffs[2]; - int new_hl; - - if (!skb_make_writable(pskb, (*pskb)->len)) - return NF_DROP; - - ip6h = (*pskb)->nh.ipv6h; - - switch (info->mode) { - case IP6T_HL_SET: - new_hl = info->hop_limit; - break; - case IP6T_HL_INC: - new_hl = ip6h->hop_limit + info->hop_limit; - if (new_hl > 255) - new_hl = 255; - break; - case IP6T_HL_DEC: - new_hl = ip6h->hop_limit - info->hop_limit; - if (new_hl < 0) - new_hl = 0; - break; - default: - new_hl = ip6h->hop_limit; - break; - } - - if (new_hl != ip6h->hop_limit) { - diffs[0] = htons(((unsigned)ip6h->hop_limit) << 8) ^ 0xFFFF; - ip6h->hop_limit = new_hl; - diffs[1] = htons(((unsigned)ip6h->hop_limit) << 8); - } - - return IP6T_CONTINUE; -} - -static int ip6t_hl_checkentry(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - struct ip6t_HL_info *info = targinfo; - - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_HL_info))) { - printk(KERN_WARNING "ip6t_HL: targinfosize %u != %Zu\n", - targinfosize, - IP6T_ALIGN(sizeof(struct ip6t_HL_info))); - return 0; - } - - if (strcmp(tablename, "mangle")) { - printk(KERN_WARNING "ip6t_HL: can only be called from " - "\"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - - if (info->mode > IP6T_HL_MAXMODE) { - printk(KERN_WARNING "ip6t_HL: invalid or unknown Mode %u\n", - info->mode); - return 0; - } - - if ((info->mode != IP6T_HL_SET) && (info->hop_limit == 0)) { - printk(KERN_WARNING "ip6t_HL: increment/decrement doesn't " - "make sense with value 0\n"); - return 0; - } - - return 1; -} - -static struct ip6t_target ip6t_HL = { - .name = "HL", - .target = ip6t_hl_target, - .checkentry = ip6t_hl_checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - return ip6t_register_target(&ip6t_HL); -} - -static void __exit fini(void) -{ - ip6t_unregister_target(&ip6t_HL); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c deleted file mode 100644 index 0cd1d1bd903..00000000000 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ /dev/null @@ -1,507 +0,0 @@ -/* - * This is a module which is used for logging packets. - */ - -/* (C) 2001 Jan Rekorajski <baggins@pld.org.pl> - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <linux/spinlock.h> -#include <linux/icmpv6.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/ipv6.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); -MODULE_DESCRIPTION("IP6 tables LOG target module"); -MODULE_LICENSE("GPL"); - -struct in_device; -#include <net/route.h> -#include <linux/netfilter_ipv6/ip6t_LOG.h> - -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -/* Use lock to serialize, so printks don't overlap */ -static DEFINE_SPINLOCK(log_lock); - -/* One level of recursion won't kill us */ -static void dump_packet(const struct nf_loginfo *info, - const struct sk_buff *skb, unsigned int ip6hoff, - int recurse) -{ - u_int8_t currenthdr; - int fragment; - struct ipv6hdr _ip6h, *ih; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int logflags; - - if (info->type == NF_LOG_TYPE_LOG) - logflags = info->u.log.logflags; - else - logflags = NF_LOG_MASK; - - ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); - if (ih == NULL) { - printk("TRUNCATED"); - return; - } - - /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000" */ - printk("SRC=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", NIP6(ih->saddr)); - printk("DST=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", NIP6(ih->daddr)); - - /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ - printk("LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", - ntohs(ih->payload_len) + sizeof(struct ipv6hdr), - (ntohl(*(u_int32_t *)ih) & 0x0ff00000) >> 20, - ih->hop_limit, - (ntohl(*(u_int32_t *)ih) & 0x000fffff)); - - fragment = 0; - ptr = ip6hoff + sizeof(struct ipv6hdr); - currenthdr = ih->nexthdr; - while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { - struct ipv6_opt_hdr _hdr, *hp; - - hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); - if (hp == NULL) { - printk("TRUNCATED"); - return; - } - - /* Max length: 48 "OPT (...) " */ - if (logflags & IP6T_LOG_IPOPT) - printk("OPT ( "); - - switch (currenthdr) { - case IPPROTO_FRAGMENT: { - struct frag_hdr _fhdr, *fh; - - printk("FRAG:"); - fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), - &_fhdr); - if (fh == NULL) { - printk("TRUNCATED "); - return; - } - - /* Max length: 6 "65535 " */ - printk("%u ", ntohs(fh->frag_off) & 0xFFF8); - - /* Max length: 11 "INCOMPLETE " */ - if (fh->frag_off & htons(0x0001)) - printk("INCOMPLETE "); - - printk("ID:%08x ", ntohl(fh->identification)); - - if (ntohs(fh->frag_off) & 0xFFF8) - fragment = 1; - - hdrlen = 8; - - break; - } - case IPPROTO_DSTOPTS: - case IPPROTO_ROUTING: - case IPPROTO_HOPOPTS: - if (fragment) { - if (logflags & IP6T_LOG_IPOPT) - printk(")"); - return; - } - hdrlen = ipv6_optlen(hp); - break; - /* Max Length */ - case IPPROTO_AH: - if (logflags & IP6T_LOG_IPOPT) { - struct ip_auth_hdr _ahdr, *ah; - - /* Max length: 3 "AH " */ - printk("AH "); - - if (fragment) { - printk(")"); - return; - } - - ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), - &_ahdr); - if (ah == NULL) { - /* - * Max length: 26 "INCOMPLETE [65535 - * bytes] )" - */ - printk("INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 15 "SPI=0xF1234567 */ - printk("SPI=0x%x ", ntohl(ah->spi)); - - } - - hdrlen = (hp->hdrlen+2)<<2; - break; - case IPPROTO_ESP: - if (logflags & IP6T_LOG_IPOPT) { - struct ip_esp_hdr _esph, *eh; - - /* Max length: 4 "ESP " */ - printk("ESP "); - - if (fragment) { - printk(")"); - return; - } - - /* - * Max length: 26 "INCOMPLETE [65535 bytes] )" - */ - eh = skb_header_pointer(skb, ptr, sizeof(_esph), - &_esph); - if (eh == NULL) { - printk("INCOMPLETE [%u bytes] )", - skb->len - ptr); - return; - } - - /* Length: 16 "SPI=0xF1234567 )" */ - printk("SPI=0x%x )", ntohl(eh->spi) ); - - } - return; - default: - /* Max length: 20 "Unknown Ext Hdr 255" */ - printk("Unknown Ext Hdr %u", currenthdr); - return; - } - if (logflags & IP6T_LOG_IPOPT) - printk(") "); - - currenthdr = hp->nexthdr; - ptr += hdrlen; - } - - switch (currenthdr) { - case IPPROTO_TCP: { - struct tcphdr _tcph, *th; - - /* Max length: 10 "PROTO=TCP " */ - printk("PROTO=TCP "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, ptr, sizeof(_tcph), &_tcph); - if (th == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & IP6T_LOG_TCPSEQ) - printk("SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - /* Max length: 13 "WINDOW=65535 " */ - printk("WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3C " */ - printk("RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - printk("CWR "); - if (th->ece) - printk("ECE "); - if (th->urg) - printk("URG "); - if (th->ack) - printk("ACK "); - if (th->psh) - printk("PSH "); - if (th->rst) - printk("RST "); - if (th->syn) - printk("SYN "); - if (th->fin) - printk("FIN "); - /* Max length: 11 "URGP=65535 " */ - printk("URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & IP6T_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { - u_int8_t _opt[60 - sizeof(struct tcphdr)], *op; - unsigned int i; - unsigned int optsize = th->doff * 4 - - sizeof(struct tcphdr); - - op = skb_header_pointer(skb, - ptr + sizeof(struct tcphdr), - optsize, _opt); - if (op == NULL) { - printk("OPT (TRUNCATED)"); - return; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); - for (i =0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); - } - break; - } - case IPPROTO_UDP: { - struct udphdr _udph, *uh; - - /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, ptr, sizeof(_udph), &_udph); - if (uh == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), - ntohs(uh->len)); - break; - } - case IPPROTO_ICMPV6: { - struct icmp6hdr _icmp6h, *ic; - - /* Max length: 13 "PROTO=ICMPv6 " */ - printk("PROTO=ICMPv6 "); - - if (fragment) - break; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); - if (ic == NULL) { - printk("INCOMPLETE [%u bytes] ", skb->len - ptr); - return; - } - - /* Max length: 18 "TYPE=255 CODE=255 " */ - printk("TYPE=%u CODE=%u ", ic->icmp6_type, ic->icmp6_code); - - switch (ic->icmp6_type) { - case ICMPV6_ECHO_REQUEST: - case ICMPV6_ECHO_REPLY: - /* Max length: 19 "ID=65535 SEQ=65535 " */ - printk("ID=%u SEQ=%u ", - ntohs(ic->icmp6_identifier), - ntohs(ic->icmp6_sequence)); - break; - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - break; - - case ICMPV6_PARAMPROB: - /* Max length: 17 "POINTER=ffffffff " */ - printk("POINTER=%08x ", ntohl(ic->icmp6_pointer)); - /* Fall through */ - case ICMPV6_DEST_UNREACH: - case ICMPV6_PKT_TOOBIG: - case ICMPV6_TIME_EXCEED: - /* Max length: 3+maxlen */ - if (recurse) { - printk("["); - dump_packet(info, skb, ptr + sizeof(_icmp6h), - 0); - printk("] "); - } - - /* Max length: 10 "MTU=65535 " */ - if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) - printk("MTU=%u ", ntohl(ic->icmp6_mtu)); - } - break; - } - /* Max length: 10 "PROTO=255 " */ - default: - printk("PROTO=%u ", currenthdr); - } - - /* Max length: 15 "UID=4294967295 " */ - if ((logflags & IP6T_LOG_UID) && recurse && skb->sk) { - read_lock_bh(&skb->sk->sk_callback_lock); - if (skb->sk->sk_socket && skb->sk->sk_socket->file) - printk("UID=%u ", skb->sk->sk_socket->file->f_uid); - read_unlock_bh(&skb->sk->sk_callback_lock); - } -} - -static struct nf_loginfo default_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = 0, - .logflags = NF_LOG_MASK, - }, - }, -}; - -static void -ip6t_log_packet(unsigned int pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - if (!loginfo) - loginfo = &default_loginfo; - - spin_lock_bh(&log_lock); - printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, - prefix, - in ? in->name : "", - out ? out->name : ""); - if (in && !out) { - unsigned int len; - /* MAC logging for input chain only. */ - printk("MAC="); - if (skb->dev && (len = skb->dev->hard_header_len) && - skb->mac.raw != skb->nh.raw) { - unsigned char *p = skb->mac.raw; - int i; - - if (skb->dev->type == ARPHRD_SIT && - (p -= ETH_HLEN) < skb->head) - p = NULL; - - if (p != NULL) { - for (i = 0; i < len; i++) - printk("%02x%s", p[i], - i == len - 1 ? "" : ":"); - } - printk(" "); - - if (skb->dev->type == ARPHRD_SIT) { - struct iphdr *iph = (struct iphdr *)skb->mac.raw; - printk("TUNNEL=%u.%u.%u.%u->%u.%u.%u.%u ", - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); - } - } else - printk(" "); - } - - dump_packet(loginfo, skb, (u8*)skb->nh.ipv6h - skb->data, 1); - printk("\n"); - spin_unlock_bh(&log_lock); -} - -static unsigned int -ip6t_log_target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ip6t_log_info *loginfo = targinfo; - struct nf_loginfo li; - - li.type = NF_LOG_TYPE_LOG; - li.u.log.level = loginfo->level; - li.u.log.logflags = loginfo->logflags; - - nf_log_packet(PF_INET6, hooknum, *pskb, in, out, &li, loginfo->prefix); - - return IP6T_CONTINUE; -} - - -static int ip6t_log_checkentry(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - const struct ip6t_log_info *loginfo = targinfo; - - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_log_info))) { - DEBUGP("LOG: targinfosize %u != %u\n", - targinfosize, IP6T_ALIGN(sizeof(struct ip6t_log_info))); - return 0; - } - - if (loginfo->level >= 8) { - DEBUGP("LOG: level %u >= 8\n", loginfo->level); - return 0; - } - - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - DEBUGP("LOG: prefix term %i\n", - loginfo->prefix[sizeof(loginfo->prefix)-1]); - return 0; - } - - return 1; -} - -static struct ip6t_target ip6t_log_reg = { - .name = "LOG", - .target = ip6t_log_target, - .checkentry = ip6t_log_checkentry, - .me = THIS_MODULE, -}; - -static struct nf_logger ip6t_logger = { - .name = "ip6t_LOG", - .logfn = &ip6t_log_packet, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - if (ip6t_register_target(&ip6t_log_reg)) - return -EINVAL; - if (nf_log_register(PF_INET6, &ip6t_logger) < 0) { - printk(KERN_WARNING "ip6t_LOG: not logging via system console " - "since somebody else already registered for PF_INET6\n"); - /* we cannot make module load fail here, since otherwise - * ip6tables userspace would abort */ - } - - return 0; -} - -static void __exit fini(void) -{ - nf_log_unregister_logger(&ip6t_logger); - ip6t_unregister_target(&ip6t_log_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_MARK.c b/net/ipv6/netfilter/ip6t_MARK.c deleted file mode 100644 index 0c7584f9217..00000000000 --- a/net/ipv6/netfilter/ip6t_MARK.c +++ /dev/null @@ -1,81 +0,0 @@ -/* This is a module which is used for setting the NFMARK field of an skb. */ - -/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/checksum.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_MARK.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ip6t_mark_target_info *markinfo = targinfo; - - if((*pskb)->nfmark != markinfo->mark) - (*pskb)->nfmark = markinfo->mark; - - return IP6T_CONTINUE; -} - -static int -checkentry(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_mark_target_info))) { - printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", - targinfosize, - IP6T_ALIGN(sizeof(struct ip6t_mark_target_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - - return 1; -} - -static struct ip6t_target ip6t_mark_reg = { - .name = "MARK", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - printk(KERN_DEBUG "registering ipv6 mark target\n"); - if (ip6t_register_target(&ip6t_mark_reg)) - return -EINVAL; - - return 0; -} - -static void __exit fini(void) -{ - ip6t_unregister_target(&ip6t_mark_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c new file mode 100644 index 00000000000..3e4e92d5e15 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -0,0 +1,137 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * 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. + * + * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6 + * NAT funded by Astaro. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_nat.h> +#include <net/addrconf.h> +#include <net/ipv6.h> + +static unsigned int +masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct in6_addr src; + struct nf_conn *ct; + struct nf_nat_range newrange; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + if (ipv6_dev_get_saddr(dev_net(par->out), par->out, + &ipv6_hdr(skb)->daddr, 0, &src) < 0) + return NF_DROP; + + nfct_nat(ct)->masq_index = par->out->ifindex; + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = src; + newrange.max_addr.in6 = src; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); +} + +static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (range->flags & NF_NAT_RANGE_MAP_IPS) + return -EINVAL; + return 0; +} + +static int device_cmp(struct nf_conn *ct, void *ifindex) +{ + const struct nf_conn_nat *nat = nfct_nat(ct); + + if (!nat) + return 0; + if (nf_ct_l3num(ct) != NFPROTO_IPV6) + return 0; + return nat->masq_index == (int)(long)ifindex; +} + +static int masq_device_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + const struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + + if (event == NETDEV_DOWN) + nf_ct_iterate_cleanup(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); + + return NOTIFY_DONE; +} + +static struct notifier_block masq_dev_notifier = { + .notifier_call = masq_device_event, +}; + +static int masq_inet_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + struct netdev_notifier_info info; + + netdev_notifier_info_init(&info, ifa->idev->dev); + return masq_device_event(this, event, &info); +} + +static struct notifier_block masq_inet_notifier = { + .notifier_call = masq_inet_event, +}; + +static struct xt_target masquerade_tg6_reg __read_mostly = { + .name = "MASQUERADE", + .family = NFPROTO_IPV6, + .checkentry = masquerade_tg6_checkentry, + .target = masquerade_tg6, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = 1 << NF_INET_POST_ROUTING, + .me = THIS_MODULE, +}; + +static int __init masquerade_tg6_init(void) +{ + int err; + + err = xt_register_target(&masquerade_tg6_reg); + if (err == 0) { + register_netdevice_notifier(&masq_dev_notifier); + register_inet6addr_notifier(&masq_inet_notifier); + } + + return err; +} +static void __exit masquerade_tg6_exit(void) +{ + unregister_inet6addr_notifier(&masq_inet_notifier); + unregister_netdevice_notifier(&masq_dev_notifier); + xt_unregister_target(&masquerade_tg6_reg); +} + +module_init(masquerade_tg6_init); +module_exit(masquerade_tg6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Xtables: automatic address SNAT"); diff --git a/net/ipv6/netfilter/ip6t_NFQUEUE.c b/net/ipv6/netfilter/ip6t_NFQUEUE.c deleted file mode 100644 index c6e3730e740..00000000000 --- a/net/ipv6/netfilter/ip6t_NFQUEUE.c +++ /dev/null @@ -1,70 +0,0 @@ -/* ip6tables module for using new netfilter netlink queue - * - * (C) 2005 by Harald Welte <laforge@netfilter.org> - * - * 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. - * - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter.h> -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv4/ipt_NFQUEUE.h> - -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("ip6tables NFQUEUE target"); -MODULE_LICENSE("GPL"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_NFQ_info *tinfo = targinfo; - - return NF_QUEUE_NR(tinfo->queuenum); -} - -static int -checkentry(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IP6T_ALIGN(sizeof(struct ipt_NFQ_info))) { - printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", - targinfosize, - IP6T_ALIGN(sizeof(struct ipt_NFQ_info))); - return 0; - } - - return 1; -} - -static struct ip6t_target ipt_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_target(&ipt_NFQ_reg); -} - -static void __exit fini(void) -{ - ip6t_unregister_target(&ipt_NFQ_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c new file mode 100644 index 00000000000..590f767db5d --- /dev/null +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -0,0 +1,153 @@ +/* + * Copyright (c) 2011, 2012 Patrick McHardy <kaber@trash.net> + * + * 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. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6t_NPT.h> +#include <linux/netfilter/x_tables.h> + +static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) +{ + struct ip6t_npt_tginfo *npt = par->targinfo; + struct in6_addr pfx; + __wsum src_sum, dst_sum; + + if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) + return -EINVAL; + + /* Ensure that LSB of prefix is zero */ + ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6)) + return -EINVAL; + ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6)) + return -EINVAL; + + src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0); + dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0); + + npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum)); + return 0; +} + +static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, + struct in6_addr *addr) +{ + unsigned int pfx_len; + unsigned int i, idx; + __be32 mask; + __sum16 sum; + + pfx_len = max(npt->src_pfx_len, npt->dst_pfx_len); + for (i = 0; i < pfx_len; i += 32) { + if (pfx_len - i >= 32) + mask = 0; + else + mask = htonl((1 << (i - pfx_len + 32)) - 1); + + idx = i / 32; + addr->s6_addr32[idx] &= mask; + addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx]; + } + + if (pfx_len <= 48) + idx = 3; + else { + for (idx = 4; idx < ARRAY_SIZE(addr->s6_addr16); idx++) { + if ((__force __sum16)addr->s6_addr16[idx] != + CSUM_MANGLED_0) + break; + } + if (idx == ARRAY_SIZE(addr->s6_addr16)) + return false; + } + + sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]), + csum_unfold(npt->adjustment))); + if (sum == CSUM_MANGLED_0) + sum = 0; + *(__force __sum16 *)&addr->s6_addr16[idx] = sum; + + return true; +} + +static unsigned int +ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_npt_tginfo *npt = par->targinfo; + + if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) { + icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, + offsetof(struct ipv6hdr, saddr)); + return NF_DROP; + } + return XT_CONTINUE; +} + +static unsigned int +ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_npt_tginfo *npt = par->targinfo; + + if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) { + icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, + offsetof(struct ipv6hdr, daddr)); + return NF_DROP; + } + return XT_CONTINUE; +} + +static struct xt_target ip6t_npt_target_reg[] __read_mostly = { + { + .name = "SNPT", + .table = "mangle", + .target = ip6t_snpt_tg, + .targetsize = sizeof(struct ip6t_npt_tginfo), + .checkentry = ip6t_npt_checkentry, + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_POST_ROUTING), + .me = THIS_MODULE, + }, + { + .name = "DNPT", + .table = "mangle", + .target = ip6t_dnpt_tg, + .targetsize = sizeof(struct ip6t_npt_tginfo), + .checkentry = ip6t_npt_checkentry, + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, +}; + +static int __init ip6t_npt_init(void) +{ + return xt_register_targets(ip6t_npt_target_reg, + ARRAY_SIZE(ip6t_npt_target_reg)); +} + +static void __exit ip6t_npt_exit(void) +{ + xt_unregister_targets(ip6t_npt_target_reg, + ARRAY_SIZE(ip6t_npt_target_reg)); +} + +module_init(ip6t_npt_init); +module_exit(ip6t_npt_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IPv6-to-IPv6 Network Prefix Translation (RFC 6296)"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS("ip6t_SNPT"); +MODULE_ALIAS("ip6t_DNPT"); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index b03e87adca9..544b0a9da1b 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -7,6 +7,8 @@ * Authors: * Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> * + * Copyright (c) 2005-2007 Patrick McHardy <kaber@trash.net> + * * Based on net/ipv4/netfilter/ipt_REJECT.c * * This program is free software; you can redistribute it and/or @@ -14,268 +16,103 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/config.h> +#include <linux/gfp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <linux/netdevice.h> -#include <net/ipv6.h> -#include <net/tcp.h> #include <net/icmp.h> -#include <net/ip6_checksum.h> -#include <net/ip6_fib.h> -#include <net/ip6_route.h> #include <net/flow.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_REJECT.h> +#include <net/netfilter/ipv6/nf_reject.h> + MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>"); -MODULE_DESCRIPTION("IP6 tables REJECT target module"); +MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); MODULE_LICENSE("GPL"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -/* Send RST reply */ -static void send_reset(struct sk_buff *oldskb) -{ - struct sk_buff *nskb; - struct tcphdr otcph, *tcph; - unsigned int otcplen, hh_len; - int tcphoff, needs_ack; - struct ipv6hdr *oip6h = oldskb->nh.ipv6h, *ip6h; - struct dst_entry *dst = NULL; - u8 proto; - struct flowi fl; - - if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || - (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) { - DEBUGP("ip6t_REJECT: addr is not unicast.\n"); - return; - } - - proto = oip6h->nexthdr; - tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto); - - if ((tcphoff < 0) || (tcphoff > oldskb->len)) { - DEBUGP("ip6t_REJECT: Can't get TCP header.\n"); - return; - } - - otcplen = oldskb->len - tcphoff; - - /* IP header checks: fragment, too short. */ - if ((proto != IPPROTO_TCP) || (otcplen < sizeof(struct tcphdr))) { - DEBUGP("ip6t_REJECT: proto(%d) != IPPROTO_TCP, or too short. otcplen = %d\n", - proto, otcplen); - return; - } - - if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr))) - BUG(); - - /* No RST for RST. */ - if (otcph.rst) { - DEBUGP("ip6t_REJECT: RST is set\n"); - return; - } - - /* Check checksum. */ - if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP, - skb_checksum(oldskb, tcphoff, otcplen, 0))) { - DEBUGP("ip6t_REJECT: TCP checksum is invalid\n"); - return; - } - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr); - ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr); - fl.fl_ip_sport = otcph.dest; - fl.fl_ip_dport = otcph.source; - dst = ip6_route_output(NULL, &fl); - if (dst == NULL) - return; - if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0)) - return; - - hh_len = (dst->dev->hard_header_len + 15)&~15; - nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr) - + sizeof(struct tcphdr) + dst->trailer_len, - GFP_ATOMIC); - - if (!nskb) { - if (net_ratelimit()) - printk("ip6t_REJECT: Can't alloc skb\n"); - dst_release(dst); - return; - } - - nskb->dst = dst; - - skb_reserve(nskb, hh_len + dst->header_len); - - ip6h = nskb->nh.ipv6h = (struct ipv6hdr *) - skb_put(nskb, sizeof(struct ipv6hdr)); - ip6h->version = 6; - ip6h->hop_limit = dst_metric(dst, RTAX_HOPLIMIT); - ip6h->nexthdr = IPPROTO_TCP; - ip6h->payload_len = htons(sizeof(struct tcphdr)); - ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); - ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr); - - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); - /* Truncate to length (no data) */ - tcph->doff = sizeof(struct tcphdr)/4; - tcph->source = otcph.dest; - tcph->dest = otcph.source; - if (otcph.ack) { - needs_ack = 0; - tcph->seq = otcph.ack_seq; - tcph->ack_seq = 0; - } else { - needs_ack = 1; - tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin - + otcplen - (otcph.doff<<2)); - tcph->seq = 0; - } - - /* Reset flags */ - ((u_int8_t *)tcph)[13] = 0; - tcph->rst = 1; - tcph->ack = needs_ack; - tcph->window = 0; - tcph->urg_ptr = 0; - tcph->check = 0; - - /* Adjust TCP checksum */ - tcph->check = csum_ipv6_magic(&nskb->nh.ipv6h->saddr, - &nskb->nh.ipv6h->daddr, - sizeof(struct tcphdr), IPPROTO_TCP, - csum_partial((char *)tcph, - sizeof(struct tcphdr), 0)); - - NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, nskb, NULL, nskb->dst->dev, - dst_output); -} - -static inline void -send_unreach(struct sk_buff *skb_in, unsigned char code, unsigned int hooknum) +static unsigned int +reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) { - if (hooknum == NF_IP6_LOCAL_OUT && skb_in->dev == NULL) - skb_in->dev = &loopback_dev; + const struct ip6t_reject_info *reject = par->targinfo; + struct net *net = dev_net((par->in != NULL) ? par->in : par->out); - icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0, NULL); -} - -static unsigned int reject6_target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ip6t_reject_info *reject = targinfo; - - DEBUGP(KERN_DEBUG "%s: medium point\n", __FUNCTION__); - /* WARNING: This code causes reentry within ip6tables. - This means that the ip6tables jump stack is now crap. We - must return an absolute verdict. --RR */ - switch (reject->with) { - case IP6T_ICMP6_NO_ROUTE: - send_unreach(*pskb, ICMPV6_NOROUTE, hooknum); - break; - case IP6T_ICMP6_ADM_PROHIBITED: - send_unreach(*pskb, ICMPV6_ADM_PROHIBITED, hooknum); - break; - case IP6T_ICMP6_NOT_NEIGHBOUR: - send_unreach(*pskb, ICMPV6_NOT_NEIGHBOUR, hooknum); - break; - case IP6T_ICMP6_ADDR_UNREACH: - send_unreach(*pskb, ICMPV6_ADDR_UNREACH, hooknum); - break; - case IP6T_ICMP6_PORT_UNREACH: - send_unreach(*pskb, ICMPV6_PORT_UNREACH, hooknum); - break; - case IP6T_ICMP6_ECHOREPLY: + pr_debug("%s: medium point\n", __func__); + switch (reject->with) { + case IP6T_ICMP6_NO_ROUTE: + nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum); + break; + case IP6T_ICMP6_ADM_PROHIBITED: + nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum); + break; + case IP6T_ICMP6_NOT_NEIGHBOUR: + nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum); + break; + case IP6T_ICMP6_ADDR_UNREACH: + nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum); + break; + case IP6T_ICMP6_PORT_UNREACH: + nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, par->hooknum); + break; + case IP6T_ICMP6_ECHOREPLY: /* Do nothing */ break; case IP6T_TCP_RESET: - send_reset(*pskb); + nf_send_reset6(net, skb, par->hooknum); break; default: - if (net_ratelimit()) - printk(KERN_WARNING "ip6t_REJECT: case %u not handled yet\n", reject->with); + net_info_ratelimited("case %u not handled yet\n", reject->with); break; } return NF_DROP; } -static int check(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) +static int reject_tg6_check(const struct xt_tgchk_param *par) { - const struct ip6t_reject_info *rejinfo = targinfo; - - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_reject_info))) { - DEBUGP("ip6t_REJECT: targinfosize %u != 0\n", targinfosize); - return 0; - } - - /* Only allow these for packet filtering. */ - if (strcmp(tablename, "filter") != 0) { - DEBUGP("ip6t_REJECT: bad table `%s'.\n", tablename); - return 0; - } - - if ((hook_mask & ~((1 << NF_IP6_LOCAL_IN) - | (1 << NF_IP6_FORWARD) - | (1 << NF_IP6_LOCAL_OUT))) != 0) { - DEBUGP("ip6t_REJECT: bad hook mask %X\n", hook_mask); - return 0; - } + const struct ip6t_reject_info *rejinfo = par->targinfo; + const struct ip6t_entry *e = par->entryinfo; if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { - printk("ip6t_REJECT: ECHOREPLY is not supported.\n"); - return 0; + pr_info("ECHOREPLY is not supported.\n"); + return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP - || (e->ipv6.invflags & IP6T_INV_PROTO)) { - DEBUGP("ip6t_REJECT: TCP_RESET illegal for non-tcp\n"); - return 0; + if (e->ipv6.proto != IPPROTO_TCP || + (e->ipv6.invflags & XT_INV_PROTO)) { + pr_info("TCP_RESET illegal for non-tcp\n"); + return -EINVAL; } } - - return 1; + return 0; } -static struct ip6t_target ip6t_reject_reg = { +static struct xt_target reject_tg6_reg __read_mostly = { .name = "REJECT", - .target = reject6_target, - .checkentry = check, + .family = NFPROTO_IPV6, + .target = reject_tg6, + .targetsize = sizeof(struct ip6t_reject_info), + .table = "filter", + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT), + .checkentry = reject_tg6_check, .me = THIS_MODULE }; -static int __init init(void) +static int __init reject_tg6_init(void) { - if (ip6t_register_target(&ip6t_reject_reg)) - return -EINVAL; - return 0; + return xt_register_target(&reject_tg6_reg); } -static void __exit fini(void) +static void __exit reject_tg6_exit(void) { - ip6t_unregister_target(&ip6t_reject_reg); + xt_unregister_target(&reject_tg6_reg); } -module_init(init); -module_exit(fini); +module_init(reject_tg6_init); +module_exit(reject_tg6_exit); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c new file mode 100644 index 00000000000..a0d17270117 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -0,0 +1,505 @@ +/* + * Copyright (c) 2013 Patrick McHardy <kaber@trash.net> + * + * 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. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/ip6_checksum.h> +#include <net/ip6_route.h> +#include <net/tcp.h> + +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_SYNPROXY.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/nf_conntrack_synproxy.h> + +static struct ipv6hdr * +synproxy_build_ip(struct sk_buff *skb, const struct in6_addr *saddr, + const struct in6_addr *daddr) +{ + struct ipv6hdr *iph; + + skb_reset_network_header(skb); + iph = (struct ipv6hdr *)skb_put(skb, sizeof(*iph)); + ip6_flow_hdr(iph, 0, 0); + iph->hop_limit = 64; //XXX + iph->nexthdr = IPPROTO_TCP; + iph->saddr = *saddr; + iph->daddr = *daddr; + + return iph; +} + +static void +synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, + struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, + struct ipv6hdr *niph, struct tcphdr *nth, + unsigned int tcp_hdr_size) +{ + struct net *net = nf_ct_net((struct nf_conn *)nfct); + struct dst_entry *dst; + struct flowi6 fl6; + + nth->check = ~tcp_v6_check(tcp_hdr_size, &niph->saddr, &niph->daddr, 0); + nskb->ip_summed = CHECKSUM_PARTIAL; + nskb->csum_start = (unsigned char *)nth - nskb->head; + nskb->csum_offset = offsetof(struct tcphdr, check); + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.saddr = niph->saddr; + fl6.daddr = niph->daddr; + fl6.fl6_sport = nth->source; + fl6.fl6_dport = nth->dest; + security_skb_classify_flow((struct sk_buff *)skb, flowi6_to_flowi(&fl6)); + dst = ip6_route_output(net, NULL, &fl6); + if (dst == NULL || dst->error) { + dst_release(dst); + goto free_nskb; + } + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) + goto free_nskb; + + skb_dst_set(nskb, dst); + + if (nfct) { + nskb->nfct = nfct; + nskb->nfctinfo = ctinfo; + nf_conntrack_get(nfct); + } + + ip6_local_out(nskb); + return; + +free_nskb: + kfree_skb(nskb); +} + +static void +synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + u16 mss = opts->mss; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->daddr, &iph->saddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->dest; + nth->dest = th->source; + nth->seq = htonl(__cookie_v6_init_sequence(iph, th, &mss)); + nth->ack_seq = htonl(ntohl(th->seq) + 1); + tcp_flag_word(nth) = TCP_FLAG_SYN | TCP_FLAG_ACK; + if (opts->options & XT_SYNPROXY_OPT_ECN) + tcp_flag_word(nth) |= TCP_FLAG_ECE; + nth->doff = tcp_hdr_size / 4; + nth->window = 0; + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_server_syn(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts, u32 recv_seq) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->saddr, &iph->daddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->source; + nth->dest = th->dest; + nth->seq = htonl(recv_seq - 1); + /* ack_seq is used to relay our ISN to the synproxy hook to initialize + * sequence number translation once a connection tracking entry exists. + */ + nth->ack_seq = htonl(ntohl(th->ack_seq) - 1); + tcp_flag_word(nth) = TCP_FLAG_SYN; + if (opts->options & XT_SYNPROXY_OPT_ECN) + tcp_flag_word(nth) |= TCP_FLAG_ECE | TCP_FLAG_CWR; + nth->doff = tcp_hdr_size / 4; + nth->window = th->window; + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_server_ack(const struct synproxy_net *snet, + const struct ip_ct_tcp *state, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->daddr, &iph->saddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->dest; + nth->dest = th->source; + nth->seq = htonl(ntohl(th->ack_seq)); + nth->ack_seq = htonl(ntohl(th->seq) + 1); + tcp_flag_word(nth) = TCP_FLAG_ACK; + nth->doff = tcp_hdr_size / 4; + nth->window = htons(state->seen[IP_CT_DIR_ORIGINAL].td_maxwin); + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); +} + +static void +synproxy_send_client_ack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + const struct synproxy_options *opts) +{ + struct sk_buff *nskb; + struct ipv6hdr *iph, *niph; + struct tcphdr *nth; + unsigned int tcp_hdr_size; + + iph = ipv6_hdr(skb); + + tcp_hdr_size = sizeof(*nth) + synproxy_options_size(opts); + nskb = alloc_skb(sizeof(*niph) + tcp_hdr_size + MAX_TCP_HEADER, + GFP_ATOMIC); + if (nskb == NULL) + return; + skb_reserve(nskb, MAX_TCP_HEADER); + + niph = synproxy_build_ip(nskb, &iph->saddr, &iph->daddr); + + skb_reset_transport_header(nskb); + nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth->source = th->source; + nth->dest = th->dest; + nth->seq = htonl(ntohl(th->seq) + 1); + nth->ack_seq = th->ack_seq; + tcp_flag_word(nth) = TCP_FLAG_ACK; + nth->doff = tcp_hdr_size / 4; + nth->window = ntohs(htons(th->window) >> opts->wscale); + nth->check = 0; + nth->urg_ptr = 0; + + synproxy_build_options(nth, opts); + + synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); +} + +static bool +synproxy_recv_client_ack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, + struct synproxy_options *opts, u32 recv_seq) +{ + int mss; + + mss = __cookie_v6_check(ipv6_hdr(skb), th, ntohl(th->ack_seq) - 1); + if (mss == 0) { + this_cpu_inc(snet->stats->cookie_invalid); + return false; + } + + this_cpu_inc(snet->stats->cookie_valid); + opts->mss = mss; + opts->options |= XT_SYNPROXY_OPT_MSS; + + if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_check_timestamp_cookie(opts); + + synproxy_send_server_syn(snet, skb, th, opts, recv_seq); + return true; +} + +static unsigned int +synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_synproxy_info *info = par->targinfo; + struct synproxy_net *snet = synproxy_pernet(dev_net(par->in)); + struct synproxy_options opts = {}; + struct tcphdr *th, _th; + + if (nf_ip6_checksum(skb, par->hooknum, par->thoff, IPPROTO_TCP)) + return NF_DROP; + + th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; + + if (th->syn && !(th->ack || th->fin || th->rst)) { + /* Initial SYN from client */ + this_cpu_inc(snet->stats->syn_received); + + if (th->ece && th->cwr) + opts.options |= XT_SYNPROXY_OPT_ECN; + + opts.options &= info->options; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_init_timestamp_cookie(info, &opts); + else + opts.options &= ~(XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM | + XT_SYNPROXY_OPT_ECN); + + synproxy_send_client_synack(skb, th, &opts); + return NF_DROP; + + } else if (th->ack && !(th->fin || th->rst || th->syn)) { + /* ACK from client */ + synproxy_recv_client_ack(snet, skb, th, &opts, ntohl(th->seq)); + return NF_DROP; + } + + return XT_CONTINUE; +} + +static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct synproxy_net *snet = synproxy_pernet(dev_net(in ? : out)); + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + struct nf_conn_synproxy *synproxy; + struct synproxy_options opts = {}; + const struct ip_ct_tcp *state; + struct tcphdr *th, _th; + __be16 frag_off; + u8 nexthdr; + int thoff; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return NF_ACCEPT; + + synproxy = nfct_synproxy(ct); + if (synproxy == NULL) + return NF_ACCEPT; + + if (nf_is_loopback_packet(skb)) + return NF_ACCEPT; + + nexthdr = ipv6_hdr(skb)->nexthdr; + thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (thoff < 0) + return NF_ACCEPT; + + th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + state = &ct->proto.tcp; + switch (state->state) { + case TCP_CONNTRACK_CLOSE: + if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - + ntohl(th->seq) + 1); + break; + } + + if (!th->syn || th->ack || + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) + break; + + /* Reopened connection - reset the sequence number and timestamp + * adjustments, they will get initialized once the connection is + * reestablished. + */ + nf_ct_seqadj_init(ct, ctinfo, 0); + synproxy->tsoff = 0; + this_cpu_inc(snet->stats->conn_reopened); + + /* fall through */ + case TCP_CONNTRACK_SYN_SENT: + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + + if (!th->syn && th->ack && + CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + /* Keep-Alives are sent with SEG.SEQ = SND.NXT-1, + * therefore we need to add 1 to make the SYN sequence + * number match the one of first SYN. + */ + if (synproxy_recv_client_ack(snet, skb, th, &opts, + ntohl(th->seq) + 1)) + this_cpu_inc(snet->stats->cookie_retrans); + + return NF_DROP; + } + + synproxy->isn = ntohl(th->ack_seq); + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy->its = opts.tsecr; + break; + case TCP_CONNTRACK_SYN_RECV: + if (!th->syn || !th->ack) + break; + + if (!synproxy_parse_options(skb, thoff, th, &opts)) + return NF_DROP; + + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy->tsoff = opts.tsval - synproxy->its; + + opts.options &= ~(XT_SYNPROXY_OPT_MSS | + XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM); + + swap(opts.tsval, opts.tsecr); + synproxy_send_server_ack(snet, state, skb, th, &opts); + + nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); + + swap(opts.tsval, opts.tsecr); + synproxy_send_client_ack(snet, skb, th, &opts); + + consume_skb(skb); + return NF_STOLEN; + default: + break; + } + + synproxy_tstamp_adjust(skb, thoff, th, ct, ctinfo, synproxy); + return NF_ACCEPT; +} + +static int synproxy_tg6_check(const struct xt_tgchk_param *par) +{ + const struct ip6t_entry *e = par->entryinfo; + + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || + e->ipv6.invflags & XT_INV_PROTO) + return -EINVAL; + + return nf_ct_l3proto_try_module_get(par->family); +} + +static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par) +{ + nf_ct_l3proto_module_put(par->family); +} + +static struct xt_target synproxy_tg6_reg __read_mostly = { + .name = "SYNPROXY", + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), + .target = synproxy_tg6, + .targetsize = sizeof(struct xt_synproxy_info), + .checkentry = synproxy_tg6_check, + .destroy = synproxy_tg6_destroy, + .me = THIS_MODULE, +}; + +static struct nf_hook_ops ipv6_synproxy_ops[] __read_mostly = { + { + .hook = ipv6_synproxy_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, + }, + { + .hook = ipv6_synproxy_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM - 1, + }, +}; + +static int __init synproxy_tg6_init(void) +{ + int err; + + err = nf_register_hooks(ipv6_synproxy_ops, + ARRAY_SIZE(ipv6_synproxy_ops)); + if (err < 0) + goto err1; + + err = xt_register_target(&synproxy_tg6_reg); + if (err < 0) + goto err2; + + return 0; + +err2: + nf_unregister_hooks(ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); +err1: + return err; +} + +static void __exit synproxy_tg6_exit(void) +{ + xt_unregister_target(&synproxy_tg6_reg); + nf_unregister_hooks(ipv6_synproxy_ops, ARRAY_SIZE(ipv6_synproxy_ops)); +} + +module_init(synproxy_tg6_init); +module_exit(synproxy_tg6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index dde37793d20..04099ab7d2e 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -6,132 +6,116 @@ * 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/ip.h> #include <linux/ipv6.h> #include <linux/types.h> #include <net/checksum.h> #include <net/ipv6.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_ah.h> MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("IPv6 AH match"); +MODULE_DESCRIPTION("Xtables: IPv6 IPsec-AH match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* Returns 1 if the spi is matched by the range, 0 otherwise */ -static inline int -spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, int invert) +static inline bool +spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) { - int r=0; - DEBUGP("ah spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ', - min,spi,max); + bool r; + + pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", + invert ? '!' : ' ', min, spi, max); r = (spi >= min && spi <= max) ^ invert; - DEBUGP(" result %s\n",r? "PASS\n" : "FAILED\n"); + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); return r; } -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) { - struct ip_auth_hdr *ah, _ah; - const struct ip6t_ah *ahinfo = matchinfo; - unsigned int ptr; + struct ip_auth_hdr _ah; + const struct ip_auth_hdr *ah; + const struct ip6t_ah *ahinfo = par->matchinfo; + unsigned int ptr = 0; unsigned int hdrlen = 0; + int err; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH) < 0) - return 0; + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah); if (ah == NULL) { - *hotdrop = 1; - return 0; + par->hotdrop = true; + return false; } hdrlen = (ah->hdrlen + 2) << 2; - DEBUGP("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen); - DEBUGP("RES %04X ", ah->reserved); - DEBUGP("SPI %u %08X\n", ntohl(ah->spi), ntohl(ah->spi)); - - DEBUGP("IPv6 AH spi %02X ", - (spi_match(ahinfo->spis[0], ahinfo->spis[1], - ntohl(ah->spi), - !!(ahinfo->invflags & IP6T_AH_INV_SPI)))); - DEBUGP("len %02X %04X %02X ", - ahinfo->hdrlen, hdrlen, - (!ahinfo->hdrlen || - (ahinfo->hdrlen == hdrlen) ^ - !!(ahinfo->invflags & IP6T_AH_INV_LEN))); - DEBUGP("res %02X %04X %02X\n", - ahinfo->hdrres, ah->reserved, - !(ahinfo->hdrres && ah->reserved)); - - return (ah != NULL) - && - (spi_match(ahinfo->spis[0], ahinfo->spis[1], - ntohl(ah->spi), - !!(ahinfo->invflags & IP6T_AH_INV_SPI))) - && - (!ahinfo->hdrlen || - (ahinfo->hdrlen == hdrlen) ^ - !!(ahinfo->invflags & IP6T_AH_INV_LEN)) - && - !(ahinfo->hdrres && ah->reserved); + pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen); + pr_debug("RES %04X ", ah->reserved); + pr_debug("SPI %u %08X\n", ntohl(ah->spi), ntohl(ah->spi)); + + pr_debug("IPv6 AH spi %02X ", + spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI))); + pr_debug("len %02X %04X %02X ", + ahinfo->hdrlen, hdrlen, + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN))); + pr_debug("res %02X %04X %02X\n", + ahinfo->hdrres, ah->reserved, + !(ahinfo->hdrres && ah->reserved)); + + return (ah != NULL) && + spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN)) && + !(ahinfo->hdrres && ah->reserved); } -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) +static int ah_mt6_check(const struct xt_mtchk_param *par) { - const struct ip6t_ah *ahinfo = matchinfo; + const struct ip6t_ah *ahinfo = par->matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_ah))) { - DEBUGP("ip6t_ah: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_ah))); - return 0; - } if (ahinfo->invflags & ~IP6T_AH_INV_MASK) { - DEBUGP("ip6t_ah: unknown flags %X\n", ahinfo->invflags); - return 0; + pr_debug("unknown flags %X\n", ahinfo->invflags); + return -EINVAL; } - return 1; + return 0; } -static struct ip6t_match ah_match = { +static struct xt_match ah_mt6_reg __read_mostly = { .name = "ah", - .match = &match, - .checkentry = &checkentry, + .family = NFPROTO_IPV6, + .match = ah_mt6, + .matchsize = sizeof(struct ip6t_ah), + .checkentry = ah_mt6_check, .me = THIS_MODULE, }; -static int __init init(void) +static int __init ah_mt6_init(void) { - return ip6t_register_match(&ah_match); + return xt_register_match(&ah_mt6_reg); } -static void __exit cleanup(void) +static void __exit ah_mt6_exit(void) { - ip6t_unregister_match(&ah_match); + xt_unregister_match(&ah_mt6_reg); } -module_init(init); -module_exit(cleanup); +module_init(ah_mt6_init); +module_exit(ah_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_dst.c b/net/ipv6/netfilter/ip6t_dst.c deleted file mode 100644 index c450a635e54..00000000000 --- a/net/ipv6/netfilter/ip6t_dst.c +++ /dev/null @@ -1,224 +0,0 @@ -/* Kernel module to match Hop-by-Hop and Destination parameters. */ - -/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ipv6.h> -#include <linux/types.h> -#include <net/checksum.h> -#include <net/ipv6.h> - -#include <asm/byteorder.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_opts.h> - -#define HOPBYHOP 0 - -MODULE_LICENSE("GPL"); -#if HOPBYHOP -MODULE_DESCRIPTION("IPv6 HbH match"); -#else -MODULE_DESCRIPTION("IPv6 DST match"); -#endif -MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); - -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -/* - * (Type & 0xC0) >> 6 - * 0 -> ignorable - * 1 -> must drop the packet - * 2 -> send ICMP PARM PROB regardless and drop packet - * 3 -> Send ICMP if not a multicast address and drop packet - * (Type & 0x20) >> 5 - * 0 -> invariant - * 1 -> can change the routing - * (Type & 0x1F) Type - * 0 -> Pad1 (only 1 byte!) - * 1 -> PadN LENGTH info (total length = length + 2) - * C0 | 2 -> JUMBO 4 x x x x ( xxxx > 64k ) - * 5 -> RTALERT 2 x x - */ - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - struct ipv6_opt_hdr _optsh, *oh; - const struct ip6t_opts *optinfo = matchinfo; - unsigned int temp; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int ret = 0; - u8 _opttype, *tp = NULL; - u8 _optlen, *lp = NULL; - unsigned int optlen; - -#if HOPBYHOP - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP) < 0) -#else - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST) < 0) -#endif - return 0; - - oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); - if (oh == NULL){ - *hotdrop = 1; - return 0; - } - - hdrlen = ipv6_optlen(oh); - if (skb->len - ptr < hdrlen){ - /* Packet smaller than it's length field */ - return 0; - } - - DEBUGP("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen); - - DEBUGP("len %02X %04X %02X ", - optinfo->hdrlen, hdrlen, - (!(optinfo->flags & IP6T_OPTS_LEN) || - ((optinfo->hdrlen == hdrlen) ^ - !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); - - ret = (oh != NULL) - && - (!(optinfo->flags & IP6T_OPTS_LEN) || - ((optinfo->hdrlen == hdrlen) ^ - !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); - - ptr += 2; - hdrlen -= 2; - if ( !(optinfo->flags & IP6T_OPTS_OPTS) ){ - return ret; - } else if (optinfo->flags & IP6T_OPTS_NSTRICT) { - DEBUGP("Not strict - not implemented"); - } else { - DEBUGP("Strict "); - DEBUGP("#%d ",optinfo->optsnr); - for(temp=0; temp<optinfo->optsnr; temp++){ - /* type field exists ? */ - if (hdrlen < 1) - break; - tp = skb_header_pointer(skb, ptr, sizeof(_opttype), - &_opttype); - if (tp == NULL) - break; - - /* Type check */ - if (*tp != (optinfo->opts[temp] & 0xFF00)>>8){ - DEBUGP("Tbad %02X %02X\n", - *tp, - (optinfo->opts[temp] & 0xFF00)>>8); - return 0; - } else { - DEBUGP("Tok "); - } - /* Length check */ - if (*tp) { - u16 spec_len; - - /* length field exists ? */ - if (hdrlen < 2) - break; - lp = skb_header_pointer(skb, ptr + 1, - sizeof(_optlen), - &_optlen); - if (lp == NULL) - break; - spec_len = optinfo->opts[temp] & 0x00FF; - - if (spec_len != 0x00FF && spec_len != *lp) { - DEBUGP("Lbad %02X %04X\n", *lp, - spec_len); - return 0; - } - DEBUGP("Lok "); - optlen = *lp + 2; - } else { - DEBUGP("Pad1\n"); - optlen = 1; - } - - /* Step to the next */ - DEBUGP("len%04X \n", optlen); - - if ((ptr > skb->len - optlen || hdrlen < optlen) && - (temp < optinfo->optsnr - 1)) { - DEBUGP("new pointer is too large! \n"); - break; - } - ptr += optlen; - hdrlen -= optlen; - } - if (temp == optinfo->optsnr) - return ret; - else return 0; - } - - return 0; -} - -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) -{ - const struct ip6t_opts *optsinfo = matchinfo; - - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_opts))) { - DEBUGP("ip6t_opts: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_opts))); - return 0; - } - if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { - DEBUGP("ip6t_opts: unknown flags %X\n", - optsinfo->invflags); - return 0; - } - - return 1; -} - -static struct ip6t_match opts_match = { -#if HOPBYHOP - .name = "hbh", -#else - .name = "dst", -#endif - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&opts_match); -} - -static void __exit cleanup(void) -{ - ip6t_unregister_match(&opts_match); -} - -module_init(init); -module_exit(cleanup); diff --git a/net/ipv6/netfilter/ip6t_esp.c b/net/ipv6/netfilter/ip6t_esp.c deleted file mode 100644 index 24bc0cde43a..00000000000 --- a/net/ipv6/netfilter/ip6t_esp.c +++ /dev/null @@ -1,116 +0,0 @@ -/* Kernel module to match ESP parameters. */ -/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> - * - * 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. - */ - - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ipv6.h> -#include <linux/types.h> -#include <net/checksum.h> -#include <net/ipv6.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_esp.h> - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("IPv6 ESP match"); -MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); - -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -/* Returns 1 if the spi is matched by the range, 0 otherwise */ -static inline int -spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, int invert) -{ - int r=0; - DEBUGP("esp spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ', - min,spi,max); - r=(spi >= min && spi <= max) ^ invert; - DEBUGP(" result %s\n",r? "PASS\n" : "FAILED\n"); - return r; -} - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - struct ip_esp_hdr _esp, *eh; - const struct ip6t_esp *espinfo = matchinfo; - unsigned int ptr; - - /* Make sure this isn't an evil packet */ - /*DEBUGP("ipv6_esp entered \n");*/ - - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ESP) < 0) - return 0; - - eh = skb_header_pointer(skb, ptr, sizeof(_esp), &_esp); - if (eh == NULL) { - *hotdrop = 1; - return 0; - } - - DEBUGP("IPv6 ESP SPI %u %08X\n", ntohl(eh->spi), ntohl(eh->spi)); - - return (eh != NULL) - && spi_match(espinfo->spis[0], espinfo->spis[1], - ntohl(eh->spi), - !!(espinfo->invflags & IP6T_ESP_INV_SPI)); -} - -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) -{ - const struct ip6t_esp *espinfo = matchinfo; - - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_esp))) { - DEBUGP("ip6t_esp: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_esp))); - return 0; - } - if (espinfo->invflags & ~IP6T_ESP_INV_MASK) { - DEBUGP("ip6t_esp: unknown flags %X\n", - espinfo->invflags); - return 0; - } - return 1; -} - -static struct ip6t_match esp_match = { - .name = "esp", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&esp_match); -} - -static void __exit cleanup(void) -{ - ip6t_unregister_match(&esp_match); -} - -module_init(init); -module_exit(cleanup); diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c index 616c2cbcd54..aab0706908c 100644 --- a/net/ipv6/netfilter/ip6t_eui64.c +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -12,90 +12,63 @@ #include <linux/ipv6.h> #include <linux/if_ether.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> -MODULE_DESCRIPTION("IPv6 EUI64 address checking match"); +MODULE_DESCRIPTION("Xtables: IPv6 EUI64 address match"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static bool +eui64_mt6(const struct sk_buff *skb, struct xt_action_param *par) { + unsigned char eui64[8]; - unsigned char eui64[8]; - int i=0; - - if ( !(skb->mac.raw >= skb->head - && (skb->mac.raw + ETH_HLEN) <= skb->data) - && offset != 0) { - *hotdrop = 1; - return 0; - } - - memset(eui64, 0, sizeof(eui64)); - - if (eth_hdr(skb)->h_proto == ntohs(ETH_P_IPV6)) { - if (skb->nh.ipv6h->version == 0x6) { - memcpy(eui64, eth_hdr(skb)->h_source, 3); - memcpy(eui64 + 5, eth_hdr(skb)->h_source + 3, 3); - eui64[3]=0xff; - eui64[4]=0xfe; - eui64[0] |= 0x02; + if (!(skb_mac_header(skb) >= skb->head && + skb_mac_header(skb) + ETH_HLEN <= skb->data) && + par->fragoff != 0) { + par->hotdrop = true; + return false; + } - i=0; - while ((skb->nh.ipv6h->saddr.s6_addr[8+i] == - eui64[i]) && (i<8)) i++; + memset(eui64, 0, sizeof(eui64)); - if ( i == 8 ) - return 1; - } - } + if (eth_hdr(skb)->h_proto == htons(ETH_P_IPV6)) { + if (ipv6_hdr(skb)->version == 0x6) { + memcpy(eui64, eth_hdr(skb)->h_source, 3); + memcpy(eui64 + 5, eth_hdr(skb)->h_source + 3, 3); + eui64[3] = 0xff; + eui64[4] = 0xfe; + eui64[0] ^= 0x02; - return 0; -} - -static int -ip6t_eui64_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (hook_mask - & ~((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN) | - (1 << NF_IP6_FORWARD))) { - printk("ip6t_eui64: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); - return 0; + if (!memcmp(ipv6_hdr(skb)->saddr.s6_addr + 8, eui64, + sizeof(eui64))) + return true; + } } - if (matchsize != IP6T_ALIGN(sizeof(int))) - return 0; - - return 1; + return false; } -static struct ip6t_match eui64_match = { +static struct xt_match eui64_mt6_reg __read_mostly = { .name = "eui64", - .match = &match, - .checkentry = &ip6t_eui64_checkentry, + .family = NFPROTO_IPV6, + .match = eui64_mt6, + .matchsize = sizeof(int), + .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD), .me = THIS_MODULE, }; -static int __init init(void) +static int __init eui64_mt6_init(void) { - return ip6t_register_match(&eui64_match); + return xt_register_match(&eui64_mt6_reg); } -static void __exit fini(void) +static void __exit eui64_mt6_exit(void) { - ip6t_unregister_match(&eui64_match); + xt_unregister_match(&eui64_mt6_reg); } -module_init(init); -module_exit(fini); +module_init(eui64_mt6_init); +module_exit(eui64_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 085d5f8eea2..3b5735e56bf 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -6,7 +6,7 @@ * 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/ipv6.h> @@ -14,144 +14,123 @@ #include <net/checksum.h> #include <net/ipv6.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_frag.h> MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("IPv6 FRAG match"); +MODULE_DESCRIPTION("Xtables: IPv6 fragment match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* Returns 1 if the id is matched by the range, 0 otherwise */ -static inline int -id_match(u_int32_t min, u_int32_t max, u_int32_t id, int invert) +static inline bool +id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) { - int r=0; - DEBUGP("frag id_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ', - min,id,max); - r=(id >= min && id <= max) ^ invert; - DEBUGP(" result %s\n",r? "PASS" : "FAILED"); - return r; + bool r; + pr_debug("id_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', + min, id, max); + r = (id >= min && id <= max) ^ invert; + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); + return r; } -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static bool +frag_mt6(const struct sk_buff *skb, struct xt_action_param *par) { - struct frag_hdr _frag, *fh; - const struct ip6t_frag *fraginfo = matchinfo; - unsigned int ptr; - - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT) < 0) - return 0; + struct frag_hdr _frag; + const struct frag_hdr *fh; + const struct ip6t_frag *fraginfo = par->matchinfo; + unsigned int ptr = 0; + int err; + + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag); - if (fh == NULL){ - *hotdrop = 1; - return 0; + if (fh == NULL) { + par->hotdrop = true; + return false; } - DEBUGP("INFO %04X ", fh->frag_off); - DEBUGP("OFFSET %04X ", ntohs(fh->frag_off) & ~0x7); - DEBUGP("RES %02X %04X", fh->reserved, ntohs(fh->frag_off) & 0x6); - DEBUGP("MF %04X ", fh->frag_off & htons(IP6_MF)); - DEBUGP("ID %u %08X\n", ntohl(fh->identification), - ntohl(fh->identification)); - - DEBUGP("IPv6 FRAG id %02X ", - (id_match(fraginfo->ids[0], fraginfo->ids[1], - ntohl(fh->identification), - !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)))); - DEBUGP("res %02X %02X%04X %02X ", - (fraginfo->flags & IP6T_FRAG_RES), fh->reserved, - ntohs(fh->frag_off) & 0x6, - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); - DEBUGP("first %02X %02X %02X ", - (fraginfo->flags & IP6T_FRAG_FST), - ntohs(fh->frag_off) & ~0x7, - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7))); - DEBUGP("mf %02X %02X %02X ", - (fraginfo->flags & IP6T_FRAG_MF), - ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_MF) - && !((ntohs(fh->frag_off) & IP6_MF)))); - DEBUGP("last %02X %02X %02X\n", - (fraginfo->flags & IP6T_FRAG_NMF), - ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF))); - - return (fh != NULL) - && - (id_match(fraginfo->ids[0], fraginfo->ids[1], + pr_debug("INFO %04X ", fh->frag_off); + pr_debug("OFFSET %04X ", ntohs(fh->frag_off) & ~0x7); + pr_debug("RES %02X %04X", fh->reserved, ntohs(fh->frag_off) & 0x6); + pr_debug("MF %04X ", fh->frag_off & htons(IP6_MF)); + pr_debug("ID %u %08X\n", ntohl(fh->identification), + ntohl(fh->identification)); + + pr_debug("IPv6 FRAG id %02X ", + id_match(fraginfo->ids[0], fraginfo->ids[1], ntohl(fh->identification), - !!(fraginfo->invflags & IP6T_FRAG_INV_IDS))) - && - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x6))) - && - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7)) - && - !((fraginfo->flags & IP6T_FRAG_MF) - && !(ntohs(fh->frag_off) & IP6_MF)) - && - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF)); + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS))); + pr_debug("res %02X %02X%04X %02X ", + fraginfo->flags & IP6T_FRAG_RES, fh->reserved, + ntohs(fh->frag_off) & 0x6, + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); + pr_debug("first %02X %02X %02X ", + fraginfo->flags & IP6T_FRAG_FST, + ntohs(fh->frag_off) & ~0x7, + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7))); + pr_debug("mf %02X %02X %02X ", + fraginfo->flags & IP6T_FRAG_MF, + ntohs(fh->frag_off) & IP6_MF, + !((fraginfo->flags & IP6T_FRAG_MF) && + !((ntohs(fh->frag_off) & IP6_MF)))); + pr_debug("last %02X %02X %02X\n", + fraginfo->flags & IP6T_FRAG_NMF, + ntohs(fh->frag_off) & IP6_MF, + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF))); + + return (fh != NULL) && + id_match(fraginfo->ids[0], fraginfo->ids[1], + ntohl(fh->identification), + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x6))) && + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7)) && + !((fraginfo->flags & IP6T_FRAG_MF) && + !(ntohs(fh->frag_off) & IP6_MF)) && + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF)); } -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) +static int frag_mt6_check(const struct xt_mtchk_param *par) { - const struct ip6t_frag *fraginfo = matchinfo; - - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_frag))) { - DEBUGP("ip6t_frag: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_frag))); - return 0; - } - if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) { - DEBUGP("ip6t_frag: unknown flags %X\n", - fraginfo->invflags); - return 0; - } - - return 1; + const struct ip6t_frag *fraginfo = par->matchinfo; + + if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) { + pr_debug("unknown flags %X\n", fraginfo->invflags); + return -EINVAL; + } + return 0; } -static struct ip6t_match frag_match = { +static struct xt_match frag_mt6_reg __read_mostly = { .name = "frag", - .match = &match, - .checkentry = &checkentry, + .family = NFPROTO_IPV6, + .match = frag_mt6, + .matchsize = sizeof(struct ip6t_frag), + .checkentry = frag_mt6_check, .me = THIS_MODULE, }; -static int __init init(void) +static int __init frag_mt6_init(void) { - return ip6t_register_match(&frag_match); + return xt_register_match(&frag_mt6_reg); } -static void __exit cleanup(void) +static void __exit frag_mt6_exit(void) { - ip6t_unregister_match(&frag_match); + xt_unregister_match(&frag_mt6_reg); } -module_init(init); -module_exit(cleanup); +module_init(frag_mt6_init); +module_exit(frag_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 1d09485111d..01df142bb02 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -6,7 +6,7 @@ * 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/ipv6.h> @@ -16,103 +16,92 @@ #include <asm/byteorder.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_opts.h> -#define HOPBYHOP 1 - MODULE_LICENSE("GPL"); -#if HOPBYHOP -MODULE_DESCRIPTION("IPv6 HbH match"); -#else -MODULE_DESCRIPTION("IPv6 DST match"); -#endif +MODULE_DESCRIPTION("Xtables: IPv6 Hop-By-Hop and Destination Header match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); - -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif +MODULE_ALIAS("ip6t_dst"); /* - * (Type & 0xC0) >> 6 - * 0 -> ignorable - * 1 -> must drop the packet - * 2 -> send ICMP PARM PROB regardless and drop packet - * 3 -> Send ICMP if not a multicast address and drop packet + * (Type & 0xC0) >> 6 + * 0 -> ignorable + * 1 -> must drop the packet + * 2 -> send ICMP PARM PROB regardless and drop packet + * 3 -> Send ICMP if not a multicast address and drop packet * (Type & 0x20) >> 5 - * 0 -> invariant - * 1 -> can change the routing + * 0 -> invariant + * 1 -> can change the routing * (Type & 0x1F) Type - * 0 -> Pad1 (only 1 byte!) - * 1 -> PadN LENGTH info (total length = length + 2) - * C0 | 2 -> JUMBO 4 x x x x ( xxxx > 64k ) - * 5 -> RTALERT 2 x x + * 0 -> Pad1 (only 1 byte!) + * 1 -> PadN LENGTH info (total length = length + 2) + * C0 | 2 -> JUMBO 4 x x x x ( xxxx > 64k ) + * 5 -> RTALERT 2 x x */ -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static struct xt_match hbh_mt6_reg[] __read_mostly; + +static bool +hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) { - struct ipv6_opt_hdr _optsh, *oh; - const struct ip6t_opts *optinfo = matchinfo; - unsigned int temp; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int ret = 0; - u8 _opttype, *tp = NULL; - u8 _optlen, *lp = NULL; - unsigned int optlen; - -#if HOPBYHOP - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP) < 0) -#else - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST) < 0) -#endif - return 0; - - oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); - if (oh == NULL){ - *hotdrop = 1; - return 0; - } - - hdrlen = ipv6_optlen(oh); - if (skb->len - ptr < hdrlen){ - /* Packet smaller than it's length field */ - return 0; - } - - DEBUGP("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen); - - DEBUGP("len %02X %04X %02X ", - optinfo->hdrlen, hdrlen, - (!(optinfo->flags & IP6T_OPTS_LEN) || - ((optinfo->hdrlen == hdrlen) ^ - !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); - - ret = (oh != NULL) - && - (!(optinfo->flags & IP6T_OPTS_LEN) || - ((optinfo->hdrlen == hdrlen) ^ - !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); - - ptr += 2; - hdrlen -= 2; - if ( !(optinfo->flags & IP6T_OPTS_OPTS) ){ - return ret; - } else if (optinfo->flags & IP6T_OPTS_NSTRICT) { - DEBUGP("Not strict - not implemented"); + struct ipv6_opt_hdr _optsh; + const struct ipv6_opt_hdr *oh; + const struct ip6t_opts *optinfo = par->matchinfo; + unsigned int temp; + unsigned int ptr = 0; + unsigned int hdrlen = 0; + bool ret = false; + u8 _opttype; + u8 _optlen; + const u_int8_t *tp = NULL; + const u_int8_t *lp = NULL; + unsigned int optlen; + int err; + + err = ipv6_find_hdr(skb, &ptr, + (par->match == &hbh_mt6_reg[0]) ? + NEXTHDR_HOP : NEXTHDR_DEST, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } + + oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); + if (oh == NULL) { + par->hotdrop = true; + return false; + } + + hdrlen = ipv6_optlen(oh); + if (skb->len - ptr < hdrlen) { + /* Packet smaller than it's length field */ + return false; + } + + pr_debug("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen); + + pr_debug("len %02X %04X %02X ", + optinfo->hdrlen, hdrlen, + (!(optinfo->flags & IP6T_OPTS_LEN) || + ((optinfo->hdrlen == hdrlen) ^ + !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); + + ret = (oh != NULL) && + (!(optinfo->flags & IP6T_OPTS_LEN) || + ((optinfo->hdrlen == hdrlen) ^ + !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); + + ptr += 2; + hdrlen -= 2; + if (!(optinfo->flags & IP6T_OPTS_OPTS)) { + return ret; } else { - DEBUGP("Strict "); - DEBUGP("#%d ",optinfo->optsnr); - for(temp=0; temp<optinfo->optsnr; temp++){ + pr_debug("Strict "); + pr_debug("#%d ", optinfo->optsnr); + for (temp = 0; temp < optinfo->optsnr; temp++) { /* type field exists ? */ if (hdrlen < 1) break; @@ -122,13 +111,12 @@ match(const struct sk_buff *skb, break; /* Type check */ - if (*tp != (optinfo->opts[temp] & 0xFF00)>>8){ - DEBUGP("Tbad %02X %02X\n", - *tp, - (optinfo->opts[temp] & 0xFF00)>>8); - return 0; + if (*tp != (optinfo->opts[temp] & 0xFF00) >> 8) { + pr_debug("Tbad %02X %02X\n", *tp, + (optinfo->opts[temp] & 0xFF00) >> 8); + return false; } else { - DEBUGP("Tok "); + pr_debug("Tok "); } /* Length check */ if (*tp) { @@ -145,23 +133,23 @@ match(const struct sk_buff *skb, spec_len = optinfo->opts[temp] & 0x00FF; if (spec_len != 0x00FF && spec_len != *lp) { - DEBUGP("Lbad %02X %04X\n", *lp, - spec_len); - return 0; + pr_debug("Lbad %02X %04X\n", *lp, + spec_len); + return false; } - DEBUGP("Lok "); + pr_debug("Lok "); optlen = *lp + 2; } else { - DEBUGP("Pad1\n"); + pr_debug("Pad1\n"); optlen = 1; } /* Step to the next */ - DEBUGP("len%04X \n", optlen); + pr_debug("len%04X\n", optlen); if ((ptr > skb->len - optlen || hdrlen < optlen) && - (temp < optinfo->optsnr - 1)) { - DEBUGP("new pointer is too large! \n"); + temp < optinfo->optsnr - 1) { + pr_debug("new pointer is too large!\n"); break; } ptr += optlen; @@ -169,56 +157,59 @@ match(const struct sk_buff *skb, } if (temp == optinfo->optsnr) return ret; - else return 0; + else + return false; } - return 0; + return false; } -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) +static int hbh_mt6_check(const struct xt_mtchk_param *par) { - const struct ip6t_opts *optsinfo = matchinfo; - - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_opts))) { - DEBUGP("ip6t_opts: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_opts))); - return 0; - } - if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { - DEBUGP("ip6t_opts: unknown flags %X\n", - optsinfo->invflags); - return 0; - } - - return 1; + const struct ip6t_opts *optsinfo = par->matchinfo; + + if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { + pr_debug("unknown flags %X\n", optsinfo->invflags); + return -EINVAL; + } + + if (optsinfo->flags & IP6T_OPTS_NSTRICT) { + pr_debug("Not strict - not implemented"); + return -EINVAL; + } + + return 0; } -static struct ip6t_match opts_match = { -#if HOPBYHOP - .name = "hbh", -#else - .name = "dst", -#endif - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, +static struct xt_match hbh_mt6_reg[] __read_mostly = { + { + /* Note, hbh_mt6 relies on the order of hbh_mt6_reg */ + .name = "hbh", + .family = NFPROTO_IPV6, + .match = hbh_mt6, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = hbh_mt6_check, + .me = THIS_MODULE, + }, + { + .name = "dst", + .family = NFPROTO_IPV6, + .match = hbh_mt6, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = hbh_mt6_check, + .me = THIS_MODULE, + }, }; -static int __init init(void) +static int __init hbh_mt6_init(void) { - return ip6t_register_match(&opts_match); + return xt_register_matches(hbh_mt6_reg, ARRAY_SIZE(hbh_mt6_reg)); } -static void __exit cleanup(void) +static void __exit hbh_mt6_exit(void) { - ip6t_unregister_match(&opts_match); + xt_unregister_matches(hbh_mt6_reg, ARRAY_SIZE(hbh_mt6_reg)); } -module_init(init); -module_exit(cleanup); +module_init(hbh_mt6_init); +module_exit(hbh_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_hl.c b/net/ipv6/netfilter/ip6t_hl.c deleted file mode 100644 index 0beaff5471d..00000000000 --- a/net/ipv6/netfilter/ip6t_hl.c +++ /dev/null @@ -1,80 +0,0 @@ -/* Hop Limit matching module */ - -/* (C) 2001-2002 Maciej Soltysiak <solt@dns.toxicfilms.tv> - * Based on HW's ttl module - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv6/ip6t_hl.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>"); -MODULE_DESCRIPTION("IP tables Hop Limit matching module"); -MODULE_LICENSE("GPL"); - -static int match(const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const void *matchinfo, - int offset, unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_hl_info *info = matchinfo; - const struct ipv6hdr *ip6h = skb->nh.ipv6h; - - switch (info->mode) { - case IP6T_HL_EQ: - return (ip6h->hop_limit == info->hop_limit); - break; - case IP6T_HL_NE: - return (!(ip6h->hop_limit == info->hop_limit)); - break; - case IP6T_HL_LT: - return (ip6h->hop_limit < info->hop_limit); - break; - case IP6T_HL_GT: - return (ip6h->hop_limit > info->hop_limit); - break; - default: - printk(KERN_WARNING "ip6t_hl: unknown mode %d\n", - info->mode); - return 0; - } - - return 0; -} - -static int checkentry(const char *tablename, const struct ip6t_ip6 *ip, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_hl_info))) - return 0; - - return 1; -} - -static struct ip6t_match hl_match = { - .name = "hl", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&hl_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&hl_match); - -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 32e67f05845..54bd9790603 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -1,7 +1,7 @@ /* ipv6header match - matches IPv6 packets based on whether they contain certain headers */ -/* Original idea: Brad Chapman +/* Original idea: Brad Chapman * Rewritten by: Andras Kis-Szabo <kisza@sch.bme.hu> */ /* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> @@ -18,23 +18,18 @@ #include <net/checksum.h> #include <net/ipv6.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_ipv6header.h> MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("IPv6 headers match"); +MODULE_DESCRIPTION("Xtables: IPv6 header types match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); -static int -ipv6header_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static bool +ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) { - const struct ip6t_ipv6header_info *info = matchinfo; + const struct ip6t_ipv6header_info *info = par->matchinfo; unsigned int temp; int len; u8 nexthdr; @@ -43,27 +38,28 @@ ipv6header_match(const struct sk_buff *skb, /* Make sure this isn't an evil packet */ /* type of the 1st exthdr */ - nexthdr = skb->nh.ipv6h->nexthdr; + nexthdr = ipv6_hdr(skb)->nexthdr; /* pointer to the 1st exthdr */ ptr = sizeof(struct ipv6hdr); /* available length */ len = skb->len - ptr; temp = 0; - while (ip6t_ext_hdr(nexthdr)) { - struct ipv6_opt_hdr _hdr, *hp; - int hdrlen; + while (ip6t_ext_hdr(nexthdr)) { + const struct ipv6_opt_hdr *hp; + struct ipv6_opt_hdr _hdr; + int hdrlen; - /* Is there enough space for the next ext header? */ - if (len < (int)sizeof(struct ipv6_opt_hdr)) - return 0; /* No more exthdr -> evaluate */ - if (nexthdr == NEXTHDR_NONE) { + if (nexthdr == NEXTHDR_NONE) { temp |= MASK_NONE; break; } + /* Is there enough space for the next ext header? */ + if (len < (int)sizeof(struct ipv6_opt_hdr)) + return false; /* ESP -> evaluate */ - if (nexthdr == NEXTHDR_ESP) { + if (nexthdr == NEXTHDR_ESP) { temp |= MASK_ESP; break; } @@ -72,43 +68,43 @@ ipv6header_match(const struct sk_buff *skb, BUG_ON(hp == NULL); /* Calculate the header length */ - if (nexthdr == NEXTHDR_FRAGMENT) { - hdrlen = 8; - } else if (nexthdr == NEXTHDR_AUTH) - hdrlen = (hp->hdrlen+2)<<2; - else - hdrlen = ipv6_optlen(hp); + if (nexthdr == NEXTHDR_FRAGMENT) + hdrlen = 8; + else if (nexthdr == NEXTHDR_AUTH) + hdrlen = (hp->hdrlen + 2) << 2; + else + hdrlen = ipv6_optlen(hp); /* set the flag */ - switch (nexthdr){ - case NEXTHDR_HOP: - temp |= MASK_HOPOPTS; - break; - case NEXTHDR_ROUTING: - temp |= MASK_ROUTING; - break; - case NEXTHDR_FRAGMENT: - temp |= MASK_FRAGMENT; - break; - case NEXTHDR_AUTH: - temp |= MASK_AH; - break; - case NEXTHDR_DEST: - temp |= MASK_DSTOPTS; - break; - default: - return 0; - break; + switch (nexthdr) { + case NEXTHDR_HOP: + temp |= MASK_HOPOPTS; + break; + case NEXTHDR_ROUTING: + temp |= MASK_ROUTING; + break; + case NEXTHDR_FRAGMENT: + temp |= MASK_FRAGMENT; + break; + case NEXTHDR_AUTH: + temp |= MASK_AH; + break; + case NEXTHDR_DEST: + temp |= MASK_DSTOPTS; + break; + default: + return false; + break; } - nexthdr = hp->nexthdr; - len -= hdrlen; - ptr += hdrlen; + nexthdr = hp->nexthdr; + len -= hdrlen; + ptr += hdrlen; if (ptr > skb->len) break; - } + } - if ( (nexthdr != NEXTHDR_NONE ) && (nexthdr != NEXTHDR_ESP) ) + if (nexthdr != NEXTHDR_NONE && nexthdr != NEXTHDR_ESP) temp |= MASK_PROTO; if (info->modeflag) @@ -122,46 +118,37 @@ ipv6header_match(const struct sk_buff *skb, } } -static int -ipv6header_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) +static int ipv6header_mt6_check(const struct xt_mtchk_param *par) { - const struct ip6t_ipv6header_info *info = matchinfo; - - /* Check for obvious errors */ - /* This match is valid in all hooks! */ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_ipv6header_info))) - return 0; + const struct ip6t_ipv6header_info *info = par->matchinfo; /* invflags is 0 or 0xff in hard mode */ - if ((!info->modeflag) && info->invflags != 0x00 - && info->invflags != 0xFF) - return 0; + if ((!info->modeflag) && info->invflags != 0x00 && + info->invflags != 0xFF) + return -EINVAL; - return 1; + return 0; } -static struct ip6t_match ip6t_ipv6header_match = { +static struct xt_match ipv6header_mt6_reg __read_mostly = { .name = "ipv6header", - .match = &ipv6header_match, - .checkentry = &ipv6header_checkentry, + .family = NFPROTO_IPV6, + .match = ipv6header_mt6, + .matchsize = sizeof(struct ip6t_ipv6header_info), + .checkentry = ipv6header_mt6_check, .destroy = NULL, .me = THIS_MODULE, }; -static int __init ipv6header_init(void) +static int __init ipv6header_mt6_init(void) { - return ip6t_register_match(&ip6t_ipv6header_match); + return xt_register_match(&ipv6header_mt6_reg); } -static void __exit ipv6header_exit(void) +static void __exit ipv6header_mt6_exit(void) { - ip6t_unregister_match(&ip6t_ipv6header_match); + xt_unregister_match(&ipv6header_mt6_reg); } -module_init(ipv6header_init); -module_exit(ipv6header_exit); - +module_init(ipv6header_mt6_init); +module_exit(ipv6header_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_length.c b/net/ipv6/netfilter/ip6t_length.c deleted file mode 100644 index e0537d3811d..00000000000 --- a/net/ipv6/netfilter/ip6t_length.c +++ /dev/null @@ -1,66 +0,0 @@ -/* Length Match - IPv6 Port */ - -/* (C) 1999-2001 James Morris <jmorros@intercode.com.au> - * - * 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. - */ - - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv6/ip6t_length.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); -MODULE_DESCRIPTION("IPv6 packet length match"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_length_info *info = matchinfo; - u_int16_t pktlen = ntohs(skb->nh.ipv6h->payload_len) + sizeof(struct ipv6hdr); - - return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_length_info))) - return 0; - - return 1; -} - -static struct ip6t_match length_match = { - .name = "length", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&length_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&length_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_limit.c b/net/ipv6/netfilter/ip6t_limit.c deleted file mode 100644 index fb782f610be..00000000000 --- a/net/ipv6/netfilter/ip6t_limit.c +++ /dev/null @@ -1,147 +0,0 @@ -/* Kernel module to control the rate - * - * 2 September 1999: Changed from the target RATE to the match - * `limit', removed logging. Did I mention that - * Alexey is a fucking genius? - * Rusty Russell (rusty@rustcorp.com.au). */ - -/* (C) 1999 Jérôme de Vivie <devivie@info.enserb.u-bordeaux.fr> - * (C) 1999 Hervé Eychenne <eychenne@info.enserb.u-bordeaux.fr> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_limit.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>"); -MODULE_DESCRIPTION("rate limiting within ip6tables"); - -/* The algorithm used is the Simple Token Bucket Filter (TBF) - * see net/sched/sch_tbf.c in the linux source tree - */ - -static DEFINE_SPINLOCK(limit_lock); - -/* Rusty: This is my (non-mathematically-inclined) understanding of - this algorithm. The `average rate' in jiffies becomes your initial - amount of credit `credit' and the most credit you can ever have - `credit_cap'. The `peak rate' becomes the cost of passing the - test, `cost'. - - `prev' tracks the last packet hit: you gain one credit per jiffy. - If you get credit balance more than this, the extra credit is - discarded. Every time the match passes, you lose `cost' credits; - if you don't have that many, the test fails. - - See Alexey's formal explanation in net/sched/sch_tbf.c. - - To avoid underflow, we multiply by 128 (ie. you get 128 credits per - jiffy). Hence a cost of 2^32-1, means one pass per 32768 seconds - at 1024HZ (or one every 9 hours). A cost of 1 means 12800 passes - per second at 100HZ. */ - -#define CREDITS_PER_JIFFY 128 - -static int -ip6t_limit_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - struct ip6t_rateinfo *r = ((struct ip6t_rateinfo *)matchinfo)->master; - unsigned long now = jiffies; - - spin_lock_bh(&limit_lock); - r->credit += (now - xchg(&r->prev, now)) * CREDITS_PER_JIFFY; - if (r->credit > r->credit_cap) - r->credit = r->credit_cap; - - if (r->credit >= r->cost) { - /* We're not limited. */ - r->credit -= r->cost; - spin_unlock_bh(&limit_lock); - return 1; - } - - spin_unlock_bh(&limit_lock); - return 0; -} - -/* Precision saver. */ -static u_int32_t -user2credits(u_int32_t user) -{ - /* If multiplying would overflow... */ - if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) - /* Divide first. */ - return (user / IP6T_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; - - return (user * HZ * CREDITS_PER_JIFFY) / IP6T_LIMIT_SCALE; -} - -static int -ip6t_limit_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ip6t_rateinfo *r = matchinfo; - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_rateinfo))) - return 0; - - /* Check for overflow. */ - if (r->burst == 0 - || user2credits(r->avg * r->burst) < user2credits(r->avg)) { - printk("Call rusty: overflow in ip6t_limit: %u/%u\n", - r->avg, r->burst); - return 0; - } - - /* User avg in seconds * IP6T_LIMIT_SCALE: convert to jiffies * - 128. */ - r->prev = jiffies; - r->credit = user2credits(r->avg * r->burst); /* Credits full. */ - r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */ - r->cost = user2credits(r->avg); - - /* For SMP, we only want to use one set of counters. */ - r->master = r; - - return 1; -} - -static struct ip6t_match ip6t_limit_reg = { - .name = "limit", - .match = ip6t_limit_match, - .checkentry = ip6t_limit_checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - if (ip6t_register_match(&ip6t_limit_reg)) - return -EINVAL; - return 0; -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&ip6t_limit_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_mac.c b/net/ipv6/netfilter/ip6t_mac.c deleted file mode 100644 index 526d43e3723..00000000000 --- a/net/ipv6/netfilter/ip6t_mac.c +++ /dev/null @@ -1,80 +0,0 @@ -/* Kernel module to match MAC address parameters. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/if_ether.h> - -#include <linux/netfilter_ipv6/ip6t_mac.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("MAC address matching module for IPv6"); -MODULE_AUTHOR("Netfilter Core Teaam <coreteam@netfilter.org>"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_mac_info *info = matchinfo; - - /* Is mac pointer valid? */ - return (skb->mac.raw >= skb->head - && (skb->mac.raw + ETH_HLEN) <= skb->data - /* If so, compare... */ - && ((memcmp(eth_hdr(skb)->h_source, info->srcaddr, ETH_ALEN) - == 0) ^ info->invert)); -} - -static int -ip6t_mac_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (hook_mask - & ~((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN) - | (1 << NF_IP6_FORWARD))) { - printk("ip6t_mac: only valid for PRE_ROUTING, LOCAL_IN or" - " FORWARD\n"); - return 0; - } - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_mac_info))) - return 0; - - return 1; -} - -static struct ip6t_match mac_match = { - .name = "mac", - .match = &match, - .checkentry = &ip6t_mac_checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&mac_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&mac_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_mark.c b/net/ipv6/netfilter/ip6t_mark.c deleted file mode 100644 index affc3de364f..00000000000 --- a/net/ipv6/netfilter/ip6t_mark.c +++ /dev/null @@ -1,66 +0,0 @@ -/* Kernel module to match NFMARK values. */ - -/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca> - * - * 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. - */ - - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv6/ip6t_mark.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("ip6tables mark match"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_mark_info *info = matchinfo; - - return ((skb->nfmark & info->mask) == info->mark) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_mark_info))) - return 0; - - return 1; -} - -static struct ip6t_match mark_match = { - .name = "mark", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&mark_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&mark_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_mh.c b/net/ipv6/netfilter/ip6t_mh.c new file mode 100644 index 00000000000..0c90c66b199 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_mh.c @@ -0,0 +1,94 @@ +/* + * Copyright (C)2006 USAGI/WIDE Project + * + * 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. + * + * Author: + * Masahide NAKAMURA @USAGI <masahide.nakamura.cz@hitachi.com> + * + * Based on net/netfilter/xt_tcpudp.c + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/types.h> +#include <linux/module.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <net/mip6.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6t_mh.h> + +MODULE_DESCRIPTION("Xtables: IPv6 Mobility Header match"); +MODULE_LICENSE("GPL"); + +/* Returns 1 if the type is matched by the range, 0 otherwise */ +static inline bool +type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert) +{ + return (type >= min && type <= max) ^ invert; +} + +static bool mh_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ip6_mh _mh; + const struct ip6_mh *mh; + const struct ip6t_mh *mhinfo = par->matchinfo; + + /* Must not be a fragment. */ + if (par->fragoff != 0) + return false; + + mh = skb_header_pointer(skb, par->thoff, sizeof(_mh), &_mh); + if (mh == NULL) { + /* We've been asked to examine this packet, and we + can't. Hence, no choice but to drop. */ + pr_debug("Dropping evil MH tinygram.\n"); + par->hotdrop = true; + return false; + } + + if (mh->ip6mh_proto != IPPROTO_NONE) { + pr_debug("Dropping invalid MH Payload Proto: %u\n", + mh->ip6mh_proto); + par->hotdrop = true; + return false; + } + + return type_match(mhinfo->types[0], mhinfo->types[1], mh->ip6mh_type, + !!(mhinfo->invflags & IP6T_MH_INV_TYPE)); +} + +static int mh_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_mh *mhinfo = par->matchinfo; + + /* Must specify no unknown invflags */ + return (mhinfo->invflags & ~IP6T_MH_INV_MASK) ? -EINVAL : 0; +} + +static struct xt_match mh_mt6_reg __read_mostly = { + .name = "mh", + .family = NFPROTO_IPV6, + .checkentry = mh_mt6_check, + .match = mh_mt6, + .matchsize = sizeof(struct ip6t_mh), + .proto = IPPROTO_MH, + .me = THIS_MODULE, +}; + +static int __init mh_mt6_init(void) +{ + return xt_register_match(&mh_mt6_reg); +} + +static void __exit mh_mt6_exit(void) +{ + xt_unregister_match(&mh_mt6_reg); +} + +module_init(mh_mt6_init); +module_exit(mh_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_multiport.c b/net/ipv6/netfilter/ip6t_multiport.c deleted file mode 100644 index 6e3246153fa..00000000000 --- a/net/ipv6/netfilter/ip6t_multiport.c +++ /dev/null @@ -1,125 +0,0 @@ -/* Kernel module to match one of a list of TCP/UDP ports: ports are in - the same place so we can treat them as equal. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/udp.h> -#include <linux/skbuff.h> -#include <linux/in.h> - -#include <linux/netfilter_ipv6/ip6t_multiport.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("ip6tables match for multiple ports"); - -#if 0 -#define duprintf(format, args...) printk(format , ## args) -#else -#define duprintf(format, args...) -#endif - -/* Returns 1 if the port is matched by the test, 0 otherwise. */ -static inline int -ports_match(const u_int16_t *portlist, enum ip6t_multiport_flags flags, - u_int8_t count, u_int16_t src, u_int16_t dst) -{ - unsigned int i; - for (i=0; i<count; i++) { - if (flags != IP6T_MULTIPORT_DESTINATION - && portlist[i] == src) - return 1; - - if (flags != IP6T_MULTIPORT_SOURCE - && portlist[i] == dst) - return 1; - } - - return 0; -} - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - u16 _ports[2], *pptr; - const struct ip6t_multiport *multiinfo = matchinfo; - - /* Must not be a fragment. */ - if (offset) - return 0; - - /* Must be big enough to read ports (both UDP and TCP have - them at the start). */ - pptr = skb_header_pointer(skb, protoff, sizeof(_ports), &_ports[0]); - if (pptr == NULL) { - /* We've been asked to examine this packet, and we - * can't. Hence, no choice but to drop. - */ - duprintf("ip6t_multiport:" - " Dropping evil offset=0 tinygram.\n"); - *hotdrop = 1; - return 0; - } - - return ports_match(multiinfo->ports, - multiinfo->flags, multiinfo->count, - ntohs(pptr[0]), ntohs(pptr[1])); -} - -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_multiport *multiinfo = matchinfo; - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_multiport))) - return 0; - - /* Must specify proto == TCP/UDP, no unknown flags or bad count */ - return (ip->proto == IPPROTO_TCP || ip->proto == IPPROTO_UDP) - && !(ip->invflags & IP6T_INV_PROTO) - && matchsize == IP6T_ALIGN(sizeof(struct ip6t_multiport)) - && (multiinfo->flags == IP6T_MULTIPORT_SOURCE - || multiinfo->flags == IP6T_MULTIPORT_DESTINATION - || multiinfo->flags == IP6T_MULTIPORT_EITHER) - && multiinfo->count <= IP6T_MULTI_PORTS; -} - -static struct ip6t_match multiport_match = { - .name = "multiport", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&multiport_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&multiport_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_owner.c b/net/ipv6/netfilter/ip6t_owner.c deleted file mode 100644 index 4de4cdad4b7..00000000000 --- a/net/ipv6/netfilter/ip6t_owner.c +++ /dev/null @@ -1,99 +0,0 @@ -/* Kernel module to match various things tied to sockets associated with - locally generated outgoing packets. */ - -/* (C) 2000-2001 Marc Boucher <marc@mbsi.ca> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/file.h> -#include <linux/rcupdate.h> -#include <net/sock.h> - -#include <linux/netfilter_ipv6/ip6t_owner.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("IP6 tables owner matching module"); -MODULE_LICENSE("GPL"); - - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_owner_info *info = matchinfo; - - if (!skb->sk || !skb->sk->sk_socket || !skb->sk->sk_socket->file) - return 0; - - if(info->match & IP6T_OWNER_UID) { - if((skb->sk->sk_socket->file->f_uid != info->uid) ^ - !!(info->invert & IP6T_OWNER_UID)) - return 0; - } - - if(info->match & IP6T_OWNER_GID) { - if((skb->sk->sk_socket->file->f_gid != info->gid) ^ - !!(info->invert & IP6T_OWNER_GID)) - return 0; - } - - return 1; -} - -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_owner_info *info = matchinfo; - - if (hook_mask - & ~((1 << NF_IP6_LOCAL_OUT) | (1 << NF_IP6_POST_ROUTING))) { - printk("ip6t_owner: only valid for LOCAL_OUT or POST_ROUTING.\n"); - return 0; - } - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_owner_info))) - return 0; - - if (info->match & (IP6T_OWNER_PID|IP6T_OWNER_SID)) { - printk("ipt_owner: pid and sid matching " - "not supported anymore\n"); - return 0; - } - - return 1; -} - -static struct ip6t_match owner_match = { - .name = "owner", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&owner_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&owner_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_physdev.c b/net/ipv6/netfilter/ip6t_physdev.c deleted file mode 100644 index 71515c86ece..00000000000 --- a/net/ipv6/netfilter/ip6t_physdev.c +++ /dev/null @@ -1,135 +0,0 @@ -/* Kernel module to match the bridge port in and - * out device for IP packets coming into contact with a bridge. */ - -/* (C) 2001-2003 Bart De Schuymer <bdschuym@pandora.be> - * - * 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. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv6/ip6t_physdev.h> -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_bridge.h> -#define MATCH 1 -#define NOMATCH 0 - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); -MODULE_DESCRIPTION("iptables bridge physical device match module"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - int i; - static const char nulldevname[IFNAMSIZ]; - const struct ip6t_physdev_info *info = matchinfo; - unsigned int ret; - const char *indev, *outdev; - struct nf_bridge_info *nf_bridge; - - /* Not a bridged IP packet or no info available yet: - * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if - * the destination device will be a bridge. */ - if (!(nf_bridge = skb->nf_bridge)) { - /* Return MATCH if the invert flags of the used options are on */ - if ((info->bitmask & IP6T_PHYSDEV_OP_BRIDGED) && - !(info->invert & IP6T_PHYSDEV_OP_BRIDGED)) - return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_ISIN) && - !(info->invert & IP6T_PHYSDEV_OP_ISIN)) - return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_ISOUT) && - !(info->invert & IP6T_PHYSDEV_OP_ISOUT)) - return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_IN) && - !(info->invert & IP6T_PHYSDEV_OP_IN)) - return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_OUT) && - !(info->invert & IP6T_PHYSDEV_OP_OUT)) - return NOMATCH; - return MATCH; - } - - /* This only makes sense in the FORWARD and POSTROUTING chains */ - if ((info->bitmask & IP6T_PHYSDEV_OP_BRIDGED) && - (!!(nf_bridge->mask & BRNF_BRIDGED) ^ - !(info->invert & IP6T_PHYSDEV_OP_BRIDGED))) - return NOMATCH; - - if ((info->bitmask & IP6T_PHYSDEV_OP_ISIN && - (!nf_bridge->physindev ^ !!(info->invert & IP6T_PHYSDEV_OP_ISIN))) || - (info->bitmask & IP6T_PHYSDEV_OP_ISOUT && - (!nf_bridge->physoutdev ^ !!(info->invert & IP6T_PHYSDEV_OP_ISOUT)))) - return NOMATCH; - - if (!(info->bitmask & IP6T_PHYSDEV_OP_IN)) - goto match_outdev; - indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname; - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { - ret |= (((const unsigned int *)indev)[i] - ^ ((const unsigned int *)info->physindev)[i]) - & ((const unsigned int *)info->in_mask)[i]; - } - - if ((ret == 0) ^ !(info->invert & IP6T_PHYSDEV_OP_IN)) - return NOMATCH; - -match_outdev: - if (!(info->bitmask & IP6T_PHYSDEV_OP_OUT)) - return MATCH; - outdev = nf_bridge->physoutdev ? - nf_bridge->physoutdev->name : nulldevname; - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { - ret |= (((const unsigned int *)outdev)[i] - ^ ((const unsigned int *)info->physoutdev)[i]) - & ((const unsigned int *)info->out_mask)[i]; - } - - return (ret != 0) ^ !(info->invert & IP6T_PHYSDEV_OP_OUT); -} - -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_physdev_info *info = matchinfo; - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_physdev_info))) - return 0; - if (!(info->bitmask & IP6T_PHYSDEV_OP_MASK) || - info->bitmask & ~IP6T_PHYSDEV_OP_MASK) - return 0; - return 1; -} - -static struct ip6t_match physdev_match = { - .name = "physdev", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&physdev_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&physdev_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c new file mode 100644 index 00000000000..790e0c6b19e --- /dev/null +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -0,0 +1,140 @@ +/* + * 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 = { + .flowi6_iif = LOOPBACK_IFINDEX, + .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: + ip6_rt_put(rt); + return ret; +} + +static bool rpfilter_is_local(const struct sk_buff *skb) +{ + const struct rt6_info *rt = (const void *) skb_dst(skb); + return rt && (rt->rt6i_flags & RTF_LOCAL); +} + +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 (rpfilter_is_local(skb)) + 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/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index beb2fd5cebb..2c99b94eeca 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -6,7 +6,7 @@ * 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/ipv6.h> @@ -16,121 +16,120 @@ #include <asm/byteorder.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_rt.h> MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("IPv6 RT match"); +MODULE_DESCRIPTION("Xtables: IPv6 Routing Header match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* Returns 1 if the id is matched by the range, 0 otherwise */ -static inline int -segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, int invert) +static inline bool +segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) { - int r=0; - DEBUGP("rt segsleft_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ', - min,id,max); - r=(id >= min && id <= max) ^ invert; - DEBUGP(" result %s\n",r? "PASS" : "FAILED"); - return r; + bool r; + pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n", + invert ? '!' : ' ', min, id, max); + r = (id >= min && id <= max) ^ invert; + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); + return r; } -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) +static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) { - struct ipv6_rt_hdr _route, *rh; - const struct ip6t_rt *rtinfo = matchinfo; - unsigned int temp; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int ret = 0; - struct in6_addr *ap, _addr; - - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING) < 0) - return 0; - - rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route); - if (rh == NULL){ - *hotdrop = 1; - return 0; - } - - hdrlen = ipv6_optlen(rh); - if (skb->len - ptr < hdrlen){ - /* Pcket smaller than its length field */ - return 0; - } - - DEBUGP("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen); - DEBUGP("TYPE %04X ", rh->type); - DEBUGP("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left); - - DEBUGP("IPv6 RT segsleft %02X ", - (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], - rh->segments_left, - !!(rtinfo->invflags & IP6T_RT_INV_SGS)))); - DEBUGP("type %02X %02X %02X ", - rtinfo->rt_type, rh->type, - (!(rtinfo->flags & IP6T_RT_TYP) || - ((rtinfo->rt_type == rh->type) ^ - !!(rtinfo->invflags & IP6T_RT_INV_TYP)))); - DEBUGP("len %02X %04X %02X ", - rtinfo->hdrlen, hdrlen, - (!(rtinfo->flags & IP6T_RT_LEN) || - ((rtinfo->hdrlen == hdrlen) ^ - !!(rtinfo->invflags & IP6T_RT_INV_LEN)))); - DEBUGP("res %02X %02X %02X ", - (rtinfo->flags & IP6T_RT_RES), ((struct rt0_hdr *)rh)->reserved, - !((rtinfo->flags & IP6T_RT_RES) && (((struct rt0_hdr *)rh)->reserved))); - - ret = (rh != NULL) - && - (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], - rh->segments_left, - !!(rtinfo->invflags & IP6T_RT_INV_SGS))) - && - (!(rtinfo->flags & IP6T_RT_LEN) || - ((rtinfo->hdrlen == hdrlen) ^ - !!(rtinfo->invflags & IP6T_RT_INV_LEN))) - && - (!(rtinfo->flags & IP6T_RT_TYP) || - ((rtinfo->rt_type == rh->type) ^ - !!(rtinfo->invflags & IP6T_RT_INV_TYP))); + struct ipv6_rt_hdr _route; + const struct ipv6_rt_hdr *rh; + const struct ip6t_rt *rtinfo = par->matchinfo; + unsigned int temp; + unsigned int ptr = 0; + unsigned int hdrlen = 0; + bool ret = false; + struct in6_addr _addr; + const struct in6_addr *ap; + int err; + + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } + + rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route); + if (rh == NULL) { + par->hotdrop = true; + return false; + } + + hdrlen = ipv6_optlen(rh); + if (skb->len - ptr < hdrlen) { + /* Pcket smaller than its length field */ + return false; + } + + pr_debug("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen); + pr_debug("TYPE %04X ", rh->type); + pr_debug("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left); + + pr_debug("IPv6 RT segsleft %02X ", + segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], + rh->segments_left, + !!(rtinfo->invflags & IP6T_RT_INV_SGS))); + pr_debug("type %02X %02X %02X ", + rtinfo->rt_type, rh->type, + (!(rtinfo->flags & IP6T_RT_TYP) || + ((rtinfo->rt_type == rh->type) ^ + !!(rtinfo->invflags & IP6T_RT_INV_TYP)))); + pr_debug("len %02X %04X %02X ", + rtinfo->hdrlen, hdrlen, + !(rtinfo->flags & IP6T_RT_LEN) || + ((rtinfo->hdrlen == hdrlen) ^ + !!(rtinfo->invflags & IP6T_RT_INV_LEN))); + pr_debug("res %02X %02X %02X ", + rtinfo->flags & IP6T_RT_RES, + ((const struct rt0_hdr *)rh)->reserved, + !((rtinfo->flags & IP6T_RT_RES) && + (((const struct rt0_hdr *)rh)->reserved))); + + ret = (rh != NULL) && + (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], + rh->segments_left, + !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && + (!(rtinfo->flags & IP6T_RT_LEN) || + ((rtinfo->hdrlen == hdrlen) ^ + !!(rtinfo->invflags & IP6T_RT_INV_LEN))) && + (!(rtinfo->flags & IP6T_RT_TYP) || + ((rtinfo->rt_type == rh->type) ^ + !!(rtinfo->invflags & IP6T_RT_INV_TYP))); if (ret && (rtinfo->flags & IP6T_RT_RES)) { - u_int32_t *rp, _reserved; + const u_int32_t *rp; + u_int32_t _reserved; rp = skb_header_pointer(skb, - ptr + offsetof(struct rt0_hdr, reserved), - sizeof(_reserved), &_reserved); + ptr + offsetof(struct rt0_hdr, + reserved), + sizeof(_reserved), + &_reserved); ret = (*rp == 0); } - DEBUGP("#%d ",rtinfo->addrnr); - if ( !(rtinfo->flags & IP6T_RT_FST) ){ - return ret; + pr_debug("#%d ", rtinfo->addrnr); + if (!(rtinfo->flags & IP6T_RT_FST)) { + return ret; } else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) { - DEBUGP("Not strict "); - if ( rtinfo->addrnr > (unsigned int)((hdrlen-8)/16) ){ - DEBUGP("There isn't enough space\n"); - return 0; + pr_debug("Not strict "); + if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) { + pr_debug("There isn't enough space\n"); + return false; } else { unsigned int i = 0; - DEBUGP("#%d ",rtinfo->addrnr); - for(temp=0; temp<(unsigned int)((hdrlen-8)/16); temp++){ + pr_debug("#%d ", rtinfo->addrnr); + for (temp = 0; + temp < (unsigned int)((hdrlen - 8) / 16); + temp++) { ap = skb_header_pointer(skb, ptr + sizeof(struct rt0_hdr) @@ -141,24 +140,26 @@ match(const struct sk_buff *skb, BUG_ON(ap == NULL); if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) { - DEBUGP("i=%d temp=%d;\n",i,temp); + pr_debug("i=%d temp=%d;\n", i, temp); i++; } - if (i==rtinfo->addrnr) break; + if (i == rtinfo->addrnr) + break; } - DEBUGP("i=%d #%d\n", i, rtinfo->addrnr); + pr_debug("i=%d #%d\n", i, rtinfo->addrnr); if (i == rtinfo->addrnr) return ret; - else return 0; + else + return false; } } else { - DEBUGP("Strict "); - if ( rtinfo->addrnr > (unsigned int)((hdrlen-8)/16) ){ - DEBUGP("There isn't enough space\n"); - return 0; + pr_debug("Strict "); + if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) { + pr_debug("There isn't enough space\n"); + return false; } else { - DEBUGP("#%d ",rtinfo->addrnr); - for(temp=0; temp<rtinfo->addrnr; temp++){ + pr_debug("#%d ", rtinfo->addrnr); + for (temp = 0; temp < rtinfo->addrnr; temp++) { ap = skb_header_pointer(skb, ptr + sizeof(struct rt0_hdr) @@ -170,63 +171,55 @@ match(const struct sk_buff *skb, if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp])) break; } - DEBUGP("temp=%d #%d\n", temp, rtinfo->addrnr); - if ((temp == rtinfo->addrnr) && (temp == (unsigned int)((hdrlen-8)/16))) + pr_debug("temp=%d #%d\n", temp, rtinfo->addrnr); + if (temp == rtinfo->addrnr && + temp == (unsigned int)((hdrlen - 8) / 16)) return ret; - else return 0; + else + return false; } } - return 0; + return false; } -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) +static int rt_mt6_check(const struct xt_mtchk_param *par) { - const struct ip6t_rt *rtinfo = matchinfo; - - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_rt))) { - DEBUGP("ip6t_rt: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_rt))); - return 0; - } - if (rtinfo->invflags & ~IP6T_RT_INV_MASK) { - DEBUGP("ip6t_rt: unknown flags %X\n", - rtinfo->invflags); - return 0; - } - if ( (rtinfo->flags & (IP6T_RT_RES|IP6T_RT_FST_MASK)) && - (!(rtinfo->flags & IP6T_RT_TYP) || - (rtinfo->rt_type != 0) || - (rtinfo->invflags & IP6T_RT_INV_TYP)) ) { - DEBUGP("`--rt-type 0' required before `--rt-0-*'"); - return 0; - } - - return 1; + const struct ip6t_rt *rtinfo = par->matchinfo; + + if (rtinfo->invflags & ~IP6T_RT_INV_MASK) { + pr_debug("unknown flags %X\n", rtinfo->invflags); + return -EINVAL; + } + if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) && + (!(rtinfo->flags & IP6T_RT_TYP) || + (rtinfo->rt_type != 0) || + (rtinfo->invflags & IP6T_RT_INV_TYP))) { + pr_debug("`--rt-type 0' required before `--rt-0-*'"); + return -EINVAL; + } + + return 0; } -static struct ip6t_match rt_match = { +static struct xt_match rt_mt6_reg __read_mostly = { .name = "rt", - .match = &match, - .checkentry = &checkentry, + .family = NFPROTO_IPV6, + .match = rt_mt6, + .matchsize = sizeof(struct ip6t_rt), + .checkentry = rt_mt6_check, .me = THIS_MODULE, }; -static int __init init(void) +static int __init rt_mt6_init(void) { - return ip6t_register_match(&rt_match); + return xt_register_match(&rt_mt6_reg); } -static void __exit cleanup(void) +static void __exit rt_mt6_exit(void) { - ip6t_unregister_match(&rt_match); + xt_unregister_match(&rt_mt6_reg); } -module_init(init); -module_exit(cleanup); +module_init(rt_mt6_init); +module_exit(rt_mt6_exit); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 4c0028671c2..ca7f6c12808 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -12,203 +12,96 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("ip6tables filter table"); -#define FILTER_VALID_HOOKS ((1 << NF_IP6_LOCAL_IN) | (1 << NF_IP6_FORWARD) | (1 << NF_IP6_LOCAL_OUT)) +#define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ + (1 << NF_INET_FORWARD) | \ + (1 << NF_INET_LOCAL_OUT)) -/* Standard entry. */ -struct ip6t_standard -{ - struct ip6t_entry entry; - struct ip6t_standard_target target; -}; - -struct ip6t_error_target -{ - struct ip6t_entry_target target; - char errorname[IP6T_FUNCTION_MAXNAMELEN]; -}; - -struct ip6t_error -{ - struct ip6t_entry entry; - struct ip6t_error_target target; -}; - -static struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[3]; - struct ip6t_error term; -} initial_table __initdata -= { { "filter", FILTER_VALID_HOOKS, 4, - sizeof(struct ip6t_standard) * 3 + sizeof(struct ip6t_error), - { [NF_IP6_LOCAL_IN] = 0, - [NF_IP6_FORWARD] = sizeof(struct ip6t_standard), - [NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 }, - { [NF_IP6_LOCAL_IN] = 0, - [NF_IP6_FORWARD] = sizeof(struct ip6t_standard), - [NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) * 2 }, - 0, NULL, { } }, - { - /* LOCAL_IN */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } }, - /* FORWARD */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } }, - /* LOCAL_OUT */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } } - }, - /* ERROR */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_error), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_error_target)), IP6T_ERROR_TARGET } }, - { } }, - "ERROR" - } - } -}; - -static struct ip6t_table packet_filter = { +static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, - .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_FILTER, }; /* The work comes in here from netfilter.c. */ static unsigned int -ip6t_hook(unsigned int hook, - struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL); -} - -static unsigned int -ip6t_local_out_hook(unsigned int hook, - struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { -#if 0 - /* root is playing with raw sockets. */ - if ((*pskb)->len < sizeof(struct iphdr) - || (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) { - if (net_ratelimit()) - printk("ip6t_hook: happy cracking.\n"); - return NF_ACCEPT; - } -#endif + const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_filter); } -static struct nf_hook_ops ip6t_ops[] = { - { - .hook = ip6t_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_IN, - .priority = NF_IP6_PRI_FILTER, - }, - { - .hook = ip6t_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_FORWARD, - .priority = NF_IP6_PRI_FILTER, - }, - { - .hook = ip6t_local_out_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_OUT, - .priority = NF_IP6_PRI_FILTER, - }, -}; +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 = true; module_param(forward, bool, 0000); -static int __init init(void) +static int __net_init ip6table_filter_net_init(struct net *net) { - int ret; - - if (forward < 0 || forward > NF_MAX_VERDICT) { - printk("iptables forward must be 0 or 1\n"); - return -EINVAL; - } + struct ip6t_replace *repl; + repl = ip6t_alloc_initial_table(&packet_filter); + if (repl == NULL) + return -ENOMEM; /* Entry 1 is the FORWARD hook */ - initial_table.entries[1].target.verdict = -forward - 1; + ((struct ip6t_standard *)repl->entries)[1].target.verdict = + forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; + + net->ipv6.ip6table_filter = + ip6t_register_table(net, &packet_filter, repl); + kfree(repl); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_filter); +} + +static void __net_exit ip6table_filter_net_exit(struct net *net) +{ + ip6t_unregister_table(net, net->ipv6.ip6table_filter); +} + +static struct pernet_operations ip6table_filter_net_ops = { + .init = ip6table_filter_net_init, + .exit = ip6table_filter_net_exit, +}; + +static int __init ip6table_filter_init(void) +{ + int ret; - /* Register table */ - ret = ip6t_register_table(&packet_filter, &initial_table.repl); + ret = register_pernet_subsys(&ip6table_filter_net_ops); if (ret < 0) return ret; /* Register hooks */ - ret = nf_register_hook(&ip6t_ops[0]); - if (ret < 0) + filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook); + if (IS_ERR(filter_ops)) { + ret = PTR_ERR(filter_ops); goto cleanup_table; - - ret = nf_register_hook(&ip6t_ops[1]); - if (ret < 0) - goto cleanup_hook0; - - ret = nf_register_hook(&ip6t_ops[2]); - if (ret < 0) - goto cleanup_hook1; + } return ret; - cleanup_hook1: - nf_unregister_hook(&ip6t_ops[1]); - cleanup_hook0: - nf_unregister_hook(&ip6t_ops[0]); cleanup_table: - ip6t_unregister_table(&packet_filter); - + unregister_pernet_subsys(&ip6table_filter_net_ops); return ret; } -static void __exit fini(void) +static void __exit ip6table_filter_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ip6t_ops[i]); - - ip6t_unregister_table(&packet_filter); + xt_hook_unlink(&packet_filter, filter_ops); + unregister_pernet_subsys(&ip6table_filter_net_ops); } -module_init(init); -module_exit(fini); +module_init(ip6table_filter_init); +module_exit(ip6table_filter_fini); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 85c1e6eada1..307bbb782d1 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -7,281 +7,140 @@ * 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. - * - * Extended to all five netfilter hooks by Brad Chapman & Harald Welte */ #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> +#include <net/ipv6.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("ip6tables mangle table"); -#define MANGLE_VALID_HOOKS ((1 << NF_IP6_PRE_ROUTING) | \ - (1 << NF_IP6_LOCAL_IN) | \ - (1 << NF_IP6_FORWARD) | \ - (1 << NF_IP6_LOCAL_OUT) | \ - (1 << NF_IP6_POST_ROUTING)) - -#if 0 -#define DEBUGP(x, args...) printk(KERN_DEBUG x, ## args) -#else -#define DEBUGP(x, args...) -#endif - -/* Standard entry. */ -struct ip6t_standard -{ - struct ip6t_entry entry; - struct ip6t_standard_target target; -}; - -struct ip6t_error_target -{ - struct ip6t_entry_target target; - char errorname[IP6T_FUNCTION_MAXNAMELEN]; -}; - -struct ip6t_error -{ - struct ip6t_entry entry; - struct ip6t_error_target target; -}; +#define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ + (1 << NF_INET_LOCAL_IN) | \ + (1 << NF_INET_FORWARD) | \ + (1 << NF_INET_LOCAL_OUT) | \ + (1 << NF_INET_POST_ROUTING)) -static struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[5]; - struct ip6t_error term; -} initial_table __initdata -= { { "mangle", MANGLE_VALID_HOOKS, 6, - sizeof(struct ip6t_standard) * 5 + sizeof(struct ip6t_error), - { [NF_IP6_PRE_ROUTING] = 0, - [NF_IP6_LOCAL_IN] = sizeof(struct ip6t_standard), - [NF_IP6_FORWARD] = sizeof(struct ip6t_standard) * 2, - [NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3, - [NF_IP6_POST_ROUTING] = sizeof(struct ip6t_standard) * 4}, - { [NF_IP6_PRE_ROUTING] = 0, - [NF_IP6_LOCAL_IN] = sizeof(struct ip6t_standard), - [NF_IP6_FORWARD] = sizeof(struct ip6t_standard) * 2, - [NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) * 3, - [NF_IP6_POST_ROUTING] = sizeof(struct ip6t_standard) * 4}, - 0, NULL, { } }, - { - /* PRE_ROUTING */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } }, - /* LOCAL_IN */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } }, - /* FORWARD */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } }, - /* LOCAL_OUT */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } }, - /* POST_ROUTING */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_standard), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_standard_target)), "" } }, { } }, - -NF_ACCEPT - 1 } } - }, - /* ERROR */ - { { { { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, { { { 0 } } }, "", "", { 0 }, { 0 }, 0, 0, 0 }, - 0, - sizeof(struct ip6t_entry), - sizeof(struct ip6t_error), - 0, { 0, 0 }, { } }, - { { { { IP6T_ALIGN(sizeof(struct ip6t_error_target)), IP6T_ERROR_TARGET } }, - { } }, - "ERROR" - } - } -}; - -static struct ip6t_table packet_mangler = { +static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, - .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_MANGLE, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6t_route_hook(unsigned int hook, - struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL); -} - static unsigned int -ip6t_local_hook(unsigned int hook, - struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) { - - unsigned long nfmark; unsigned int ret; struct in6_addr saddr, daddr; u_int8_t hop_limit; - u_int32_t flowlabel; - + u_int32_t flowlabel, mark; + int err; #if 0 /* root is playing with raw sockets. */ - if ((*pskb)->len < sizeof(struct iphdr) - || (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) { - if (net_ratelimit()) - printk("ip6t_hook: happy cracking.\n"); + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) { + net_warn_ratelimited("ip6t_hook: happy cracking\n"); return NF_ACCEPT; } #endif - /* save source/dest address, nfmark, hoplimit, flowlabel, priority, */ - memcpy(&saddr, &(*pskb)->nh.ipv6h->saddr, sizeof(saddr)); - memcpy(&daddr, &(*pskb)->nh.ipv6h->daddr, sizeof(daddr)); - nfmark = (*pskb)->nfmark; - hop_limit = (*pskb)->nh.ipv6h->hop_limit; + /* save source/dest address, mark, hoplimit, flowlabel, priority, */ + memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); + memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); + mark = skb->mark; + hop_limit = ipv6_hdr(skb)->hop_limit; /* flowlabel and prio (includes version, which shouldn't change either */ - flowlabel = *((u_int32_t *) (*pskb)->nh.ipv6h); - - ret = ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL); + flowlabel = *((u_int32_t *)ipv6_hdr(skb)); + + ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, + dev_net(out)->ipv6.ip6table_mangle); + + if (ret != NF_DROP && ret != NF_STOLEN && + (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || + !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit || + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { + err = ip6_route_me_harder(skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } - if (ret != NF_DROP && ret != NF_STOLEN - && (memcmp(&(*pskb)->nh.ipv6h->saddr, &saddr, sizeof(saddr)) - || memcmp(&(*pskb)->nh.ipv6h->daddr, &daddr, sizeof(daddr)) - || (*pskb)->nfmark != nfmark - || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) { + return ret; +} - /* something which could affect routing has changed */ +/* The work comes in here from netfilter.c. */ +static unsigned int +ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (ops->hooknum == NF_INET_LOCAL_OUT) + return ip6t_mangle_out(skb, out); + if (ops->hooknum == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, ops->hooknum, in, out, + dev_net(out)->ipv6.ip6table_mangle); + /* INPUT/FORWARD */ + return ip6t_do_table(skb, ops->hooknum, in, out, + dev_net(in)->ipv6.ip6table_mangle); +} - DEBUGP("ip6table_mangle: we'd need to re-route a packet\n"); - } +static struct nf_hook_ops *mangle_ops __read_mostly; +static int __net_init ip6table_mangle_net_init(struct net *net) +{ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_mangler); + if (repl == NULL) + return -ENOMEM; + net->ipv6.ip6table_mangle = + ip6t_register_table(net, &packet_mangler, repl); + kfree(repl); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_mangle); +} - return ret; +static void __net_exit ip6table_mangle_net_exit(struct net *net) +{ + ip6t_unregister_table(net, net->ipv6.ip6table_mangle); } -static struct nf_hook_ops ip6t_ops[] = { - { - .hook = ip6t_route_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_PRE_ROUTING, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_local_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_IN, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_route_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_FORWARD, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_local_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_OUT, - .priority = NF_IP6_PRI_MANGLE, - }, - { - .hook = ip6t_route_hook, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_POST_ROUTING, - .priority = NF_IP6_PRI_MANGLE, - }, +static struct pernet_operations ip6table_mangle_net_ops = { + .init = ip6table_mangle_net_init, + .exit = ip6table_mangle_net_exit, }; -static int __init init(void) +static int __init ip6table_mangle_init(void) { int ret; - /* Register table */ - ret = ip6t_register_table(&packet_mangler, &initial_table.repl); + ret = register_pernet_subsys(&ip6table_mangle_net_ops); if (ret < 0) return ret; /* Register hooks */ - ret = nf_register_hook(&ip6t_ops[0]); - if (ret < 0) + mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook); + if (IS_ERR(mangle_ops)) { + ret = PTR_ERR(mangle_ops); goto cleanup_table; - - ret = nf_register_hook(&ip6t_ops[1]); - if (ret < 0) - goto cleanup_hook0; - - ret = nf_register_hook(&ip6t_ops[2]); - if (ret < 0) - goto cleanup_hook1; - - ret = nf_register_hook(&ip6t_ops[3]); - if (ret < 0) - goto cleanup_hook2; - - ret = nf_register_hook(&ip6t_ops[4]); - if (ret < 0) - goto cleanup_hook3; + } return ret; - cleanup_hook3: - nf_unregister_hook(&ip6t_ops[3]); - cleanup_hook2: - nf_unregister_hook(&ip6t_ops[2]); - cleanup_hook1: - nf_unregister_hook(&ip6t_ops[1]); - cleanup_hook0: - nf_unregister_hook(&ip6t_ops[0]); cleanup_table: - ip6t_unregister_table(&packet_mangler); - + unregister_pernet_subsys(&ip6table_mangle_net_ops); return ret; } -static void __exit fini(void) +static void __exit ip6table_mangle_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ip6t_ops[i]); - - ip6t_unregister_table(&packet_mangler); + xt_hook_unlink(&packet_mangler, mangle_ops); + unregister_pernet_subsys(&ip6table_mangle_net_ops); } -module_init(init); -module_exit(fini); +module_init(ip6table_mangle_init); +module_exit(ip6table_mangle_fini); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c new file mode 100644 index 00000000000..387d8b8fc18 --- /dev/null +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -0,0 +1,330 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * 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. + * + * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT + * funded by Astaro. + */ + +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> + +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> + +static const struct xt_table nf_nat_ipv6_table = { + .name = "nat", + .valid_hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + .af = NFPROTO_IPV6, +}; + +static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + /* Force range to this IP; let proto decide mapping for + * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). + */ + struct nf_nat_range range; + + range.flags = 0; + pr_debug("Allocating NULL binding for %p (%pI6)\n", ct, + HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 : + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6); + + return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); +} + +static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct) +{ + struct net *net = nf_ct_net(ct); + unsigned int ret; + + ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat); + if (ret == NF_ACCEPT) { + if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) + ret = alloc_null_binding(ct, hooknum); + } + return ret; +} + +static unsigned int +nf_nat_ipv6_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + __be16 frag_off; + int hdrlen; + u8 nexthdr; + + ct = nf_ct_get(skb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + * have dropped it. Hence it's the user's responsibilty to + * packet filter it out, or implement conntrack/NAT for that + * protocol. 8) --RR + */ + if (!ct) + return NF_ACCEPT; + + /* Don't try to NAT if this packet is not conntracked */ + if (nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + nexthdr = ipv6_hdr(skb)->nexthdr; + hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, + ops->hooknum, + hdrlen)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + unsigned int ret; + + ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct); + if (ret != NF_ACCEPT) + return ret; + } else { + pr_debug("Already setup manip %s for ct %p\n", + maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", + ct); + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + goto oif_changed; + } + break; + + default: + /* ESTABLISHED */ + NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || + ctinfo == IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) + goto oif_changed; + } + + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; +} + +static unsigned int +nf_nat_ipv6_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + struct in6_addr daddr = ipv6_hdr(skb)->daddr; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int +nf_nat_ipv6_out(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ +#ifdef CONFIG_XFRM + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + int err; +#endif + unsigned int ret; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3) || + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) { + err = nf_xfrm_me_harder(skb, AF_INET6); + if (err < 0) + ret = NF_DROP_ERR(err); + } + } +#endif + return ret; +} + +static unsigned int +nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + int err; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.src.u3)) { + err = ip6_route_me_harder(skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#ifdef CONFIG_XFRM + else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) { + err = nf_xfrm_me_harder(skb, AF_INET6); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#endif + } + return ret; +} + +static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_in, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_out, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_local_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_NAT_SRC, + }, +}; + +static int __net_init ip6table_nat_net_init(struct net *net) +{ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); + if (repl == NULL) + return -ENOMEM; + net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); + kfree(repl); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_nat); +} + +static void __net_exit ip6table_nat_net_exit(struct net *net) +{ + ip6t_unregister_table(net, net->ipv6.ip6table_nat); +} + +static struct pernet_operations ip6table_nat_net_ops = { + .init = ip6table_nat_net_init, + .exit = ip6table_nat_net_exit, +}; + +static int __init ip6table_nat_init(void) +{ + int err; + + err = register_pernet_subsys(&ip6table_nat_net_ops); + if (err < 0) + goto err1; + + err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); + if (err < 0) + goto err2; + return 0; + +err2: + unregister_pernet_subsys(&ip6table_nat_net_ops); +err1: + return err; +} + +static void __exit ip6table_nat_exit(void) +{ + nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); + unregister_pernet_subsys(&ip6table_nat_net_ops); +} + +module_init(ip6table_nat_init); +module_exit(ip6table_nat_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index c2982efd14a..5274740acec 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -5,180 +5,83 @@ */ #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> -#define RAW_VALID_HOOKS ((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_OUT)) +#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -#if 0 -#define DEBUGP(x, args...) printk(KERN_DEBUG x, ## args) -#else -#define DEBUGP(x, args...) -#endif - -/* Standard entry. */ -struct ip6t_standard -{ - struct ip6t_entry entry; - struct ip6t_standard_target target; +static const struct xt_table packet_raw = { + .name = "raw", + .valid_hooks = RAW_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_RAW, }; -struct ip6t_error_target +/* The work comes in here from netfilter.c. */ +static unsigned int +ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - struct ip6t_entry_target target; - char errorname[IP6T_FUNCTION_MAXNAMELEN]; -}; + const struct net *net = dev_net((in != NULL) ? in : out); -struct ip6t_error -{ - struct ip6t_entry entry; - struct ip6t_error_target target; -}; + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_raw); +} -static struct -{ - struct ip6t_replace repl; - struct ip6t_standard entries[2]; - struct ip6t_error term; -} initial_table __initdata = { - .repl = { - .name = "raw", - .valid_hooks = RAW_VALID_HOOKS, - .num_entries = 3, - .size = sizeof(struct ip6t_standard) * 2 + sizeof(struct ip6t_error), - .hook_entry = { - [NF_IP6_PRE_ROUTING] = 0, - [NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) - }, - .underflow = { - [NF_IP6_PRE_ROUTING] = 0, - [NF_IP6_LOCAL_OUT] = sizeof(struct ip6t_standard) - }, - }, - .entries = { - /* PRE_ROUTING */ - { - .entry = { - .target_offset = sizeof(struct ip6t_entry), - .next_offset = sizeof(struct ip6t_standard), - }, - .target = { - .target = { - .u = { - .target_size = IP6T_ALIGN(sizeof(struct ip6t_standard_target)), - }, - }, - .verdict = -NF_ACCEPT - 1, - }, - }, - - /* LOCAL_OUT */ - { - .entry = { - .target_offset = sizeof(struct ip6t_entry), - .next_offset = sizeof(struct ip6t_standard), - }, - .target = { - .target = { - .u = { - .target_size = IP6T_ALIGN(sizeof(struct ip6t_standard_target)), - }, - }, - .verdict = -NF_ACCEPT - 1, - }, - }, - }, - /* ERROR */ - .term = { - .entry = { - .target_offset = sizeof(struct ip6t_entry), - .next_offset = sizeof(struct ip6t_error), - }, - .target = { - .target = { - .u = { - .user = { - .target_size = IP6T_ALIGN(sizeof(struct ip6t_error_target)), - .name = IP6T_ERROR_TARGET, - }, - }, - }, - .errorname = "ERROR", - }, - } -}; +static struct nf_hook_ops *rawtable_ops __read_mostly; -static struct ip6t_table packet_raw = { - .name = "raw", - .valid_hooks = RAW_VALID_HOOKS, - .lock = RW_LOCK_UNLOCKED, - .me = THIS_MODULE -}; +static int __net_init ip6table_raw_net_init(struct net *net) +{ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&packet_raw); + if (repl == NULL) + return -ENOMEM; + net->ipv6.ip6table_raw = + ip6t_register_table(net, &packet_raw, repl); + kfree(repl); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_raw); +} -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6t_hook(unsigned int hook, - struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static void __net_exit ip6table_raw_net_exit(struct net *net) { - return ip6t_do_table(pskb, hook, in, out, &packet_raw, NULL); + ip6t_unregister_table(net, net->ipv6.ip6table_raw); } -static struct nf_hook_ops ip6t_ops[] = { - { - .hook = ip6t_hook, - .pf = PF_INET6, - .hooknum = NF_IP6_PRE_ROUTING, - .priority = NF_IP6_PRI_FIRST, - .owner = THIS_MODULE, - }, - { - .hook = ip6t_hook, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_OUT, - .priority = NF_IP6_PRI_FIRST, - .owner = THIS_MODULE, - }, +static struct pernet_operations ip6table_raw_net_ops = { + .init = ip6table_raw_net_init, + .exit = ip6table_raw_net_exit, }; -static int __init init(void) +static int __init ip6table_raw_init(void) { int ret; - /* Register table */ - ret = ip6t_register_table(&packet_raw, &initial_table.repl); + ret = register_pernet_subsys(&ip6table_raw_net_ops); if (ret < 0) return ret; /* Register hooks */ - ret = nf_register_hook(&ip6t_ops[0]); - if (ret < 0) + rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook); + if (IS_ERR(rawtable_ops)) { + ret = PTR_ERR(rawtable_ops); goto cleanup_table; - - ret = nf_register_hook(&ip6t_ops[1]); - if (ret < 0) - goto cleanup_hook0; + } return ret; - cleanup_hook0: - nf_unregister_hook(&ip6t_ops[0]); cleanup_table: - ip6t_unregister_table(&packet_raw); - + unregister_pernet_subsys(&ip6table_raw_net_ops); return ret; } -static void __exit fini(void) +static void __exit ip6table_raw_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ip6t_ops[i]); - - ip6t_unregister_table(&packet_raw); + xt_hook_unlink(&packet_raw, rawtable_ops); + unregister_pernet_subsys(&ip6table_raw_net_ops); } -module_init(init); -module_exit(fini); +module_init(ip6table_raw_init); +module_exit(ip6table_raw_fini); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c new file mode 100644 index 00000000000..ab3b0219ecf --- /dev/null +++ b/net/ipv6/netfilter/ip6table_security.c @@ -0,0 +1,103 @@ +/* + * "security" table for IPv6 + * + * This is for use by Mandatory Access Control (MAC) security models, + * which need to be able to manage security policy in separate context + * to DAC. + * + * Based on iptable_mangle.c + * + * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling + * Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org> + * Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com> + * + * 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. + */ +#include <linux/module.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>"); +MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); + +#define SECURITY_VALID_HOOKS (1 << NF_INET_LOCAL_IN) | \ + (1 << NF_INET_FORWARD) | \ + (1 << NF_INET_LOCAL_OUT) + +static const struct xt_table security_table = { + .name = "security", + .valid_hooks = SECURITY_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_SECURITY, +}; + +static unsigned int +ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + const struct net *net = dev_net((in != NULL) ? in : out); + + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_security); +} + +static struct nf_hook_ops *sectbl_ops __read_mostly; + +static int __net_init ip6table_security_net_init(struct net *net) +{ + struct ip6t_replace *repl; + + repl = ip6t_alloc_initial_table(&security_table); + if (repl == NULL) + return -ENOMEM; + net->ipv6.ip6table_security = + ip6t_register_table(net, &security_table, repl); + kfree(repl); + return PTR_ERR_OR_ZERO(net->ipv6.ip6table_security); +} + +static void __net_exit ip6table_security_net_exit(struct net *net) +{ + ip6t_unregister_table(net, net->ipv6.ip6table_security); +} + +static struct pernet_operations ip6table_security_net_ops = { + .init = ip6table_security_net_init, + .exit = ip6table_security_net_exit, +}; + +static int __init ip6table_security_init(void) +{ + int ret; + + ret = register_pernet_subsys(&ip6table_security_net_ops); + if (ret < 0) + return ret; + + sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook); + if (IS_ERR(sectbl_ops)) { + ret = PTR_ERR(sectbl_ops); + goto cleanup_table; + } + + return ret; + +cleanup_table: + unregister_pernet_subsys(&ip6table_security_net_ops); + return ret; +} + +static void __exit ip6table_security_fini(void) +{ + xt_hook_unlink(&security_table, sectbl_ops); + unregister_pernet_subsys(&ip6table_security_net_ops); +} + +module_init(ip6table_security_init); +module_exit(ip6table_security_fini); diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c new file mode 100644 index 00000000000..4cbc6b290dd --- /dev/null +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -0,0 +1,483 @@ +/* + * Copyright (C)2004 USAGI/WIDE Project + * + * 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. + * + * Author: + * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> + */ + +#include <linux/types.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/netfilter.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +#include <linux/netfilter_bridge.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/netfilter/nf_log.h> + +static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, + struct nf_conntrack_tuple *tuple) +{ + const u_int32_t *ap; + u_int32_t _addrs[8]; + + ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr), + sizeof(_addrs), _addrs); + if (ap == NULL) + return false; + + memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6)); + memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6)); + + return true; +} + +static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + memcpy(tuple->src.u3.ip6, orig->dst.u3.ip6, sizeof(tuple->src.u3.ip6)); + memcpy(tuple->dst.u3.ip6, orig->src.u3.ip6, sizeof(tuple->dst.u3.ip6)); + + return true; +} + +static int ipv6_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) +{ + return seq_printf(s, "src=%pI6 dst=%pI6 ", + tuple->src.u3.ip6, tuple->dst.u3.ip6); +} + +static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + unsigned int *dataoff, u_int8_t *protonum) +{ + unsigned int extoff = nhoff + sizeof(struct ipv6hdr); + __be16 frag_off; + int protoff; + u8 nexthdr; + + if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr), + &nexthdr, sizeof(nexthdr)) != 0) { + pr_debug("ip6_conntrack_core: can't get nexthdr\n"); + return -NF_ACCEPT; + } + protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off); + /* + * (protoff == skb->len) means the packet has not data, just + * IPv6 and possibly extensions headers, but it is tracked anyway + */ + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("ip6_conntrack_core: can't find proto in pkt\n"); + return -NF_ACCEPT; + } + + *dataoff = protoff; + *protonum = nexthdr; + return NF_ACCEPT; +} + +static unsigned int ipv6_helper(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + const struct nf_conn_help *help; + const struct nf_conntrack_helper *helper; + enum ip_conntrack_info ctinfo; + __be16 frag_off; + int protoff; + u8 nexthdr; + + /* This is where we call the helper: as the packet goes out. */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + /* rcu_read_lock()ed by nf_hook_slow */ + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + nexthdr = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + + return helper->help(skb, protoff, ct, ctinfo); +} + +static unsigned int ipv6_confirm(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned char pnum = ipv6_hdr(skb)->nexthdr; + int protoff; + __be16 frag_off; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; + + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + goto out; + } + + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } +out: + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb); +} + +static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return nf_conntrack_in(dev_net(in), PF_INET6, ops->hooknum, skb); +} + +static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct ipv6hdr)) { + net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); + return NF_ACCEPT; + } + return nf_conntrack_in(dev_net(out), PF_INET6, ops->hooknum, skb); +} + +static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { + { + .hook = ipv6_conntrack_in, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_conntrack_local, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv6_confirm, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_LAST, + }, + { + .hook = ipv6_helper, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv6_confirm, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_LAST-1, + }, +}; + +static int +ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *inet6 = inet6_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct sockaddr_in6 sin6; + struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; + struct nf_conn *ct; + + tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.in6 = sk->sk_v6_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.dst.protonum = sk->sk_protocol; + + if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) + return -ENOPROTOOPT; + + if (*len < 0 || (unsigned int) *len < sizeof(sin6)) + return -EINVAL; + + h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + if (!h) { + pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", + &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + sin6.sin6_family = AF_INET6; + sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; + sin6.sin6_flowinfo = inet6->flow_label & IPV6_FLOWINFO_MASK; + memcpy(&sin6.sin6_addr, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, + sizeof(sin6.sin6_addr)); + + nf_ct_put(ct); + sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, + sk->sk_bound_dev_if); + return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static int ipv6_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + if (nla_put(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4, + &tuple->src.u3.ip6) || + nla_put(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4, + &tuple->dst.u3.ip6)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nla_policy ipv6_nla_policy[CTA_IP_MAX+1] = { + [CTA_IP_V6_SRC] = { .len = sizeof(u_int32_t)*4 }, + [CTA_IP_V6_DST] = { .len = sizeof(u_int32_t)*4 }, +}; + +static int ipv6_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *t) +{ + if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST]) + return -EINVAL; + + memcpy(&t->src.u3.ip6, nla_data(tb[CTA_IP_V6_SRC]), + sizeof(u_int32_t) * 4); + memcpy(&t->dst.u3.ip6, nla_data(tb[CTA_IP_V6_DST]), + sizeof(u_int32_t) * 4); + + return 0; +} + +static int ipv6_nlattr_tuple_size(void) +{ + return nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1); +} +#endif + +struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { + .l3proto = PF_INET6, + .name = "ipv6", + .pkt_to_tuple = ipv6_pkt_to_tuple, + .invert_tuple = ipv6_invert_tuple, + .print_tuple = ipv6_print_tuple, + .get_l4proto = ipv6_get_l4proto, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = ipv6_tuple_to_nlattr, + .nlattr_tuple_size = ipv6_nlattr_tuple_size, + .nlattr_to_tuple = ipv6_nlattr_to_tuple, + .nla_policy = ipv6_nla_policy, +#endif + .me = THIS_MODULE, +}; + +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); + +static struct nf_sockopt_ops so_getorigdst6 = { + .pf = NFPROTO_IPV6, + .get_optmin = IP6T_SO_ORIGINAL_DST, + .get_optmax = IP6T_SO_ORIGINAL_DST + 1, + .get = ipv6_getorigdst, + .owner = THIS_MODULE, +}; + +static int ipv6_net_init(struct net *net) +{ + int ret = 0; + + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp6); + if (ret < 0) { + pr_err("nf_conntrack_tcp6: pernet registration failed\n"); + goto out; + } + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp6); + if (ret < 0) { + pr_err("nf_conntrack_udp6: pernet registration failed\n"); + goto cleanup_tcp6; + } + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmpv6); + if (ret < 0) { + pr_err("nf_conntrack_icmp6: pernet registration failed\n"); + goto cleanup_udp6; + } + ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: pernet registration failed.\n"); + goto cleanup_icmpv6; + } + return 0; + cleanup_icmpv6: + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6); + cleanup_udp6: + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6); + cleanup_tcp6: + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6); + out: + return ret; +} + +static void ipv6_net_exit(struct net *net) +{ + nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6); +} + +static struct pernet_operations ipv6_net_ops = { + .init = ipv6_net_init, + .exit = ipv6_net_exit, +}; + +static int __init nf_conntrack_l3proto_ipv6_init(void) +{ + int ret = 0; + + need_conntrack(); + nf_defrag_ipv6_enable(); + + ret = nf_register_sockopt(&so_getorigdst6); + if (ret < 0) { + pr_err("Unable to register netfilter socket option\n"); + return ret; + } + + ret = register_pernet_subsys(&ipv6_net_ops); + if (ret < 0) + goto cleanup_sockopt; + + ret = nf_register_hooks(ipv6_conntrack_ops, + ARRAY_SIZE(ipv6_conntrack_ops)); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register pre-routing defrag " + "hook.\n"); + goto cleanup_pernet; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n"); + goto cleanup_hooks; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register udp6 proto.\n"); + goto cleanup_tcp6; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmpv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register icmpv6 proto.\n"); + goto cleanup_udp6; + } + + ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n"); + goto cleanup_icmpv6; + } + return ret; + + cleanup_icmpv6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); + cleanup_udp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6); + cleanup_tcp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + cleanup_hooks: + nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); + cleanup_pernet: + unregister_pernet_subsys(&ipv6_net_ops); + cleanup_sockopt: + nf_unregister_sockopt(&so_getorigdst6); + return ret; +} + +static void __exit nf_conntrack_l3proto_ipv6_fini(void) +{ + synchronize_net(); + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); + nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); + unregister_pernet_subsys(&ipv6_net_ops); + nf_unregister_sockopt(&so_getorigdst6); +} + +module_init(nf_conntrack_l3proto_ipv6_init); +module_exit(nf_conntrack_l3proto_ipv6_fini); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c new file mode 100644 index 00000000000..b3807c5cb88 --- /dev/null +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -0,0 +1,396 @@ +/* + * Copyright (C)2003,2004 USAGI/WIDE Project + * + * 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. + * + * Author: + * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> + */ + +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/in6.h> +#include <linux/icmpv6.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <net/ip6_checksum.h> +#include <linux/seq_file.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h> +#include <net/netfilter/nf_log.h> + +static unsigned int nf_ct_icmpv6_timeout __read_mostly = 30*HZ; + +static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + +static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct nf_conntrack_tuple *tuple) +{ + const struct icmp6hdr *hp; + struct icmp6hdr _hdr; + + hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hp == NULL) + return false; + tuple->dst.u.icmp.type = hp->icmp6_type; + tuple->src.u.icmp.id = hp->icmp6_identifier; + tuple->dst.u.icmp.code = hp->icmp6_code; + + return true; +} + +/* Add 1; spaces filled with 0. */ +static const u_int8_t invmap[] = { + [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, + [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, + [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY +1 +}; + +static const u_int8_t noct_valid_new[] = { + [ICMPV6_MGM_QUERY - 130] = 1, + [ICMPV6_MGM_REPORT -130] = 1, + [ICMPV6_MGM_REDUCTION - 130] = 1, + [NDISC_ROUTER_SOLICITATION - 130] = 1, + [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, + [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, + [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, + [ICMPV6_MLD2_REPORT - 130] = 1 +}; + +static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + int type = orig->dst.u.icmp.type - 128; + if (type < 0 || type >= sizeof(invmap) || !invmap[type]) + return false; + + tuple->src.u.icmp.id = orig->src.u.icmp.id; + tuple->dst.u.icmp.type = invmap[type] - 1; + tuple->dst.u.icmp.code = orig->dst.u.icmp.code; + return true; +} + +/* Print out the per-protocol part of the tuple. */ +static int icmpv6_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) +{ + return seq_printf(s, "type=%u code=%u id=%u ", + tuple->dst.u.icmp.type, + tuple->dst.u.icmp.code, + ntohs(tuple->src.u.icmp.id)); +} + +static unsigned int *icmpv6_get_timeouts(struct net *net) +{ + return &icmpv6_pernet(net)->timeout; +} + +/* Returns verdict for packet, or -1 for invalid. */ +static int icmpv6_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + u_int8_t pf, + unsigned int hooknum, + unsigned int *timeout) +{ + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + + return NF_ACCEPT; +} + +/* Called when a new connection for this protocol found. */ +static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff, unsigned int *timeouts) +{ + static const u_int8_t valid_new[] = { + [ICMPV6_ECHO_REQUEST - 128] = 1, + [ICMPV6_NI_QUERY - 128] = 1 + }; + int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128; + + if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { + /* Can't create a new ICMPv6 `conn' with this. */ + pr_debug("icmpv6: can't create new conn with type %u\n", + type + 128); + nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple); + if (LOG_INVALID(nf_ct_net(ct), IPPROTO_ICMPV6)) + nf_log_packet(nf_ct_net(ct), PF_INET6, 0, skb, NULL, + NULL, NULL, + "nf_ct_icmpv6: invalid new with type %d ", + type + 128); + return false; + } + return true; +} + +static int +icmpv6_error_message(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, + unsigned int icmp6off, + enum ip_conntrack_info *ctinfo, + unsigned int hooknum) +{ + struct nf_conntrack_tuple intuple, origtuple; + const struct nf_conntrack_tuple_hash *h; + const struct nf_conntrack_l4proto *inproto; + u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; + + NF_CT_ASSERT(skb->nfct == NULL); + + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct icmp6hdr), + PF_INET6, &origtuple)) { + pr_debug("icmpv6_error: Can't get tuple\n"); + return -NF_ACCEPT; + } + + /* rcu_read_lock()ed by nf_hook_slow */ + inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum); + + /* Ordinarily, we'd expect the inverted tupleproto, but it's + been preserved inside the ICMP. */ + if (!nf_ct_invert_tuple(&intuple, &origtuple, + &nf_conntrack_l3proto_ipv6, inproto)) { + pr_debug("icmpv6_error: Can't invert tuple\n"); + return -NF_ACCEPT; + } + + *ctinfo = IP_CT_RELATED; + + h = nf_conntrack_find_get(net, zone, &intuple); + if (!h) { + pr_debug("icmpv6_error: no match\n"); + return -NF_ACCEPT; + } else { + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + *ctinfo += IP_CT_IS_REPLY; + } + + /* Update skb to refer to this connection */ + skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; + skb->nfctinfo = *ctinfo; + return NF_ACCEPT; +} + +static int +icmpv6_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, + enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum) +{ + const struct icmp6hdr *icmp6h; + struct icmp6hdr _ih; + int type; + + icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); + if (icmp6h == NULL) { + if (LOG_INVALID(net, IPPROTO_ICMPV6)) + nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL, + "nf_ct_icmpv6: short packet "); + return -NF_ACCEPT; + } + + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { + if (LOG_INVALID(net, IPPROTO_ICMPV6)) + nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL, + "nf_ct_icmpv6: ICMPv6 checksum failed "); + return -NF_ACCEPT; + } + + type = icmp6h->icmp6_type - 130; + if (type >= 0 && type < sizeof(noct_valid_new) && + noct_valid_new[type]) { + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + return NF_ACCEPT; + } + + /* is not error message ? */ + if (icmp6h->icmp6_type >= 128) + return NF_ACCEPT; + + return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum); +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *t) +{ + if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { + [CTA_PROTO_ICMPV6_TYPE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMPV6_CODE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMPV6_ID] = { .type = NLA_U16 }, +}; + +static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMPV6_TYPE] || + !tb[CTA_PROTO_ICMPV6_CODE] || + !tb[CTA_PROTO_ICMPV6_ID]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); + + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) + return -EINVAL; + + return 0; +} + +static int icmpv6_nlattr_tuple_size(void) +{ + return nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); +} +#endif + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) +{ + unsigned int *timeout = data; + struct nf_icmp_net *in = icmpv6_pernet(net); + + if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; + } else { + /* Set default ICMPv6 timeout. */ + *timeout = in->timeout; + } + return 0; +} + +static int +icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { + [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + +#ifdef CONFIG_SYSCTL +static struct ctl_table icmpv6_sysctl_table[] = { + { + .procname = "nf_conntrack_icmpv6_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; +#endif /* CONFIG_SYSCTL */ + +static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmpv6_sysctl_table, + sizeof(icmpv6_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmpv6_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmpv6_timeout; + + return icmpv6_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6.pn; +} + +struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = +{ + .l3proto = PF_INET6, + .l4proto = IPPROTO_ICMPV6, + .name = "icmpv6", + .pkt_to_tuple = icmpv6_pkt_to_tuple, + .invert_tuple = icmpv6_invert_tuple, + .print_tuple = icmpv6_print_tuple, + .packet = icmpv6_packet, + .get_timeouts = icmpv6_get_timeouts, + .new = icmpv6_new, + .error = icmpv6_error, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = icmpv6_tuple_to_nlattr, + .nlattr_tuple_size = icmpv6_nlattr_tuple_size, + .nlattr_to_tuple = icmpv6_nlattr_to_tuple, + .nla_policy = icmpv6_nla_policy, +#endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, + .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmpv6_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .init_net = icmpv6_init_net, + .get_net_proto = icmpv6_get_net_proto, +}; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c new file mode 100644 index 00000000000..0d5279fd852 --- /dev/null +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -0,0 +1,694 @@ +/* + * IPv6 fragment reassembly for connection tracking + * + * Copyright (C)2004 USAGI/WIDE Project + * + * Author: + * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> + * + * Based on: net/ipv6/reassembly.c + * + * 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. + */ + +#define pr_fmt(fmt) "IPv6-nf: " fmt + +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <linux/jiffies.h> +#include <linux/net.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/in6.h> +#include <linux/ipv6.h> +#include <linux/icmpv6.h> +#include <linux/random.h> +#include <linux/slab.h> + +#include <net/sock.h> +#include <net/snmp.h> +#include <net/inet_frag.h> + +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/transp_v6.h> +#include <net/rawv6.h> +#include <net/ndisc.h> +#include <net/addrconf.h> +#include <net/inet_ecn.h> +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <linux/sysctl.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + + +struct nf_ct_frag6_skb_cb +{ + struct inet6_skb_parm h; + int offset; + struct sk_buff *orig; +}; + +#define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb*)((skb)->cb)) + +static struct inet_frags nf_frags; + +#ifdef CONFIG_SYSCTL +static struct ctl_table nf_ct_frag6_sysctl_table[] = { + { + .procname = "nf_conntrack_frag6_timeout", + .data = &init_net.nf_frag.frags.timeout, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "nf_conntrack_frag6_low_thresh", + .data = &init_net.nf_frag.frags.low_thresh, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "nf_conntrack_frag6_high_thresh", + .data = &init_net.nf_frag.frags.high_thresh, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static int nf_ct_frag6_sysctl_register(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = nf_ct_frag6_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), + GFP_KERNEL); + if (table == NULL) + goto err_alloc; + + table[0].data = &net->nf_frag.frags.timeout; + table[1].data = &net->nf_frag.frags.low_thresh; + table[2].data = &net->nf_frag.frags.high_thresh; + } + + hdr = register_net_sysctl(net, "net/netfilter", table); + if (hdr == NULL) + goto err_reg; + + net->nf_frag.sysctl.frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) +{ + struct ctl_table *table; + + table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +#else +static int nf_ct_frag6_sysctl_register(struct net *net) +{ + return 0; +} +static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) +{ +} +#endif + +static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) +{ + return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); +} + +static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr, + const struct in6_addr *daddr) +{ + u32 c; + + net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd)); + c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, nf_frags.rnd); + return c & (INETFRAGS_HASHSZ - 1); +} + + +static unsigned int nf_hashfn(struct inet_frag_queue *q) +{ + const struct frag_queue *nq; + + nq = container_of(q, struct frag_queue, q); + return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); +} + +static void nf_skb_free(struct sk_buff *skb) +{ + if (NFCT_FRAG6_CB(skb)->orig) + kfree_skb(NFCT_FRAG6_CB(skb)->orig); +} + +static void nf_ct_frag6_expire(unsigned long data) +{ + struct frag_queue *fq; + struct net *net; + + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + net = container_of(fq->q.net, struct net, nf_frag.frags); + + ip6_expire_frag_queue(net, fq, &nf_frags); +} + +/* Creation primitives. */ +static inline struct frag_queue *fq_find(struct net *net, __be32 id, + u32 user, struct in6_addr *src, + struct in6_addr *dst, u8 ecn) +{ + struct inet_frag_queue *q; + struct ip6_create_arg arg; + unsigned int hash; + + arg.id = id; + arg.user = user; + arg.src = src; + arg.dst = dst; + arg.ecn = ecn; + + read_lock_bh(&nf_frags.lock); + hash = nf_hash_frag(id, src, dst); + + q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); + local_bh_enable(); + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } + return container_of(q, struct frag_queue, q); +} + + +static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, + const struct frag_hdr *fhdr, int nhoff) +{ + struct sk_buff *prev, *next; + unsigned int payload_len; + int offset, end; + u8 ecn; + + if (fq->q.last_in & INET_FRAG_COMPLETE) { + pr_debug("Already completed\n"); + goto err; + } + + payload_len = ntohs(ipv6_hdr(skb)->payload_len); + + offset = ntohs(fhdr->frag_off) & ~0x7; + end = offset + (payload_len - + ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); + + if ((unsigned int)end > IPV6_MAXPLEN) { + pr_debug("offset is too large.\n"); + return -1; + } + + ecn = ip6_frag_ecn(ipv6_hdr(skb)); + + if (skb->ip_summed == CHECKSUM_COMPLETE) { + const unsigned char *nh = skb_network_header(skb); + skb->csum = csum_sub(skb->csum, + csum_partial(nh, (u8 *)(fhdr + 1) - nh, + 0)); + } + + /* Is this the final fragment? */ + if (!(fhdr->frag_off & htons(IP6_MF))) { + /* If we already have some bits beyond end + * or have different end, the segment is corrupted. + */ + if (end < fq->q.len || + ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) { + pr_debug("already received last fragment\n"); + goto err; + } + fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.len = end; + } else { + /* Check if the fragment is rounded to 8 bytes. + * Required by the RFC. + */ + if (end & 0x7) { + /* RFC2460 says always send parameter problem in + * this case. -DaveM + */ + pr_debug("end of fragment not rounded to 8 bytes.\n"); + return -1; + } + if (end > fq->q.len) { + /* Some bits beyond end -> corruption. */ + if (fq->q.last_in & INET_FRAG_LAST_IN) { + pr_debug("last packet already reached.\n"); + goto err; + } + fq->q.len = end; + } + } + + if (end == offset) + goto err; + + /* Point into the IP datagram 'data' part. */ + if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) { + pr_debug("queue: message is too short.\n"); + goto err; + } + if (pskb_trim_rcsum(skb, end - offset)) { + pr_debug("Can't trim\n"); + goto err; + } + + /* Find out which fragments are in front and at the back of us + * in the chain of fragments so far. We must know where to put + * this fragment, right? + */ + prev = fq->q.fragments_tail; + if (!prev || NFCT_FRAG6_CB(prev)->offset < offset) { + next = NULL; + goto found; + } + prev = NULL; + for (next = fq->q.fragments; next != NULL; next = next->next) { + if (NFCT_FRAG6_CB(next)->offset >= offset) + break; /* bingo! */ + prev = next; + } + +found: + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. + */ + + /* Check for overlap with preceding fragment. */ + if (prev && + (NFCT_FRAG6_CB(prev)->offset + prev->len) > offset) + goto discard_fq; + + /* Look for overlap with succeeding segment. */ + if (next && NFCT_FRAG6_CB(next)->offset < end) + goto discard_fq; + + NFCT_FRAG6_CB(skb)->offset = offset; + + /* Insert this fragment in the chain of fragments. */ + skb->next = next; + if (!next) + fq->q.fragments_tail = skb; + if (prev) + prev->next = skb; + else + fq->q.fragments = skb; + + if (skb->dev) { + fq->iif = skb->dev->ifindex; + skb->dev = NULL; + } + fq->q.stamp = skb->tstamp; + fq->q.meat += skb->len; + fq->ecn |= ecn; + if (payload_len > fq->q.max_size) + fq->q.max_size = payload_len; + add_frag_mem_limit(&fq->q, skb->truesize); + + /* The first fragment. + * nhoffset is obtained from the first fragment, of course. + */ + if (offset == 0) { + fq->nhoffset = nhoff; + fq->q.last_in |= INET_FRAG_FIRST_IN; + } + + inet_frag_lru_move(&fq->q); + return 0; + +discard_fq: + inet_frag_kill(&fq->q, &nf_frags); +err: + return -1; +} + +/* + * Check if this packet is complete. + * Returns NULL on failure by any reason, and pointer + * to current nexthdr field in reassembled frame. + * + * It is called with locked fq, and caller must check that + * queue is eligible for reassembly i.e. it is not COMPLETE, + * the last and the first frames arrived and all the bits are here. + */ +static struct sk_buff * +nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) +{ + struct sk_buff *fp, *op, *head = fq->q.fragments; + int payload_len; + u8 ecn; + + inet_frag_kill(&fq->q, &nf_frags); + + WARN_ON(head == NULL); + WARN_ON(NFCT_FRAG6_CB(head)->offset != 0); + + ecn = ip_frag_ecn_table[fq->ecn]; + if (unlikely(ecn == 0xff)) + goto out_fail; + + /* Unfragmented part is taken from the first segment. */ + payload_len = ((head->data - skb_network_header(head)) - + sizeof(struct ipv6hdr) + fq->q.len - + sizeof(struct frag_hdr)); + if (payload_len > IPV6_MAXPLEN) { + pr_debug("payload len is too large.\n"); + goto out_oversize; + } + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) { + pr_debug("skb is cloned but can't expand head"); + goto out_oom; + } + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + 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_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; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + + NFCT_FRAG6_CB(clone)->orig = NULL; + add_frag_mem_limit(&fq->q, clone->truesize); + } + + /* We have to remove fragment header from datagram and to relocate + * header in order to calculate ICV correctly. */ + skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; + memmove(head->head + sizeof(struct frag_hdr), head->head, + (head->data - head->head) - sizeof(struct frag_hdr)); + head->mac_header += sizeof(struct frag_hdr); + head->network_header += sizeof(struct frag_hdr); + + skb_shinfo(head)->frag_list = head->next; + skb_reset_transport_header(head); + skb_push(head, head->data - skb_network_header(head)); + + for (fp=head->next; fp; fp = fp->next) { + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + } + sub_frag_mem_limit(&fq->q, head->truesize); + + head->ignore_df = 1; + head->next = NULL; + head->dev = dev; + head->tstamp = fq->q.stamp; + ipv6_hdr(head)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); + IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; + + /* Yes, and fold redundant checksum back. 8) */ + if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_partial(skb_network_header(head), + skb_network_header_len(head), + head->csum); + + fq->q.fragments = NULL; + fq->q.fragments_tail = NULL; + + /* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */ + fp = skb_shinfo(head)->frag_list; + if (fp && NFCT_FRAG6_CB(fp)->orig == NULL) + /* at above code, head skb is divided into two skbs. */ + fp = fp->next; + + op = NFCT_FRAG6_CB(head)->orig; + for (; fp; fp = fp->next) { + struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig; + + op->next = orig; + op = orig; + NFCT_FRAG6_CB(fp)->orig = NULL; + } + + return head; + +out_oversize: + net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", + payload_len); + goto out_fail; +out_oom: + net_dbg_ratelimited("nf_ct_frag6_reasm: no memory for reassembly\n"); +out_fail: + return NULL; +} + +/* + * find the header just before Fragment Header. + * + * if success return 0 and set ... + * (*prevhdrp): the value of "Next Header Field" in the header + * just before Fragment Header. + * (*prevhoff): the offset of "Next Header Field" in the header + * just before Fragment Header. + * (*fhoff) : the offset of Fragment Header. + * + * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c + * + */ +static int +find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) +{ + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + const int netoff = skb_network_offset(skb); + u8 prev_nhoff = netoff + offsetof(struct ipv6hdr, nexthdr); + int start = netoff + sizeof(struct ipv6hdr); + int len = skb->len - start; + u8 prevhdr = NEXTHDR_IPV6; + + while (nexthdr != NEXTHDR_FRAGMENT) { + struct ipv6_opt_hdr hdr; + int hdrlen; + + if (!ipv6_ext_hdr(nexthdr)) { + return -1; + } + if (nexthdr == NEXTHDR_NONE) { + pr_debug("next header is none\n"); + return -1; + } + if (len < (int)sizeof(struct ipv6_opt_hdr)) { + pr_debug("too short\n"); + return -1; + } + if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) + BUG(); + if (nexthdr == NEXTHDR_AUTH) + hdrlen = (hdr.hdrlen+2)<<2; + else + hdrlen = ipv6_optlen(&hdr); + + prevhdr = nexthdr; + prev_nhoff = start; + + nexthdr = hdr.nexthdr; + len -= hdrlen; + start += hdrlen; + } + + if (len < 0) + return -1; + + *prevhdrp = prevhdr; + *prevhoff = prev_nhoff; + *fhoff = start; + + return 0; +} + +struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) +{ + struct sk_buff *clone; + struct net_device *dev = skb->dev; + struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev) + : dev_net(skb->dev); + struct frag_hdr *fhdr; + struct frag_queue *fq; + struct ipv6hdr *hdr; + int fhoff, nhoff; + u8 prevhdr; + struct sk_buff *ret_skb = NULL; + + /* Jumbo payload inhibits frag. header */ + if (ipv6_hdr(skb)->payload_len == 0) { + pr_debug("payload len = 0\n"); + return skb; + } + + if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) + return skb; + + clone = skb_clone(skb, GFP_ATOMIC); + if (clone == NULL) { + pr_debug("Can't clone skb\n"); + return skb; + } + + NFCT_FRAG6_CB(clone)->orig = skb; + + if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) { + pr_debug("message is too short.\n"); + goto ret_orig; + } + + skb_set_transport_header(clone, fhoff); + hdr = ipv6_hdr(clone); + fhdr = (struct frag_hdr *)skb_transport_header(clone); + + local_bh_disable(); + inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false); + local_bh_enable(); + + fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, + ip6_frag_ecn(hdr)); + if (fq == NULL) { + pr_debug("Can't find and can't create new queue\n"); + goto ret_orig; + } + + spin_lock_bh(&fq->q.lock); + + if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) { + spin_unlock_bh(&fq->q.lock); + pr_debug("Can't insert skb to queue\n"); + inet_frag_put(&fq->q, &nf_frags); + goto ret_orig; + } + + if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + ret_skb = nf_ct_frag6_reasm(fq, dev); + if (ret_skb == NULL) + pr_debug("Can't reassemble fragmented packets\n"); + } + spin_unlock_bh(&fq->q.lock); + + inet_frag_put(&fq->q, &nf_frags); + return ret_skb; + +ret_orig: + kfree_skb(clone); + return skb; +} + +void nf_ct_frag6_consume_orig(struct sk_buff *skb) +{ + struct sk_buff *s, *s2; + + for (s = NFCT_FRAG6_CB(skb)->orig; s;) { + s2 = s->next; + s->next = NULL; + consume_skb(s); + s = s2; + } +} + +static int nf_ct_net_init(struct net *net) +{ + net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH; + net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT; + inet_frags_init_net(&net->nf_frag.frags); + + return nf_ct_frag6_sysctl_register(net); +} + +static void nf_ct_net_exit(struct net *net) +{ + nf_ct_frags6_sysctl_unregister(net); + inet_frags_exit_net(&net->nf_frag.frags, &nf_frags); +} + +static struct pernet_operations nf_ct_net_ops = { + .init = nf_ct_net_init, + .exit = nf_ct_net_exit, +}; + +int nf_ct_frag6_init(void) +{ + int ret = 0; + + nf_frags.hashfn = nf_hashfn; + nf_frags.constructor = ip6_frag_init; + nf_frags.destructor = NULL; + nf_frags.skb_free = nf_skb_free; + nf_frags.qsize = sizeof(struct frag_queue); + nf_frags.match = ip6_frag_match; + nf_frags.frag_expire = nf_ct_frag6_expire; + nf_frags.secret_interval = 10 * 60 * HZ; + inet_frags_init(&nf_frags); + + ret = register_pernet_subsys(&nf_ct_net_ops); + if (ret) + inet_frags_fini(&nf_frags); + + return ret; +} + +void nf_ct_frag6_cleanup(void) +{ + unregister_pernet_subsys(&nf_ct_net_ops); + inet_frags_fini(&nf_frags); +} diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c new file mode 100644 index 00000000000..7b9a748c6ba --- /dev/null +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -0,0 +1,140 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * + * 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. + */ + +#include <linux/types.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/netfilter.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> +#include <linux/sysctl.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#endif +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + +static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ + u16 zone = NF_CT_DEFAULT_ZONE; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + if (skb->nfct) + zone = nf_ct_zone((struct nf_conn *)skb->nfct); +#endif + +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge && + skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; +#endif + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN + zone; + else + return IP6_DEFRAG_CONNTRACK_OUT + zone; + +} + +static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct sk_buff *reasm; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + /* Previously seen (loopback)? */ + if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) + return NF_ACCEPT; +#endif + + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(ops->hooknum, skb)); + /* queued */ + if (reasm == NULL) + return NF_STOLEN; + + /* error occurred or not fragmented */ + if (reasm == skb) + return NF_ACCEPT; + + nf_ct_frag6_consume_orig(reasm); + + NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, reasm, + (struct net_device *) in, (struct net_device *) out, + okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); + + return NF_STOLEN; +} + +static struct nf_hook_ops ipv6_defrag_ops[] = { + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, +}; + +static int __init nf_defrag_init(void) +{ + int ret = 0; + + ret = nf_ct_frag6_init(); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't initialize frag6.\n"); + return ret; + } + ret = nf_register_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't register hooks\n"); + goto cleanup_frag6; + } + return ret; + +cleanup_frag6: + nf_ct_frag6_cleanup(); + return ret; + +} + +static void __exit nf_defrag_fini(void) +{ + nf_unregister_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); + nf_ct_frag6_cleanup(); +} + +void nf_defrag_ipv6_enable(void) +{ +} +EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); + +module_init(nf_defrag_init); +module_exit(nf_defrag_fini); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c new file mode 100644 index 00000000000..abfe75a2e31 --- /dev/null +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -0,0 +1,288 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * 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. + * + * Development of IPv6 NAT funded by Astaro. + */ +#include <linux/types.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <net/secure_seq.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <net/ip6_route.h> +#include <net/ipv6.h> + +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static const struct nf_nat_l3proto nf_nat_l3proto_ipv6; + +#ifdef CONFIG_XFRM +static void nf_nat_ipv6_decode_session(struct sk_buff *skb, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + unsigned long statusbit, + struct flowi *fl) +{ + const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; + struct flowi6 *fl6 = &fl->u.ip6; + + if (ct->status & statusbit) { + fl6->daddr = t->dst.u3.in6; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl6->fl6_dport = t->dst.u.all; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl6->saddr = t->src.u3.in6; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl6->fl6_sport = t->src.u.all; + } +} +#endif + +static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t, + const struct nf_nat_range *range) +{ + return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 && + ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0; +} + +static u32 nf_nat_ipv6_secure_port(const struct nf_conntrack_tuple *t, + __be16 dport) +{ + return secure_ipv6_port_ephemeral(t->src.u3.ip6, t->dst.u3.ip6, dport); +} + +static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, + unsigned int iphdroff, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype) +{ + struct ipv6hdr *ipv6h; + __be16 frag_off; + int hdroff; + u8 nexthdr; + + if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) + return false; + + ipv6h = (void *)skb->data + iphdroff; + nexthdr = ipv6h->nexthdr; + hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), + &nexthdr, &frag_off); + if (hdroff < 0) + goto manip_addr; + + if ((frag_off & htons(~0x7)) == 0 && + !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, + target, maniptype)) + return false; +manip_addr: + if (maniptype == NF_NAT_MANIP_SRC) + ipv6h->saddr = target->src.u3.in6; + else + ipv6h->daddr = target->dst.u3.in6; + + return true; +} + +static void nf_nat_ipv6_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype) +{ + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); + const struct in6_addr *oldip, *newip; + + if (maniptype == NF_NAT_MANIP_SRC) { + oldip = &ipv6h->saddr; + newip = &t->src.u3.in6; + } else { + oldip = &ipv6h->daddr; + newip = &t->dst.u3.in6; + } + inet_proto_csum_replace16(check, skb, oldip->s6_addr32, + newip->s6_addr32, 1); +} + +static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, + u8 proto, void *data, __sum16 *check, + int datalen, int oldlen) +{ + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(rt->rt6i_flags & RTF_LOCAL) && + (!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + + skb_network_offset(skb) + + (data - (void *)skb->data); + skb->csum_offset = (void *)check - data; + *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, proto, 0); + } else { + *check = 0; + *check = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, proto, + csum_partial(data, datalen, + 0)); + if (proto == IPPROTO_UDP && !*check) + *check = CSUM_MANGLED_0; + } + } else + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), 1); +} + +static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range) +{ + if (tb[CTA_NAT_V6_MINIP]) { + nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], + sizeof(struct in6_addr)); + range->flags |= NF_NAT_RANGE_MAP_IPS; + } + + if (tb[CTA_NAT_V6_MAXIP]) + nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP], + sizeof(struct in6_addr)); + else + range->max_addr = range->min_addr; + + return 0; +} + +static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { + .l3proto = NFPROTO_IPV6, + .secure_port = nf_nat_ipv6_secure_port, + .in_range = nf_nat_ipv6_in_range, + .manip_pkt = nf_nat_ipv6_manip_pkt, + .csum_update = nf_nat_ipv6_csum_update, + .csum_recalc = nf_nat_ipv6_csum_recalc, + .nlattr_to_range = nf_nat_ipv6_nlattr_to_range, +#ifdef CONFIG_XFRM + .decode_session = nf_nat_ipv6_decode_session, +#endif +}; + +int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + unsigned int hdrlen) +{ + struct { + struct icmp6hdr icmp6; + struct ipv6hdr ip6; + } *inside; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); + const struct nf_nat_l4proto *l4proto; + struct nf_conntrack_tuple target; + unsigned long statusbit; + + NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY); + + if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + return 0; + if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) + return 0; + + inside = (void *)skb->data + hdrlen; + if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { + if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) + return 0; + if (ct->status & IPS_NAT_MASK) + return 0; + } + + if (manip == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply direction */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + + l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, inside->ip6.nexthdr); + if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), + l4proto, &ct->tuplehash[!dir].tuple, !manip)) + return 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + inside = (void *)skb->data + hdrlen; + inside->icmp6.icmp6_cksum = 0; + inside->icmp6.icmp6_cksum = + csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + skb->len - hdrlen, IPPROTO_ICMPV6, + csum_partial(&inside->icmp6, + skb->len - hdrlen, 0)); + } + + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, IPPROTO_ICMPV6); + if (!nf_nat_ipv6_manip_pkt(skb, 0, l4proto, &target, manip)) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); + +static int __init nf_nat_l3proto_ipv6_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6); + if (err < 0) + goto err1; + err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv6); + if (err < 0) + goto err2; + return err; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6); +err1: + return err; +} + +static void __exit nf_nat_l3proto_ipv6_exit(void) +{ + nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6); + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6); +} + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("nf-nat-" __stringify(AF_INET6)); + +module_init(nf_nat_l3proto_ipv6_init); +module_exit(nf_nat_l3proto_ipv6_exit); diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c new file mode 100644 index 00000000000..2205e8eeeac --- /dev/null +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -0,0 +1,90 @@ +/* + * Copyright (c) 2011 Patrick Mchardy <kaber@trash.net> + * + * 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. + * + * Based on Rusty Russell's IPv4 ICMP NAT code. Development of IPv6 + * NAT funded by Astaro. + */ + +#include <linux/types.h> +#include <linux/init.h> +#include <linux/icmpv6.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static bool +icmpv6_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) && + ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id); +} + +static void +icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + static u16 id; + unsigned int range_size; + unsigned int i; + + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; + + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) + range_size = 0xffff; + + for (i = 0; ; ++id) { + tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) + + (id % range_size)); + if (++i == range_size || !nf_nat_used_tuple(tuple, ct)) + return; + } +} + +static bool +icmpv6_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct icmp6hdr *hdr; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct icmp6hdr *)(skb->data + hdroff); + l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum, + tuple, maniptype); + if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || + hdr->icmp6_type == ICMPV6_ECHO_REPLY) { + inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, + hdr->icmp6_identifier, + tuple->src.u.icmp.id, 0); + hdr->icmp6_identifier = tuple->src.u.icmp.id; + } + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = { + .l4proto = IPPROTO_ICMPV6, + .manip_pkt = icmpv6_manip_pkt, + .in_range = icmpv6_in_range, + .unique_tuple = icmpv6_unique_tuple, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c new file mode 100644 index 00000000000..0d812b31277 --- /dev/null +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -0,0 +1,128 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org> + * + * 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. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/ipv6.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv6.h> + +static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + /* malformed packet, drop it */ + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + return NF_DROP; + + return nft_do_chain(&pkt, ops); +} + +static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (unlikely(skb->len < sizeof(struct ipv6hdr))) { + if (net_ratelimit()) + pr_info("nf_tables_ipv6: ignoring short SOCK_RAW " + "packet\n"); + return NF_ACCEPT; + } + + return nft_do_chain_ipv6(ops, skb, in, out, okfn); +} + +struct nft_af_info nft_af_ipv6 __read_mostly = { + .family = NFPROTO_IPV6, + .nhooks = NF_INET_NUMHOOKS, + .owner = THIS_MODULE, + .nops = 1, + .hooks = { + [NF_INET_LOCAL_IN] = nft_do_chain_ipv6, + [NF_INET_LOCAL_OUT] = nft_ipv6_output, + [NF_INET_FORWARD] = nft_do_chain_ipv6, + [NF_INET_PRE_ROUTING] = nft_do_chain_ipv6, + [NF_INET_POST_ROUTING] = nft_do_chain_ipv6, + }, +}; +EXPORT_SYMBOL_GPL(nft_af_ipv6); + +static int nf_tables_ipv6_init_net(struct net *net) +{ + net->nft.ipv6 = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.ipv6 == NULL) + return -ENOMEM; + + memcpy(net->nft.ipv6, &nft_af_ipv6, sizeof(nft_af_ipv6)); + + if (nft_register_afinfo(net, net->nft.ipv6) < 0) + goto err; + + return 0; +err: + kfree(net->nft.ipv6); + return -ENOMEM; +} + +static void nf_tables_ipv6_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.ipv6); + kfree(net->nft.ipv6); +} + +static struct pernet_operations nf_tables_ipv6_net_ops = { + .init = nf_tables_ipv6_init_net, + .exit = nf_tables_ipv6_exit_net, +}; + +static const struct nf_chain_type filter_ipv6 = { + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING), +}; + +static int __init nf_tables_ipv6_init(void) +{ + int ret; + + nft_register_chain_type(&filter_ipv6); + ret = register_pernet_subsys(&nf_tables_ipv6_net_ops); + if (ret < 0) + nft_unregister_chain_type(&filter_ipv6); + + return ret; +} + +static void __exit nf_tables_ipv6_exit(void) +{ + unregister_pernet_subsys(&nf_tables_ipv6_net_ops); + nft_unregister_chain_type(&filter_ipv6); +} + +module_init(nf_tables_ipv6_init); +module_exit(nf_tables_ipv6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_FAMILY(AF_INET6); diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c new file mode 100644 index 00000000000..d189fcb437f --- /dev/null +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -0,0 +1,205 @@ +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv6.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/ipv6.h> + +/* + * IPv6 NAT chains + */ + +static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_conn_nat *nat; + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + __be16 frag_off; + int hdrlen; + u8 nexthdr; + struct nft_pktinfo pkt; + unsigned int ret; + + if (ct == NULL || nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + nat = nf_ct_nat_ext_add(ct); + if (nat == NULL) + return NF_ACCEPT; + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED + IP_CT_IS_REPLY: + nexthdr = ipv6_hdr(skb)->nexthdr; + hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, + ops->hooknum, + hdrlen)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall through */ + case IP_CT_NEW: + if (nf_nat_initialized(ct, maniptype)) + break; + + nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out); + + ret = nft_do_chain(&pkt, ops); + if (ret != NF_ACCEPT) + return ret; + if (!nf_nat_initialized(ct, maniptype)) { + ret = nf_nat_alloc_null_binding(ct, ops->hooknum); + if (ret != NF_ACCEPT) + return ret; + } + default: + break; + } + + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); +} + +static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct in6_addr daddr = ipv6_hdr(skb)->daddr; + unsigned int ret; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo __maybe_unused; + const struct nf_conn *ct __maybe_unused; + unsigned int ret; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) + if (nf_xfrm_me_harder(skb, AF_INET6) < 0) + ret = NF_DROP; + } +#endif + return ret; +} + +static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + unsigned int ret; + + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.src.u3)) { + if (ip6_route_me_harder(skb)) + ret = NF_DROP; + } +#ifdef CONFIG_XFRM + else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) + if (nf_xfrm_me_harder(skb, AF_INET6)) + ret = NF_DROP; +#endif + } + return ret; +} + +static const struct nf_chain_type nft_chain_nat_ipv6 = { + .name = "nat", + .type = NFT_CHAIN_T_NAT, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .hooks = { + [NF_INET_PRE_ROUTING] = nf_nat_ipv6_prerouting, + [NF_INET_POST_ROUTING] = nf_nat_ipv6_postrouting, + [NF_INET_LOCAL_OUT] = nf_nat_ipv6_output, + [NF_INET_LOCAL_IN] = nf_nat_ipv6_fn, + }, +}; + +static int __init nft_chain_nat_ipv6_init(void) +{ + int err; + + err = nft_register_chain_type(&nft_chain_nat_ipv6); + if (err < 0) + return err; + + return 0; +} + +static void __exit nft_chain_nat_ipv6_exit(void) +{ + nft_unregister_chain_type(&nft_chain_nat_ipv6); +} + +module_init(nft_chain_nat_ipv6_init); +module_exit(nft_chain_nat_ipv6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); +MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c new file mode 100644 index 00000000000..42031299585 --- /dev/null +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -0,0 +1,88 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org> + * + * 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. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv6.h> +#include <net/route.h> + +static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + struct nft_pktinfo pkt; + struct in6_addr saddr, daddr; + u_int8_t hop_limit; + u32 mark, flowlabel; + + /* malformed packet, drop it */ + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + return NF_DROP; + + /* save source/dest address, mark, hoplimit, flowlabel, priority */ + memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); + memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); + mark = skb->mark; + hop_limit = ipv6_hdr(skb)->hop_limit; + + /* flowlabel and prio (includes version, which shouldn't change either */ + flowlabel = *((u32 *)ipv6_hdr(skb)); + + ret = nft_do_chain(&pkt, ops); + if (ret != NF_DROP && ret != NF_QUEUE && + (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || + memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit || + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) + return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; + + return ret; +} + +static const struct nf_chain_type nft_chain_route_ipv6 = { + .name = "route", + .type = NFT_CHAIN_T_ROUTE, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_INET_LOCAL_OUT), + .hooks = { + [NF_INET_LOCAL_OUT] = nf_route_table_hook, + }, +}; + +static int __init nft_chain_route_init(void) +{ + return nft_register_chain_type(&nft_chain_route_ipv6); +} + +static void __exit nft_chain_route_exit(void) +{ + nft_unregister_chain_type(&nft_chain_route_ipv6); +} + +module_init(nft_chain_route_init); +module_exit(nft_chain_route_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route"); diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c new file mode 100644 index 00000000000..0bc19fa8782 --- /dev/null +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -0,0 +1,76 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * 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. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> +#include <net/netfilter/ipv6/nf_reject.h> + +void nft_reject_ipv6_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nf_send_unreach6(net, pkt->skb, priv->icmp_code, + pkt->ops->hooknum); + break; + case NFT_REJECT_TCP_RST: + nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + break; + } + + data[NFT_REG_VERDICT].verdict = NF_DROP; +} +EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval); + +static struct nft_expr_type nft_reject_ipv6_type; +static const struct nft_expr_ops nft_reject_ipv6_ops = { + .type = &nft_reject_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_ipv6_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "reject", + .ops = &nft_reject_ipv6_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_ipv6_module_init(void) +{ + return nft_register_expr(&nft_reject_ipv6_type); +} + +static void __exit nft_reject_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_reject_ipv6_type); +} + +module_init(nft_reject_ipv6_module_init); +module_exit(nft_reject_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject"); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c new file mode 100644 index 00000000000..5ec867e4a8b --- /dev/null +++ b/net/ipv6/output_core.c @@ -0,0 +1,98 @@ +/* + * IPv6 library code, needed by static components when full IPv6 support is + * not configured or static. These functions are needed by GSO/GRO implementation. + */ +#include <linux/export.h> +#include <net/ipv6.h> +#include <net/ip6_fib.h> +#include <net/addrconf.h> +#include <net/secure_seq.h> + +int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int packet_len = skb_tail_pointer(skb) - + skb_network_header(skb); + int found_rhdr = 0; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + found_rhdr = 1; + break; + case NEXTHDR_DEST: +#if IS_ENABLED(CONFIG_IPV6_MIP6) + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + break; +#endif + if (found_rhdr) + return offset; + break; + default : + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); + } + + return offset; +} +EXPORT_SYMBOL(ip6_find_1stfragopt); + +#if IS_ENABLED(CONFIG_IPV6) +int ip6_dst_hoplimit(struct dst_entry *dst) +{ + int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); + if (hoplimit == 0) { + struct net_device *dev = dst->dev; + struct inet6_dev *idev; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) + hoplimit = idev->cnf.hop_limit; + else + hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; + rcu_read_unlock(); + } + return hoplimit; +} +EXPORT_SYMBOL(ip6_dst_hoplimit); +#endif + +int __ip6_local_out(struct sk_buff *skb) +{ + int len; + + len = skb->len - sizeof(struct ipv6hdr); + if (len > IPV6_MAXPLEN) + len = 0; + ipv6_hdr(skb)->payload_len = htons(len); + IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); + + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + skb_dst(skb)->dev, dst_output); +} +EXPORT_SYMBOL_GPL(__ip6_local_out); + +int ip6_local_out(struct sk_buff *skb) +{ + int err; + + err = __ip6_local_out(skb); + if (likely(err == 1)) + err = dst_output(skb); + + return err; +} +EXPORT_SYMBOL_GPL(ip6_local_out); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c new file mode 100644 index 00000000000..5b7a1ed2aba --- /dev/null +++ b/net/ipv6/ping.c @@ -0,0 +1,275 @@ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * "Ping" sockets + * + * 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. + * + * Based on ipv4/ping.c code. + * + * Authors: Lorenzo Colitti (IPv6 support) + * Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6), + * Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32) + * + */ + +#include <net/addrconf.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/protocol.h> +#include <net/udp.h> +#include <net/transp_v6.h> +#include <net/ping.h> + +struct proto pingv6_prot = { + .name = "PINGv6", + .owner = THIS_MODULE, + .init = ping_init_sock, + .close = ping_close, + .connect = ip6_datagram_connect_v6_only, + .disconnect = udp_disconnect, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .sendmsg = ping_v6_sendmsg, + .recvmsg = ping_recvmsg, + .bind = ping_bind, + .backlog_rcv = ping_queue_rcv_skb, + .hash = ping_hash, + .unhash = ping_unhash, + .get_port = ping_get_port, + .obj_size = sizeof(struct raw6_sock), +}; +EXPORT_SYMBOL_GPL(pingv6_prot); + +static struct inet_protosw pingv6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMPV6, + .prot = &pingv6_prot, + .ops = &inet6_dgram_ops, + .flags = INET_PROTOSW_REUSE, +}; + + +/* Compatibility glue so we can support IPv6 when it's compiled as a module */ +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) +{ + return -EAFNOSUPPORT; +} +static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ +} +static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) +{ + return -EAFNOSUPPORT; +} +static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) {} +static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict) +{ + return 0; +} + +int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct icmp6hdr user_icmph; + int addr_type; + struct in6_addr *daddr; + int iif = 0; + struct flowi6 fl6; + int err; + int hlimit; + struct dst_entry *dst; + struct rt6_info *rt; + struct pingfakehdr pfh; + + pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); + + err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, + sizeof(user_icmph)); + if (err) + return err; + + if (msg->msg_name) { + DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); + if (msg->msg_namelen < sizeof(struct sockaddr_in6) || + u->sin6_family != AF_INET6) { + return -EINVAL; + } + if (sk->sk_bound_dev_if && + sk->sk_bound_dev_if != u->sin6_scope_id) { + return -EINVAL; + } + daddr = &(u->sin6_addr); + iif = u->sin6_scope_id; + } else { + if (sk->sk_state != TCP_ESTABLISHED) + return -EDESTADDRREQ; + daddr = &sk->sk_v6_daddr; + } + + if (!iif) + iif = sk->sk_bound_dev_if; + + addr_type = ipv6_addr_type(daddr); + if (__ipv6_addr_needs_scope_id(addr_type) && !iif) + return -EINVAL; + if (addr_type & IPV6_ADDR_MAPPED) + return -EINVAL; + + /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ + + memset(&fl6, 0, sizeof(fl6)); + + fl6.flowi6_proto = IPPROTO_ICMPV6; + fl6.saddr = np->saddr; + fl6.daddr = *daddr; + fl6.flowi6_mark = sk->sk_mark; + fl6.fl6_icmp_type = user_icmph.icmp6_type; + fl6.fl6_icmp_code = user_icmph.icmp6_code; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr); + if (IS_ERR(dst)) + return PTR_ERR(dst); + rt = (struct rt6_info *) dst; + + np = inet6_sk(sk); + if (!np) + return -EBADF; + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + + pfh.icmph.type = user_icmph.icmp6_type; + pfh.icmph.code = user_icmph.icmp6_code; + pfh.icmph.checksum = 0; + pfh.icmph.un.echo.id = inet->inet_sport; + pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; + pfh.iov = msg->msg_iov; + pfh.wcheck = 0; + pfh.family = AF_INET6; + + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + + lock_sock(sk); + err = ip6_append_data(sk, ping_getfrag, &pfh, len, + 0, hlimit, + np->tclass, NULL, &fl6, rt, + MSG_DONTWAIT, np->dontfrag); + + if (err) { + ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); + ip6_flush_pending_frames(sk); + } else { + err = icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *) &pfh.icmph, + len); + } + release_sock(sk); + + if (err) + return err; + + return len; +} + +#ifdef CONFIG_PROC_FS +static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos) +{ + return ping_seq_start(seq, pos, AF_INET6); +} + +static int ping_v6_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct ping_iter_state *) seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } + return 0; +} + +static struct ping_seq_afinfo ping_v6_seq_afinfo = { + .name = "icmp6", + .family = AF_INET6, + .seq_fops = &ping_seq_fops, + .seq_ops = { + .start = ping_v6_seq_start, + .show = ping_v6_seq_show, + .next = ping_seq_next, + .stop = ping_seq_stop, + }, +}; + +static int __net_init ping_v6_proc_init_net(struct net *net) +{ + return ping_proc_register(net, &ping_v6_seq_afinfo); +} + +static void __net_init ping_v6_proc_exit_net(struct net *net) +{ + return ping_proc_unregister(net, &ping_v6_seq_afinfo); +} + +static struct pernet_operations ping_v6_net_ops = { + .init = ping_v6_proc_init_net, + .exit = ping_v6_proc_exit_net, +}; +#endif + +int __init pingv6_init(void) +{ +#ifdef CONFIG_PROC_FS + int ret = register_pernet_subsys(&ping_v6_net_ops); + if (ret) + return ret; +#endif + pingv6_ops.ipv6_recv_error = ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = + ip6_datagram_recv_specific_ctl; + pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; + return inet6_register_protosw(&pingv6_protosw); +} + +/* This never gets called because it's not possible to unload the ipv6 module, + * but just in case. + */ +void pingv6_exit(void) +{ + pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; + pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; + pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; + pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; +#ifdef CONFIG_PROC_FS + unregister_pernet_subsys(&ping_v6_net_ops); +#endif + inet6_unregister_protosw(&pingv6_protosw); +} diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 50a13e75d70..3317440ea34 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -7,8 +7,6 @@ * PROC file system. This is very similar to the IPv4 version, * except it reports the sockets in the INET6 address family. * - * Version: $Id: proc.c,v 1.17 2002/02/01 22:01:04 davem Exp $ - * * Authors: David S. Miller (davem@caip.rutgers.edu) * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> * @@ -17,49 +15,54 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> -#include <linux/sched.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/ipv6.h> #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> #include <net/tcp.h> +#include <net/udp.h> #include <net/transp_v6.h> #include <net/ipv6.h> -#ifdef CONFIG_PROC_FS -static struct proc_dir_entry *proc_net_devsnmp6; - -static int fold_prot_inuse(struct proto *proto) -{ - int res = 0; - int cpu; - - for (cpu=0; cpu<NR_CPUS; cpu++) - res += proto->stats[cpu].inuse; - - return res; -} - static int sockstat6_seq_show(struct seq_file *seq, void *v) { + struct net *net = seq->private; + seq_printf(seq, "TCP6: inuse %d\n", - fold_prot_inuse(&tcpv6_prot)); + sock_prot_inuse_get(net, &tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", - fold_prot_inuse(&udpv6_prot)); + sock_prot_inuse_get(net, &udpv6_prot)); + seq_printf(seq, "UDPLITE6: inuse %d\n", + sock_prot_inuse_get(net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", - fold_prot_inuse(&rawv6_prot)); + sock_prot_inuse_get(net, &rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", - ip6_frag_nqueues, atomic_read(&ip6_frag_mem)); + ip6_frag_nqueues(net), ip6_frag_mem(net)); return 0; } -static struct snmp_mib snmp6_ipstats_list[] = { +static int sockstat6_seq_open(struct inode *inode, struct file *file) +{ + return single_open_net(inode, file, sockstat6_seq_show); +} + +static const struct file_operations sockstat6_seq_fops = { + .owner = THIS_MODULE, + .open = sockstat6_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release_net, +}; + +static const struct snmp_mib snmp6_ipstats_list[] = { /* ipv6 mib according to RFC 2465 */ - SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INRECEIVES), + SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INPKTS), SNMP_MIB_ITEM("Ip6InHdrErrors", IPSTATS_MIB_INHDRERRORS), SNMP_MIB_ITEM("Ip6InTooBigErrors", IPSTATS_MIB_INTOOBIGERRORS), SNMP_MIB_ITEM("Ip6InNoRoutes", IPSTATS_MIB_INNOROUTES), @@ -69,7 +72,7 @@ static struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("Ip6InDelivers", IPSTATS_MIB_INDELIVERS), SNMP_MIB_ITEM("Ip6OutForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS), - SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTREQUESTS), + SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTPKTS), SNMP_MIB_ITEM("Ip6OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("Ip6OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("Ip6ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -81,117 +84,183 @@ static struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6FragCreates", IPSTATS_MIB_FRAGCREATES), SNMP_MIB_ITEM("Ip6InMcastPkts", IPSTATS_MIB_INMCASTPKTS), SNMP_MIB_ITEM("Ip6OutMcastPkts", IPSTATS_MIB_OUTMCASTPKTS), + SNMP_MIB_ITEM("Ip6InOctets", IPSTATS_MIB_INOCTETS), + SNMP_MIB_ITEM("Ip6OutOctets", IPSTATS_MIB_OUTOCTETS), + SNMP_MIB_ITEM("Ip6InMcastOctets", IPSTATS_MIB_INMCASTOCTETS), + SNMP_MIB_ITEM("Ip6OutMcastOctets", IPSTATS_MIB_OUTMCASTOCTETS), + SNMP_MIB_ITEM("Ip6InBcastOctets", IPSTATS_MIB_INBCASTOCTETS), + SNMP_MIB_ITEM("Ip6OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS), + /* IPSTATS_MIB_CSUMERRORS is not relevant in IPv6 (no checksum) */ + SNMP_MIB_ITEM("Ip6InNoECTPkts", IPSTATS_MIB_NOECTPKTS), + SNMP_MIB_ITEM("Ip6InECT1Pkts", IPSTATS_MIB_ECT1PKTS), + SNMP_MIB_ITEM("Ip6InECT0Pkts", IPSTATS_MIB_ECT0PKTS), + SNMP_MIB_ITEM("Ip6InCEPkts", IPSTATS_MIB_CEPKTS), SNMP_MIB_SENTINEL }; -static struct snmp_mib snmp6_icmp6_list[] = { -/* icmpv6 mib according to RFC 2466 - - Exceptions: {In|Out}AdminProhibs are removed, because I see - no good reasons to account them separately - of another dest.unreachs. - OutErrs is zero identically. - OutEchos too. - OutRouterAdvertisements too. - OutGroupMembQueries too. - */ +static const struct snmp_mib snmp6_icmp6_list[] = { +/* icmpv6 mib according to RFC 2466 */ SNMP_MIB_ITEM("Icmp6InMsgs", ICMP6_MIB_INMSGS), SNMP_MIB_ITEM("Icmp6InErrors", ICMP6_MIB_INERRORS), - SNMP_MIB_ITEM("Icmp6InDestUnreachs", ICMP6_MIB_INDESTUNREACHS), - SNMP_MIB_ITEM("Icmp6InPktTooBigs", ICMP6_MIB_INPKTTOOBIGS), - SNMP_MIB_ITEM("Icmp6InTimeExcds", ICMP6_MIB_INTIMEEXCDS), - SNMP_MIB_ITEM("Icmp6InParmProblems", ICMP6_MIB_INPARMPROBLEMS), - SNMP_MIB_ITEM("Icmp6InEchos", ICMP6_MIB_INECHOS), - SNMP_MIB_ITEM("Icmp6InEchoReplies", ICMP6_MIB_INECHOREPLIES), - SNMP_MIB_ITEM("Icmp6InGroupMembQueries", ICMP6_MIB_INGROUPMEMBQUERIES), - SNMP_MIB_ITEM("Icmp6InGroupMembResponses", ICMP6_MIB_INGROUPMEMBRESPONSES), - SNMP_MIB_ITEM("Icmp6InGroupMembReductions", ICMP6_MIB_INGROUPMEMBREDUCTIONS), - SNMP_MIB_ITEM("Icmp6InRouterSolicits", ICMP6_MIB_INROUTERSOLICITS), - SNMP_MIB_ITEM("Icmp6InRouterAdvertisements", ICMP6_MIB_INROUTERADVERTISEMENTS), - SNMP_MIB_ITEM("Icmp6InNeighborSolicits", ICMP6_MIB_INNEIGHBORSOLICITS), - SNMP_MIB_ITEM("Icmp6InNeighborAdvertisements", ICMP6_MIB_INNEIGHBORADVERTISEMENTS), - SNMP_MIB_ITEM("Icmp6InRedirects", ICMP6_MIB_INREDIRECTS), SNMP_MIB_ITEM("Icmp6OutMsgs", ICMP6_MIB_OUTMSGS), - SNMP_MIB_ITEM("Icmp6OutDestUnreachs", ICMP6_MIB_OUTDESTUNREACHS), - SNMP_MIB_ITEM("Icmp6OutPktTooBigs", ICMP6_MIB_OUTPKTTOOBIGS), - SNMP_MIB_ITEM("Icmp6OutTimeExcds", ICMP6_MIB_OUTTIMEEXCDS), - SNMP_MIB_ITEM("Icmp6OutParmProblems", ICMP6_MIB_OUTPARMPROBLEMS), - SNMP_MIB_ITEM("Icmp6OutEchoReplies", ICMP6_MIB_OUTECHOREPLIES), - SNMP_MIB_ITEM("Icmp6OutRouterSolicits", ICMP6_MIB_OUTROUTERSOLICITS), - SNMP_MIB_ITEM("Icmp6OutNeighborSolicits", ICMP6_MIB_OUTNEIGHBORSOLICITS), - SNMP_MIB_ITEM("Icmp6OutNeighborAdvertisements", ICMP6_MIB_OUTNEIGHBORADVERTISEMENTS), - SNMP_MIB_ITEM("Icmp6OutRedirects", ICMP6_MIB_OUTREDIRECTS), - SNMP_MIB_ITEM("Icmp6OutGroupMembResponses", ICMP6_MIB_OUTGROUPMEMBRESPONSES), - SNMP_MIB_ITEM("Icmp6OutGroupMembReductions", ICMP6_MIB_OUTGROUPMEMBREDUCTIONS), + SNMP_MIB_ITEM("Icmp6OutErrors", ICMP6_MIB_OUTERRORS), + SNMP_MIB_ITEM("Icmp6InCsumErrors", ICMP6_MIB_CSUMERRORS), SNMP_MIB_SENTINEL }; -static struct snmp_mib snmp6_udp6_list[] = { +/* RFC 4293 v6 ICMPMsgStatsTable; named items for RFC 2466 compatibility */ +static const char *const icmp6type2name[256] = { + [ICMPV6_DEST_UNREACH] = "DestUnreachs", + [ICMPV6_PKT_TOOBIG] = "PktTooBigs", + [ICMPV6_TIME_EXCEED] = "TimeExcds", + [ICMPV6_PARAMPROB] = "ParmProblems", + [ICMPV6_ECHO_REQUEST] = "Echos", + [ICMPV6_ECHO_REPLY] = "EchoReplies", + [ICMPV6_MGM_QUERY] = "GroupMembQueries", + [ICMPV6_MGM_REPORT] = "GroupMembResponses", + [ICMPV6_MGM_REDUCTION] = "GroupMembReductions", + [ICMPV6_MLD2_REPORT] = "MLDv2Reports", + [NDISC_ROUTER_ADVERTISEMENT] = "RouterAdvertisements", + [NDISC_ROUTER_SOLICITATION] = "RouterSolicits", + [NDISC_NEIGHBOUR_ADVERTISEMENT] = "NeighborAdvertisements", + [NDISC_NEIGHBOUR_SOLICITATION] = "NeighborSolicits", + [NDISC_REDIRECT] = "Redirects", +}; + + +static const struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_ITEM("Udp6InDatagrams", UDP_MIB_INDATAGRAMS), SNMP_MIB_ITEM("Udp6NoPorts", UDP_MIB_NOPORTS), SNMP_MIB_ITEM("Udp6InErrors", UDP_MIB_INERRORS), SNMP_MIB_ITEM("Udp6OutDatagrams", UDP_MIB_OUTDATAGRAMS), + SNMP_MIB_ITEM("Udp6RcvbufErrors", UDP_MIB_RCVBUFERRORS), + SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS), + SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS), + SNMP_MIB_SENTINEL +}; + +static const struct snmp_mib snmp6_udplite6_list[] = { + SNMP_MIB_ITEM("UdpLite6InDatagrams", UDP_MIB_INDATAGRAMS), + SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS), + SNMP_MIB_ITEM("UdpLite6InErrors", UDP_MIB_INERRORS), + SNMP_MIB_ITEM("UdpLite6OutDatagrams", UDP_MIB_OUTDATAGRAMS), + SNMP_MIB_ITEM("UdpLite6RcvbufErrors", UDP_MIB_RCVBUFERRORS), + SNMP_MIB_ITEM("UdpLite6SndbufErrors", UDP_MIB_SNDBUFERRORS), + SNMP_MIB_ITEM("UdpLite6InCsumErrors", UDP_MIB_CSUMERRORS), SNMP_MIB_SENTINEL }; -static unsigned long -fold_field(void *mib[], int offt) +static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib) { - unsigned long res = 0; - int i; - - for_each_cpu(i) { - res += *(((unsigned long *)per_cpu_ptr(mib[0], i)) + offt); - res += *(((unsigned long *)per_cpu_ptr(mib[1], i)) + offt); - } - return res; + char name[32]; + int i; + + /* print by name -- deprecated items */ + for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { + int icmptype; + const char *p; + + icmptype = i & 0xff; + p = icmp6type2name[icmptype]; + if (!p) /* don't print un-named types here */ + continue; + snprintf(name, sizeof(name), "Icmp6%s%s", + i & 0x100 ? "Out" : "In", p); + seq_printf(seq, "%-32s\t%lu\n", name, + atomic_long_read(smib + i)); + } + + /* print by number (nonzero only) - ICMPMsgStat format */ + for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { + unsigned long val; + + val = atomic_long_read(smib + i); + if (!val) + continue; + snprintf(name, sizeof(name), "Icmp6%sType%u", + i & 0x100 ? "Out" : "In", i & 0xff); + seq_printf(seq, "%-32s\t%lu\n", name, val); + } } -static inline void -snmp6_seq_show_item(struct seq_file *seq, void **mib, struct snmp_mib *itemlist) +/* can be called either with percpu mib (pcpumib != NULL), + * or shared one (smib != NULL) + */ +static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib, + atomic_long_t *smib, + const struct snmp_mib *itemlist) { int i; - for (i=0; itemlist[i].name; i++) - seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, - fold_field(mib, itemlist[i].entry)); + unsigned long val; + + for (i = 0; itemlist[i].name; i++) { + val = pcpumib ? + snmp_fold_field(pcpumib, itemlist[i].entry) : + atomic_long_read(smib + itemlist[i].entry); + seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val); + } } -static int snmp6_seq_show(struct seq_file *seq, void *v) +static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib, + const struct snmp_mib *itemlist, size_t syncpoff) { - struct inet6_dev *idev = (struct inet6_dev *)seq->private; + int i; - if (idev) { - seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); - snmp6_seq_show_item(seq, (void **)idev->stats.icmpv6, snmp6_icmp6_list); - } else { - snmp6_seq_show_item(seq, (void **)ipv6_statistics, snmp6_ipstats_list); - snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list); - snmp6_seq_show_item(seq, (void **)udp_stats_in6, snmp6_udp6_list); - } + for (i = 0; itemlist[i].name; i++) + seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, + snmp_fold_field64(mib, itemlist[i].entry, syncpoff)); +} + +static int snmp6_seq_show(struct seq_file *seq, void *v) +{ + struct net *net = (struct net *)seq->private; + + snmp6_seq_show_item64(seq, net->mib.ipv6_statistics, + snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); + snmp6_seq_show_item(seq, net->mib.icmpv6_statistics, + NULL, snmp6_icmp6_list); + snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs); + snmp6_seq_show_item(seq, net->mib.udp_stats_in6, + NULL, snmp6_udp6_list); + snmp6_seq_show_item(seq, net->mib.udplite_stats_in6, + NULL, snmp6_udplite6_list); return 0; } -static int sockstat6_seq_open(struct inode *inode, struct file *file) +static int snmp6_seq_open(struct inode *inode, struct file *file) { - return single_open(file, sockstat6_seq_show, NULL); + return single_open_net(inode, file, snmp6_seq_show); } -static struct file_operations sockstat6_seq_fops = { +static const struct file_operations snmp6_seq_fops = { .owner = THIS_MODULE, - .open = sockstat6_seq_open, + .open = snmp6_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; -static int snmp6_seq_open(struct inode *inode, struct file *file) +static int snmp6_dev_seq_show(struct seq_file *seq, void *v) { - return single_open(file, snmp6_seq_show, PDE(inode)->data); + struct inet6_dev *idev = (struct inet6_dev *)seq->private; + + seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); + snmp6_seq_show_item64(seq, idev->stats.ipv6, + snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); + snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs, + snmp6_icmp6_list); + snmp6_seq_show_icmpv6msg(seq, idev->stats.icmpv6msgdev->mibs); + return 0; } -static struct file_operations snmp6_seq_fops = { +static int snmp6_dev_seq_open(struct inode *inode, struct file *file) +{ + return single_open(file, snmp6_dev_seq_show, PDE_DATA(inode)); +} + +static const struct file_operations snmp6_dev_seq_fops = { .owner = THIS_MODULE, - .open = snmp6_seq_open, + .open = snmp6_dev_seq_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, @@ -200,102 +269,77 @@ static struct file_operations snmp6_seq_fops = { int snmp6_register_dev(struct inet6_dev *idev) { struct proc_dir_entry *p; + struct net *net; if (!idev || !idev->dev) return -EINVAL; - if (!proc_net_devsnmp6) + net = dev_net(idev->dev); + if (!net->mib.proc_net_devsnmp6) return -ENOENT; - p = create_proc_entry(idev->dev->name, S_IRUGO, proc_net_devsnmp6); + p = proc_create_data(idev->dev->name, S_IRUGO, + net->mib.proc_net_devsnmp6, + &snmp6_dev_seq_fops, idev); if (!p) return -ENOMEM; - p->data = idev; - p->proc_fops = &snmp6_seq_fops; - idev->stats.proc_dir_entry = p; return 0; } int snmp6_unregister_dev(struct inet6_dev *idev) { - if (!proc_net_devsnmp6) + struct net *net = dev_net(idev->dev); + if (!net->mib.proc_net_devsnmp6) return -ENOENT; - if (!idev || !idev->stats.proc_dir_entry) + if (!idev->stats.proc_dir_entry) return -EINVAL; - remove_proc_entry(idev->stats.proc_dir_entry->name, - proc_net_devsnmp6); + proc_remove(idev->stats.proc_dir_entry); + idev->stats.proc_dir_entry = NULL; return 0; } -int __init ipv6_misc_proc_init(void) +static int __net_init ipv6_proc_init_net(struct net *net) { - int rc = 0; + if (!proc_create("sockstat6", S_IRUGO, net->proc_net, + &sockstat6_seq_fops)) + return -ENOMEM; - if (!proc_net_fops_create("snmp6", S_IRUGO, &snmp6_seq_fops)) + if (!proc_create("snmp6", S_IRUGO, net->proc_net, &snmp6_seq_fops)) goto proc_snmp6_fail; - proc_net_devsnmp6 = proc_mkdir("dev_snmp6", proc_net); - if (!proc_net_devsnmp6) + net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net); + if (!net->mib.proc_net_devsnmp6) goto proc_dev_snmp6_fail; + return 0; - if (!proc_net_fops_create("sockstat6", S_IRUGO, &sockstat6_seq_fops)) - goto proc_sockstat6_fail; -out: - return rc; - -proc_sockstat6_fail: - proc_net_remove("dev_snmp6"); proc_dev_snmp6_fail: - proc_net_remove("snmp6"); + remove_proc_entry("snmp6", net->proc_net); proc_snmp6_fail: - rc = -ENOMEM; - goto out; -} - -void ipv6_misc_proc_exit(void) -{ - proc_net_remove("sockstat6"); - proc_net_remove("dev_snmp6"); - proc_net_remove("snmp6"); + remove_proc_entry("sockstat6", net->proc_net); + return -ENOMEM; } -#else /* CONFIG_PROC_FS */ - - -int snmp6_register_dev(struct inet6_dev *idev) +static void __net_exit ipv6_proc_exit_net(struct net *net) { - return 0; + remove_proc_entry("sockstat6", net->proc_net); + remove_proc_entry("dev_snmp6", net->proc_net); + remove_proc_entry("snmp6", net->proc_net); } -int snmp6_unregister_dev(struct inet6_dev *idev) -{ - return 0; -} -#endif /* CONFIG_PROC_FS */ +static struct pernet_operations ipv6_proc_ops = { + .init = ipv6_proc_init_net, + .exit = ipv6_proc_exit_net, +}; -int snmp6_alloc_dev(struct inet6_dev *idev) +int __init ipv6_misc_proc_init(void) { - int err = -ENOMEM; - - if (!idev || !idev->dev) - return -EINVAL; - - if (snmp6_mib_init((void **)idev->stats.icmpv6, sizeof(struct icmpv6_mib), - __alignof__(struct icmpv6_mib)) < 0) - goto err_icmp; - - return 0; - -err_icmp: - return err; + return register_pernet_subsys(&ipv6_proc_ops); } -int snmp6_free_dev(struct inet6_dev *idev) +void ipv6_misc_proc_exit(void) { - snmp6_mib_free((void **)idev->stats.icmpv6); - return 0; + unregister_pernet_subsys(&ipv6_proc_ops); } - diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 52c1d58b6ca..e048cf1bb6a 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -5,8 +5,6 @@ * * PF_INET6 protocol dispatch tables. * - * Version: $Id: protocol.c,v 1.10 2001/05/18 02:25:49 davem Exp $ - * * Authors: Pedro Roque <roque@di.fc.ul.pt> * * This program is free software; you can redistribute it and/or @@ -22,65 +20,54 @@ * - Removed unused variable 'inet6_protocol_base' * - Modified inet6_del_protocol() to correctly maintain copy bit. */ - -#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/module.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> - -#include <net/sock.h> -#include <net/snmp.h> - -#include <net/ipv6.h> +#include <linux/spinlock.h> #include <net/protocol.h> -struct inet6_protocol *inet6_protos[MAX_INET_PROTOS]; -static DEFINE_SPINLOCK(inet6_proto_lock); +#if IS_ENABLED(CONFIG_IPV6) +const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet6_protos); - -int inet6_add_protocol(struct inet6_protocol *prot, unsigned char protocol) +int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { - int ret, hash = protocol & (MAX_INET_PROTOS - 1); + return !cmpxchg((const struct inet6_protocol **)&inet6_protos[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet6_add_protocol); - spin_lock_bh(&inet6_proto_lock); +int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol) +{ + int ret; - if (inet6_protos[hash]) { - ret = -1; - } else { - inet6_protos[hash] = prot; - ret = 0; - } + ret = (cmpxchg((const struct inet6_protocol **)&inet6_protos[protocol], + prot, NULL) == prot) ? 0 : -1; - spin_unlock_bh(&inet6_proto_lock); + synchronize_net(); return ret; } +EXPORT_SYMBOL(inet6_del_protocol); +#endif -/* - * Remove a protocol from the hash tables. - */ - -int inet6_del_protocol(struct inet6_protocol *prot, unsigned char protocol) -{ - int ret, hash = protocol & (MAX_INET_PROTOS - 1); +const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly; - spin_lock_bh(&inet6_proto_lock); +int inet6_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet6_add_offload); - if (inet6_protos[hash] != prot) { - ret = -1; - } else { - inet6_protos[hash] = NULL; - ret = 0; - } +int inet6_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; - spin_unlock_bh(&inet6_proto_lock); + ret = (cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; synchronize_net(); return ret; } +EXPORT_SYMBOL(inet6_del_offload); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a1265a320b1..b2dc60b0c76 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1,17 +1,15 @@ /* * RAW sockets for IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * - * $Id: raw.c,v 1.51 2002/02/01 22:01:04 davem Exp $ - * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support - * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) + * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data * * This program is free software; you can redistribute it and/or @@ -23,8 +21,8 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> +#include <linux/slab.h> #include <linux/sockios.h> -#include <linux/sched.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> @@ -32,10 +30,12 @@ #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> +#include <linux/skbuff.h> +#include <linux/compat.h> #include <asm/uaccess.h> #include <asm/ioctls.h> -#include <asm/bug.h> +#include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> @@ -50,57 +50,46 @@ #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> +#if IS_ENABLED(CONFIG_IPV6_MIP6) +#include <net/mip6.h> +#endif +#include <linux/mroute6.h> +#include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/export.h> -struct hlist_head raw_v6_htable[RAWV6_HTABLE_SIZE]; -DEFINE_RWLOCK(raw_v6_lock); - -static void raw_v6_hash(struct sock *sk) -{ - struct hlist_head *list = &raw_v6_htable[inet_sk(sk)->num & - (RAWV6_HTABLE_SIZE - 1)]; +#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ - write_lock_bh(&raw_v6_lock); - sk_add_node(sk, list); - sock_prot_inc_use(sk->sk_prot); - write_unlock_bh(&raw_v6_lock); -} +static struct raw_hashinfo raw_v6_hashinfo = { + .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), +}; -static void raw_v6_unhash(struct sock *sk) +static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, + unsigned short num, const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif) { - write_lock_bh(&raw_v6_lock); - if (sk_del_node_init(sk)) - sock_prot_dec_use(sk->sk_prot); - write_unlock_bh(&raw_v6_lock); -} + bool is_multicast = ipv6_addr_is_multicast(loc_addr); + sk_for_each_from(sk) + if (inet_sk(sk)->inet_num == num) { -/* Grumble... icmp and ip_input want to get at this... */ -struct sock *__raw_v6_lookup(struct sock *sk, unsigned short num, - struct in6_addr *loc_addr, struct in6_addr *rmt_addr, - int dif) -{ - struct hlist_node *node; - int is_multicast = ipv6_addr_is_multicast(loc_addr); - - sk_for_each_from(sk, node) - if (inet_sk(sk)->num == num) { - struct ipv6_pinfo *np = inet6_sk(sk); + if (!net_eq(sock_net(sk), net)) + continue; - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) @@ -118,22 +107,46 @@ found: * 0 - deliver * 1 - block */ -static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) +static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { - struct icmp6hdr *icmph; - struct raw6_sock *rp = raw6_sk(sk); + struct icmp6hdr _hdr; + const struct icmp6hdr *hdr; - if (pskb_may_pull(skb, sizeof(struct icmp6hdr))) { - __u32 *data = &rp->filter.data[0]; - int bit_nr; - - icmph = (struct icmp6hdr *) skb->data; - bit_nr = icmph->icmp6_type; + /* We require only the four bytes of the ICMPv6 header, not any + * additional bytes of message body in "struct icmp6hdr". + */ + hdr = skb_header_pointer(skb, skb_transport_offset(skb), + ICMPV6_HDRLEN, &_hdr); + if (hdr) { + const __u32 *data = &raw6_sk(sk)->filter.data[0]; + unsigned int type = hdr->icmp6_type; - return (data[bit_nr >> 5] & (1 << (bit_nr & 31))) != 0; + return (data[type >> 5] & (1U << (type & 31))) != 0; } + return 1; +} + +#if IS_ENABLED(CONFIG_IPV6_MIP6) +typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); + +static mh_filter_t __rcu *mh_filter __read_mostly; + +int rawv6_mh_filter_register(mh_filter_t filter) +{ + rcu_assign_pointer(mh_filter, filter); + return 0; +} +EXPORT_SYMBOL(rawv6_mh_filter_register); + +int rawv6_mh_filter_unregister(mh_filter_t filter) +{ + RCU_INIT_POINTER(mh_filter, NULL); + synchronize_rcu(); return 0; } +EXPORT_SYMBOL(rawv6_mh_filter_unregister); + +#endif /* * demultiplex raw sockets. @@ -142,66 +155,110 @@ static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) * * Caller owns SKB so we must make clones. */ -int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) +static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { - struct in6_addr *saddr; - struct in6_addr *daddr; + const struct in6_addr *saddr; + const struct in6_addr *daddr; struct sock *sk; - int delivered = 0; + bool delivered = false; __u8 hash; + struct net *net; - saddr = &skb->nh.ipv6h->saddr; + saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; - hash = nexthdr & (MAX_INET_PROTOS - 1); + hash = nexthdr & (RAW_HTABLE_SIZE - 1); - read_lock(&raw_v6_lock); - sk = sk_head(&raw_v6_htable[hash]); - - /* - * The first socket found will be delivered after - * delivery to transport protocols. - */ + read_lock(&raw_v6_hashinfo.lock); + sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk == NULL) goto out; - sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, IP6CB(skb)->iif); + net = dev_net(skb->dev); + sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif); while (sk) { - delivered = 1; - if (nexthdr != IPPROTO_ICMPV6 || !icmpv6_filter(sk, skb)) { + int filtered; + + delivered = true; + switch (nexthdr) { + case IPPROTO_ICMPV6: + filtered = icmpv6_filter(sk, skb); + break; + +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPPROTO_MH: + { + /* XXX: To validate MH only once for each packet, + * this is placed here. It should be after checking + * xfrm policy, however it doesn't. The checking xfrm + * policy is placed in rawv6_rcv() because it is + * required for each socket. + */ + mh_filter_t *filter; + + filter = rcu_dereference(mh_filter); + filtered = filter ? (*filter)(sk, skb) : 0; + break; + } +#endif + default: + filtered = 0; + break; + } + + if (filtered < 0) + break; + if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ - if (clone) + if (clone) { + nf_reset(clone); rawv6_rcv(sk, clone); + } } - sk = __raw_v6_lookup(sk_next(sk), nexthdr, daddr, saddr, + sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, IP6CB(skb)->iif); } out: - read_unlock(&raw_v6_lock); + read_unlock(&raw_v6_hashinfo.lock); return delivered; } +bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) +{ + struct sock *raw_sk; + + raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); + if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) + raw_sk = NULL; + + return raw_sk != NULL; +} + /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; - __u32 v4addr = 0; + __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; + + if (addr->sin6_family != AF_INET6) + return -EINVAL; + addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) - return(-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; lock_sock(sk); @@ -209,11 +266,12 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE) goto out; + rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; - if (addr_type & IPV6_ADDR_LINKLOCAL) { + if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another @@ -221,47 +279,46 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) */ sk->sk_bound_dev_if = addr->sin6_scope_id; } - + /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) - goto out; + goto out_unlock; - dev = dev_get_by_index(sk->sk_bound_dev_if); - if (!dev) { - err = -ENODEV; - goto out; - } + err = -ENODEV; + dev = dev_get_by_index_rcu(sock_net(sk), + sk->sk_bound_dev_if); + if (!dev) + goto out_unlock; } - + /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { err = -EADDRNOTAVAIL; - if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); - goto out; + if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, + dev, 0)) { + goto out_unlock; } } - if (dev) - dev_put(dev); } - inet->rcv_saddr = inet->saddr = v4addr; - ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); + inet->inet_rcv_saddr = inet->inet_saddr = v4addr; + sk->sk_v6_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(); out: release_sock(sk); return err; } -void rawv6_err(struct sock *sk, struct sk_buff *skb, +static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -277,9 +334,14 @@ void rawv6_err(struct sock *sk, struct sk_buff *skb, return; harderr = icmpv6_err_convert(type, code, &err); - if (type == ICMPV6_PKT_TOOBIG) + if (type == ICMPV6_PKT_TOOBIG) { + ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); - + } + if (type == NDISC_REDIRECT) { + ip6_sk_redirect(skb, sk); + return; + } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) @@ -293,33 +355,59 @@ void rawv6_err(struct sock *sk, struct sk_buff *skb, } } -static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) +void raw6_icmp_error(struct sk_buff *skb, int nexthdr, + u8 type, u8 code, int inner_offset, __be32 info) { - if ((raw6_sk(sk)->checksum || sk->sk_filter) && - skb->ip_summed != CHECKSUM_UNNECESSARY) { - if ((unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) { - /* FIXME: increment a raw6 drops counter here */ - kfree_skb(skb); - return 0; + struct sock *sk; + int hash; + const struct in6_addr *saddr, *daddr; + struct net *net; + + hash = nexthdr & (RAW_HTABLE_SIZE - 1); + + read_lock(&raw_v6_hashinfo.lock); + sk = sk_head(&raw_v6_hashinfo.ht[hash]); + if (sk != NULL) { + /* Note: ipv6_hdr(skb) != skb->data */ + const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; + saddr = &ip6h->saddr; + daddr = &ip6h->daddr; + net = dev_net(skb->dev); + + while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, + IP6CB(skb)->iif))) { + rawv6_err(sk, skb, NULL, type, code, + inner_offset, info); + sk = sk_next(sk); } - skb->ip_summed = CHECKSUM_UNNECESSARY; + } + read_unlock(&raw_v6_hashinfo.lock); +} + +static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && + skb_checksum_complete(skb)) { + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + return NET_RX_DROP; } /* Charge it to the socket. */ - if (sock_queue_rcv_skb(sk,skb)<0) { - /* FIXME: increment a raw6 drops counter here */ + skb_dst_drop(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); - return 0; + return NET_RX_DROP; } return 0; } /* - * This is next to useless... + * This is next to useless... * if we demultiplex in network layer we don't need the extra call - * just to queue the skb... - * maybe we could have the network decide upon a hint if it + * just to queue the skb... + * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) @@ -327,40 +415,35 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); - return NET_RX_DROP; - } + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + return NET_RX_DROP; + } if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) { - if (skb->ip_summed == CHECKSUM_HW) { - skb_postpull_rcsum(skb, skb->nh.raw, - skb->h.raw - skb->nh.raw); + if (skb->ip_summed == CHECKSUM_COMPLETE) { + skb_postpull_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); + if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; - if (csum_ipv6_magic(&skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr, - skb->len, inet->num, skb->csum)) { - LIMIT_NETDEBUG(KERN_DEBUG "raw v6 hw csum failure.\n"); - skb->ip_summed = CHECKSUM_NONE; - } - } - if (skb->ip_summed == CHECKSUM_NONE) - skb->csum = ~csum_ipv6_magic(&skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr, - skb->len, inet->num, 0); } + if (!skb_csum_unnecessary(skb)) + skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len, + inet->inet_num, 0)); if (inet->hdrincl) { - if (skb->ip_summed != CHECKSUM_UNNECESSARY && - (unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) { - /* FIXME: increment a raw6 drops counter here */ + if (skb_checksum_complete(skb)) { + atomic_inc(&sk->sk_drops); kfree_skb(skb); - return 0; + return NET_RX_DROP; } - skb->ip_summed = CHECKSUM_UNNECESSARY; } rawv6_rcv_skb(sk, skb); @@ -378,34 +461,34 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; - - if (addr_len) - *addr_len=sizeof(*sin6); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); + + if (np->rxpmtu && np->rxopt.bits.rxpmtu) + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; - if (copied > len) { - copied = len; - msg->msg_flags |= MSG_TRUNC; - } + if (copied > len) { + copied = len; + msg->msg_flags |= MSG_TRUNC; + } - if (skb->ip_summed==CHECKSUM_UNNECESSARY) { + if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); } else if (msg->msg_flags&MSG_TRUNC) { - if ((unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) + if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); } else { @@ -419,17 +502,18 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; - ipv6_addr_copy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr); + sin6->sin6_port = 0; + 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) - sin6->sin6_scope_id = IP6CB(skb)->iif; + sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, + IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) @@ -441,28 +525,16 @@ out: return err; csum_copy_err: - /* Clear queue. */ - if (flags&MSG_PEEK) { - int clear = 0; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); - clear = 1; - } - spin_unlock_bh(&sk->sk_receive_queue.lock); - if (clear) - kfree_skb(skb); - } + skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; - /* FIXME: increment a raw6 drops counter here */ - goto out_free; + goto out; } -static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, +static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct sk_buff *skb; @@ -470,8 +542,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, int offset; int len; int total_len; - u32 tmp_csum; - u16 csum; + __wsum tmp_csum; + __sum16 csum; if (!rp->checksum) goto send; @@ -480,7 +552,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, goto out; offset = rp->offset; - total_len = inet_sk(sk)->cork.length - (skb->nh.raw - skb->data); + total_len = inet_sk(sk)->cork.base.length; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); @@ -503,7 +575,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, if (csum_skb) continue; - len = skb->len - (skb->h.raw - skb->data); + len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; @@ -515,22 +587,20 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, skb = csum_skb; } - offset += skb->h.raw - skb->data; + offset += skb_transport_offset(skb); if (skb_copy_bits(skb, offset, &csum, 2)) BUG(); /* in case cksum was not initialized */ if (unlikely(csum)) - tmp_csum = csum_sub(tmp_csum, csum); + tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); - tmp_csum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - total_len, fl->proto, tmp_csum); + csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, + total_len, fl6->flowi6_proto, tmp_csum); - if (tmp_csum == 0) - tmp_csum = -1; + if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) + csum = CSUM_MANGLED_0; - csum = tmp_csum; if (skb_store_bits(skb, offset, &csum, 2)) BUG(); @@ -541,47 +611,53 @@ out: } static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, - struct flowi *fl, struct rt6_info *rt, + struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *iph; struct sk_buff *skb; - unsigned int hh_len; 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->u.dst.dev->mtu) { - ipv6_local_error(sk, EMSGSIZE, fl, rt->u.dst.dev->mtu); + if (length > rt->dst.dev->mtu) { + ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); - - skb = sock_alloc_send_skb(sk, length+hh_len+15, - flags&MSG_DONTWAIT, &err); + skb = sock_alloc_send_skb(sk, + length + hlen + tlen + 15, + flags & MSG_DONTWAIT, &err); if (skb == NULL) - goto error; - skb_reserve(skb, hh_len); + goto error; + skb_reserve(skb, hlen); + skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; - skb->dst = dst_clone(&rt->u.dst); + skb->mark = sk->sk_mark; + skb_dst_set(skb, &rt->dst); + *dstp = NULL; - skb->nh.ipv6h = iph = (struct ipv6hdr *)skb_put(skb, length); + skb_put(skb, length); + skb_reset_network_header(skb); + iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; - skb->h.raw = skb->nh.raw; + skb->transport_header = skb->network_header; err = memcpy_fromiovecend((void *)iph, from, 0, length); if (err) goto error_fault; - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); - err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, rt->u.dst.dev, - dst_output); + IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, + rt->dst.dev, dst_output); if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; out: @@ -591,27 +667,30 @@ error_fault: err = -EFAULT; kfree_skb(skb); error: - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); - return err; + IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !np->recverr) + err = 0; + return err; } -static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) +static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg) { struct iovec *iov; u8 __user *type = NULL; u8 __user *code = NULL; + u8 len = 0; int probed = 0; int i; if (!msg->msg_iov) - return; + return 0; for (i = 0; i < msg->msg_iovlen; i++) { iov = &msg->msg_iov[i]; if (!iov) continue; - switch (fl->proto) { + switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: /* check if one-byte field is readable or not. */ if (iov->iov_base && iov->iov_len < 1) @@ -626,11 +705,25 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) code = iov->iov_base; if (type && code) { - get_user(fl->fl_icmp_type, type); - get_user(fl->fl_icmp_code, code); + if (get_user(fl6->fl6_icmp_type, type) || + get_user(fl6->fl6_icmp_code, code)) + return -EFAULT; probed = 1; } break; + case IPPROTO_MH: + if (iov->iov_base && iov->iov_len < 1) + break; + /* check if type field is readable or not. */ + if (iov->iov_len > 2 - len) { + u8 __user *p = iov->iov_base; + if (get_user(fl6->fl6_mh_type, &p[2 - len])) + return -EFAULT; + probed = 1; + } else + len += iov->iov_len; + + break; default: probed = 1; break; @@ -638,68 +731,71 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) if (probed) break; } + return 0; } static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; - struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name; - struct in6_addr *daddr, *final_p = NULL, final; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); + struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; - struct flowi fl; + struct flowi6 fl6; int addr_len = msg->msg_namelen; int hlimit = -1; int tclass = -1; + int dontfrag = -1; u16 proto; int err; /* Rough check on arithmetic overflow, - better check is made in ip6_build_xmit + better check is made in ip6_append_data(). */ - if (len < 0) + if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ - if (msg->msg_flags & MSG_OOB) + if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* - * Get and verify the address. + * Get and verify the address. */ - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); + + fl6.flowi6_mark = sk->sk_mark; if (sin6) { - if (addr_len < SIN6_LEN_RFC2133) + if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - if (sin6->sin6_family && sin6->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + if (sin6->sin6_family && sin6->sin6_family != AF_INET6) + return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) - proto = inet->num; - else if (proto != inet->num) - return(-EINVAL); + proto = inet->inet_num; + else if (proto != inet->inet_num) + return -EINVAL; if (proto > 255) - return(-EINVAL); + return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { - fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - daddr = &flowlabel->dst; } } @@ -708,46 +804,38 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && - ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) - fl.oif = sin6->sin6_scope_id; + __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) + fl6.flowi6_oif = sin6->sin6_scope_id; } else { - if (sk->sk_state != TCP_ESTABLISHED) + if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - - proto = inet->num; - daddr = &np->daddr; - fl.fl6_flowlabel = np->flow_label; - } - if (ipv6_addr_any(daddr)) { - /* - * unspecified destination address - * treated as error... is this correct ? - */ - fl6_sock_release(flowlabel); - return(-EINVAL); + proto = inet->inet_num; + daddr = &sk->sk_v6_daddr; + fl6.flowlabel = np->flow_label; } - if (fl.oif == 0) - fl.oif = sk->sk_bound_dev_if; + if (fl6.flowi6_oif == 0) + fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; } @@ -756,76 +844,65 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, } if (opt == NULL) opt = np->opt; - opt = fl6_merge_options(&opt_space, flowlabel, opt); - - fl.proto = proto; - rawv6_probe_proto_opt(&fl, msg); - - ipv6_addr_copy(&fl.fl6_dst, daddr); - if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - - /* merge ip6_build_xmit from ip6_output */ - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + if (flowlabel) + opt = fl6_merge_options(&opt_space, flowlabel, opt); + opt = ipv6_fixup_options(&opt_space, opt); - if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) - fl.oif = np->mcast_oif; - - err = ip6_dst_lookup(sk, &dst, &fl); + fl6.flowi6_proto = proto; + err = rawv6_probe_proto_opt(&fl6, msg); if (err) goto out; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) - goto out; + if (!ipv6_addr_any(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)) + fl6.saddr = np->saddr; - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl.fl6_dst)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hlimit < 0) - hlimit = ipv6_get_hoplimit(dst->dev); - } + final_p = fl6_update_dst(&fl6, opt, &final); + + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) + fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (tclass < 0) { - tclass = np->cork.tclass; - if (tclass < 0) - tclass = 0; + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto out; } + if (hlimit < 0) + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + + if (tclass < 0) + tclass = np->tclass; + + if (dontfrag < 0) + dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: - if (inet->hdrincl) { - err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl, (struct rt6_info*)dst, msg->msg_flags); - } else { + if (inet->hdrincl) + err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags); + else { lock_sock(sk); err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, - len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst, - msg->msg_flags); + len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst, + msg->msg_flags, dontfrag); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) - err = rawv6_push_pending_frames(sk, &fl, rp); + err = rawv6_push_pending_frames(sk, &fl6, rp); + release_sock(sk); } done: - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? - &np->daddr : NULL); - - release_sock(sk); -out: + dst_release(dst); +out: fl6_sock_release(flowlabel); return err<0?err:len; do_confirm: @@ -836,7 +913,7 @@ do_confirm: goto done; } -static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, +static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int optlen) { switch (optname) { @@ -848,12 +925,12 @@ static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, return 0; default: return -ENOPROTOOPT; - }; + } return 0; } -static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, +static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; @@ -873,87 +950,113 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, return 0; default: return -ENOPROTOOPT; - }; + } return 0; } -static int rawv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; - switch(level) { - case SOL_RAW: - break; - - case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_seticmpfilter(sk, level, optname, optval, - optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM) - break; - default: - return ipv6_setsockopt(sk, level, optname, optval, - optlen); - }; - - if (get_user(val, (int __user *)optval)) + if (get_user(val, (int __user *)optval)) return -EFAULT; switch (optname) { - case IPV6_CHECKSUM: - /* You may get strange result with a positive odd offset; - RFC2292bis agrees with me. */ - if (val > 0 && (val&1)) - return(-EINVAL); - if (val < 0) { - rp->checksum = 0; - } else { - rp->checksum = 1; - rp->offset = val; - } + case IPV6_CHECKSUM: + if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && + level == IPPROTO_IPV6) { + /* + * RFC3542 tells that IPV6_CHECKSUM socket + * option in the IPPROTO_IPV6 level is not + * allowed on ICMPv6 sockets. + * If you want to set it, use IPPROTO_RAW + * level IPV6_CHECKSUM socket option + * (Linux extension). + */ + return -EINVAL; + } + + /* You may get strange result with a positive odd offset; + RFC2292bis agrees with me. */ + if (val > 0 && (val&1)) + return -EINVAL; + if (val < 0) { + rp->checksum = 0; + } else { + rp->checksum = 1; + rp->offset = val; + } + + return 0; - return 0; + default: + return -ENOPROTOOPT; + } +} + +static int rawv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) +{ + switch (level) { + case SOL_RAW: + break; + + case SOL_ICMPV6: + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_seticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) break; + default: + return ipv6_setsockopt(sk, level, optname, optval, optlen); + } - default: - return(-ENOPROTOOPT); + return do_rawv6_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) +{ + switch (level) { + case SOL_RAW: + break; + case SOL_ICMPV6: + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_seticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return compat_ipv6_setsockopt(sk, level, optname, + optval, optlen); } + return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } +#endif -static int rawv6_getsockopt(struct sock *sk, int level, int optname, +static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; - switch(level) { - case SOL_RAW: - break; - - case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_geticmpfilter(sk, level, optname, optval, - optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM) - break; - default: - return ipv6_getsockopt(sk, level, optname, optval, - optlen); - }; - if (get_user(len,optlen)) return -EFAULT; switch (optname) { case IPV6_CHECKSUM: + /* + * We allow getsockopt() for IPPROTO_IPV6-level + * IPV6_CHECKSUM socket option on ICMPv6 sockets + * since RFC3542 is silent about it. + */ if (rp->checksum == 0) val = -1; else @@ -973,226 +1076,267 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, return 0; } -static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int rawv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - switch(cmd) { - case SIOCOUTQ: - { - int amount = atomic_read(&sk->sk_wmem_alloc); - return put_user(amount, (int __user *)arg); - } - case SIOCINQ: - { - struct sk_buff *skb; - int amount = 0; - - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) - amount = skb->tail - skb->h.raw; - spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); - } + switch (level) { + case SOL_RAW: + break; - default: - return -ENOIOCTLCMD; + case SOL_ICMPV6: + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_geticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return ipv6_getsockopt(sk, level, optname, optval, optlen); } -} - -static void rawv6_close(struct sock *sk, long timeout) -{ - if (inet_sk(sk)->num == IPPROTO_RAW) - ip6_ra_control(sk, -1, NULL); - sk_common_release(sk); + return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } -static int rawv6_init_sk(struct sock *sk) +#ifdef CONFIG_COMPAT +static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - if (inet_sk(sk)->num == IPPROTO_ICMPV6) { - struct raw6_sock *rp = raw6_sk(sk); - rp->checksum = 1; - rp->offset = 2; + switch (level) { + case SOL_RAW: + break; + case SOL_ICMPV6: + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_geticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return compat_ipv6_getsockopt(sk, level, optname, + optval, optlen); } - return(0); + return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } +#endif -struct proto rawv6_prot = { - .name = "RAWv6", - .owner = THIS_MODULE, - .close = rawv6_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = rawv6_ioctl, - .init = rawv6_init_sk, - .destroy = inet6_destroy_sock, - .setsockopt = rawv6_setsockopt, - .getsockopt = rawv6_getsockopt, - .sendmsg = rawv6_sendmsg, - .recvmsg = rawv6_recvmsg, - .bind = rawv6_bind, - .backlog_rcv = rawv6_rcv_skb, - .hash = raw_v6_hash, - .unhash = raw_v6_unhash, - .obj_size = sizeof(struct raw6_sock), -}; - -#ifdef CONFIG_PROC_FS -struct raw6_iter_state { - int bucket; -}; - -#define raw6_seq_private(seq) ((struct raw6_iter_state *)(seq)->private) - -static struct sock *raw6_get_first(struct seq_file *seq) +static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { - struct sock *sk; - struct hlist_node *node; - struct raw6_iter_state* state = raw6_seq_private(seq); + switch (cmd) { + case SIOCOUTQ: { + int amount = sk_wmem_alloc_get(sk); - for (state->bucket = 0; state->bucket < RAWV6_HTABLE_SIZE; ++state->bucket) - sk_for_each(sk, node, &raw_v6_htable[state->bucket]) - if (sk->sk_family == PF_INET6) - goto out; - sk = NULL; -out: - return sk; -} - -static struct sock *raw6_get_next(struct seq_file *seq, struct sock *sk) -{ - struct raw6_iter_state* state = raw6_seq_private(seq); + return put_user(amount, (int __user *)arg); + } + case SIOCINQ: { + struct sk_buff *skb; + int amount = 0; - do { - sk = sk_next(sk); -try_again: - ; - } while (sk && sk->sk_family != PF_INET6); + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + if (skb != NULL) + amount = skb_tail_pointer(skb) - + skb_transport_header(skb); + spin_unlock_bh(&sk->sk_receive_queue.lock); + return put_user(amount, (int __user *)arg); + } - if (!sk && ++state->bucket < RAWV6_HTABLE_SIZE) { - sk = sk_head(&raw_v6_htable[state->bucket]); - goto try_again; + default: +#ifdef CONFIG_IPV6_MROUTE + return ip6mr_ioctl(sk, cmd, (void __user *)arg); +#else + return -ENOIOCTLCMD; +#endif } - return sk; } -static struct sock *raw6_get_idx(struct seq_file *seq, loff_t pos) +#ifdef CONFIG_COMPAT +static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { - struct sock *sk = raw6_get_first(seq); - if (sk) - while (pos && (sk = raw6_get_next(seq, sk)) != NULL) - --pos; - return pos ? NULL : sk; + switch (cmd) { + case SIOCOUTQ: + case SIOCINQ: + return -ENOIOCTLCMD; + default: +#ifdef CONFIG_IPV6_MROUTE + return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); +#else + return -ENOIOCTLCMD; +#endif + } } +#endif -static void *raw6_seq_start(struct seq_file *seq, loff_t *pos) +static void rawv6_close(struct sock *sk, long timeout) { - read_lock(&raw_v6_lock); - return *pos ? raw6_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + if (inet_sk(sk)->inet_num == IPPROTO_RAW) + ip6_ra_control(sk, -1); + ip6mr_sk_done(sk); + sk_common_release(sk); } -static void *raw6_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void raw6_destroy(struct sock *sk) { - struct sock *sk; + lock_sock(sk); + ip6_flush_pending_frames(sk); + release_sock(sk); - if (v == SEQ_START_TOKEN) - sk = raw6_get_first(seq); - else - sk = raw6_get_next(seq, v); - ++*pos; - return sk; + inet6_destroy_sock(sk); } -static void raw6_seq_stop(struct seq_file *seq, void *v) +static int rawv6_init_sk(struct sock *sk) { - read_unlock(&raw_v6_lock); -} + struct raw6_sock *rp = raw6_sk(sk); -static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) -{ - struct ipv6_pinfo *np = inet6_sk(sp); - struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = 0; - srcp = inet_sk(sp)->num; - seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n", - i, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), - 0, 0L, 0, - sock_i_uid(sp), 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp); + switch (inet_sk(sk)->inet_num) { + case IPPROTO_ICMPV6: + rp->checksum = 1; + rp->offset = 2; + break; + case IPPROTO_MH: + rp->checksum = 1; + rp->offset = 4; + break; + default: + break; + } + return 0; } +struct proto rawv6_prot = { + .name = "RAWv6", + .owner = THIS_MODULE, + .close = rawv6_close, + .destroy = raw6_destroy, + .connect = ip6_datagram_connect_v6_only, + .disconnect = udp_disconnect, + .ioctl = rawv6_ioctl, + .init = rawv6_init_sk, + .setsockopt = rawv6_setsockopt, + .getsockopt = rawv6_getsockopt, + .sendmsg = rawv6_sendmsg, + .recvmsg = rawv6_recvmsg, + .bind = rawv6_bind, + .backlog_rcv = rawv6_rcv_skb, + .hash = raw_hash_sk, + .unhash = raw_unhash_sk, + .obj_size = sizeof(struct raw6_sock), + .h.raw_hash = &raw_v6_hashinfo, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_rawv6_setsockopt, + .compat_getsockopt = compat_rawv6_getsockopt, + .compat_ioctl = compat_rawv6_ioctl, +#endif +}; + +#ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode\n"); - else - raw6_sock_seq_show(seq, v, raw6_seq_private(seq)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + struct sock *sp = v; + __u16 srcp = inet_sk(sp)->inet_num; + ip6_dgram_sock_seq_show(seq, v, srcp, 0, + raw_seq_private(seq)->bucket); + } return 0; } -static struct seq_operations raw6_seq_ops = { - .start = raw6_seq_start, - .next = raw6_seq_next, - .stop = raw6_seq_stop, +static const struct seq_operations raw6_seq_ops = { + .start = raw_seq_start, + .next = raw_seq_next, + .stop = raw_seq_stop, .show = raw6_seq_show, }; static int raw6_seq_open(struct inode *inode, struct file *file) { - struct seq_file *seq; - int rc = -ENOMEM; - struct raw6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - goto out; - rc = seq_open(file, &raw6_seq_ops); - if (rc) - goto out_kfree; - seq = file->private_data; - seq->private = s; - memset(s, 0, sizeof(*s)); -out: - return rc; -out_kfree: - kfree(s); - goto out; + return raw_seq_open(inode, file, &raw_v6_hashinfo, &raw6_seq_ops); } -static struct file_operations raw6_seq_fops = { +static const struct file_operations raw6_seq_fops = { .owner = THIS_MODULE, .open = raw6_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; -int __init raw6_proc_init(void) +static int __net_init raw6_init_net(struct net *net) { - if (!proc_net_fops_create("raw6", S_IRUGO, &raw6_seq_fops)) + if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops)) return -ENOMEM; + return 0; } +static void __net_exit raw6_exit_net(struct net *net) +{ + remove_proc_entry("raw6", net->proc_net); +} + +static struct pernet_operations raw6_net_ops = { + .init = raw6_init_net, + .exit = raw6_exit_net, +}; + +int __init raw6_proc_init(void) +{ + return register_pernet_subsys(&raw6_net_ops); +} + void raw6_proc_exit(void) { - proc_net_remove("raw6"); + unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ + +/* Same as inet6_dgram_ops, sans udp_poll. */ +static const struct proto_ops inet6_sockraw_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_dgram_connect, /* ok */ + .socketpair = sock_no_socketpair, /* a do nothing */ + .accept = sock_no_accept, /* a do nothing */ + .getname = inet6_getname, + .poll = datagram_poll, /* ok */ + .ioctl = inet6_ioctl, /* must change */ + .listen = sock_no_listen, /* ok */ + .shutdown = inet_shutdown, /* ok */ + .setsockopt = sock_common_setsockopt, /* ok */ + .getsockopt = sock_common_getsockopt, /* ok */ + .sendmsg = inet_sendmsg, /* ok */ + .recvmsg = sock_common_recvmsg, /* ok */ + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif +}; + +static struct inet_protosw rawv6_protosw = { + .type = SOCK_RAW, + .protocol = IPPROTO_IP, /* wild card */ + .prot = &rawv6_prot, + .ops = &inet6_sockraw_ops, + .flags = INET_PROTOSW_REUSE, +}; + +int __init rawv6_init(void) +{ + int ret; + + ret = inet6_register_protosw(&rawv6_protosw); + if (ret) + goto out; +out: + return ret; +} + +void rawv6_exit(void) +{ + inet6_unregister_protosw(&rawv6_protosw); +} diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e4fe9ee484d..cc85a9ba501 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -1,11 +1,9 @@ /* * IPv6 fragment reassembly - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> - * - * $Id: reassembly.c,v 1.26 2001/03/07 22:00:57 davem Exp $ + * Pedro Roque <roque@di.fc.ul.pt> * * Based on: net/ipv4/ip_fragment.c * @@ -15,8 +13,8 @@ * 2 of the License, or (at your option) any later version. */ -/* - * Fixes: +/* + * Fixes: * Andi Kleen Make it work with multiple hosts. * More RFC compliance. * @@ -28,7 +26,9 @@ * YOSHIFUJI,H. @USAGI Always remove fragment header to * calculate ICV correctly. */ -#include <linux/config.h> + +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> @@ -43,21 +43,22 @@ #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/jhash.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/export.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> +#include <net/ip6_route.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/rawv6.h> #include <net/ndisc.h> #include <net/addrconf.h> - -int sysctl_ip6frag_high_thresh = 256*1024; -int sysctl_ip6frag_low_thresh = 192*1024; - -int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT; +#include <net/inet_frag.h> +#include <net/inet_ecn.h> struct ip6frag_skb_cb { @@ -67,391 +68,185 @@ struct ip6frag_skb_cb #define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb)) - -/* - * Equivalent of ipv4 struct ipq - */ - -struct frag_queue -{ - struct frag_queue *next; - struct list_head lru_list; /* lru list member */ - - __u32 id; /* fragment id */ - struct in6_addr saddr; - struct in6_addr daddr; - - spinlock_t lock; - atomic_t refcnt; - struct timer_list timer; /* expire timer */ - struct sk_buff *fragments; - int len; - int meat; - int iif; - struct timeval stamp; - unsigned int csum; - __u8 last_in; /* has first/last segment arrived? */ -#define COMPLETE 4 -#define FIRST_IN 2 -#define LAST_IN 1 - __u16 nhoffset; - struct frag_queue **pprev; -}; - -/* Hash table. */ - -#define IP6Q_HASHSZ 64 - -static struct frag_queue *ip6_frag_hash[IP6Q_HASHSZ]; -static DEFINE_RWLOCK(ip6_frag_lock); -static u32 ip6_frag_hash_rnd; -static LIST_HEAD(ip6_frag_lru_list); -int ip6_frag_nqueues = 0; - -static __inline__ void __fq_unlink(struct frag_queue *fq) -{ - if(fq->next) - fq->next->pprev = fq->pprev; - *fq->pprev = fq->next; - list_del(&fq->lru_list); - ip6_frag_nqueues--; -} - -static __inline__ void fq_unlink(struct frag_queue *fq) +static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { - write_lock(&ip6_frag_lock); - __fq_unlink(fq); - write_unlock(&ip6_frag_lock); + return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); } -static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr, - struct in6_addr *daddr) -{ - u32 a, b, c; - - a = saddr->s6_addr32[0]; - b = saddr->s6_addr32[1]; - c = saddr->s6_addr32[2]; +static struct inet_frags ip6_frags; - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; - c += ip6_frag_hash_rnd; - __jhash_mix(a, b, c); +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, + struct net_device *dev); - a += saddr->s6_addr32[3]; - b += daddr->s6_addr32[0]; - c += daddr->s6_addr32[1]; - __jhash_mix(a, b, c); - - a += daddr->s6_addr32[2]; - b += daddr->s6_addr32[3]; - c += id; - __jhash_mix(a, b, c); - - return c & (IP6Q_HASHSZ - 1); -} - -static struct timer_list ip6_frag_secret_timer; -int sysctl_ip6frag_secret_interval = 10 * 60 * HZ; - -static void ip6_frag_secret_rebuild(unsigned long dummy) -{ - unsigned long now = jiffies; - int i; - - write_lock(&ip6_frag_lock); - get_random_bytes(&ip6_frag_hash_rnd, sizeof(u32)); - for (i = 0; i < IP6Q_HASHSZ; i++) { - struct frag_queue *q; - - q = ip6_frag_hash[i]; - while (q) { - struct frag_queue *next = q->next; - unsigned int hval = ip6qhashfn(q->id, - &q->saddr, - &q->daddr); - - if (hval != i) { - /* Unlink. */ - if (q->next) - q->next->pprev = q->pprev; - *q->pprev = q->next; - - /* Relink to new hash chain. */ - if ((q->next = ip6_frag_hash[hval]) != NULL) - q->next->pprev = &q->next; - ip6_frag_hash[hval] = q; - q->pprev = &ip6_frag_hash[hval]; - } - - q = next; - } - } - write_unlock(&ip6_frag_lock); - - mod_timer(&ip6_frag_secret_timer, now + sysctl_ip6frag_secret_interval); -} - -atomic_t ip6_frag_mem = ATOMIC_INIT(0); - -/* Memory Tracking Functions. */ -static inline void frag_kfree_skb(struct sk_buff *skb, int *work) -{ - if (work) - *work -= skb->truesize; - atomic_sub(skb->truesize, &ip6_frag_mem); - kfree_skb(skb); -} - -static inline void frag_free_queue(struct frag_queue *fq, int *work) +/* + * callers should be careful not to use the hash value outside the ipfrag_lock + * as doing so could race with ipfrag_hash_rnd being recalculated. + */ +static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, + const struct in6_addr *daddr) { - if (work) - *work -= sizeof(struct frag_queue); - atomic_sub(sizeof(struct frag_queue), &ip6_frag_mem); - kfree(fq); -} + u32 c; -static inline struct frag_queue *frag_alloc_queue(void) -{ - struct frag_queue *fq = kmalloc(sizeof(struct frag_queue), GFP_ATOMIC); + net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd)); + c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, ip6_frags.rnd); - if(!fq) - return NULL; - atomic_add(sizeof(struct frag_queue), &ip6_frag_mem); - return fq; + return c & (INETFRAGS_HASHSZ - 1); } -/* Destruction primitives. */ - -/* Complete destruction of fq. */ -static void ip6_frag_destroy(struct frag_queue *fq, int *work) +static unsigned int ip6_hashfn(struct inet_frag_queue *q) { - struct sk_buff *fp; - - BUG_TRAP(fq->last_in&COMPLETE); - BUG_TRAP(del_timer(&fq->timer) == 0); - - /* Release all fragment data. */ - fp = fq->fragments; - while (fp) { - struct sk_buff *xp = fp->next; - - frag_kfree_skb(fp, work); - fp = xp; - } - - frag_free_queue(fq, work); -} + struct frag_queue *fq; -static __inline__ void fq_put(struct frag_queue *fq, int *work) -{ - if (atomic_dec_and_test(&fq->refcnt)) - ip6_frag_destroy(fq, work); + fq = container_of(q, struct frag_queue, q); + return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr); } -/* Kill fq entry. It is not destroyed immediately, - * because caller (and someone more) holds reference count. - */ -static __inline__ void fq_kill(struct frag_queue *fq) +bool ip6_frag_match(struct inet_frag_queue *q, void *a) { - if (del_timer(&fq->timer)) - atomic_dec(&fq->refcnt); + struct frag_queue *fq; + struct ip6_create_arg *arg = a; - if (!(fq->last_in & COMPLETE)) { - fq_unlink(fq); - atomic_dec(&fq->refcnt); - fq->last_in |= COMPLETE; - } + fq = container_of(q, struct frag_queue, q); + return fq->id == arg->id && + fq->user == arg->user && + ipv6_addr_equal(&fq->saddr, arg->src) && + ipv6_addr_equal(&fq->daddr, arg->dst); } +EXPORT_SYMBOL(ip6_frag_match); -static void ip6_evictor(void) +void ip6_frag_init(struct inet_frag_queue *q, void *a) { - struct frag_queue *fq; - struct list_head *tmp; - int work; - - work = atomic_read(&ip6_frag_mem) - sysctl_ip6frag_low_thresh; - if (work <= 0) - return; - - while(work > 0) { - read_lock(&ip6_frag_lock); - if (list_empty(&ip6_frag_lru_list)) { - read_unlock(&ip6_frag_lock); - return; - } - tmp = ip6_frag_lru_list.next; - fq = list_entry(tmp, struct frag_queue, lru_list); - atomic_inc(&fq->refcnt); - read_unlock(&ip6_frag_lock); - - spin_lock(&fq->lock); - if (!(fq->last_in&COMPLETE)) - fq_kill(fq); - spin_unlock(&fq->lock); - - fq_put(fq, &work); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); - } + struct frag_queue *fq = container_of(q, struct frag_queue, q); + struct ip6_create_arg *arg = a; + + fq->id = arg->id; + fq->user = arg->user; + fq->saddr = *arg->src; + fq->daddr = *arg->dst; + fq->ecn = arg->ecn; } +EXPORT_SYMBOL(ip6_frag_init); -static void ip6_frag_expire(unsigned long data) +void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, + struct inet_frags *frags) { - struct frag_queue *fq = (struct frag_queue *) data; + struct net_device *dev = NULL; - spin_lock(&fq->lock); + spin_lock(&fq->q.lock); - if (fq->last_in & COMPLETE) + if (fq->q.last_in & INET_FRAG_COMPLETE) goto out; - fq_kill(fq); + inet_frag_kill(&fq->q, frags); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, fq->iif); + if (!dev) + goto out_rcu_unlock; - /* Send error only if the first segment arrived. */ - if (fq->last_in&FIRST_IN && fq->fragments) { - struct net_device *dev = dev_get_by_index(fq->iif); - - /* - But use as source device on which LAST ARRIVED - segment was received. And do not use fq->dev - pointer directly, device might already disappeared. - */ - if (dev) { - fq->fragments->dev = dev; - icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, - dev); - dev_put(dev); - } - } -out: - spin_unlock(&fq->lock); - fq_put(fq, NULL); -} - -/* Creation primitives. */ + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + /* Don't send error if the first segment did not arrive. */ + if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments) + goto out_rcu_unlock; -static struct frag_queue *ip6_frag_intern(unsigned int hash, - struct frag_queue *fq_in) -{ - struct frag_queue *fq; - - write_lock(&ip6_frag_lock); -#ifdef CONFIG_SMP - for (fq = ip6_frag_hash[hash]; fq; fq = fq->next) { - if (fq->id == fq_in->id && - ipv6_addr_equal(&fq_in->saddr, &fq->saddr) && - ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) { - atomic_inc(&fq->refcnt); - write_unlock(&ip6_frag_lock); - fq_in->last_in |= COMPLETE; - fq_put(fq_in, NULL); - return fq; - } - } -#endif - fq = fq_in; - - if (!mod_timer(&fq->timer, jiffies + sysctl_ip6frag_time)) - atomic_inc(&fq->refcnt); - - atomic_inc(&fq->refcnt); - if((fq->next = ip6_frag_hash[hash]) != NULL) - fq->next->pprev = &fq->next; - ip6_frag_hash[hash] = fq; - fq->pprev = &ip6_frag_hash[hash]; - INIT_LIST_HEAD(&fq->lru_list); - list_add_tail(&fq->lru_list, &ip6_frag_lru_list); - ip6_frag_nqueues++; - write_unlock(&ip6_frag_lock); - return fq; + /* + But use as source device on which LAST ARRIVED + segment was received. And do not use fq->dev + pointer directly, device might already disappeared. + */ + fq->q.fragments->dev = dev; + icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); +out_rcu_unlock: + rcu_read_unlock(); +out: + spin_unlock(&fq->q.lock); + inet_frag_put(&fq->q, frags); } +EXPORT_SYMBOL(ip6_expire_frag_queue); - -static struct frag_queue * -ip6_frag_create(unsigned int hash, u32 id, struct in6_addr *src, struct in6_addr *dst) +static void ip6_frag_expire(unsigned long data) { struct frag_queue *fq; + struct net *net; - if ((fq = frag_alloc_queue()) == NULL) - goto oom; - - memset(fq, 0, sizeof(struct frag_queue)); + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + net = container_of(fq->q.net, struct net, ipv6.frags); - fq->id = id; - ipv6_addr_copy(&fq->saddr, src); - ipv6_addr_copy(&fq->daddr, dst); - - init_timer(&fq->timer); - fq->timer.function = ip6_frag_expire; - fq->timer.data = (long) fq; - spin_lock_init(&fq->lock); - atomic_set(&fq->refcnt, 1); - - return ip6_frag_intern(hash, fq); - -oom: - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); - return NULL; + ip6_expire_frag_queue(net, fq, &ip6_frags); } static __inline__ struct frag_queue * -fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(struct net *net, __be32 id, const struct in6_addr *src, + const struct in6_addr *dst, u8 ecn) { - struct frag_queue *fq; - unsigned int hash = ip6qhashfn(id, src, dst); - - read_lock(&ip6_frag_lock); - for(fq = ip6_frag_hash[hash]; fq; fq = fq->next) { - if (fq->id == id && - ipv6_addr_equal(src, &fq->saddr) && - ipv6_addr_equal(dst, &fq->daddr)) { - atomic_inc(&fq->refcnt); - read_unlock(&ip6_frag_lock); - return fq; - } + struct inet_frag_queue *q; + struct ip6_create_arg arg; + unsigned int hash; + + arg.id = id; + arg.user = IP6_DEFRAG_LOCAL_DELIVER; + arg.src = src; + arg.dst = dst; + arg.ecn = ecn; + + read_lock(&ip6_frags.lock); + hash = inet6_hash_frag(id, src, dst); + + q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; } - read_unlock(&ip6_frag_lock); - - return ip6_frag_create(hash, id, src, dst); + return container_of(q, struct frag_queue, q); } - -static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, +static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff) { struct sk_buff *prev, *next; + struct net_device *dev; int offset, end; + struct net *net = dev_net(skb_dst(skb)->dev); + u8 ecn; - if (fq->last_in & COMPLETE) + if (fq->q.last_in & INET_FRAG_COMPLETE) goto err; offset = ntohs(fhdr->frag_off) & ~0x7; - end = offset + (ntohs(skb->nh.ipv6h->payload_len) - - ((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1))); + end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - + ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw); - return; + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, + ((u8 *)&fhdr->frag_off - + skb_network_header(skb))); + return -1; } - if (skb->ip_summed == CHECKSUM_HW) - skb->csum = csum_sub(skb->csum, - csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0)); + ecn = ip6_frag_ecn(ipv6_hdr(skb)); + + if (skb->ip_summed == CHECKSUM_COMPLETE) { + const unsigned char *nh = skb_network_header(skb); + skb->csum = csum_sub(skb->csum, + csum_partial(nh, (u8 *)(fhdr + 1) - nh, + 0)); + } /* Is this the final fragment? */ if (!(fhdr->frag_off & htons(IP6_MF))) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ - if (end < fq->len || - ((fq->last_in & LAST_IN) && end != fq->len)) + if (end < fq->q.len || + ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; - fq->last_in |= LAST_IN; - fq->len = end; + fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. * Required by the RFC. @@ -460,16 +255,17 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* RFC2460 says always send parameter problem in * this case. -DaveM */ - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, payload_len)); - return; + return -1; } - if (end > fq->len) { + if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ - if (fq->last_in & LAST_IN) + if (fq->q.last_in & INET_FRAG_LAST_IN) goto err; - fq->len = end; + fq->q.len = end; } } @@ -479,7 +275,7 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) goto err; - + if (pskb_trim_rcsum(skb, end - offset)) goto err; @@ -487,97 +283,86 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, * in the chain of fragments so far. We must know where to put * this fragment, right? */ + prev = fq->q.fragments_tail; + if (!prev || FRAG6_CB(prev)->offset < offset) { + next = NULL; + goto found; + } prev = NULL; - for(next = fq->fragments; next != NULL; next = next->next) { + for(next = fq->q.fragments; next != NULL; next = next->next) { if (FRAG6_CB(next)->offset >= offset) break; /* bingo! */ prev = next; } - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. +found: + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. */ - if (prev) { - int i = (FRAG6_CB(prev)->offset + prev->len) - offset; - if (i > 0) { - offset += i; - if (end <= offset) - goto err; - if (!pskb_pull(skb, i)) - goto err; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } - - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. - */ - while (next && FRAG6_CB(next)->offset < end) { - int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */ - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - if (!pskb_pull(next, i)) - goto err; - FRAG6_CB(next)->offset += i; /* next fragment */ - fq->meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragment is completely overridden with - * new one drop it. - */ - next = next->next; + /* Check for overlap with preceding fragment. */ + if (prev && + (FRAG6_CB(prev)->offset + prev->len) > offset) + goto discard_fq; - if (prev) - prev->next = next; - else - fq->fragments = next; - - fq->meat -= free_it->len; - frag_kfree_skb(free_it, NULL); - } - } + /* Look for overlap with succeeding segment. */ + if (next && FRAG6_CB(next)->offset < end) + goto discard_fq; FRAG6_CB(skb)->offset = offset; /* Insert this fragment in the chain of fragments. */ skb->next = next; + if (!next) + fq->q.fragments_tail = skb; if (prev) prev->next = skb; else - fq->fragments = skb; + fq->q.fragments = skb; - if (skb->dev) - fq->iif = skb->dev->ifindex; - skb->dev = NULL; - skb_get_timestamp(skb, &fq->stamp); - fq->meat += skb->len; - atomic_add(skb->truesize, &ip6_frag_mem); + dev = skb->dev; + if (dev) { + fq->iif = dev->ifindex; + skb->dev = NULL; + } + fq->q.stamp = skb->tstamp; + fq->q.meat += skb->len; + fq->ecn |= ecn; + add_frag_mem_limit(&fq->q, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. */ if (offset == 0) { fq->nhoffset = nhoff; - fq->last_in |= FIRST_IN; + fq->q.last_in |= INET_FRAG_FIRST_IN; + } + + if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = ip6_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; } - write_lock(&ip6_frag_lock); - list_move_tail(&fq->lru_list, &ip6_frag_lru_list); - write_unlock(&ip6_frag_lock); - return; + skb_dst_drop(skb); + inet_frag_lru_move(&fq->q); + return -1; + +discard_fq: + inet_frag_kill(&fq->q, &ip6_frags); err: - IP6_INC_STATS(IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS); kfree_skb(skb); + return -1; } /* @@ -589,32 +374,60 @@ err: * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, - unsigned int *nhoffp, +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) { - struct sk_buff *fp, *head = fq->fragments; + struct net *net = container_of(fq->q.net, struct net, ipv6.frags); + struct sk_buff *fp, *head = fq->q.fragments; int payload_len; unsigned int nhoff; + int sum_truesize; + u8 ecn; + + inet_frag_kill(&fq->q, &ip6_frags); + + ecn = ip_frag_ecn_table[fq->ecn]; + if (unlikely(ecn == 0xff)) + goto out_fail; + + /* Make the one we just received the head. */ + if (prev) { + head = prev->next; + fp = skb_clone(head, GFP_ATOMIC); - fq_kill(fq); + if (!fp) + goto out_oom; + + fp->next = head->next; + if (!fp->next) + fq->q.fragments_tail = fp; + prev->next = fp; + + skb_morph(head, fq->q.fragments); + head->next = fq->q.fragments->next; - BUG_TRAP(head != NULL); - BUG_TRAP(FRAG6_CB(head)->offset == 0); + consume_skb(fq->q.fragments); + fq->q.fragments = head; + } + + WARN_ON(head == NULL); + WARN_ON(FRAG6_CB(head)->offset != 0); /* Unfragmented part is taken from the first segment. */ - payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr); + payload_len = ((head->data - skb_network_header(head)) - + sizeof(struct ipv6hdr) + fq->q.len - + sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) goto out_oversize; /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) + if (skb_unclone(head, GFP_ATOMIC)) goto out_oom; /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_shinfo(head)->frag_list) { + if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; @@ -623,146 +436,332 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, clone->next = head->next; head->next = clone; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_shinfo(head)->frag_list = NULL; - for (i=0; i<skb_shinfo(head)->nr_frags; i++) - plen += skb_shinfo(head)->frags[i].size; + skb_frag_list_init(head); + 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; clone->csum = 0; clone->ip_summed = head->ip_summed; - atomic_add(clone->truesize, &ip6_frag_mem); + add_frag_mem_limit(&fq->q, clone->truesize); } /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ nhoff = fq->nhoffset; - head->nh.raw[nhoff] = head->h.raw[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, + skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; + memmove(head->head + sizeof(struct frag_hdr), head->head, (head->data - head->head) - sizeof(struct frag_hdr)); - head->mac.raw += sizeof(struct frag_hdr); - head->nh.raw += sizeof(struct frag_hdr); + head->mac_header += sizeof(struct frag_hdr); + head->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(head); + skb_push(head, head->data - skb_network_header(head)); - skb_shinfo(head)->frag_list = head->next; - head->h.raw = head->data; - skb_push(head, head->data - head->nh.raw); - atomic_sub(head->truesize, &ip6_frag_mem); + sum_truesize = head->truesize; + for (fp = head->next; fp;) { + bool headstolen; + int delta; + struct sk_buff *next = fp->next; - for (fp=head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - atomic_sub(fp->truesize, &ip6_frag_mem); + + if (skb_try_coalesce(head, fp, &headstolen, &delta)) { + kfree_skb_partial(fp, headstolen); + } else { + if (!skb_shinfo(head)->frag_list) + skb_shinfo(head)->frag_list = fp; + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + } + fp = next; } + sub_frag_mem_limit(&fq->q, sum_truesize); head->next = NULL; head->dev = dev; - skb_set_timestamp(head, &fq->stamp); - head->nh.ipv6h->payload_len = htons(payload_len); - - *skb_in = head; + head->tstamp = fq->q.stamp; + ipv6_hdr(head)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); + IP6CB(head)->nhoff = nhoff; + IP6CB(head)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_HW) - head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum); - - IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS); - fq->fragments = NULL; - *nhoffp = nhoff; + if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_partial(skb_network_header(head), + skb_network_header_len(head), + head->csum); + + rcu_read_lock(); + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); + rcu_read_unlock(); + fq->q.fragments = NULL; + fq->q.fragments_tail = NULL; return 1; out_oversize: - if (net_ratelimit()) - printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len); + net_dbg_ratelimited("ip6_frag_reasm: payload len = %d\n", payload_len); goto out_fail; out_oom: - if (net_ratelimit()) - printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n"); + net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n"); out_fail: - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + rcu_read_lock(); + IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + rcu_read_unlock(); return -1; } -static int ipv6_frag_rcv(struct sk_buff **skbp, unsigned int *nhoffp) +static int ipv6_frag_rcv(struct sk_buff *skb) { - struct sk_buff *skb = *skbp; - struct net_device *dev = skb->dev; struct frag_hdr *fhdr; struct frag_queue *fq; - struct ipv6hdr *hdr; + const struct ipv6hdr *hdr = ipv6_hdr(skb); + struct net *net = dev_net(skb_dst(skb)->dev); + int evicted; - hdr = skb->nh.ipv6h; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) + goto fail_hdr; - IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ - if (hdr->payload_len==0) { - IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw); - return -1; - } - if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+sizeof(struct frag_hdr))) { - IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw); - return -1; - } + if (hdr->payload_len==0) + goto fail_hdr; - hdr = skb->nh.ipv6h; - fhdr = (struct frag_hdr *)skb->h.raw; + if (!pskb_may_pull(skb, (skb_transport_offset(skb) + + sizeof(struct frag_hdr)))) + goto fail_hdr; + + hdr = ipv6_hdr(skb); + fhdr = (struct frag_hdr *)skb_transport_header(skb); if (!(fhdr->frag_off & htons(0xFFF9))) { /* It is not a fragmented frame */ - skb->h.raw += sizeof(struct frag_hdr); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS); + skb->transport_header += sizeof(struct frag_hdr); + IP6_INC_STATS_BH(net, + ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); - *nhoffp = (u8*)fhdr - skb->nh.raw; + IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; return 1; } - if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh) - ip6_evictor(); - - if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) { - int ret = -1; + evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false); + if (evicted) + IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS, evicted); - spin_lock(&fq->lock); + fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, + ip6_frag_ecn(hdr)); + if (fq != NULL) { + int ret; - ip6_frag_queue(fq, skb, fhdr, *nhoffp); + spin_lock(&fq->q.lock); - if (fq->last_in == (FIRST_IN|LAST_IN) && - fq->meat == fq->len) - ret = ip6_frag_reasm(fq, skbp, nhoffp, dev); + ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff); - spin_unlock(&fq->lock); - fq_put(fq, NULL); + spin_unlock(&fq->q.lock); + inet_frag_put(&fq->q, &ip6_frags); return ret; } - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; + +fail_hdr: + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); + return -1; } -static struct inet6_protocol frag_protocol = +static const struct inet6_protocol frag_protocol = { .handler = ipv6_frag_rcv, .flags = INET6_PROTO_NOPOLICY, }; -void __init ipv6_frag_init(void) +#ifdef CONFIG_SYSCTL +static struct ctl_table ip6_frags_ns_ctl_table[] = { + { + .procname = "ip6frag_high_thresh", + .data = &init_net.ipv6.frags.high_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "ip6frag_low_thresh", + .data = &init_net.ipv6.frags.low_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "ip6frag_time", + .data = &init_net.ipv6.frags.timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static struct ctl_table ip6_frags_ctl_table[] = { + { + .procname = "ip6frag_secret_interval", + .data = &ip6_frags.secret_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static int __net_init ip6_frags_ns_sysctl_register(struct net *net) { - if (inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT) < 0) - printk(KERN_ERR "ipv6_frag_init: Could not register protocol\n"); + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = ip6_frags_ns_ctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL); + if (table == NULL) + goto err_alloc; + + table[0].data = &net->ipv6.frags.high_thresh; + table[1].data = &net->ipv6.frags.low_thresh; + table[2].data = &net->ipv6.frags.timeout; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + } + + hdr = register_net_sysctl(net, "net/ipv6", table); + if (hdr == NULL) + goto err_reg; + + net->ipv6.sysctl.frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net) +{ + struct ctl_table *table; + + table = net->ipv6.sysctl.frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct ctl_table_header *ip6_ctl_header; + +static int ip6_frags_sysctl_register(void) +{ + ip6_ctl_header = register_net_sysctl(&init_net, "net/ipv6", + ip6_frags_ctl_table); + return ip6_ctl_header == NULL ? -ENOMEM : 0; +} + +static void ip6_frags_sysctl_unregister(void) +{ + unregister_net_sysctl_table(ip6_ctl_header); +} +#else +static inline int ip6_frags_ns_sysctl_register(struct net *net) +{ + return 0; +} + +static inline void ip6_frags_ns_sysctl_unregister(struct net *net) +{ +} + +static inline int ip6_frags_sysctl_register(void) +{ + return 0; +} + +static inline void ip6_frags_sysctl_unregister(void) +{ +} +#endif + +static int __net_init ipv6_frags_init_net(struct net *net) +{ + net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH; + net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT; + + inet_frags_init_net(&net->ipv6.frags); + + return ip6_frags_ns_sysctl_register(net); +} - ip6_frag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^ - (jiffies ^ (jiffies >> 6))); +static void __net_exit ipv6_frags_exit_net(struct net *net) +{ + ip6_frags_ns_sysctl_unregister(net); + inet_frags_exit_net(&net->ipv6.frags, &ip6_frags); +} - init_timer(&ip6_frag_secret_timer); - ip6_frag_secret_timer.function = ip6_frag_secret_rebuild; - ip6_frag_secret_timer.expires = jiffies + sysctl_ip6frag_secret_interval; - add_timer(&ip6_frag_secret_timer); +static struct pernet_operations ip6_frags_ops = { + .init = ipv6_frags_init_net, + .exit = ipv6_frags_exit_net, +}; + +int __init ipv6_frag_init(void) +{ + int ret; + + ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT); + if (ret) + goto out; + + ret = ip6_frags_sysctl_register(); + if (ret) + goto err_sysctl; + + ret = register_pernet_subsys(&ip6_frags_ops); + if (ret) + goto err_pernet; + + ip6_frags.hashfn = ip6_hashfn; + ip6_frags.constructor = ip6_frag_init; + ip6_frags.destructor = NULL; + ip6_frags.skb_free = NULL; + ip6_frags.qsize = sizeof(struct frag_queue); + ip6_frags.match = ip6_frag_match; + ip6_frags.frag_expire = ip6_frag_expire; + ip6_frags.secret_interval = 10 * 60 * HZ; + inet_frags_init(&ip6_frags); +out: + return ret; + +err_pernet: + ip6_frags_sysctl_unregister(); +err_sysctl: + inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT); + goto out; +} + +void ipv6_frag_exit(void) +{ + inet_frags_fini(&ip6_frags); + ip6_frags_sysctl_unregister(); + unregister_pernet_subsys(&ip6_frags_ops); + inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 227e99ed510..f23fbd28a50 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3,9 +3,7 @@ * FIB front-end. * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> - * - * $Id: route.c,v 1.56 2001/10/31 21:55:55 davem Exp $ + * Pedro Roque <roque@di.fc.ul.pt> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -22,10 +20,15 @@ * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. + * Ville Nuorvala + * Fixed routing subtrees. */ -#include <linux/config.h> +#define pr_fmt(fmt) "IPv6: " fmt + +#include <linux/capability.h> #include <linux/errno.h> +#include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> @@ -34,15 +37,14 @@ #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> +#include <linux/mroute6.h> #include <linux/init.h> -#include <linux/netlink.h> #include <linux/if_arp.h> - -#ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> -#endif - +#include <linux/nsproxy.h> +#include <linux/slab.h> +#include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ip6_fib.h> @@ -53,6 +55,9 @@ #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/xfrm.h> +#include <net/netevent.h> +#include <net/netlink.h> +#include <net/nexthop.h> #include <asm/uaccess.h> @@ -60,98 +65,282 @@ #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 int ip6_rt_max_size = 4096; -static int ip6_rt_gc_min_interval = HZ / 2; -static int ip6_rt_gc_timeout = 60*HZ; -int ip6_rt_gc_interval = 30*HZ; -static int ip6_rt_gc_elasticity = 9; -static int ip6_rt_mtu_expires = 10*60*HZ; -static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; +enum rt6_nud_state { + RT6_NUD_FAIL_HARD = -3, + RT6_NUD_FAIL_PROBE = -2, + RT6_NUD_FAIL_DO_RR = -1, + RT6_NUD_SUCCEED = 1 +}; -static struct rt6_info * ip6_rt_copy(struct rt6_info *ort); +static struct rt6_info *ip6_rt_copy(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_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 *, struct net_device *dev, int how); -static int ip6_dst_gc(void); +static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); -static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb); +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +static int rt6_score_route(struct rt6_info *rt, int oif, int strict); + +#ifdef CONFIG_IPV6_ROUTE_INFO +static struct rt6_info *rt6_add_route_info(struct net *net, + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex, + unsigned int pref); +static struct rt6_info *rt6_get_route_info(struct net *net, + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex); +#endif + +static void rt6_bind_peer(struct rt6_info *rt, int create) +{ + struct inet_peer_base *base; + struct inet_peer *peer; -static struct dst_ops ip6_dst_ops = { + base = inetpeer_base_ptr(rt->_rt6i_peer); + if (!base) + return; + + peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); + if (peer) { + if (!rt6_set_peer(rt, peer)) + inet_putpeer(peer); + } +} + +static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create) +{ + if (rt6_has_peer(rt)) + return rt6_peer_ptr(rt); + + rt6_bind_peer(rt, create); + return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL); +} + +static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt) +{ + return __rt6_get_peer(rt, 1); +} + +static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + struct rt6_info *rt = (struct rt6_info *) dst; + struct inet_peer *peer; + u32 *p = NULL; + + if (!(rt->dst.flags & DST_HOST)) + return NULL; + + peer = rt6_get_peer_create(rt); + if (peer) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + p = peer->metrics; + if (inet_metrics_new(peer) || + (old & DST_METRICS_FORCE_OVERWRITE)) + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} + +static inline const void *choose_neigh_daddr(struct rt6_info *rt, + struct sk_buff *skb, + const void *daddr) +{ + struct in6_addr *p = &rt->rt6i_gateway; + + if (!ipv6_addr_any(p)) + return (const void *) p; + else if (skb) + return &ipv6_hdr(skb)->daddr; + return daddr; +} + +static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) +{ + struct rt6_info *rt = (struct rt6_info *) dst; + struct neighbour *n; + + daddr = choose_neigh_daddr(rt, skb, daddr); + n = __ipv6_neigh_lookup(dst->dev, daddr); + if (n) + return n; + return neigh_create(&nd_tbl, daddr, dst->dev); +} + +static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, - .protocol = __constant_htons(ETH_P_IPV6), + .protocol = cpu_to_be16(ETH_P_IPV6), .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, + .default_advmss = ip6_default_advmss, + .mtu = ip6_mtu, + .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, - .entry_size = sizeof(struct rt6_info), + .redirect = rt6_do_redirect, + .local_out = __ip6_local_out, + .neigh_lookup = ip6_neigh_lookup, }; -struct rt6_info ip6_null_entry = { - .u = { - .dst = { - .__refcnt = ATOMIC_INIT(1), - .__use = 1, - .dev = &loopback_dev, - .obsolete = -1, - .error = -ENETUNREACH, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_discard, - .output = ip6_pkt_discard_out, - .ops = &ip6_dst_ops, - .path = (struct dst_entry*)&ip6_null_entry, - } +static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) +{ + 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, struct sock *sk, + struct sk_buff *skb, u32 mtu) +{ +} + +static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} + +static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, + unsigned long old) +{ + return NULL; +} + +static struct dst_ops ip6_dst_blackhole_ops = { + .family = AF_INET6, + .protocol = cpu_to_be16(ETH_P_IPV6), + .destroy = ip6_dst_destroy, + .check = ip6_dst_check, + .mtu = ip6_blackhole_mtu, + .default_advmss = ip6_default_advmss, + .update_pmtu = ip6_rt_blackhole_update_pmtu, + .redirect = ip6_rt_blackhole_redirect, + .cow_metrics = ip6_rt_blackhole_cow_metrics, + .neigh_lookup = ip6_neigh_lookup, +}; + +static const u32 ip6_template_metrics[RTAX_MAX] = { + [RTAX_HOPLIMIT - 1] = 0, +}; + +static const struct rt6_info ip6_null_entry_template = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = DST_OBSOLETE_FORCE_CHK, + .error = -ENETUNREACH, + .input = ip6_pkt_discard, + .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_protocol = RTPROT_KERNEL, .rt6i_metric = ~(u32) 0, .rt6i_ref = ATOMIC_INIT(1), }; -struct fib6_node ip6_routing_table = { - .leaf = &ip6_null_entry, - .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, -}; +#ifdef CONFIG_IPV6_MULTIPLE_TABLES -/* Protects all the ip6 fib */ +static const struct rt6_info ip6_prohibit_entry_template = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = DST_OBSOLETE_FORCE_CHK, + .error = -EACCES, + .input = ip6_pkt_prohibit, + .output = ip6_pkt_prohibit_out, + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_protocol = RTPROT_KERNEL, + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; -DEFINE_RWLOCK(rt6_lock); +static const struct rt6_info ip6_blk_hole_entry_template = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = DST_OBSOLETE_FORCE_CHK, + .error = -EINVAL, + .input = dst_discard, + .output = dst_discard_sk, + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_protocol = RTPROT_KERNEL, + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; +#endif /* allocate dst with ip6_dst_ops */ -static __inline__ struct rt6_info *ip6_dst_alloc(void) +static inline struct rt6_info *ip6_dst_alloc(struct net *net, + struct net_device *dev, + int flags, + struct fib6_table *table) { - return (struct rt6_info *)dst_alloc(&ip6_dst_ops); + struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, + 0, DST_OBSOLETE_FORCE_CHK, flags); + + if (rt) { + struct dst_entry *dst = &rt->dst; + + memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); + rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); + rt->rt6i_genid = rt_genid_ipv6(net); + INIT_LIST_HEAD(&rt->rt6i_siblings); + } + return rt; } static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; + struct dst_entry *from = dst->from; + + if (!(rt->dst.flags & DST_HOST)) + dst_destroy_metrics_generic(dst); - if (idev != NULL) { + if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); - } + } + + dst->from = NULL; + dst_release(from); + + if (rt6_has_peer(rt)) { + struct inet_peer *peer = rt6_peer_ptr(rt); + inet_putpeer(peer); + } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -159,425 +348,742 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - - if (dev != &loopback_dev && idev != NULL && idev->dev == dev) { - struct inet6_dev *loopback_idev = in6_dev_get(&loopback_dev); - if (loopback_idev != NULL) { - rt->rt6i_idev = loopback_idev; - in6_dev_put(idev); + struct net_device *loopback_dev = + dev_net(dev)->loopback_dev; + + if (dev != loopback_dev) { + if (idev && idev->dev == dev) { + struct inet6_dev *loopback_idev = + in6_dev_get(loopback_dev); + if (loopback_idev) { + rt->rt6i_idev = loopback_idev; + in6_dev_put(idev); + } } } } -static __inline__ int rt6_check_expired(const struct rt6_info *rt) +static bool rt6_check_expired(const struct rt6_info *rt) { - return (rt->rt6i_flags & RTF_EXPIRES && - time_after(jiffies, rt->rt6i_expires)); + if (rt->rt6i_flags & RTF_EXPIRES) { + if (time_after(jiffies, rt->dst.expires)) + return true; + } else if (rt->dst.from) { + return rt6_check_expired((struct rt6_info *) rt->dst.from); + } + return false; +} + +/* Multipath route selection: + * Hash based function using packet header and flowlabel. + * Adapted from fib_info_hashfn() + */ +static int rt6_info_hash_nhsfn(unsigned int candidate_count, + const struct flowi6 *fl6) +{ + unsigned int val = fl6->flowi6_proto; + + val ^= ipv6_addr_hash(&fl6->daddr); + val ^= ipv6_addr_hash(&fl6->saddr); + + /* Work only if this not encapsulated */ + switch (fl6->flowi6_proto) { + case IPPROTO_UDP: + case IPPROTO_TCP: + case IPPROTO_SCTP: + val ^= (__force u16)fl6->fl6_sport; + val ^= (__force u16)fl6->fl6_dport; + break; + + case IPPROTO_ICMPV6: + val ^= (__force u16)fl6->fl6_icmp_type; + val ^= (__force u16)fl6->fl6_icmp_code; + break; + } + /* RFC6438 recommands to use flowlabel */ + val ^= (__force u32)fl6->flowlabel; + + /* Perhaps, we need to tune, this function? */ + val = val ^ (val >> 7) ^ (val >> 12); + return val % candidate_count; +} + +static struct rt6_info *rt6_multipath_select(struct rt6_info *match, + struct flowi6 *fl6, int oif, + int strict) +{ + struct rt6_info *sibling, *next_sibling; + int route_choosen; + + route_choosen = rt6_info_hash_nhsfn(match->rt6i_nsiblings + 1, fl6); + /* Don't change the route, if route_choosen == 0 + * (siblings does not include ourself) + */ + if (route_choosen) + list_for_each_entry_safe(sibling, next_sibling, + &match->rt6i_siblings, rt6i_siblings) { + route_choosen--; + if (route_choosen == 0) { + if (rt6_score_route(sibling, oif, strict) < 0) + break; + match = sibling; + break; + } + } + return match; } /* - * Route lookup. Any rt6_lock is implied. + * Route lookup. Any table->tb6_lock is implied. */ -static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt, +static inline struct rt6_info *rt6_device_match(struct net *net, + struct rt6_info *rt, + const struct in6_addr *saddr, int oif, - int strict) + int flags) { struct rt6_info *local = NULL; struct rt6_info *sprt; - if (oif) { - for (sprt = rt; sprt; sprt = sprt->u.next) { - struct net_device *dev = sprt->rt6i_dev; + if (!oif && ipv6_addr_any(saddr)) + goto out; + + for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { + 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 (strict && oif) + if (flags & RT6_LOOKUP_F_IFACE && oif) continue; - if (local && (!oif || + if (local && (!oif || local->rt6i_idev->dev->ifindex == oif)) continue; } local = sprt; } + } else { + if (ipv6_chk_addr(net, saddr, dev, + flags & RT6_LOOKUP_F_IFACE)) + return sprt; } + } + if (oif) { if (local) return local; - if (strict) - return &ip6_null_entry; + if (flags & RT6_LOOKUP_F_IFACE) + return net->ipv6.ip6_null_entry; } +out: return rt; } +#ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + +static void rt6_probe(struct rt6_info *rt) +{ + struct neighbour *neigh; + /* + * Okay, this does not seem to be appropriate + * for now, however, we need to check if it + * is really so; aka Router Reachability Probing. + * + * Router Reachability Probe MUST be rate-limited + * to no more than one per minute. + */ + if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) + return; + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + write_lock(&neigh->lock); + if (neigh->nud_state & NUD_VALID) + goto out; + } + + if (!neigh || + time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + + if (neigh && work) + __neigh_set_probe_once(neigh); + + if (neigh) + write_unlock(&neigh->lock); + + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } + } else { +out: + write_unlock(&neigh->lock); + } + rcu_read_unlock_bh(); +} +#else +static inline void rt6_probe(struct rt6_info *rt) +{ +} +#endif + /* - * pointer to the last default router chosen. BH is disabled locally. + * Default Router Selection (RFC 2461 6.3.6) */ -static struct rt6_info *rt6_dflt_pointer; -static DEFINE_SPINLOCK(rt6_dflt_lock); +static inline int rt6_check_dev(struct rt6_info *rt, int oif) +{ + struct net_device *dev = rt->dst.dev; + if (!oif || dev->ifindex == oif) + return 2; + if ((dev->flags & IFF_LOOPBACK) && + rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif) + return 1; + return 0; +} -void rt6_reset_dflt_pointer(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) { - spin_lock_bh(&rt6_dflt_lock); - if (rt == NULL || rt == rt6_dflt_pointer) { - RT6_TRACE("reset default router: %p->NULL\n", rt6_dflt_pointer); - rt6_dflt_pointer = NULL; + struct neighbour *neigh; + enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; + + if (rt->rt6i_flags & RTF_NONEXTHOP || + !(rt->rt6i_flags & RTF_GATEWAY)) + return RT6_NUD_SUCCEED; + + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + read_lock(&neigh->lock); + if (neigh->nud_state & NUD_VALID) + ret = RT6_NUD_SUCCEED; +#ifdef CONFIG_IPV6_ROUTER_PREF + else if (!(neigh->nud_state & NUD_FAILED)) + ret = RT6_NUD_SUCCEED; + else + ret = RT6_NUD_FAIL_PROBE; +#endif + read_unlock(&neigh->lock); + } else { + ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? + RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } - spin_unlock_bh(&rt6_dflt_lock); + rcu_read_unlock_bh(); + + return ret; } -/* Default Router Selection (RFC 2461 6.3.6) */ -static struct rt6_info *rt6_best_dflt(struct rt6_info *rt, int oif) +static int rt6_score_route(struct rt6_info *rt, int oif, + int strict) { - struct rt6_info *match = NULL; - struct rt6_info *sprt; - int mpri = 0; + int m; - for (sprt = rt; sprt; sprt = sprt->u.next) { - struct neighbour *neigh; - int m = 0; + m = rt6_check_dev(rt, oif); + if (!m && (strict & RT6_LOOKUP_F_IFACE)) + return RT6_NUD_FAIL_HARD; +#ifdef CONFIG_IPV6_ROUTER_PREF + m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; +#endif + if (strict & RT6_LOOKUP_F_REACHABLE) { + int n = rt6_check_neigh(rt); + if (n < 0) + return n; + } + return m; +} - if (!oif || - (sprt->rt6i_dev && - sprt->rt6i_dev->ifindex == oif)) - m += 8; +static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, + int *mpri, struct rt6_info *match, + bool *do_rr) +{ + int m; + bool match_do_rr = false; - if (rt6_check_expired(sprt)) - continue; + if (rt6_check_expired(rt)) + goto out; - if (sprt == rt6_dflt_pointer) - m += 4; + m = rt6_score_route(rt, oif, strict); + if (m == RT6_NUD_FAIL_DO_RR) { + match_do_rr = true; + m = 0; /* lowest valid score */ + } else if (m == RT6_NUD_FAIL_HARD) { + goto out; + } - if ((neigh = sprt->rt6i_nexthop) != NULL) { - read_lock_bh(&neigh->lock); - switch (neigh->nud_state) { - case NUD_REACHABLE: - m += 3; - break; + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(rt); - case NUD_STALE: - case NUD_DELAY: - case NUD_PROBE: - m += 2; - break; + /* note that m can be RT6_NUD_FAIL_PROBE at this point */ + if (m > *mpri) { + *do_rr = match_do_rr; + *mpri = m; + match = rt; + } +out: + return match; +} - case NUD_NOARP: - case NUD_PERMANENT: - m += 1; - break; +static struct rt6_info *find_rr_leaf(struct fib6_node *fn, + struct rt6_info *rr_head, + u32 metric, int oif, int strict, + bool *do_rr) +{ + struct rt6_info *rt, *match; + int mpri = -1; - case NUD_INCOMPLETE: - default: - read_unlock_bh(&neigh->lock); - continue; - } - read_unlock_bh(&neigh->lock); - } else { - continue; - } + match = NULL; + for (rt = rr_head; rt && rt->rt6i_metric == metric; + rt = rt->dst.rt6_next) + match = find_match(rt, oif, strict, &mpri, match, do_rr); + for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; + rt = rt->dst.rt6_next) + match = find_match(rt, oif, strict, &mpri, match, do_rr); - if (m > mpri || m >= 12) { - match = sprt; - mpri = m; - if (m >= 12) { - /* we choose the last default router if it - * is in (probably) reachable state. - * If route changed, we should do pmtu - * discovery. --yoshfuji - */ - break; - } - } - } + return match; +} - spin_lock(&rt6_dflt_lock); - if (!match) { - /* - * No default routers are known to be reachable. - * SHOULD round robin - */ - if (rt6_dflt_pointer) { - for (sprt = rt6_dflt_pointer->u.next; - sprt; sprt = sprt->u.next) { - if (sprt->u.dst.obsolete <= 0 && - sprt->u.dst.error == 0 && - !rt6_check_expired(sprt)) { - match = sprt; - break; - } - } - for (sprt = rt; - !match && sprt; - sprt = sprt->u.next) { - if (sprt->u.dst.obsolete <= 0 && - sprt->u.dst.error == 0 && - !rt6_check_expired(sprt)) { - match = sprt; - break; - } - if (sprt == rt6_dflt_pointer) - break; - } - } +static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) +{ + struct rt6_info *match, *rt0; + struct net *net; + bool do_rr = false; + + rt0 = fn->rr_ptr; + if (!rt0) + fn->rr_ptr = rt0 = fn->leaf; + + match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + &do_rr); + + if (do_rr) { + struct rt6_info *next = rt0->dst.rt6_next; + + /* no entries matched; do round-robin */ + if (!next || next->rt6i_metric != rt0->rt6i_metric) + next = fn->leaf; + + if (next != rt0) + fn->rr_ptr = next; } - if (match) { - if (rt6_dflt_pointer != match) - RT6_TRACE("changed default router: %p->%p\n", - rt6_dflt_pointer, match); - rt6_dflt_pointer = match; + net = dev_net(rt0->dst.dev); + return match ? match : net->ipv6.ip6_null_entry; +} + +#ifdef CONFIG_IPV6_ROUTE_INFO +int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, + const struct in6_addr *gwaddr) +{ + struct net *net = dev_net(dev); + struct route_info *rinfo = (struct route_info *) opt; + struct in6_addr prefix_buf, *prefix; + unsigned int pref; + unsigned long lifetime; + struct rt6_info *rt; + + if (len < sizeof(struct route_info)) { + return -EINVAL; } - spin_unlock(&rt6_dflt_lock); - if (!match) { - /* - * Last Resort: if no default routers found, - * use addrconf default route. - * We don't record this route. - */ - for (sprt = ip6_routing_table.leaf; - sprt; sprt = sprt->u.next) { - if (!rt6_check_expired(sprt) && - (sprt->rt6i_flags & RTF_DEFAULT) && - (!oif || - (sprt->rt6i_dev && - sprt->rt6i_dev->ifindex == oif))) { - match = sprt; - break; - } + /* Sanity check for prefix_len and length */ + if (rinfo->length > 3) { + return -EINVAL; + } else if (rinfo->prefix_len > 128) { + return -EINVAL; + } else if (rinfo->prefix_len > 64) { + if (rinfo->length < 2) { + return -EINVAL; } - if (!match) { - /* no default route. give up. */ - match = &ip6_null_entry; + } else if (rinfo->prefix_len > 0) { + if (rinfo->length < 1) { + return -EINVAL; } } - return match; + pref = rinfo->route_pref; + if (pref == ICMPV6_ROUTER_PREF_INVALID) + return -EINVAL; + + lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); + + if (rinfo->length == 3) + prefix = (struct in6_addr *)rinfo->prefix; + else { + /* this function is safe */ + ipv6_addr_prefix(&prefix_buf, + (struct in6_addr *)rinfo->prefix, + rinfo->prefix_len); + prefix = &prefix_buf; + } + + if (rinfo->prefix_len == 0) + rt = rt6_get_dflt_router(gwaddr, dev); + else + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, + gwaddr, dev->ifindex); + + if (rt && !lifetime) { + ip6_del_rt(rt); + rt = NULL; + } + + if (!rt && lifetime) + rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex, + pref); + else if (rt) + rt->rt6i_flags = RTF_ROUTEINFO | + (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + + if (rt) { + if (!addrconf_finite_timeout(lifetime)) + rt6_clean_expires(rt); + else + rt6_set_expires(rt, jiffies + HZ * lifetime); + + ip6_rt_put(rt); + } + return 0; } +#endif -struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, - int oif, int strict) +#define BACKTRACK(__net, saddr) \ +do { \ + if (rt == __net->ipv6.ip6_null_entry) { \ + struct fib6_node *pn; \ + while (1) { \ + if (fn->fn_flags & RTN_TL_ROOT) \ + goto out; \ + pn = fn->parent; \ + if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \ + fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \ + else \ + fn = pn; \ + if (fn->fn_flags & RTN_RTINFO) \ + goto restart; \ + } \ + } \ +} while (0) + +static struct rt6_info *ip6_pol_route_lookup(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, int flags) { struct fib6_node *fn; struct rt6_info *rt; - read_lock_bh(&rt6_lock); - fn = fib6_lookup(&ip6_routing_table, daddr, saddr); - rt = rt6_device_match(fn->leaf, oif, strict); - dst_hold(&rt->u.dst); - rt->u.dst.__use++; - read_unlock_bh(&rt6_lock); - - rt->u.dst.lastuse = jiffies; - if (rt->u.dst.error == 0) - return rt; - dst_release(&rt->u.dst); + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); +restart: + rt = fn->leaf; + rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags); + BACKTRACK(net, &fl6->saddr); +out: + dst_use(&rt->dst, jiffies); + read_unlock_bh(&table->tb6_lock); + return rt; + +} + +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) +{ + struct flowi6 fl6 = { + .flowi6_oif = oif, + .daddr = *daddr, + }; + struct dst_entry *dst; + int flags = strict ? RT6_LOOKUP_F_IFACE : 0; + + if (saddr) { + memcpy(&fl6.saddr, saddr, sizeof(*saddr)); + flags |= RT6_LOOKUP_F_HAS_SADDR; + } + + dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup); + if (dst->error == 0) + return (struct rt6_info *) dst; + + dst_release(dst); + return NULL; } -/* ip6_ins_rt is called with FREE rt6_lock. +EXPORT_SYMBOL(rt6_lookup); + +/* ip6_ins_rt is called with FREE table->tb6_lock. It takes new route entry, the addition fails by any reason the route is freed. In any case, if caller does not hold it, it may be destroyed. */ -int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { int err; + struct fib6_table *table; - write_lock_bh(&rt6_lock); - err = fib6_add(&ip6_routing_table, rt, nlh, _rtattr, req); - write_unlock_bh(&rt6_lock); + table = rt->rt6i_table; + write_lock_bh(&table->tb6_lock); + err = fib6_add(&table->tb6_root, rt, info, mx, mx_len); + write_unlock_bh(&table->tb6_lock); return err; } -/* No rt6_lock! If COW failed, the function returns dead route entry - with dst->error set to errno value. - */ +int ip6_ins_rt(struct rt6_info *rt) +{ + struct nl_info info = { + .nl_net = dev_net(rt->dst.dev), + }; + return __ip6_ins_rt(rt, &info, NULL, 0); +} -static struct rt6_info *rt6_cow(struct rt6_info *ort, struct in6_addr *daddr, - struct in6_addr *saddr, struct netlink_skb_parms *req) +static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { - int err; struct rt6_info *rt; /* * Clone the route. */ - rt = ip6_rt_copy(ort); + rt = ip6_rt_copy(ort, daddr); if (rt) { - ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); + if (ort->rt6i_dst.plen != 128 && + ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) + rt->rt6i_flags |= RTF_ANYCAST; - if (!(rt->rt6i_flags&RTF_GATEWAY)) - ipv6_addr_copy(&rt->rt6i_gateway, daddr); - - rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; - rt->u.dst.flags |= DST_HOST; #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 - - rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); - - dst_hold(&rt->u.dst); - - err = ip6_ins_rt(rt, NULL, NULL, req); - if (err == 0) - return rt; - - rt->u.dst.error = err; - - return rt; } - dst_hold(&ip6_null_entry.u.dst); - return &ip6_null_entry; -} -#define BACKTRACK() \ -if (rt == &ip6_null_entry && strict) { \ - while ((fn = fn->parent) != NULL) { \ - if (fn->fn_flags & RTN_ROOT) { \ - dst_hold(&rt->u.dst); \ - goto out; \ - } \ - if (fn->fn_flags & RTN_RTINFO) \ - goto restart; \ - } \ + return rt; } +static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, + const struct in6_addr *daddr) +{ + struct rt6_info *rt = ip6_rt_copy(ort, daddr); -void ip6_route_input(struct sk_buff *skb) + if (rt) + rt->rt6i_flags |= RTF_CACHE; + return rt; +} + +static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, + struct flowi6 *fl6, int flags) { struct fib6_node *fn; - struct rt6_info *rt; - int strict; + struct rt6_info *rt, *nrt; + int strict = 0; int attempts = 3; + int err; + int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE; - strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL); + strict |= flags & RT6_LOOKUP_F_IFACE; relookup: - read_lock_bh(&rt6_lock); + read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr); +restart_2: + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = fn->leaf; - - if ((rt->rt6i_flags & RTF_CACHE)) { - rt = rt6_device_match(rt, skb->dev->ifindex, strict); - BACKTRACK(); - dst_hold(&rt->u.dst); + rt = rt6_select(fn, oif, strict | reachable); + if (rt->rt6i_nsiblings) + rt = rt6_multipath_select(rt, fl6, oif, strict | reachable); + BACKTRACK(net, &fl6->saddr); + if (rt == net->ipv6.ip6_null_entry || + rt->rt6i_flags & RTF_CACHE) goto out; - } - rt = rt6_device_match(rt, skb->dev->ifindex, strict); - BACKTRACK(); + dst_hold(&rt->dst); + read_unlock_bh(&table->tb6_lock); - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) { - struct rt6_info *nrt; - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); - - nrt = rt6_cow(rt, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr, - &NETLINK_CB(skb)); + if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) + nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); + else if (!(rt->dst.flags & DST_HOST)) + nrt = rt6_alloc_clone(rt, &fl6->daddr); + else + goto out2; - dst_release(&rt->u.dst); - rt = nrt; + ip6_rt_put(rt); + rt = nrt ? : net->ipv6.ip6_null_entry; - if (rt->u.dst.error != -EEXIST || --attempts <= 0) + dst_hold(&rt->dst); + if (nrt) { + err = ip6_ins_rt(nrt); + if (!err) goto out2; - - /* Race condition! In the gap, when rt6_lock was - released someone could insert this route. Relookup. - */ - dst_release(&rt->u.dst); - goto relookup; } - dst_hold(&rt->u.dst); + + if (--attempts <= 0) + goto out2; + + /* + * Race condition! In the gap, when table->tb6_lock was + * released someone could insert this route. Relookup. + */ + ip6_rt_put(rt); + goto relookup; out: - read_unlock_bh(&rt6_lock); + if (reachable) { + reachable = 0; + goto restart_2; + } + dst_hold(&rt->dst); + read_unlock_bh(&table->tb6_lock); out2: - rt->u.dst.lastuse = jiffies; - rt->u.dst.__use++; - skb->dst = (struct dst_entry *) rt; + rt->dst.lastuse = jiffies; + rt->dst.__use++; + + return rt; } -struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) +static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, + struct flowi6 *fl6, int flags) { - struct fib6_node *fn; - struct rt6_info *rt; - int strict; - int attempts = 3; + return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags); +} - strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL); +static struct dst_entry *ip6_route_input_lookup(struct net *net, + struct net_device *dev, + struct flowi6 *fl6, int flags) +{ + if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) + flags |= RT6_LOOKUP_F_IFACE; -relookup: - read_lock_bh(&rt6_lock); + return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input); +} - fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src); +void ip6_route_input(struct sk_buff *skb) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct net *net = dev_net(skb->dev); + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct flowi6 fl6 = { + .flowi6_iif = skb->dev->ifindex, + .daddr = iph->daddr, + .saddr = iph->saddr, + .flowlabel = ip6_flowinfo(iph), + .flowi6_mark = skb->mark, + .flowi6_proto = iph->nexthdr, + }; -restart: - rt = fn->leaf; + skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags)); +} - if ((rt->rt6i_flags & RTF_CACHE)) { - rt = rt6_device_match(rt, fl->oif, strict); - BACKTRACK(); - dst_hold(&rt->u.dst); - goto out; - } - if (rt->rt6i_flags & RTF_DEFAULT) { - if (rt->rt6i_metric >= IP6_RT_PRIO_ADDRCONF) - rt = rt6_best_dflt(rt, fl->oif); - } else { - rt = rt6_device_match(rt, fl->oif, strict); - BACKTRACK(); - } +static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, + struct flowi6 *fl6, int flags) +{ + return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); +} - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) { - struct rt6_info *nrt; - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); +struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, + struct flowi6 *fl6) +{ + int flags = 0; - nrt = rt6_cow(rt, &fl->fl6_dst, &fl->fl6_src, NULL); + fl6->flowi6_iif = LOOPBACK_IFINDEX; - dst_release(&rt->u.dst); - rt = nrt; + if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) + flags |= RT6_LOOKUP_F_IFACE; - if (rt->u.dst.error != -EEXIST || --attempts <= 0) - goto out2; + if (!ipv6_addr_any(&fl6->saddr)) + flags |= RT6_LOOKUP_F_HAS_SADDR; + else if (sk) + flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); + + return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); +} + +EXPORT_SYMBOL(ip6_route_output); + +struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) +{ + struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; + struct dst_entry *new = NULL; + + rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); + if (rt) { + new = &rt->dst; - /* Race condition! In the gap, when rt6_lock was - released someone could insert this route. Relookup. - */ - dst_release(&rt->u.dst); - goto relookup; + memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); + rt6_init_peer(rt, net->ipv6.peers); + + new->__use = 1; + new->input = dst_discard; + new->output = dst_discard_sk; + + if (dst_metrics_read_only(&ort->dst)) + new->_metrics = ort->dst._metrics; + else + dst_copy_metrics(new, &ort->dst); + rt->rt6i_idev = ort->rt6i_idev; + if (rt->rt6i_idev) + in6_dev_hold(rt->rt6i_idev); + + rt->rt6i_gateway = ort->rt6i_gateway; + rt->rt6i_flags = ort->rt6i_flags; + rt->rt6i_metric = 0; + + memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); +#ifdef CONFIG_IPV6_SUBTREES + memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); +#endif + + dst_free(new); } - dst_hold(&rt->u.dst); -out: - read_unlock_bh(&rt6_lock); -out2: - rt->u.dst.lastuse = jiffies; - rt->u.dst.__use++; - return &rt->u.dst; + dst_release(dst_orig); + return new ? new : ERR_PTR(-ENOMEM); } - /* * Destination cache support functions */ @@ -588,10 +1094,20 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; - if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) - return dst; + /* All IPV6 dsts are created with ->obsolete set to the value + * DST_OBSOLETE_FORCE_CHK which forces validation calls down + * into this function always. + */ + if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) + return NULL; - return NULL; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; + + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -599,59 +1115,218 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) struct rt6_info *rt = (struct rt6_info *) dst; if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - ip6_del_rt(rt, NULL, NULL, NULL); - else + if (rt->rt6i_flags & RTF_CACHE) { + if (rt6_check_expired(rt)) { + ip6_del_rt(rt); + dst = NULL; + } + } else { dst_release(dst); + dst = NULL; + } } - return NULL; + return dst; } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); - rt = (struct rt6_info *) skb->dst; + rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags&RTF_CACHE) { - dst_set_expires(&rt->u.dst, 0); - rt->rt6i_flags |= RTF_EXPIRES; - } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; + } } } -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct rt6_info *rt6 = (struct rt6_info*)dst; + dst_confirm(dst); if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { + struct net *net = dev_net(dst->dev); + rt6->rt6i_flags |= RTF_MODIFIED; if (mtu < IPV6_MIN_MTU) { + u32 features = dst_metric(dst, RTAX_FEATURES); mtu = IPV6_MIN_MTU; - dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + features |= RTAX_FEATURE_ALLFRAG; + dst_metric_set(dst, RTAX_FEATURES, features); } - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); + rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } } -/* Protected by rt6_lock. */ -static struct dst_entry *ndisc_dst_gc_list; -static int ipv6_get_mtu(struct net_device *dev); +void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, + int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark); + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = ip6_flowinfo(iph); + + dst = ip6_route_output(net, NULL, &fl6); + if (!dst->error) + ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu)); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_update_pmtu); + +void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) +{ + ip6_update_pmtu(skb, sock_net(sk), mtu, + sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); + +/* Handle redirects */ +struct ip6rd_flowi { + struct flowi6 fl6; + struct in6_addr gateway; +}; + +static struct rt6_info *__ip6_route_redirect(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + int flags) +{ + struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; + struct rt6_info *rt; + struct fib6_node *fn; + + /* Get the "current" route for this destination and + * check if the redirect has come from approriate router. + * + * RFC 4861 specifies that redirects should only be + * accepted if they come from the nexthop to the target. + * Due to the way the routes are chosen, this notion + * is a bit fuzzy and one might need to check all possible + * routes. + */ + + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); +restart: + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (rt6_check_expired(rt)) + continue; + if (rt->dst.error) + break; + if (!(rt->rt6i_flags & RTF_GATEWAY)) + continue; + if (fl6->flowi6_oif != rt->dst.dev->ifindex) + continue; + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + continue; + break; + } + + if (!rt) + rt = net->ipv6.ip6_null_entry; + else if (rt->dst.error) { + rt = net->ipv6.ip6_null_entry; + goto out; + } + BACKTRACK(net, &fl6->saddr); +out: + dst_hold(&rt->dst); + + read_unlock_bh(&table->tb6_lock); + + return rt; +}; + +static struct dst_entry *ip6_route_redirect(struct net *net, + const struct flowi6 *fl6, + const struct in6_addr *gateway) +{ + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct ip6rd_flowi rdfl; + + rdfl.fl6 = *fl6; + rdfl.gateway = *gateway; + + return fib6_rule_lookup(net, &rdfl.fl6, + flags, __ip6_route_redirect); +} + +void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) +{ + const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = ip6_flowinfo(iph); + + dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr); + rt6_do_redirect(dst, NULL, skb); + dst_release(dst); +} +EXPORT_SYMBOL_GPL(ip6_redirect); -static inline unsigned int ipv6_advmss(unsigned int mtu) +void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, + u32 mark) { + const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; + fl6.flowi6_oif = oif; + fl6.flowi6_mark = mark; + fl6.daddr = msg->dest; + fl6.saddr = iph->daddr; + + dst = ip6_route_redirect(net, &fl6, &iph->saddr); + rt6_do_redirect(dst, NULL, skb); + dst_release(dst); +} + +void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) +{ + ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark); +} +EXPORT_SYMBOL_GPL(ip6_sk_redirect); + +static unsigned int ip6_default_advmss(const struct dst_entry *dst) +{ + struct net_device *dev = dst->dev; + unsigned int mtu = dst_mtu(dst); + struct net *net = dev_net(dev); + mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); - if (mtu < ip6_rt_min_advmss) - mtu = ip6_rt_min_advmss; + if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) + mtu = net->ipv6.sysctl.ip6_rt_min_advmss; /* - * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and - * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. - * IPV6_MAXPLEN is also valid and means: "any MSS, + * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and + * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. + * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) @@ -659,158 +1334,159 @@ static inline unsigned int ipv6_advmss(unsigned int mtu) return mtu; } -struct dst_entry *ndisc_dst_alloc(struct net_device *dev, - struct neighbour *neigh, - struct in6_addr *addr, - int (*output)(struct sk_buff *)) +static unsigned int ip6_mtu(const struct dst_entry *dst) { + struct inet6_dev *idev; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu) + goto out; + + mtu = IPV6_MIN_MTU; + + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); + if (idev) + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + +out: + return min_t(unsigned int, mtu, IP6_MAX_MTU); +} + +static struct dst_entry *icmp6_dst_gc_list; +static DEFINE_SPINLOCK(icmp6_dst_lock); + +struct dst_entry *icmp6_dst_alloc(struct net_device *dev, + 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)) - return NULL; + if (unlikely(!idev)) + return ERR_PTR(-ENODEV); - rt = ip6_dst_alloc(); - if (unlikely(rt == NULL)) { + rt = ip6_dst_alloc(net, dev, 0, NULL); + if (unlikely(!rt)) { in6_dev_put(idev); + dst = ERR_PTR(-ENOMEM); goto out; } - dev_hold(dev); - if (neigh) - neigh_hold(neigh); - else - neigh = ndisc_get_neigh(dev, addr); - - rt->rt6i_dev = dev; - rt->rt6i_idev = idev; - rt->rt6i_nexthop = neigh; - atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255; - rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); - rt->u.dst.output = output; - -#if 0 /* there's no chance to use these for ndisc */ - rt->u.dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST - ? DST_HOST - : 0; - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); + rt->dst.flags |= DST_HOST; + rt->dst.output = ip6_output; + atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; + rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; -#endif + rt->rt6i_idev = idev; + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); + + spin_lock_bh(&icmp6_dst_lock); + rt->dst.next = icmp6_dst_gc_list; + icmp6_dst_gc_list = &rt->dst; + spin_unlock_bh(&icmp6_dst_lock); - write_lock_bh(&rt6_lock); - rt->u.dst.next = ndisc_dst_gc_list; - ndisc_dst_gc_list = &rt->u.dst; - write_unlock_bh(&rt6_lock); + fib6_force_start_gc(net); - fib6_force_start_gc(); + dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); out: - return (struct dst_entry *)rt; + return dst; } -int ndisc_dst_gc(int *more) +int icmp6_dst_gc(void) { - struct dst_entry *dst, *next, **pprev; - int freed; + struct dst_entry *dst, **pprev; + int more = 0; + + spin_lock_bh(&icmp6_dst_lock); + pprev = &icmp6_dst_gc_list; - next = NULL; - pprev = &ndisc_dst_gc_list; - freed = 0; while ((dst = *pprev) != NULL) { if (!atomic_read(&dst->__refcnt)) { *pprev = dst->next; dst_free(dst); - freed++; } else { pprev = &dst->next; - (*more)++; + ++more; } } - return freed; -} - -static int ip6_dst_gc(void) -{ - static unsigned expire = 30*HZ; - static unsigned long last_gc; - unsigned long now = jiffies; - - if (time_after(last_gc + ip6_rt_gc_min_interval, now) && - atomic_read(&ip6_dst_ops.entries) <= ip6_rt_max_size) - goto out; - - expire++; - fib6_run_gc(expire); - last_gc = now; - if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh) - expire = ip6_rt_gc_timeout>>1; + spin_unlock_bh(&icmp6_dst_lock); -out: - expire -= expire>>ip6_rt_gc_elasticity; - return (atomic_read(&ip6_dst_ops.entries) > ip6_rt_max_size); + return more; } -/* Clean host part of a prefix. Not necessary in radix tree, - but results in cleaner routing tables. - - Remove it only when all the things will work! - */ - -static int ipv6_get_mtu(struct net_device *dev) +static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), + void *arg) { - int mtu = IPV6_MIN_MTU; - struct inet6_dev *idev; + struct dst_entry *dst, **pprev; - idev = in6_dev_get(dev); - if (idev) { - mtu = idev->cnf.mtu6; - in6_dev_put(idev); + spin_lock_bh(&icmp6_dst_lock); + pprev = &icmp6_dst_gc_list; + while ((dst = *pprev) != NULL) { + struct rt6_info *rt = (struct rt6_info *) dst; + if (func(rt, arg)) { + *pprev = dst->next; + dst_free(dst); + } else { + pprev = &dst->next; + } } - return mtu; + spin_unlock_bh(&icmp6_dst_lock); } -int ipv6_get_hoplimit(struct net_device *dev) +static int ip6_dst_gc(struct dst_ops *ops) { - int hoplimit = ipv6_devconf.hop_limit; - struct inet6_dev *idev; + struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); + int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; + int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; + int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; + int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; + unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + int entries; + + entries = dst_entries_get_fast(ops); + if (time_after(rt_last_gc + rt_min_interval, jiffies) && + entries <= rt_max_size) + goto out; - idev = in6_dev_get(dev); - if (idev) { - hoplimit = idev->cnf.hop_limit; - in6_dev_put(idev); - } - return hoplimit; + net->ipv6.ip6_rt_gc_expire++; + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + entries = dst_entries_get_slow(ops); + if (entries < ops->gc_thresh) + net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; +out: + net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + return entries > rt_max_size; } /* * */ -int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +int ip6_route_add(struct fib6_config *cfg) { int err; - struct rtmsg *r; - struct rtattr **rta; + struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; + struct fib6_table *table; int addr_type; - rta = (struct rtattr **) _rtattr; - - if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128) + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) return -EINVAL; #ifndef CONFIG_IPV6_SUBTREES - if (rtmsg->rtmsg_src_len) + if (cfg->fc_src_len) return -EINVAL; #endif - if (rtmsg->rtmsg_ifindex) { + if (cfg->fc_ifindex) { err = -ENODEV; - dev = dev_get_by_index(rtmsg->rtmsg_ifindex); + dev = dev_get_by_index(net, cfg->fc_ifindex); if (!dev) goto out; idev = in6_dev_get(dev); @@ -818,59 +1494,80 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto out; } - if (rtmsg->rtmsg_metric == 0) - rtmsg->rtmsg_metric = IP6_RT_PRIO_USER; + if (cfg->fc_metric == 0) + cfg->fc_metric = IP6_RT_PRIO_USER; + + 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) { + pr_warn("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(); + rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table); - if (rt == NULL) { + if (!rt) { err = -ENOMEM; goto out; } - rt->u.dst.obsolete = -1; - rt->rt6i_expires = clock_t_to_jiffies(rtmsg->rtmsg_info); - if (nlh && (r = NLMSG_DATA(nlh))) { - rt->rt6i_protocol = r->rtm_protocol; - } else { - rt->rt6i_protocol = RTPROT_BOOT; - } + if (cfg->fc_flags & RTF_EXPIRES) + rt6_set_expires(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); + else + rt6_clean_expires(rt); - addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst); + if (cfg->fc_protocol == RTPROT_UNSPEC) + cfg->fc_protocol = RTPROT_BOOT; + rt->rt6i_protocol = cfg->fc_protocol; + + addr_type = ipv6_addr_type(&cfg->fc_dst); if (addr_type & IPV6_ADDR_MULTICAST) - rt->u.dst.input = ip6_mc_input; + rt->dst.input = ip6_mc_input; + else if (cfg->fc_flags & RTF_LOCAL) + rt->dst.input = ip6_input; else - rt->u.dst.input = ip6_forward; + rt->dst.input = ip6_forward; - rt->u.dst.output = ip6_output; + rt->dst.output = ip6_output; - ipv6_addr_prefix(&rt->rt6i_dst.addr, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len); - rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len; - if (rt->rt6i_dst.plen == 128) - rt->u.dst.flags = DST_HOST; + ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); + rt->rt6i_dst.plen = cfg->fc_dst_len; + if (rt->rt6i_dst.plen == 128) { + rt->dst.flags |= DST_HOST; + dst_metrics_set_force_overwrite(&rt->dst); + } #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_prefix(&rt->rt6i_src.addr, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); - rt->rt6i_src.plen = rtmsg->rtmsg_src_len; + ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); + rt->rt6i_src.plen = cfg->fc_src_len; #endif - rt->rt6i_metric = rtmsg->rtmsg_metric; + rt->rt6i_metric = cfg->fc_metric; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes */ - if ((rtmsg->rtmsg_flags&RTF_REJECT) || - (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) { + if ((cfg->fc_flags & RTF_REJECT) || + (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 != &loopback_dev) { + if (dev != net->loopback_dev) { if (dev) { dev_put(dev); in6_dev_put(idev); } - dev = &loopback_dev; + dev = net->loopback_dev; dev_hold(dev); idev = in6_dev_get(dev); if (!idev) { @@ -878,19 +1575,35 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto out; } } - rt->u.dst.output = ip6_pkt_discard_out; - rt->u.dst.input = ip6_pkt_discard; - rt->u.dst.error = -ENETUNREACH; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; + switch (cfg->fc_type) { + case RTN_BLACKHOLE: + rt->dst.error = -EINVAL; + rt->dst.output = dst_discard_sk; + rt->dst.input = dst_discard; + break; + case RTN_PROHIBIT: + rt->dst.error = -EACCES; + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; + break; + case RTN_THROW: + default: + rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN + : -ENETUNREACH; + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; + break; + } goto install_route; } - if (rtmsg->rtmsg_flags & RTF_GATEWAY) { - struct in6_addr *gw_addr; + if (cfg->fc_flags & RTF_GATEWAY) { + const struct in6_addr *gw_addr; int gwa_type; - gw_addr = &rtmsg->rtmsg_gateway; - ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway); + gw_addr = &cfg->fc_gateway; + rt->rt6i_gateway = *gw_addr; gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -904,80 +1617,61 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, some exceptions. --ANK */ err = -EINVAL; - if (!(gwa_type&IPV6_ADDR_UNICAST)) + if (!(gwa_type & IPV6_ADDR_UNICAST)) goto out; - grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1); + 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) { - dst_release(&grt->u.dst); + if (dev != grt->dst.dev) { + ip6_rt_put(grt); 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->u.dst); + ip6_rt_put(grt); if (err) 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 (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) { - rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); - if (IS_ERR(rt->rt6i_nexthop)) { - err = PTR_ERR(rt->rt6i_nexthop); - rt->rt6i_nexthop = NULL; + if (!ipv6_addr_any(&cfg->fc_prefsrc)) { + if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { + err = -EINVAL; goto out; } - } + rt->rt6i_prefsrc.addr = cfg->fc_prefsrc; + rt->rt6i_prefsrc.plen = 128; + } else + rt->rt6i_prefsrc.plen = 0; - rt->rt6i_flags = rtmsg->rtmsg_flags; + rt->rt6i_flags = cfg->fc_flags; install_route: - if (rta && rta[RTA_METRICS-1]) { - int attrlen = RTA_PAYLOAD(rta[RTA_METRICS-1]); - struct rtattr *attr = RTA_DATA(rta[RTA_METRICS-1]); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > RTAX_MAX) { - err = -EINVAL; - goto out; - } - rt->u.dst.metrics[flavor-1] = - *(u32 *)RTA_DATA(attr); - } - attr = RTA_NEXT(attr, attrlen); - } - } - - if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0) - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; - if (!rt->u.dst.metrics[RTAX_MTU-1]) - rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); - if (!rt->u.dst.metrics[RTAX_ADVMSS-1]) - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); - rt->u.dst.dev = dev; + rt->dst.dev = dev; rt->rt6i_idev = idev; - return ip6_ins_rt(rt, nlh, _rtattr, req); + rt->rt6i_table = table; + + cfg->fc_nlinfo.nl_net = dev_net(dev); + + return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len); out: if (dev) @@ -985,377 +1679,414 @@ out: if (idev) in6_dev_put(idev); if (rt) - dst_free((struct dst_entry *) rt); + dst_free(&rt->dst); return err; } -int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +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->dst.dev); - write_lock_bh(&rt6_lock); - - rt6_reset_dflt_pointer(NULL); - - err = fib6_del(rt, nlh, _rtattr, req); - dst_release(&rt->u.dst); + if (rt == net->ipv6.ip6_null_entry) { + err = -ENOENT; + goto out; + } - write_unlock_bh(&rt6_lock); + table = rt->rt6i_table; + write_lock_bh(&table->tb6_lock); + err = fib6_del(rt, info); + write_unlock_bh(&table->tb6_lock); +out: + ip6_rt_put(rt); return err; } -static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int ip6_del_rt(struct rt6_info *rt) +{ + struct nl_info info = { + .nl_net = dev_net(rt->dst.dev), + }; + return __ip6_del_rt(rt, &info); +} + +static int ip6_route_del(struct fib6_config *cfg) { + struct fib6_table *table; struct fib6_node *fn; struct rt6_info *rt; int err = -ESRCH; - read_lock_bh(&rt6_lock); + table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); + if (!table) + return err; + + read_lock_bh(&table->tb6_lock); + + fn = fib6_locate(&table->tb6_root, + &cfg->fc_dst, cfg->fc_dst_len, + &cfg->fc_src, cfg->fc_src_len); - fn = fib6_locate(&ip6_routing_table, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); - if (fn) { - for (rt = fn->leaf; rt; rt = rt->u.next) { - if (rtmsg->rtmsg_ifindex && - (rt->rt6i_dev == NULL || - rt->rt6i_dev->ifindex != rtmsg->rtmsg_ifindex)) + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (cfg->fc_ifindex && + (!rt->dst.dev || + rt->dst.dev->ifindex != cfg->fc_ifindex)) continue; - if (rtmsg->rtmsg_flags&RTF_GATEWAY && - !ipv6_addr_equal(&rtmsg->rtmsg_gateway, &rt->rt6i_gateway)) + if (cfg->fc_flags & RTF_GATEWAY && + !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) continue; - if (rtmsg->rtmsg_metric && - rtmsg->rtmsg_metric != rt->rt6i_metric) + if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + dst_hold(&rt->dst); + read_unlock_bh(&table->tb6_lock); - return ip6_del_rt(rt, nlh, _rtattr, req); + return __ip6_del_rt(rt, &cfg->fc_nlinfo); } } - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); return err; } -/* - * Handle redirects - */ -void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, - struct neighbour *neigh, u8 *lladdr, int on_link) +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { - struct rt6_info *rt, *nrt; + struct net *net = dev_net(skb->dev); + struct netevent_redirect netevent; + struct rt6_info *rt, *nrt = NULL; + struct ndisc_options ndopts; + struct inet6_dev *in6_dev; + struct neighbour *neigh; + struct rd_msg *msg; + int optlen, on_link; + u8 *lladdr; + + optlen = skb_tail_pointer(skb) - skb_transport_header(skb); + optlen -= sizeof(*msg); + + if (optlen < 0) { + net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); + return; + } - /* Locate old route to this destination. */ - rt = rt6_lookup(dest, NULL, neigh->dev->ifindex, 1); + msg = (struct rd_msg *)icmp6_hdr(skb); - if (rt == NULL) + if (ipv6_addr_is_multicast(&msg->dest)) { + net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; + } - if (neigh->dev != rt->rt6i_dev) - goto out; + on_link = 0; + if (ipv6_addr_equal(&msg->dest, &msg->target)) { + on_link = 1; + } else if (ipv6_addr_type(&msg->target) != + (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { + net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); + return; + } - /* - * Current route is on-link; redirect is always invalid. - * - * Seems, previous statement is not true. It could - * be node, which looks for us as on-link (f.e. proxy ndisc) - * But then router serving it might decide, that we should - * know truth 8)8) --ANK (980726). - */ - if (!(rt->rt6i_flags&RTF_GATEWAY)) - goto out; + in6_dev = __in6_dev_get(skb->dev); + if (!in6_dev) + return; + if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) + return; - /* - * RFC 2461 specifies that redirects should only be - * accepted if they come from the nexthop to the target. - * Due to the way default routers are chosen, this notion - * is a bit fuzzy and one might need to check all default - * routers. + /* RFC2461 8.1: + * The IP source address of the Redirect MUST be the same as the current + * first-hop router for the specified ICMP Destination Address. */ - if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway)) { - if (rt->rt6i_flags & RTF_DEFAULT) { - struct rt6_info *rt1; - - read_lock(&rt6_lock); - for (rt1 = ip6_routing_table.leaf; rt1; rt1 = rt1->u.next) { - if (ipv6_addr_equal(saddr, &rt1->rt6i_gateway)) { - dst_hold(&rt1->u.dst); - dst_release(&rt->u.dst); - read_unlock(&rt6_lock); - rt = rt1; - goto source_ok; - } - } - read_unlock(&rt6_lock); + + if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) { + net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); + return; + } + + lladdr = NULL; + if (ndopts.nd_opts_tgt_lladdr) { + lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, + skb->dev); + if (!lladdr) { + net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); + return; } - if (net_ratelimit()) - printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop " - "for redirect target\n"); - goto out; } -source_ok: + rt = (struct rt6_info *) dst; + if (rt == net->ipv6.ip6_null_entry) { + net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); + return; + } + + /* Redirect received -> path was valid. + * Look, redirects are sent only in response to data packets, + * so that this nexthop apparently is reachable. --ANK + */ + dst_confirm(&rt->dst); + + neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); + if (!neigh) + return; /* * We have finally decided to accept it. */ - neigh_update(neigh, lladdr, NUD_STALE, + neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER)) ); - /* - * Redirect received -> path was valid. - * Look, redirects are sent only in response to data packets, - * so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->u.dst); - - /* Duplicate redirect: silently ignore. */ - if (neigh == rt->u.dst.neighbour) - goto out; - - nrt = ip6_rt_copy(rt); - if (nrt == NULL) + nrt = ip6_rt_copy(rt, &msg->dest); + 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_dst.addr, dest); - nrt->rt6i_dst.plen = 128; - nrt->u.dst.flags |= DST_HOST; - - ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); - nrt->rt6i_nexthop = neigh_clone(neigh); - /* Reset pmtu, it may be better */ - nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); - nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst)); + nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - if (ip6_ins_rt(nrt, NULL, NULL, NULL)) + if (ip6_ins_rt(nrt)) goto out; - if (rt->rt6i_flags&RTF_CACHE) { - ip6_del_rt(rt, NULL, NULL, NULL); - return; - } + netevent.old = &rt->dst; + netevent.new = &nrt->dst; + netevent.daddr = &msg->dest; + netevent.neigh = neigh; + call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); -out: - dst_release(&rt->u.dst); - return; -} - -/* - * Handle ICMP "packet too big" messages - * i.e. Path MTU discovery - */ - -void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, - struct net_device *dev, u32 pmtu) -{ - struct rt6_info *rt, *nrt; - int allfrag = 0; - - rt = rt6_lookup(daddr, saddr, dev->ifindex, 0); - if (rt == NULL) - return; - - if (pmtu >= dst_mtu(&rt->u.dst)) - goto out; - - if (pmtu < IPV6_MIN_MTU) { - /* - * According to RFC2460, PMTU is set to the IPv6 Minimum Link - * MTU (1280) and a fragment header should always be included - * after a node receiving Too Big message reporting PMTU is - * less than the IPv6 Minimum Link MTU. - */ - pmtu = IPV6_MIN_MTU; - allfrag = 1; - } - - /* New mtu received -> path was valid. - They are sent only in response to data packets, - so that this nexthop apparently is reachable. --ANK - */ - dst_confirm(&rt->u.dst); - - /* Host route. If it is static, it would be better - not to override it, but add new one, so that - when cache entry will expire old pmtu - would return automatically. - */ if (rt->rt6i_flags & RTF_CACHE) { - rt->u.dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; - dst_set_expires(&rt->u.dst, ip6_rt_mtu_expires); - rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; - goto out; - } - - /* Network route. - Two cases are possible: - 1. It is connected route. Action: COW - 2. It is gatewayed route or NONEXTHOP route. Action: clone it. - */ - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) { - nrt = rt6_cow(rt, daddr, saddr, NULL); - if (!nrt->u.dst.error) { - nrt->u.dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; - /* According to RFC 1981, detecting PMTU increase shouldn't be - happened within 5 mins, the recommended timer is 10 mins. - Here this route expiration time is set to ip6_rt_mtu_expires - which is 10 mins. After 10 mins the decreased pmtu is expired - and detecting PMTU increase will be automatically happened. - */ - dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - } - dst_release(&nrt->u.dst); - } else { - nrt = ip6_rt_copy(rt); - if (nrt == NULL) - goto out; - ipv6_addr_copy(&nrt->rt6i_dst.addr, daddr); - nrt->rt6i_dst.plen = 128; - nrt->u.dst.flags |= DST_HOST; - nrt->rt6i_nexthop = neigh_clone(rt->rt6i_nexthop); - dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC|RTF_CACHE|RTF_EXPIRES; - nrt->u.dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; - ip6_ins_rt(nrt, NULL, NULL, NULL); + rt = (struct rt6_info *) dst_clone(&rt->dst); + ip6_del_rt(rt); } out: - dst_release(&rt->u.dst); + neigh_release(neigh); } /* * Misc support functions */ -static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) +static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, + const struct in6_addr *dest) { - struct rt6_info *rt = ip6_dst_alloc(); + struct net *net = dev_net(ort->dst.dev); + struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0, + ort->rt6i_table); if (rt) { - rt->u.dst.input = ort->u.dst.input; - rt->u.dst.output = ort->u.dst.output; + rt->dst.input = ort->dst.input; + rt->dst.output = ort->dst.output; + rt->dst.flags |= DST_HOST; - memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); - rt->u.dst.dev = ort->u.dst.dev; - if (rt->u.dst.dev) - dev_hold(rt->u.dst.dev); + rt->rt6i_dst.addr = *dest; + rt->rt6i_dst.plen = 128; + dst_copy_metrics(&rt->dst, &ort->dst); + rt->dst.error = ort->dst.error; rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); - rt->u.dst.lastuse = jiffies; - rt->rt6i_expires = 0; + rt->dst.lastuse = jiffies; - ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); - rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; + rt->rt6i_flags = ort->rt6i_flags; + rt6_set_from(rt, ort); rt->rt6i_metric = 0; - memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif + memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key)); + rt->rt6i_table = ort->rt6i_table; } return rt; } -struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev) -{ - struct rt6_info *rt; +#ifdef CONFIG_IPV6_ROUTE_INFO +static struct rt6_info *rt6_get_route_info(struct net *net, + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex) +{ struct fib6_node *fn; + struct rt6_info *rt = NULL; + struct fib6_table *table; + + table = fib6_get_table(net, RT6_TABLE_INFO); + if (!table) + return NULL; + + read_lock_bh(&table->tb6_lock); + fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0); + if (!fn) + goto out; + + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if (rt->dst.dev->ifindex != ifindex) + continue; + if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) + continue; + if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) + continue; + dst_hold(&rt->dst); + break; + } +out: + read_unlock_bh(&table->tb6_lock); + return rt; +} + +static struct rt6_info *rt6_add_route_info(struct net *net, + const struct in6_addr *prefix, int prefixlen, + const struct in6_addr *gwaddr, int ifindex, + unsigned int pref) +{ + struct fib6_config cfg = { + .fc_table = RT6_TABLE_INFO, + .fc_metric = IP6_RT_PRIO_USER, + .fc_ifindex = ifindex, + .fc_dst_len = prefixlen, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | + RTF_UP | RTF_PREF(pref), + .fc_nlinfo.portid = 0, + .fc_nlinfo.nlh = NULL, + .fc_nlinfo.nl_net = net, + }; - fn = &ip6_routing_table; + cfg.fc_dst = *prefix; + cfg.fc_gateway = *gwaddr; - write_lock_bh(&rt6_lock); - for (rt = fn->leaf; rt; rt=rt->u.next) { - if (dev == rt->rt6i_dev && + /* We should treat it as a default route if prefix length is 0. */ + if (!prefixlen) + cfg.fc_flags |= RTF_DEFAULT; + + ip6_route_add(&cfg); + + return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex); +} +#endif + +struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev) +{ + struct rt6_info *rt; + struct fib6_table *table; + + table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT); + if (!table) + return NULL; + + read_lock_bh(&table->tb6_lock); + for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) { + if (dev == rt->dst.dev && + ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; } if (rt) - dst_hold(&rt->u.dst); - write_unlock_bh(&rt6_lock); + dst_hold(&rt->dst); + read_unlock_bh(&table->tb6_lock); return rt; } -struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, - struct net_device *dev) +struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, + struct net_device *dev, + unsigned int pref) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_DFLT, + .fc_metric = IP6_RT_PRIO_USER, + .fc_ifindex = dev->ifindex, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | + RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + .fc_nlinfo.portid = 0, + .fc_nlinfo.nlh = NULL, + .fc_nlinfo.nl_net = dev_net(dev), + }; - memset(&rtmsg, 0, sizeof(struct in6_rtmsg)); - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr); - rtmsg.rtmsg_metric = 1024; - rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES; + cfg.fc_gateway = *gwaddr; - rtmsg.rtmsg_ifindex = dev->ifindex; + ip6_route_add(&cfg); - ip6_route_add(&rtmsg, NULL, NULL, NULL); return rt6_get_dflt_router(gwaddr, dev); } -void rt6_purge_dflt_routers(void) +void rt6_purge_dflt_routers(struct net *net) { struct rt6_info *rt; + struct fib6_table *table; + + /* NOTE: Keep consistent with rt6_get_dflt_router */ + table = fib6_get_table(net, RT6_TABLE_DFLT); + if (!table) + return; restart: - read_lock_bh(&rt6_lock); - for (rt = ip6_routing_table.leaf; rt; rt = rt->u.next) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { - dst_hold(&rt->u.dst); + read_lock_bh(&table->tb6_lock); + for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { + dst_hold(&rt->dst); + read_unlock_bh(&table->tb6_lock); + ip6_del_rt(rt); + goto restart; + } + } + read_unlock_bh(&table->tb6_lock); +} - rt6_reset_dflt_pointer(NULL); +static void rtmsg_to_fib6_config(struct net *net, + struct in6_rtmsg *rtmsg, + struct fib6_config *cfg) +{ + memset(cfg, 0, sizeof(*cfg)); - read_unlock_bh(&rt6_lock); + cfg->fc_table = RT6_TABLE_MAIN; + cfg->fc_ifindex = rtmsg->rtmsg_ifindex; + cfg->fc_metric = rtmsg->rtmsg_metric; + cfg->fc_expires = rtmsg->rtmsg_info; + cfg->fc_dst_len = rtmsg->rtmsg_dst_len; + cfg->fc_src_len = rtmsg->rtmsg_src_len; + cfg->fc_flags = rtmsg->rtmsg_flags; - ip6_del_rt(rt, NULL, NULL, NULL); + cfg->fc_nlinfo.nl_net = net; - goto restart; - } - } - read_unlock_bh(&rt6_lock); + cfg->fc_dst = rtmsg->rtmsg_dst; + cfg->fc_src = rtmsg->rtmsg_src; + cfg->fc_gateway = rtmsg->rtmsg_gateway; } -int ipv6_route_ioctl(unsigned int cmd, void __user *arg) +int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) { + struct fib6_config cfg; struct in6_rtmsg rtmsg; int err; switch(cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = copy_from_user(&rtmsg, arg, sizeof(struct in6_rtmsg)); if (err) return -EFAULT; - + + rtmsg_to_fib6_config(net, &rtmsg, &cfg); + rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&rtmsg, NULL, NULL, NULL); + err = ip6_route_add(&cfg); break; case SIOCDELRT: - err = ip6_route_del(&rtmsg, NULL, NULL, NULL); + err = ip6_route_del(&cfg); break; default: err = -EINVAL; @@ -1363,7 +2094,7 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) rtnl_unlock(); return err; - }; + } return -EINVAL; } @@ -1372,18 +2103,49 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) * Drop the packet on the floor */ -static int ip6_pkt_discard(struct sk_buff *skb) +static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOROUTE, 0, skb->dev); + int type; + struct dst_entry *dst = skb_dst(skb); + switch (ipstats_mib_noroutes) { + case IPSTATS_MIB_INNOROUTES: + type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); + if (type == IPV6_ADDR_ANY) { + IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + IPSTATS_MIB_INADDRERRORS); + break; + } + /* FALLTHROUGH */ + case IPSTATS_MIB_OUTNOROUTES: + IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + ipstats_mib_noroutes); + break; + } + icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb(skb); return 0; } -static int ip6_pkt_discard_out(struct sk_buff *skb) +static int ip6_pkt_discard(struct sk_buff *skb) +{ + return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); +} + +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb) { - skb->dev = skb->dst->dev; - return ip6_pkt_discard(skb); + skb->dev = skb_dst(skb)->dev; + return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); +} + +static int ip6_pkt_prohibit(struct sk_buff *skb) +{ + return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); +} + +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb) +{ + skb->dev = skb_dst(skb)->dev; + return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } /* @@ -1392,64 +2154,138 @@ static int ip6_pkt_discard_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 rt6_info *rt = ip6_dst_alloc(); - - if (rt == NULL) + struct net *net = dev_net(idev->dev); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, + DST_NOCOUNT, NULL); + if (!rt) return ERR_PTR(-ENOMEM); - dev_hold(&loopback_dev); in6_dev_hold(idev); - rt->u.dst.flags = DST_HOST; - rt->u.dst.input = ip6_input; - rt->u.dst.output = ip6_output; - rt->rt6i_dev = &loopback_dev; + rt->dst.flags |= DST_HOST; + rt->dst.input = ip6_input; + rt->dst.output = ip6_output; rt->rt6i_idev = idev; - rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; - rt->u.dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; - if (!anycast) + if (anycast) + rt->rt6i_flags |= RTF_ANYCAST; + else rt->rt6i_flags |= RTF_LOCAL; - rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); - if (rt->rt6i_nexthop == NULL) { - dst_free((struct dst_entry *) rt); - return ERR_PTR(-ENOMEM); - } - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); + rt->rt6i_gateway = *addr; + rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; + rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); - atomic_set(&rt->u.dst.__refcnt, 1); + atomic_set(&rt->dst.__refcnt, 1); return rt; } -static int fib6_ifdown(struct rt6_info *rt, void *arg) +int ip6_route_get_saddr(struct net *net, + struct rt6_info *rt, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr) +{ + struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt); + int err = 0; + if (rt->rt6i_prefsrc.plen) + *saddr = rt->rt6i_prefsrc.addr; + else + err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, + daddr, prefs, saddr); + return err; +} + +/* remove deleted ip from prefsrc entries */ +struct arg_dev_net_ip { + struct net_device *dev; + struct net *net; + struct in6_addr *addr; +}; + +static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) +{ + struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev; + struct net *net = ((struct arg_dev_net_ip *)arg)->net; + struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; + + if (((void *)rt->dst.dev == dev || !dev) && + rt != net->ipv6.ip6_null_entry && + ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + /* remove prefsrc entry */ + rt->rt6i_prefsrc.plen = 0; + } + return 0; +} + +void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) +{ + struct net *net = dev_net(ifp->idev->dev); + struct arg_dev_net_ip adni = { + .dev = ifp->idev->dev, + .net = net, + .addr = &ifp->addr, + }; + fib6_clean_all(net, fib6_remove_prefsrc, &adni); +} + +#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +/* Remove routers and update dst entries when gateway turn into host. */ +static int fib6_clean_tohost(struct rt6_info *rt, void *arg) { - if (((void*)rt->rt6i_dev == arg || arg == NULL) && - rt != &ip6_null_entry) { - RT6_TRACE("deleted by ifdown %p\n", rt); + struct in6_addr *gateway = (struct in6_addr *)arg; + + if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || + ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { return -1; } return 0; } -void rt6_ifdown(struct net_device *dev) +void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) +{ + fib6_clean_all(net, fib6_clean_tohost, gateway); +} + +struct arg_dev_net { + struct net_device *dev; + struct net *net; +}; + +static int fib6_ifdown(struct rt6_info *rt, void *arg) { - write_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, fib6_ifdown, 0, dev); - write_unlock_bh(&rt6_lock); + const struct arg_dev_net *adn = arg; + const struct net_device *dev = adn->dev; + + if ((rt->dst.dev == dev || !dev) && + rt != adn->net->ipv6.ip6_null_entry) + return -1; + + return 0; } -struct rt6_mtu_change_arg +void rt6_ifdown(struct net *net, struct net_device *dev) { + struct arg_dev_net adn = { + .dev = dev, + .net = net, + }; + + fib6_clean_all(net, fib6_ifdown, &adn); + icmp6_clean_all(fib6_ifdown, &adn); +} + +struct rt6_mtu_change_arg { struct net_device *dev; - unsigned mtu; + unsigned int mtu; }; static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) @@ -1464,7 +2300,7 @@ 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 @@ -1481,102 +2317,230 @@ 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 && - !dst_metric_locked(&rt->u.dst, RTAX_MTU) && - (dst_mtu(&rt->u.dst) > arg->mtu || - (dst_mtu(&rt->u.dst) < arg->mtu && - dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) - rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu; - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(arg->mtu); + 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 && + dst_mtu(&rt->dst) == idev->cnf.mtu6))) { + dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); + } return 0; } -void rt6_mtu_change(struct net_device *dev, unsigned mtu) +void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { - struct rt6_mtu_change_arg arg; + struct rt6_mtu_change_arg arg = { + .dev = dev, + .mtu = mtu, + }; - arg.dev = dev; - arg.mtu = mtu; - read_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, rt6_mtu_change_route, 0, &arg); - read_unlock_bh(&rt6_lock); + fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } -static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta, - struct in6_rtmsg *rtmsg) +static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { + [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_OIF] = { .type = NLA_U32 }, + [RTA_IIF] = { .type = NLA_U32 }, + [RTA_PRIORITY] = { .type = NLA_U32 }, + [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, +}; + +static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct fib6_config *cfg) { - memset(rtmsg, 0, sizeof(*rtmsg)); + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; + int err; - rtmsg->rtmsg_dst_len = r->rtm_dst_len; - rtmsg->rtmsg_src_len = r->rtm_src_len; - rtmsg->rtmsg_flags = RTF_UP; - if (r->rtm_type == RTN_UNREACHABLE) - rtmsg->rtmsg_flags |= RTF_REJECT; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; + + err = -EINVAL; + rtm = nlmsg_data(nlh); + memset(cfg, 0, sizeof(*cfg)); + + cfg->fc_table = rtm->rtm_table; + cfg->fc_dst_len = rtm->rtm_dst_len; + cfg->fc_src_len = rtm->rtm_src_len; + cfg->fc_flags = RTF_UP; + cfg->fc_protocol = rtm->rtm_protocol; + cfg->fc_type = rtm->rtm_type; + + if (rtm->rtm_type == RTN_UNREACHABLE || + rtm->rtm_type == RTN_BLACKHOLE || + rtm->rtm_type == RTN_PROHIBIT || + rtm->rtm_type == RTN_THROW) + cfg->fc_flags |= RTF_REJECT; + + if (rtm->rtm_type == RTN_LOCAL) + cfg->fc_flags |= RTF_LOCAL; + + cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; + cfg->fc_nlinfo.nlh = nlh; + cfg->fc_nlinfo.nl_net = sock_net(skb->sk); + + if (tb[RTA_GATEWAY]) { + nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16); + cfg->fc_flags |= RTF_GATEWAY; + } - if (rta[RTA_GATEWAY-1]) { - if (rta[RTA_GATEWAY-1]->rta_len != RTA_LENGTH(16)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_gateway, RTA_DATA(rta[RTA_GATEWAY-1]), 16); - rtmsg->rtmsg_flags |= RTF_GATEWAY; + if (tb[RTA_DST]) { + int plen = (rtm->rtm_dst_len + 7) >> 3; + + if (nla_len(tb[RTA_DST]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } - if (rta[RTA_DST-1]) { - if (RTA_PAYLOAD(rta[RTA_DST-1]) < ((r->rtm_dst_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_dst, RTA_DATA(rta[RTA_DST-1]), ((r->rtm_dst_len+7)>>3)); + + if (tb[RTA_SRC]) { + int plen = (rtm->rtm_src_len + 7) >> 3; + + if (nla_len(tb[RTA_SRC]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } - if (rta[RTA_SRC-1]) { - if (RTA_PAYLOAD(rta[RTA_SRC-1]) < ((r->rtm_src_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_src, RTA_DATA(rta[RTA_SRC-1]), ((r->rtm_src_len+7)>>3)); + + if (tb[RTA_PREFSRC]) + nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16); + + if (tb[RTA_OIF]) + cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); + + if (tb[RTA_PRIORITY]) + cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); + + if (tb[RTA_METRICS]) { + cfg->fc_mx = nla_data(tb[RTA_METRICS]); + cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } - if (rta[RTA_OIF-1]) { - if (rta[RTA_OIF-1]->rta_len != RTA_LENGTH(sizeof(int))) - return -EINVAL; - memcpy(&rtmsg->rtmsg_ifindex, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + + if (tb[RTA_TABLE]) + cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + + if (tb[RTA_MULTIPATH]) { + cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); + cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); } - if (rta[RTA_PRIORITY-1]) { - if (rta[RTA_PRIORITY-1]->rta_len != RTA_LENGTH(4)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_metric, RTA_DATA(rta[RTA_PRIORITY-1]), 4); + + err = 0; +errout: + return err; +} + +static int ip6_route_multipath(struct fib6_config *cfg, int add) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 0, last_err = 0; + +beginning: + rtnh = (struct rtnexthop *)cfg->fc_mp; + remaining = cfg->fc_mp_len; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + if (err) { + last_err = err; + /* If we are trying to remove a route, do not stop the + * loop when ip6_route_del() fails (because next hop is + * already gone), we should try to remove all next hops. + */ + if (add) { + /* If add fails, we should try to delete all + * next hops that have been already added. + */ + add = 0; + goto beginning; + } + } + /* Because each route is added like a single route we remove + * this flag after the first nexthop (if there is a collision, + * we have already fail to add the first nexthop: + * fib6_add_rt2node() has reject it). + */ + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + rtnh = rtnh_next(rtnh, &remaining); } - return 0; + + return last_err; } -int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 0); + else + return ip6_route_del(&cfg); } -int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + if (cfg.fc_mp) + return ip6_route_multipath(&cfg, 1); + else + return ip6_route_add(&cfg); } -struct rt6_rtnl_dump_arg +static inline size_t rt6_nlmsg_size(void) { - struct sk_buff *skb; - struct netlink_callback *cb; -}; + return NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(16) /* RTA_SRC */ + + nla_total_size(16) /* RTA_DST */ + + nla_total_size(16) /* RTA_GATEWAY */ + + nla_total_size(16) /* RTA_PREFSRC */ + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(4) /* RTA_OIF */ + + nla_total_size(4) /* RTA_PRIORITY */ + + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + + nla_total_size(sizeof(struct rta_cacheinfo)); +} -static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, +static int rt6_fill_node(struct net *net, + struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, - int iif, int type, u32 pid, u32 seq, - int prefix, unsigned int flags) + int iif, int type, u32 portid, u32 seq, + int prefix, int nowait, unsigned int flags) { struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - struct rta_cacheinfo ci; + struct nlmsghdr *nlh; + long expires; + u32 table; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -1585,281 +2549,289 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, } } - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); + if (!nlh) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt->rt6i_dst.plen; rtm->rtm_src_len = rt->rt6i_src.plen; rtm->rtm_tos = 0; - rtm->rtm_table = RT_TABLE_MAIN; - if (rt->rt6i_flags&RTF_REJECT) - rtm->rtm_type = RTN_UNREACHABLE; - else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) + if (rt->rt6i_table) + table = rt->rt6i_table->tb6_id; + else + table = RT6_TABLE_UNSPEC; + rtm->rtm_table = table; + if (nla_put_u32(skb, RTA_TABLE, table)) + goto nla_put_failure; + if (rt->rt6i_flags & RTF_REJECT) { + switch (rt->dst.error) { + case -EINVAL: + rtm->rtm_type = RTN_BLACKHOLE; + break; + case -EACCES: + rtm->rtm_type = RTN_PROHIBIT; + break; + case -EAGAIN: + rtm->rtm_type = RTN_THROW; + break; + default: + rtm->rtm_type = RTN_UNREACHABLE; + break; + } + } + else if (rt->rt6i_flags & RTF_LOCAL) + rtm->rtm_type = RTN_LOCAL; + 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) - rtm->rtm_protocol = RTPROT_RA; + else if (rt->rt6i_flags & RTF_ADDRCONF) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO)) + rtm->rtm_protocol = RTPROT_RA; + else + rtm->rtm_protocol = RTPROT_KERNEL; + } - if (rt->rt6i_flags&RTF_CACHE) + if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dst) { - RTA_PUT(skb, RTA_DST, 16, dst); - rtm->rtm_dst_len = 128; + if (nla_put(skb, RTA_DST, 16, dst)) + goto nla_put_failure; + rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); + if (nla_put(skb, RTA_DST, 16, &rt->rt6i_dst.addr)) + goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { - RTA_PUT(skb, RTA_SRC, 16, src); - rtm->rtm_src_len = 128; - } else if (rtm->rtm_src_len) - RTA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); + if (nla_put(skb, RTA_SRC, 16, src)) + goto nla_put_failure; + rtm->rtm_src_len = 128; + } else if (rtm->rtm_src_len && + nla_put(skb, RTA_SRC, 16, &rt->rt6i_src.addr)) + goto nla_put_failure; #endif - if (iif) - RTA_PUT(skb, RTA_IIF, 4, &iif); - else if (dst) { + if (iif) { +#ifdef CONFIG_IPV6_MROUTE + if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { + int err = ip6mr_get_route(net, skb, rtm, nowait); + if (err <= 0) { + if (!nowait) { + if (err == 0) + return 0; + goto nla_put_failure; + } else { + if (err == -EMSGSIZE) + goto nla_put_failure; + } + } + } else +#endif + if (nla_put_u32(skb, RTA_IIF, iif)) + goto nla_put_failure; + } else if (dst) { struct in6_addr saddr_buf; - if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0) - RTA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); - } - if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) - goto rtattr_failure; - if (rt->u.dst.neighbour) - RTA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); - if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->rt6i_dev->ifindex); - RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric); - ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse); - if (rt->rt6i_expires) - ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies); - else - ci.rta_expires = 0; - ci.rta_used = rt->u.dst.__use; - ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt); - ci.rta_error = rt->u.dst.error; - ci.rta_id = 0; - ci.rta_ts = 0; - ci.rta_tsage = 0; - RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 && + nla_put(skb, RTA_PREFSRC, 16, &saddr_buf)) + goto nla_put_failure; + } + + if (rt->rt6i_prefsrc.plen) { + struct in6_addr saddr_buf; + saddr_buf = rt->rt6i_prefsrc.addr; + if (nla_put(skb, RTA_PREFSRC, 16, &saddr_buf)) + goto nla_put_failure; + } + + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) + goto nla_put_failure; + + if (rt->rt6i_flags & RTF_GATEWAY) { + if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0) + goto nla_put_failure; + } + + if (rt->dst.dev && + nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) + goto nla_put_failure; + if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) + goto nla_put_failure; + + expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } -static int rt6_dump_route(struct rt6_info *rt, void *p_arg) +int rt6_dump_route(struct rt6_info *rt, void *p_arg) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; int prefix; - if (arg->cb->nlh->nlmsg_len >= NLMSG_LENGTH(sizeof(struct rtmsg))) { - struct rtmsg *rtm = NLMSG_DATA(arg->cb->nlh); + if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) { + struct rtmsg *rtm = nlmsg_data(arg->cb->nlh); prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0; } else prefix = 0; - return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, - NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, - prefix, NLM_F_MULTI); + return rt6_fill_node(arg->net, + arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, + NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, + prefix, 0, NLM_F_MULTI); } -static int fib6_dump_node(struct fib6_walker_t *w) +static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh) { - int res; + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[RTA_MAX+1]; struct rt6_info *rt; + struct sk_buff *skb; + struct rtmsg *rtm; + struct flowi6 fl6; + int err, iif = 0, oif = 0; - for (rt = w->leaf; rt; rt = rt->u.next) { - res = rt6_dump_route(rt, w->args); - if (res < 0) { - /* Frame is full, suspend walking */ - w->leaf = rt; - return 1; - } - BUG_TRAP(res!=0); - } - w->leaf = NULL; - return 0; -} + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; -static void fib6_dump_end(struct netlink_callback *cb) -{ - struct fib6_walker_t *w = (void*)cb->args[0]; + err = -EINVAL; + memset(&fl6, 0, sizeof(fl6)); + + if (tb[RTA_SRC]) { + if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) + goto errout; - if (w) { - cb->args[0] = 0; - fib6_walker_unlink(w); - kfree(w); + fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } - if (cb->args[1]) { - cb->done = (void*)cb->args[1]; - cb->args[1] = 0; + + if (tb[RTA_DST]) { + if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) + goto errout; + + fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } -} -static int fib6_dump_done(struct netlink_callback *cb) -{ - fib6_dump_end(cb); - return cb->done(cb); -} + if (tb[RTA_IIF]) + iif = nla_get_u32(tb[RTA_IIF]); -int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct rt6_rtnl_dump_arg arg; - struct fib6_walker_t *w; - int res; + if (tb[RTA_OIF]) + oif = nla_get_u32(tb[RTA_OIF]); - arg.skb = skb; - arg.cb = cb; + if (tb[RTA_MARK]) + fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); - w = (void*)cb->args[0]; - if (w == NULL) { - /* New dump: - * - * 1. hook callback destructor. - */ - cb->args[1] = (long)cb->done; - cb->done = fib6_dump_done; + if (iif) { + struct net_device *dev; + int flags = 0; - /* - * 2. allocate and initialize walker. - */ - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w == NULL) - return -ENOMEM; - RT6_TRACE("dump<%p", w); - memset(w, 0, sizeof(*w)); - w->root = &ip6_routing_table; - w->func = fib6_dump_node; - w->args = &arg; - cb->args[0] = (long)w; - read_lock_bh(&rt6_lock); - res = fib6_walk(w); - read_unlock_bh(&rt6_lock); + dev = __dev_get_by_index(net, iif); + if (!dev) { + err = -ENODEV; + goto errout; + } + + fl6.flowi6_iif = iif; + + if (!ipv6_addr_any(&fl6.saddr)) + flags |= RT6_LOOKUP_F_HAS_SADDR; + + rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6, + flags); } else { - w->args = &arg; - read_lock_bh(&rt6_lock); - res = fib6_walk_continue(w); - read_unlock_bh(&rt6_lock); - } -#if RT6_DEBUG >= 3 - if (res <= 0 && skb->len == 0) - RT6_TRACE("%p>dump end\n", w); -#endif - res = res < 0 ? res : skb->len; - /* res < 0 is an error. (really, impossible) - res == 0 means that dump is complete, but skb still can contain data. - res > 0 dump is not complete, but frame is full. - */ - /* Destroy walker, if dump of this table is complete. */ - if (res <= 0) - fib6_dump_end(cb); - return res; -} + fl6.flowi6_oif = oif; -int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) -{ - struct rtattr **rta = arg; - int iif = 0; - int err = -ENOBUFS; - struct sk_buff *skb; - struct flowi fl; - struct rt6_info *rt; + rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); + } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (skb == NULL) - goto out; + if (!skb) { + ip6_rt_put(rt); + err = -ENOBUFS; + goto errout; + } /* Reserve room for dummy headers, this skb can pass through good chunk of routing engine. */ - skb->mac.raw = skb->data; + skb_reset_mac_header(skb); skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); - memset(&fl, 0, sizeof(fl)); - if (rta[RTA_SRC-1]) - ipv6_addr_copy(&fl.fl6_src, - (struct in6_addr*)RTA_DATA(rta[RTA_SRC-1])); - if (rta[RTA_DST-1]) - ipv6_addr_copy(&fl.fl6_dst, - (struct in6_addr*)RTA_DATA(rta[RTA_DST-1])); - - if (rta[RTA_IIF-1]) - memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int)); + skb_dst_set(skb, &rt->dst); - if (iif) { - struct net_device *dev; - dev = __dev_get_by_index(iif); - if (!dev) { - err = -ENODEV; - goto out_free; - } + err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0, 0, 0); + if (err < 0) { + kfree_skb(skb); + goto errout; } - fl.oif = 0; - if (rta[RTA_OIF-1]) - memcpy(&fl.oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) +{ + struct sk_buff *skb; + struct net *net = info->nl_net; + u32 seq; + int err; - rt = (struct rt6_info*)ip6_route_output(NULL, &fl); + err = -ENOBUFS; + seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb->dst = &rt->u.dst; + skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); + if (!skb) + goto errout; - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - err = rt6_fill_node(skb, rt, - &fl.fl6_dst, &fl.fl6_src, - iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).pid, - nlh->nlmsg_seq, 0, 0); + err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, + event, info->portid, seq, 0, 0, 0); if (err < 0) { - err = -EMSGSIZE; - goto out_free; + /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; } - - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: - return err; -out_free: - kfree_skb(skb); - goto out; + rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, + info->nlh, gfp_any()); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh, - struct netlink_skb_parms *req) +static int ip6_route_dev_notify(struct notifier_block *this, + unsigned long event, void *ptr) { - struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct rtmsg)+256); - u32 pid = current->pid; - u32 seq = 0; - - if (req) - pid = req->pid; - if (nlh) - seq = nlh->nlmsg_seq; - - skb = alloc_skb(size, gfp_any()); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, ENOBUFS); - return; - } - if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0) < 0) { - kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, EINVAL); - return; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + + if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { + net->ipv6.ip6_null_entry->dst.dev = dev; + net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + net->ipv6.ip6_prohibit_entry->dst.dev = dev; + net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); + net->ipv6.ip6_blk_hole_entry->dst.dev = dev; + net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); +#endif } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_ROUTE; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_ROUTE, gfp_any()); + + return NOTIFY_OK; } /* @@ -1868,267 +2840,397 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh, #ifdef CONFIG_PROC_FS -#define RT6_INFO_LEN (32 + 4 + 32 + 4 + 32 + 40 + 5 + 1) - -struct rt6_proc_arg -{ - char *buffer; - int offset; - int length; - int skip; - int len; +static const struct file_operations ipv6_route_proc_fops = { + .owner = THIS_MODULE, + .open = ipv6_route_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, }; -static int rt6_info_route(struct rt6_info *rt, void *p_arg) -{ - struct rt6_proc_arg *arg = (struct rt6_proc_arg *) p_arg; - int i; - - if (arg->skip < arg->offset / RT6_INFO_LEN) { - arg->skip++; - return 0; - } - - if (arg->len >= arg->length) - return 0; - - for (i=0; i<16; i++) { - sprintf(arg->buffer + arg->len, "%02x", - rt->rt6i_dst.addr.s6_addr[i]); - arg->len += 2; - } - arg->len += sprintf(arg->buffer + arg->len, " %02x ", - rt->rt6i_dst.plen); - -#ifdef CONFIG_IPV6_SUBTREES - for (i=0; i<16; i++) { - sprintf(arg->buffer + arg->len, "%02x", - rt->rt6i_src.addr.s6_addr[i]); - arg->len += 2; - } - arg->len += sprintf(arg->buffer + arg->len, " %02x ", - rt->rt6i_src.plen); -#else - sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000 00 "); - arg->len += 36; -#endif - - if (rt->rt6i_nexthop) { - for (i=0; i<16; i++) { - sprintf(arg->buffer + arg->len, "%02x", - rt->rt6i_nexthop->primary_key[i]); - arg->len += 2; - } - } else { - sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000"); - arg->len += 32; - } - arg->len += sprintf(arg->buffer + arg->len, - " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt), - rt->u.dst.__use, rt->rt6i_flags, - rt->rt6i_dev ? rt->rt6i_dev->name : ""); - return 0; -} - -static int rt6_proc_info(char *buffer, char **start, off_t offset, int length) -{ - struct rt6_proc_arg arg; - arg.buffer = buffer; - arg.offset = offset; - arg.length = length; - arg.skip = 0; - arg.len = 0; - - read_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, rt6_info_route, 0, &arg); - read_unlock_bh(&rt6_lock); - - *start = buffer; - if (offset) - *start += offset % RT6_INFO_LEN; - - arg.len -= offset % RT6_INFO_LEN; - - if (arg.len > length) - arg.len = length; - if (arg.len < 0) - arg.len = 0; - - return arg.len; -} - static int rt6_stats_seq_show(struct seq_file *seq, void *v) { + struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", - rt6_stats.fib_nodes, rt6_stats.fib_route_nodes, - rt6_stats.fib_rt_alloc, rt6_stats.fib_rt_entries, - rt6_stats.fib_rt_cache, - atomic_read(&ip6_dst_ops.entries), - rt6_stats.fib_discarded_routes); + net->ipv6.rt6_stats->fib_nodes, + net->ipv6.rt6_stats->fib_route_nodes, + net->ipv6.rt6_stats->fib_rt_alloc, + net->ipv6.rt6_stats->fib_rt_entries, + net->ipv6.rt6_stats->fib_rt_cache, + dst_entries_get_slow(&net->ipv6.ip6_dst_ops), + net->ipv6.rt6_stats->fib_discarded_routes); return 0; } static int rt6_stats_seq_open(struct inode *inode, struct file *file) { - return single_open(file, rt6_stats_seq_show, NULL); + return single_open_net(inode, file, rt6_stats_seq_show); } -static struct file_operations rt6_stats_seq_fops = { +static const struct file_operations rt6_stats_seq_fops = { .owner = THIS_MODULE, .open = rt6_stats_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL -static int flush_delay; - static -int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp, +int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - if (write) { - proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - fib6_run_gc(flush_delay <= 0 ? ~0UL : (unsigned long)flush_delay); - return 0; - } else + struct net *net; + int delay; + if (!write) return -EINVAL; + + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; + proc_dointvec(ctl, write, buffer, lenp, ppos); + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); + return 0; } -ctl_table ipv6_route_table[] = { - { - .ctl_name = NET_IPV6_ROUTE_FLUSH, +struct ctl_table ipv6_route_table_template[] = { + { .procname = "flush", - .data = &flush_delay, + .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, - .proc_handler = &ipv6_sysctl_rtcache_flush + .proc_handler = ipv6_sysctl_rtcache_flush }, { - .ctl_name = NET_IPV6_ROUTE_GC_THRESH, .procname = "gc_thresh", - .data = &ip6_dst_ops.gc_thresh, + .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_MAX_SIZE, .procname = "max_size", - .data = &ip6_rt_max_size, + .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL, .procname = "gc_min_interval", - .data = &ip6_rt_gc_min_interval, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT, .procname = "gc_timeout", - .data = &ip6_rt_gc_timeout, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_INTERVAL, .procname = "gc_interval", - .data = &ip6_rt_gc_interval, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY, .procname = "gc_elasticity", - .data = &ip6_rt_gc_elasticity, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES, .procname = "mtu_expires", - .data = &ip6_rt_mtu_expires, + .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS, .procname = "min_adv_mss", - .data = &ip6_rt_min_advmss, + .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, .procname = "gc_min_interval_ms", - .data = &ip6_rt_gc_min_interval, + .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, + .proc_handler = proc_dointvec_ms_jiffies, }, - { .ctl_name = 0 } + { } }; +struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) +{ + struct ctl_table *table; + + table = kmemdup(ipv6_route_table_template, + sizeof(ipv6_route_table_template), + GFP_KERNEL); + + if (table) { + table[0].data = &net->ipv6.sysctl.flush_delay; + table[0].extra1 = net; + table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; + table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; + table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; + table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; + table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; + table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; + table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; + table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + } + + return table; +} #endif -void __init ip6_route_init(void) +static int __net_init ip6_route_net_init(struct net *net) { - struct proc_dir_entry *p; + int ret = -ENOMEM; + + memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, + sizeof(net->ipv6.ip6_dst_ops)); + + if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) + goto out_ip6_dst_ops; + + net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, + sizeof(*net->ipv6.ip6_null_entry), + GFP_KERNEL); + if (!net->ipv6.ip6_null_entry) + goto out_ip6_dst_entries; + net->ipv6.ip6_null_entry->dst.path = + (struct dst_entry *)net->ipv6.ip6_null_entry; + net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_init_metrics(&net->ipv6.ip6_null_entry->dst, + ip6_template_metrics, true); + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, + sizeof(*net->ipv6.ip6_prohibit_entry), + GFP_KERNEL); + if (!net->ipv6.ip6_prohibit_entry) + goto out_ip6_null_entry; + net->ipv6.ip6_prohibit_entry->dst.path = + (struct dst_entry *)net->ipv6.ip6_prohibit_entry; + net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, + ip6_template_metrics, true); + + net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, + sizeof(*net->ipv6.ip6_blk_hole_entry), + GFP_KERNEL); + if (!net->ipv6.ip6_blk_hole_entry) + goto out_ip6_prohibit_entry; + net->ipv6.ip6_blk_hole_entry->dst.path = + (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; + net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; + dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, + ip6_template_metrics, true); +#endif - ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache", - sizeof(struct rt6_info), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!ip6_dst_ops.kmem_cachep) - panic("cannot create ip6_dst_cache"); + net->ipv6.sysctl.flush_delay = 0; + net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; + net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; + net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; + net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; + net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; + net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; - fib6_init(); -#ifdef CONFIG_PROC_FS - p = proc_net_create("ipv6_route", 0, rt6_proc_info); - if (p) - p->owner = THIS_MODULE; + net->ipv6.ip6_rt_gc_expire = 30*HZ; + + ret = 0; +out: + return ret; - proc_net_fops_create("rt6_stats", S_IRUGO, &rt6_stats_seq_fops); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +out_ip6_prohibit_entry: + kfree(net->ipv6.ip6_prohibit_entry); +out_ip6_null_entry: + kfree(net->ipv6.ip6_null_entry); #endif -#ifdef CONFIG_XFRM - xfrm6_init(); +out_ip6_dst_entries: + dst_entries_destroy(&net->ipv6.ip6_dst_ops); +out_ip6_dst_ops: + goto out; +} + +static void __net_exit ip6_route_net_exit(struct net *net) +{ + kfree(net->ipv6.ip6_null_entry); +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + kfree(net->ipv6.ip6_prohibit_entry); + kfree(net->ipv6.ip6_blk_hole_entry); #endif + dst_entries_destroy(&net->ipv6.ip6_dst_ops); } -void ip6_route_cleanup(void) +static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_net_remove("ipv6_route"); - proc_net_remove("rt6_stats"); + proc_create("ipv6_route", 0, net->proc_net, &ipv6_route_proc_fops); + proc_create("rt6_stats", S_IRUGO, net->proc_net, &rt6_stats_seq_fops); #endif -#ifdef CONFIG_XFRM - xfrm6_fini(); + return 0; +} + +static void __net_exit ip6_route_net_exit_late(struct net *net) +{ +#ifdef CONFIG_PROC_FS + remove_proc_entry("ipv6_route", net->proc_net); + remove_proc_entry("rt6_stats", net->proc_net); #endif - rt6_ifdown(NULL); +} + +static struct pernet_operations ip6_route_net_ops = { + .init = ip6_route_net_init, + .exit = ip6_route_net_exit, +}; + +static int __net_init ipv6_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); + + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv6.peers = bp; + return 0; +} + +static void __net_exit ipv6_inetpeer_exit(struct net *net) +{ + struct inet_peer_base *bp = net->ipv6.peers; + + net->ipv6.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} + +static struct pernet_operations ipv6_inetpeer_ops = { + .init = ipv6_inetpeer_init, + .exit = ipv6_inetpeer_exit, +}; + +static struct pernet_operations ip6_route_net_late_ops = { + .init = ip6_route_net_init_late, + .exit = ip6_route_net_exit_late, +}; + +static struct notifier_block ip6_route_dev_notifier = { + .notifier_call = ip6_route_dev_notify, + .priority = 0, +}; + +int __init ip6_route_init(void) +{ + int ret; + + ret = -ENOMEM; + ip6_dst_ops_template.kmem_cachep = + kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!ip6_dst_ops_template.kmem_cachep) + goto out; + + ret = dst_entries_init(&ip6_dst_blackhole_ops); + if (ret) + goto out_kmem_cache; + + ret = register_pernet_subsys(&ipv6_inetpeer_ops); + if (ret) + goto out_dst_entries; + + ret = register_pernet_subsys(&ip6_route_net_ops); + if (ret) + goto out_register_inetpeer; + + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; + + /* Registering of the loopback is done before this portion of code, + * the loopback reference in rt6_info will not be taken, do it + * manually for init_net */ + init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES + init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); + #endif + ret = fib6_init(); + if (ret) + goto out_register_subsys; + + ret = xfrm6_init(); + if (ret) + goto out_fib6_init; + + ret = fib6_rules_init(); + if (ret) + goto xfrm6_init; + + ret = register_pernet_subsys(&ip6_route_net_late_ops); + if (ret) + goto fib6_rules_init; + + ret = -ENOBUFS; + if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) || + __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) || + __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL)) + goto out_register_late_subsys; + + ret = register_netdevice_notifier(&ip6_route_dev_notifier); + if (ret) + goto out_register_late_subsys; + +out: + return ret; + +out_register_late_subsys: + unregister_pernet_subsys(&ip6_route_net_late_ops); +fib6_rules_init: + fib6_rules_cleanup(); +xfrm6_init: + xfrm6_fini(); +out_fib6_init: + fib6_gc_cleanup(); +out_register_subsys: + unregister_pernet_subsys(&ip6_route_net_ops); +out_register_inetpeer: + unregister_pernet_subsys(&ipv6_inetpeer_ops); +out_dst_entries: + dst_entries_destroy(&ip6_dst_blackhole_ops); +out_kmem_cache: + kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); + goto out; +} + +void ip6_route_cleanup(void) +{ + unregister_netdevice_notifier(&ip6_route_dev_notifier); + unregister_pernet_subsys(&ip6_route_net_late_ops); + fib6_rules_cleanup(); + xfrm6_fini(); fib6_gc_cleanup(); - kmem_cache_destroy(ip6_dst_ops.kmem_cachep); + unregister_pernet_subsys(&ipv6_inetpeer_ops); + unregister_pernet_subsys(&ip6_route_net_ops); + dst_entries_destroy(&ip6_dst_blackhole_ops); + kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c3123c9e1a8..4f408176dc6 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -3,11 +3,9 @@ * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * - * $Id: sit.c,v 1.53 2001/09/25 05:09:53 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 @@ -16,23 +14,27 @@ * Changes: * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support + * Fred Templin <fred.l.templin@boeing.com>: isatap support */ -#include <linux/config.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> +#include <linux/capability.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/icmp.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> +#include <linux/if_ether.h> #include <net/sock.h> #include <net/snmp.h> @@ -47,10 +49,12 @@ #include <net/ip.h> #include <net/udp.h> #include <net/icmp.h> -#include <net/ipip.h> +#include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/dsfield.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c @@ -59,51 +63,72 @@ */ #define HASH_SIZE 16 -#define HASH(addr) ((addr^(addr>>4))&0xF) +#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) + +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); -static int ipip6_fb_tunnel_init(struct net_device *dev); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); +static void ipip6_dev_free(struct net_device *dev); +static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, + __be32 *v4dst); +static struct rtnl_link_ops sit_link_ops __read_mostly; + +static int sit_net_id __read_mostly; +struct sit_net { + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel __rcu **tunnels[4]; + + struct net_device *fb_tunnel_dev; +}; -static struct net_device *ipip6_fb_tunnel_dev; - -static struct ip_tunnel *tunnels_r_l[HASH_SIZE]; -static struct ip_tunnel *tunnels_r[HASH_SIZE]; -static struct ip_tunnel *tunnels_l[HASH_SIZE]; -static struct ip_tunnel *tunnels_wc[1]; -static struct ip_tunnel **tunnels[4] = { tunnels_wc, tunnels_l, tunnels_r, tunnels_r_l }; - -static DEFINE_RWLOCK(ipip6_lock); - -static struct ip_tunnel * ipip6_tunnel_lookup(u32 remote, u32 local) +/* + * Must be invoked with rcu_read_lock + */ +static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, + struct net_device *dev, __be32 remote, __be32 local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip_tunnel *t; + struct sit_net *sitn = net_generic(net, sit_net_id); - for (t = tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && - remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + remote == t->parms.iph.daddr && + (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (t->dev->flags & IFF_UP)) return t; } - for (t = tunnels_r[h0]; t; t = t->next) { - if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) + for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { + if (remote == t->parms.iph.daddr && + (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (t->dev->flags & IFF_UP)) return t; } - for (t = tunnels_l[h1]; t; t = t->next) { - if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) + for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { + if (local == t->parms.iph.saddr && + (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (t->dev->flags & IFF_UP)) return t; } - if ((t = tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP)) + t = rcu_dereference(sitn->tunnels_wc[0]); + if ((t != NULL) && (t->dev->flags & IFF_UP)) return t; return NULL; } -static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t) +static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, + struct ip_tunnel_parm *parms) { - u32 remote = t->parms.iph.daddr; - u32 local = t->parms.iph.saddr; - unsigned h = 0; + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; + unsigned int h = 0; int prio = 0; if (remote) { @@ -114,134 +139,400 @@ static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t) prio |= 1; h ^= HASH(local); } - return &tunnels[prio][h]; + return &sitn->tunnels[prio][h]; } -static void ipip6_tunnel_unlink(struct ip_tunnel *t) +static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, + struct ip_tunnel *t) { - struct ip_tunnel **tp; + return __ipip6_bucket(sitn, &t->parms); +} - for (tp = ipip6_bucket(t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - write_lock_bh(&ipip6_lock); - *tp = t->next; - write_unlock_bh(&ipip6_lock); +static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) +{ + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipip6_bucket(sitn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } } -static void ipip6_tunnel_link(struct ip_tunnel *t) +static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) +{ + struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); + + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); + rcu_assign_pointer(*tp, t); +} + +static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) +{ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel *t = netdev_priv(dev); + + if (t->dev == sitn->fb_tunnel_dev) { + ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); + t->ip6rd.relay_prefix = 0; + t->ip6rd.prefixlen = 16; + t->ip6rd.relay_prefixlen = 0; + } else { + struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); + memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); + } +#endif +} + +static int ipip6_tunnel_create(struct net_device *dev) { - struct ip_tunnel **tp = ipip6_bucket(t); + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + int err; + + err = ipip6_tunnel_init(dev); + if (err < 0) + goto out; + ipip6_tunnel_clone_6rd(dev, sitn); + + if ((__force u16)t->parms.i_flags & SIT_ISATAP) + dev->priv_flags |= IFF_ISATAP; - t->next = *tp; - write_lock_bh(&ipip6_lock); - *tp = t; - write_unlock_bh(&ipip6_lock); + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &sit_link_ops; + + dev_hold(dev); + + ipip6_tunnel_link(sitn, t); + return 0; + +out: + return err; } -static struct ip_tunnel * ipip6_tunnel_locate(struct ip_tunnel_parm *parms, int create) +static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, + struct ip_tunnel_parm *parms, int create) { - u32 remote = parms->iph.daddr; - u32 local = parms->iph.saddr; - struct ip_tunnel *t, **tp, *nt; + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; struct net_device *dev; - unsigned h = 0; - int prio = 0; char name[IFNAMSIZ]; + struct sit_net *sitn = net_generic(net, sit_net_id); - if (remote) { - prio |= 2; - h ^= HASH(remote); - } - if (local) { - prio |= 1; - h ^= HASH(local); - } - for (tp = &tunnels[prio][h]; (t = *tp) != NULL; tp = &t->next) { - if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) - return t; + for (tp = __ipip6_bucket(sitn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { + if (local == t->parms.iph.saddr && + remote == t->parms.iph.daddr && + parms->link == t->parms.link) { + if (create) + return NULL; + else + return t; + } } if (!create) goto failed; if (parms->name[0]) strlcpy(name, parms->name, IFNAMSIZ); - else { - int i; - for (i=1; i<100; i++) { - sprintf(name, "sit%d", i); - if (__dev_get_by_name(name) == NULL) - break; - } - if (i==100) - goto failed; - } + else + strcpy(name, "sit%d"); dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup); if (dev == NULL) return NULL; - nt = dev->priv; - dev->init = ipip6_tunnel_init; - nt->parms = *parms; + dev_net_set(dev, net); - if (register_netdevice(dev) < 0) { - free_netdev(dev); - goto failed; - } + nt = netdev_priv(dev); - dev_hold(dev); + nt->parms = *parms; + if (ipip6_tunnel_create(dev) < 0) + goto failed_free; - ipip6_tunnel_link(nt); return nt; +failed_free: + ipip6_dev_free(dev); failed: return NULL; } -static void ipip6_tunnel_uninit(struct net_device *dev) +#define for_each_prl_rcu(start) \ + for (prl = rcu_dereference(start); \ + prl; \ + prl = rcu_dereference(prl->next)) + +static struct ip_tunnel_prl_entry * +__ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { - if (dev == ipip6_fb_tunnel_dev) { - write_lock_bh(&ipip6_lock); - tunnels_wc[0] = NULL; - write_unlock_bh(&ipip6_lock); - dev_put(dev); + struct ip_tunnel_prl_entry *prl; + + for_each_prl_rcu(t->prl) + if (prl->addr == addr) + break; + return prl; + +} + +static int ipip6_tunnel_get_prl(struct ip_tunnel *t, + struct ip_tunnel_prl __user *a) +{ + struct ip_tunnel_prl kprl, *kp; + struct ip_tunnel_prl_entry *prl; + unsigned int cmax, c = 0, ca, len; + int ret = 0; + + if (copy_from_user(&kprl, a, sizeof(kprl))) + return -EFAULT; + cmax = kprl.datalen / sizeof(kprl); + if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) + cmax = 1; + + /* For simple GET or for root users, + * we try harder to allocate. + */ + kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? + kcalloc(cmax, sizeof(*kp), GFP_KERNEL) : + NULL; + + rcu_read_lock(); + + ca = t->prl_count < cmax ? t->prl_count : cmax; + + if (!kp) { + /* We don't try hard to allocate much memory for + * non-root users. + * For root users, retry allocating enough memory for + * the answer. + */ + kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC); + if (!kp) { + ret = -ENOMEM; + goto out; + } + } + + c = 0; + for_each_prl_rcu(t->prl) { + if (c >= cmax) + break; + if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) + continue; + kp[c].addr = prl->addr; + kp[c].flags = prl->flags; + c++; + if (kprl.addr != htonl(INADDR_ANY)) + break; + } +out: + rcu_read_unlock(); + + len = sizeof(*kp) * c; + ret = 0; + if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) + ret = -EFAULT; + + kfree(kp); + + return ret; +} + +static int +ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) +{ + struct ip_tunnel_prl_entry *p; + int err = 0; + + if (a->addr == htonl(INADDR_ANY)) + return -EINVAL; + + ASSERT_RTNL(); + + for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { + if (p->addr == a->addr) { + if (chg) { + p->flags = a->flags; + goto out; + } + err = -EEXIST; + goto out; + } + } + + if (chg) { + err = -ENXIO; + goto out; + } + + p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL); + if (!p) { + err = -ENOBUFS; + goto out; + } + + p->next = t->prl; + p->addr = a->addr; + p->flags = a->flags; + t->prl_count++; + rcu_assign_pointer(t->prl, p); +out: + return err; +} + +static void prl_list_destroy_rcu(struct rcu_head *head) +{ + struct ip_tunnel_prl_entry *p, *n; + + p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); + do { + n = rcu_dereference_protected(p->next, 1); + kfree(p); + p = n; + } while (p); +} + +static int +ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) +{ + struct ip_tunnel_prl_entry *x; + struct ip_tunnel_prl_entry __rcu **p; + int err = 0; + + ASSERT_RTNL(); + + if (a && a->addr != htonl(INADDR_ANY)) { + for (p = &t->prl; + (x = rtnl_dereference(*p)) != NULL; + p = &x->next) { + if (x->addr == a->addr) { + *p = x->next; + kfree_rcu(x, rcu_head); + t->prl_count--; + goto out; + } + } + err = -ENXIO; } else { - ipip6_tunnel_unlink((struct ip_tunnel*)dev->priv); - dev_put(dev); + x = rtnl_dereference(t->prl); + if (x) { + t->prl_count = 0; + call_rcu(&x->rcu_head, prl_list_destroy_rcu); + t->prl = NULL; + } } +out: + return err; } +static int +isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) +{ + struct ip_tunnel_prl_entry *p; + int ok = 1; + + rcu_read_lock(); + p = __ipip6_tunnel_locate_prl(t, iph->saddr); + if (p) { + if (p->flags & PRL_DEFAULT) + skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT; + else + skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT; + } else { + const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; + + if (ipv6_addr_is_isatap(addr6) && + (addr6->s6_addr32[3] == iph->saddr) && + ipv6_chk_prefix(addr6, t->dev)) + skb->ndisc_nodetype = NDISC_NODETYPE_HOST; + else + ok = 0; + } + rcu_read_unlock(); + return ok; +} -static void ipip6_err(struct sk_buff *skb, u32 info) +static void ipip6_tunnel_uninit(struct net_device *dev) { -#ifndef I_WISH_WORLD_WERE_PERFECT + struct ip_tunnel *tunnel = netdev_priv(dev); + struct sit_net *sitn = net_generic(tunnel->net, sit_net_id); + + if (dev == sitn->fb_tunnel_dev) { + RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); + } else { + ipip6_tunnel_unlink(sitn, tunnel); + ipip6_tunnel_del_prl(tunnel, NULL); + } + ip_tunnel_dst_reset_all(tunnel); + dev_put(dev); +} -/* It is not :-( All the routers (except for Linux) return only - 8 bytes of packet payload. It means, that precise relaying of - ICMP in the real Internet is absolutely infeasible. +/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH + * if sufficient data bytes are available */ - struct iphdr *iph = (struct iphdr*)skb->data; - int type = skb->h.icmph->type; - int code = skb->h.icmph->code; +static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct rt6_info *rt; + struct sk_buff *skb2; + + if (!pskb_may_pull(skb, iph->ihl * 4 + sizeof(struct ipv6hdr) + 8)) + return 1; + + skb2 = skb_clone(skb, GFP_ATOMIC); + + if (!skb2) + return 1; + + skb_dst_drop(skb2); + skb_pull(skb2, iph->ihl * 4); + skb_reset_network_header(skb2); + + rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); + + if (rt && rt->dst.dev) + skb2->dev = rt->dst.dev; + + icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); + + if (rt) + ip6_rt_put(rt); + + kfree_skb(skb2); + + return 0; +} + +static int ipip6_err(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *)skb->data; + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; + int err; switch (type) { default: case ICMP_PARAMETERPROB: - return; + return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: /* Impossible event. */ - return; - case ICMP_FRAG_NEEDED: - /* Soft state for pmtu is maintained by IP core. */ - return; + return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -252,166 +543,258 @@ static void ipip6_err(struct sk_buff *skb, u32 info) break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) - return; + return 0; + break; + case ICMP_REDIRECT: break; } - read_lock(&ipip6_lock); - t = ipip6_tunnel_lookup(iph->daddr, iph->saddr); - if (t == NULL || t->parms.iph.daddr == 0) + err = -ENOENT; + + t = ipip6_tunnel_lookup(dev_net(skb->dev), + skb->dev, + iph->daddr, + iph->saddr); + if (t == NULL) + goto out; + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + t->parms.link, 0, IPPROTO_IPV6, 0); + err = 0; + goto out; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, + IPPROTO_IPV6, 0); + err = 0; + goto out; + } + + if (t->parms.iph.daddr == 0) goto out; + + err = 0; + if (!ipip6_err_gen_icmpv6_unreach(skb)) + goto out; + if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; - if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO) + if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipip6_lock); - return; -#else - struct iphdr *iph = (struct iphdr*)dp; - int hlen = iph->ihl<<2; - struct ipv6hdr *iph6; - int type = skb->h.icmph->type; - int code = skb->h.icmph->code; - int rel_type = 0; - int rel_code = 0; - int rel_info = 0; - struct sk_buff *skb2; - struct rt6_info *rt6i; + return err; +} - if (len < hlen + sizeof(struct ipv6hdr)) - return; - iph6 = (struct ipv6hdr*)(dp + hlen); +static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, + const struct in6_addr *v6addr) +{ + __be32 v4embed = 0; + if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) + return true; + return false; +} - switch (type) { - default: - return; - case ICMP_PARAMETERPROB: - if (skb->h.icmph->un.gateway < hlen) - return; +/* Checks if an address matches an address on the tunnel interface. + * Used to detect the NAT of proto 41 packets and let them pass spoofing test. + * Long story: + * This function is called after we considered the packet as spoofed + * in is_spoofed_6rd. + * We may have a router that is doing NAT for proto 41 packets + * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb + * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd + * function will return true, dropping the packet. + * But, we can still check if is spoofed against the IP + * addresses associated with the interface. + */ +static bool only_dnatted(const struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + int prefix_len; - /* So... This guy found something strange INSIDE encapsulated - packet. Well, he is fool, but what can we do ? - */ - rel_type = ICMPV6_PARAMPROB; - rel_info = skb->h.icmph->un.gateway - hlen; - break; +#ifdef CONFIG_IPV6_SIT_6RD + prefix_len = tunnel->ip6rd.prefixlen + 32 + - tunnel->ip6rd.relay_prefixlen; +#else + prefix_len = 48; +#endif + return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); +} - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_SR_FAILED: - case ICMP_PORT_UNREACH: - /* Impossible event. */ - return; - case ICMP_FRAG_NEEDED: - /* Too complicated case ... */ - return; - default: - /* All others are translated to HOST_UNREACH. - rfc2003 contains "deep thoughts" about NET_UNREACH, - I believe, it is just ether pollution. --ANK - */ - rel_type = ICMPV6_DEST_UNREACH; - rel_code = ICMPV6_ADDR_UNREACH; - break; - } - break; - case ICMP_TIME_EXCEEDED: - if (code != ICMP_EXC_TTL) - return; - rel_type = ICMPV6_TIME_EXCEED; - rel_code = ICMPV6_EXC_HOPLIMIT; - break; +/* Returns true if a packet is spoofed */ +static bool packet_is_spoofed(struct sk_buff *skb, + const struct iphdr *iph, + struct ip_tunnel *tunnel) +{ + const struct ipv6hdr *ipv6h; + + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) + return true; + + return false; } - /* Prepare fake skb to feed it to icmpv6_send */ - skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) - return; - dst_release(skb2->dst); - skb2->dst = NULL; - skb_pull(skb2, skb->data - (u8*)iph6); - skb2->nh.raw = skb2->data; - - /* Try to guess incoming interface */ - rt6i = rt6_lookup(&iph6->saddr, NULL, NULL, 0); - if (rt6i && rt6i->rt6i_dev) { - skb2->dev = rt6i->rt6i_dev; - - rt6i = rt6_lookup(&iph6->daddr, &iph6->saddr, NULL, 0); - - if (rt6i && rt6i->rt6i_dev && rt6i->rt6i_dev->type == ARPHRD_SIT) { - struct ip_tunnel * t = (struct ip_tunnel*)rt6i->rt6i_dev->priv; - if (rel_type == ICMPV6_TIME_EXCEED && t->parms.iph.ttl) { - rel_type = ICMPV6_DEST_UNREACH; - rel_code = ICMPV6_ADDR_UNREACH; - } - icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev); - } + if (tunnel->dev->flags & IFF_POINTOPOINT) + return false; + + ipv6h = ipv6_hdr(skb); + + if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { + net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; } - kfree_skb(skb2); - return; -#endif -} -static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) -{ - if (INET_ECN_is_ce(iph->tos)) - IP6_ECN_set_ce(skb->nh.ipv6h); + if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) + return false; + + if (only_dnatted(tunnel, &ipv6h->daddr)) + return false; + + net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; } static int ipip6_rcv(struct sk_buff *skb) { - struct iphdr *iph; + const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; + int err; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto out; + tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->saddr, iph->daddr); + if (tunnel != NULL) { + struct pcpu_sw_netstats *tstats; - iph = skb->nh.iph; + if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && + tunnel->parms.iph.protocol != 0) + goto out; - read_lock(&ipip6_lock); - if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) { - secpath_reset(skb); - skb->mac.raw = skb->nh.raw; - skb->nh.raw = skb->data; - memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options)); + skb->mac_header = skb->network_header; + skb_reset_network_header(skb); + IPCB(skb)->flags = 0; skb->protocol = htons(ETH_P_IPV6); - skb->pkt_type = PACKET_HOST; - tunnel->stat.rx_packets++; - tunnel->stat.rx_bytes += skb->len; - skb->dev = tunnel->dev; - dst_release(skb->dst); - skb->dst = NULL; - nf_reset(skb); - ipip6_ecn_decapsulate(iph, skb); + + if (packet_is_spoofed(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; + } + + __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); + + err = IP_ECN_decapsulate(iph, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &iph->saddr, iph->tos); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto out; + } + } + + tstats = this_cpu_ptr(tunnel->dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + netif_rx(skb); - read_unlock(&ipip6_lock); + return 0; } - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); - kfree_skb(skb); - read_unlock(&ipip6_lock); + /* no tunnel matched, let upstream know, ipsec may handle it */ + return 1; out: + kfree_skb(skb); return 0; } -/* Returns the embedded IPv4 address if the IPv6 address - comes from 6to4 (RFC 3056) addr space */ +static const struct tnl_ptk_info tpi = { + /* no tunnel info required for ipip. */ + .proto = htons(ETH_P_IP), +}; -static inline u32 try_6to4(struct in6_addr *v6dst) +static int ipip_rcv(struct sk_buff *skb) { - u32 dst = 0; + const struct iphdr *iph; + struct ip_tunnel *tunnel; + + iph = ip_hdr(skb); + tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->saddr, iph->daddr); + if (tunnel != NULL) { + if (tunnel->parms.iph.protocol != IPPROTO_IPIP && + tunnel->parms.iph.protocol != 0) + goto drop; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto)) + goto drop; + return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + } + return 1; + +drop: + kfree_skb(skb); + return 0; +} + +/* + * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function + * stores the embedded IPv4 address in v4dst and returns true. + */ +static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, + __be32 *v4dst) +{ +#ifdef CONFIG_IPV6_SIT_6RD + if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, + tunnel->ip6rd.prefixlen)) { + unsigned int pbw0, pbi0; + int pbi1; + u32 d; + + pbw0 = tunnel->ip6rd.prefixlen >> 5; + pbi0 = tunnel->ip6rd.prefixlen & 0x1f; + + d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen; + + pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; + if (pbi1 > 0) + d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> + (32 - pbi1); + + *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); + return true; + } +#else if (v6dst->s6_addr16[0] == htons(0x2002)) { - /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ - memcpy(&dst, &v6dst->s6_addr16[1], 4); + /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ + memcpy(v4dst, &v6dst->s6_addr16[1], 4); + return true; } +#endif + return false; +} + +static inline __be32 try_6rd(struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + __be32 dst = 0; + check_6rd(tunnel, v6dst, &dst); return dst; } @@ -420,107 +803,140 @@ static inline u32 try_6to4(struct in6_addr *v6dst) * and that skb is filled properly by that function. */ -static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) { - struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv; - struct net_device_stats *stats = &tunnel->stat; - struct iphdr *tiph = &tunnel->parms.iph; - struct ipv6hdr *iph6 = skb->nh.ipv6h; + struct ip_tunnel *tunnel = netdev_priv(dev); + const struct iphdr *tiph = &tunnel->parms.iph; + const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; + __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ - struct iphdr *iph; /* Our new IP header */ - int max_headroom; /* The extra header space needed */ - u32 dst = tiph->daddr; + struct net_device *tdev; /* Device to other host */ + unsigned int max_headroom; /* The extra header space needed */ + __be32 dst = tiph->daddr; + struct flowi4 fl4; int mtu; - struct in6_addr *addr6; + const struct in6_addr *addr6; int addr_type; - - if (tunnel->recursion++) { - tunnel->stat.collisions++; - goto tx_error; - } + u8 ttl; + int err; if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; + if (tos == 1) + tos = ipv6_get_dsfield(iph6); + + /* ISATAP (RFC4214) - must come before 6to4 */ + if (dev->priv_flags & IFF_ISATAP) { + struct neighbour *neigh = NULL; + bool do_tx_error = false; + + if (skb_dst(skb)) + neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); + + if (neigh == NULL) { + net_dbg_ratelimited("nexthop == NULL\n"); + goto tx_error; + } + + addr6 = (const struct in6_addr *)&neigh->primary_key; + addr_type = ipv6_addr_type(addr6); + + if ((addr_type & IPV6_ADDR_UNICAST) && + ipv6_addr_is_isatap(addr6)) + dst = addr6->s6_addr32[3]; + else + do_tx_error = true; + + neigh_release(neigh); + if (do_tx_error) + goto tx_error; + } + if (!dst) - dst = try_6to4(&iph6->daddr); + dst = try_6rd(tunnel, &iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; + bool do_tx_error = false; - if (skb->dst) - neigh = skb->dst->neighbour; + if (skb_dst(skb)) + neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - if (net_ratelimit()) - printk(KERN_DEBUG "sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } - addr6 = (struct in6_addr*)&neigh->primary_key; + addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { - addr6 = &skb->nh.ipv6h->daddr; + addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } - if ((addr_type & IPV6_ADDR_COMPATv4) == 0) - goto tx_error_icmp; + if ((addr_type & IPV6_ADDR_COMPATv4) != 0) + dst = addr6->s6_addr32[3]; + else + do_tx_error = true; - dst = addr6->s6_addr32[3]; + neigh_release(neigh); + if (do_tx_error) + goto tx_error; } - { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) } }, - .oif = tunnel->parms.link, - .proto = IPPROTO_IPV6 }; - if (ip_route_output_key(&rt, &fl)) { - tunnel->stat.tx_carrier_errors++; - goto tx_error_icmp; - } + rt = ip_route_output_ports(tunnel->net, &fl4, NULL, + dst, tiph->saddr, + 0, 0, + IPPROTO_IPV6, RT_TOS(tos), + tunnel->parms.link); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); - tunnel->stat.tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); - tunnel->stat.collisions++; + dev->stats.collisions++; goto tx_error; } - if (tiph->frag_off) - mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); - else - mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu; + if (df) { + mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); - if (mtu < 68) { - tunnel->stat.collisions++; - ip_rt_put(rt); - goto tx_error; - } - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - if (tunnel->parms.iph.daddr && skb->dst) - skb->dst->ops->update_pmtu(skb->dst, mtu); + if (mtu < 68) { + dev->stats.collisions++; + ip_rt_put(rt); + goto tx_error; + } - if (skb->len > mtu) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); - ip_rt_put(rt); - goto tx_error; + if (mtu < IPV6_MIN_MTU) { + mtu = IPV6_MIN_MTU; + df = 0; + } + + if (tunnel->parms.iph.daddr && skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + + if (skb->len > mtu && !skb_is_gso(skb)) { + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + ip_rt_put(rt); + goto tx_error; + } } if (tunnel->err_count > 0) { - if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) { + if (time_before(jiffies, + tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else @@ -532,91 +948,231 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) */ max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr); - if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { + if (skb_headroom(skb) < max_headroom || skb_shared(skb) || + (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; - dev_kfree_skb(skb); - tunnel->recursion--; - return 0; + dev->stats.tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); dev_kfree_skb(skb); skb = new_skb; - iph6 = skb->nh.ipv6h; + iph6 = ipv6_hdr(skb); } + ttl = tiph->ttl; + if (ttl == 0) + ttl = iph6->hop_limit; + tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - skb->h.raw = skb->nh.raw; - skb->nh.raw = skb_push(skb, sizeof(struct iphdr)); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - dst_release(skb->dst); - skb->dst = &rt->u.dst; + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); + if (IS_ERR(skb)) { + ip_rt_put(rt); + goto out; + } - /* - * Push down and install the IPIP header. - */ + err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, + IPPROTO_IPV6, tos, ttl, df, + !net_eq(tunnel->net, dev_net(dev))); + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + return NETDEV_TX_OK; - iph = skb->nh.iph; - iph->version = 4; - iph->ihl = sizeof(struct iphdr)>>2; - if (mtu > IPV6_MIN_MTU) - iph->frag_off = htons(IP_DF); - else - iph->frag_off = 0; +tx_error_icmp: + dst_link_failure(skb); +tx_error: + kfree_skb(skb); +out: + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + const struct iphdr *tiph = &tunnel->parms.iph; - iph->protocol = IPPROTO_IPV6; - iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - iph->daddr = rt->rt_dst; - iph->saddr = rt->rt_src; + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + if (IS_ERR(skb)) + goto out; - if ((iph->ttl = tiph->ttl) == 0) - iph->ttl = iph6->hop_limit; + ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP); + return NETDEV_TX_OK; +out: + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} - nf_reset(skb); +static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + ipip_tunnel_xmit(skb, dev); + break; + case htons(ETH_P_IPV6): + ipip6_tunnel_xmit(skb, dev); + break; + default: + goto tx_err; + } - IPTUNNEL_XMIT(); - tunnel->recursion--; - return 0; + return NETDEV_TX_OK; -tx_error_icmp: - dst_link_failure(skb); -tx_error: - stats->tx_errors++; - dev_kfree_skb(skb); - tunnel->recursion--; +tx_err: + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; + +} + +static void ipip6_tunnel_bind_dev(struct net_device *dev) +{ + struct net_device *tdev = NULL; + struct ip_tunnel *tunnel; + const struct iphdr *iph; + struct flowi4 fl4; + + tunnel = netdev_priv(dev); + iph = &tunnel->parms.iph; + + if (iph->daddr) { + struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4, + NULL, + iph->daddr, iph->saddr, + 0, 0, + IPPROTO_IPV6, + RT_TOS(iph->tos), + tunnel->parms.link); + + if (!IS_ERR(rt)) { + tdev = rt->dst.dev; + ip_rt_put(rt); + } + dev->flags |= IFF_POINTOPOINT; + } + + if (!tdev && tunnel->parms.link) + tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); + + if (tdev) { + dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); + dev->mtu = tdev->mtu - sizeof(struct iphdr); + if (dev->mtu < IPV6_MIN_MTU) + dev->mtu = IPV6_MIN_MTU; + } + dev->iflink = tunnel->parms.link; +} + +static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) +{ + struct net *net = t->net; + struct sit_net *sitn = net_generic(net, sit_net_id); + + ipip6_tunnel_unlink(sitn, t); + synchronize_net(); + t->parms.iph.saddr = p->iph.saddr; + t->parms.iph.daddr = p->iph.daddr; + memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + memcpy(t->dev->broadcast, &p->iph.daddr, 4); + ipip6_tunnel_link(sitn, t); + t->parms.iph.ttl = p->iph.ttl; + t->parms.iph.tos = p->iph.tos; + if (t->parms.link != p->link) { + t->parms.link = p->link; + ipip6_tunnel_bind_dev(t->dev); + } + ip_tunnel_dst_reset_all(t); + netdev_state_change(t->dev); +} + +#ifdef CONFIG_IPV6_SIT_6RD +static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, + struct ip_tunnel_6rd *ip6rd) +{ + struct in6_addr prefix; + __be32 relay_prefix; + + if (ip6rd->relay_prefixlen > 32 || + ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) + return -EINVAL; + + ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) + return -EINVAL; + if (ip6rd->relay_prefixlen) + relay_prefix = ip6rd->relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd->relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd->relay_prefix) + return -EINVAL; + + t->ip6rd.prefix = prefix; + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd->prefixlen; + t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + ip_tunnel_dst_reset_all(t); + netdev_state_change(t->dev); return 0; } +#endif static int ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip_tunnel_parm p; - struct ip_tunnel *t; + struct ip_tunnel_prl prl; + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = t->net; + struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif switch (cmd) { case SIOCGETTUNNEL: - t = NULL; - if (dev == ipip6_fb_tunnel_dev) { +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCGET6RD: +#endif + if (dev == sitn->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; break; } - t = ipip6_tunnel_locate(&p, 0); + t = ipip6_tunnel_locate(net, &p, 0); + if (t == NULL) + t = netdev_priv(dev); } - if (t == NULL) - t = (struct ip_tunnel*)dev->priv; - memcpy(&p, &t->parms, sizeof(p)); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - err = -EFAULT; + + err = -EFAULT; + if (cmd == SIOCGETTUNNEL) { + memcpy(&p, &t->parms, sizeof(p)); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, + sizeof(p))) + goto done; +#ifdef CONFIG_IPV6_SIT_6RD + } else { + ip6rd.prefix = t->ip6rd.prefix; + ip6rd.relay_prefix = t->ip6rd.relay_prefix; + ip6rd.prefixlen = t->ip6rd.prefixlen; + ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd, + sizeof(ip6rd))) + goto done; +#endif + } + err = 0; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -624,15 +1180,19 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; err = -EINVAL; - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPV6 || + if (p.iph.protocol != IPPROTO_IPV6 && + p.iph.protocol != IPPROTO_IPIP && + p.iph.protocol != 0) + goto done; + if (p.iph.version != 4 || p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF))) goto done; if (p.iph.ttl) p.iph.frag_off |= htons(IP_DF); - t = ipip6_tunnel_locate(&p, cmd == SIOCADDTUNNEL); + t = ipip6_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL); - if (dev != ipip6_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { + if (dev != sitn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t != NULL) { if (t->dev != dev) { err = -EEXIST; @@ -644,23 +1204,14 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = -EINVAL; break; } - t = (struct ip_tunnel*)dev->priv; - ipip6_tunnel_unlink(t); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - ipip6_tunnel_link(t); - netdev_state_change(dev); + t = netdev_priv(dev); } + + ipip6_tunnel_update(t, &p); } if (t) { err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.iph.ttl = p.iph.ttl; - t->parms.iph.tos = p.iph.tos; - } if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p))) err = -EFAULT; } else @@ -669,24 +1220,82 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; - if (dev == ipip6_fb_tunnel_dev) { + if (dev == sitn->fb_tunnel_dev) { err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) goto done; err = -ENOENT; - if ((t = ipip6_tunnel_locate(&p, 0)) == NULL) + if ((t = ipip6_tunnel_locate(net, &p, 0)) == NULL) goto done; err = -EPERM; - if (t == ipip6_fb_tunnel_dev->priv) + if (t == netdev_priv(sitn->fb_tunnel_dev)) goto done; dev = t->dev; } - err = unregister_netdevice(dev); + unregister_netdevice(dev); + err = 0; + break; + + case SIOCGETPRL: + err = -EINVAL; + if (dev == sitn->fb_tunnel_dev) + goto done; + err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data); + break; + + case SIOCADDPRL: + case SIOCDELPRL: + case SIOCCHGPRL: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + goto done; + err = -EINVAL; + if (dev == sitn->fb_tunnel_dev) + goto done; + err = -EFAULT; + if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl))) + goto done; + + switch (cmd) { + case SIOCDELPRL: + err = ipip6_tunnel_del_prl(t, &prl); + break; + case SIOCADDPRL: + case SIOCCHGPRL: + err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); + break; + } + ip_tunnel_dst_reset_all(t); + netdev_state_change(dev); break; +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCADD6RD: + case SIOCCHG6RD: + case SIOCDEL6RD: + err = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data, + sizeof(ip6rd))) + goto done; + + if (cmd != SIOCDEL6RD) { + err = ipip6_tunnel_update_6rd(t, &ip6rd); + if (err < 0) + goto done; + } else + ipip6_tunnel_clone_6rd(dev, sitn); + + err = 0; + break; +#endif + default: err = -EINVAL; } @@ -695,11 +1304,6 @@ done: return err; } -static struct net_device_stats *ipip6_tunnel_get_stats(struct net_device *dev) -{ - return &(((struct ip_tunnel*)dev->priv)->stat); -} - static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr)) @@ -708,74 +1312,79 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static const struct net_device_ops ipip6_netdev_ops = { + .ndo_uninit = ipip6_tunnel_uninit, + .ndo_start_xmit = sit_tunnel_xmit, + .ndo_do_ioctl = ipip6_tunnel_ioctl, + .ndo_change_mtu = ipip6_tunnel_change_mtu, + .ndo_get_stats64 = ip_tunnel_get_stats64, +}; + +static void ipip6_dev_free(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + + free_percpu(tunnel->dst_cache); + free_percpu(dev->tstats); + free_netdev(dev); +} + +#define SIT_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_GSO_SOFTWARE | \ + NETIF_F_HW_CSUM) + static void ipip6_tunnel_setup(struct net_device *dev) { - SET_MODULE_OWNER(dev); - dev->uninit = ipip6_tunnel_uninit; - dev->destructor = free_netdev; - dev->hard_start_xmit = ipip6_tunnel_xmit; - dev->get_stats = ipip6_tunnel_get_stats; - dev->do_ioctl = ipip6_tunnel_ioctl; - dev->change_mtu = ipip6_tunnel_change_mtu; + dev->netdev_ops = &ipip6_netdev_ops; + dev->destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); - dev->mtu = 1500 - sizeof(struct iphdr); + dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr); dev->flags = IFF_NOARP; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->iflink = 0; dev->addr_len = 4; + dev->features |= NETIF_F_LLTX; + dev->features |= SIT_FEATURES; + dev->hw_features |= SIT_FEATURES; } static int ipip6_tunnel_init(struct net_device *dev) { - struct net_device *tdev = NULL; - struct ip_tunnel *tunnel; - struct iphdr *iph; - - tunnel = (struct ip_tunnel*)dev->priv; - iph = &tunnel->parms.iph; + struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); + tunnel->net = dev_net(dev); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); - if (iph->daddr) { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) } }, - .oif = tunnel->parms.link, - .proto = IPPROTO_IPV6 }; - struct rtable *rt; - if (!ip_route_output_key(&rt, &fl)) { - tdev = rt->u.dst.dev; - ip_rt_put(rt); - } - dev->flags |= IFF_POINTOPOINT; - } - - if (!tdev && tunnel->parms.link) - tdev = __dev_get_by_index(tunnel->parms.link); + ipip6_tunnel_bind_dev(dev); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; - if (tdev) { - dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); - dev->mtu = tdev->mtu - sizeof(struct iphdr); - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; } - dev->iflink = tunnel->parms.link; return 0; } -static int __init ipip6_fb_tunnel_init(struct net_device *dev) +static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) { - struct ip_tunnel *tunnel = dev->priv; + struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); tunnel->dev = dev; + tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); iph->version = 4; @@ -783,68 +1392,441 @@ static int __init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + dev_hold(dev); - tunnels_wc[0] = tunnel; + rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); + return 0; +} + +static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data || !data[IFLA_IPTUN_PROTO]) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + +static void ipip6_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPV6; + parms->iph.ihl = 5; + parms->iph.ttl = 64; + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + + if (data[IFLA_IPTUN_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + + if (data[IFLA_IPTUN_TTL]) { + parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); + if (parms->iph.ttl) + parms->iph.frag_off = htons(IP_DF); + } + + if (data[IFLA_IPTUN_TOS]) + parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); + + if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) + parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_FLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); + +} + +#ifdef CONFIG_IPV6_SIT_6RD +/* This function returns true when 6RD attributes are present in the nl msg */ +static bool ipip6_netlink_6rd_parms(struct nlattr *data[], + struct ip_tunnel_6rd *ip6rd) +{ + bool ret = false; + memset(ip6rd, 0, sizeof(*ip6rd)); + + if (!data) + return ret; + + if (data[IFLA_IPTUN_6RD_PREFIX]) { + ret = true; + nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX], + sizeof(struct in6_addr)); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { + ret = true; + ip6rd->relay_prefix = + nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); + } + + if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { + ret = true; + ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { + ret = true; + ip6rd->relay_prefixlen = + nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); + } + + return ret; +} +#endif + +static int ipip6_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip_tunnel *nt; +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + int err; + + nt = netdev_priv(dev); + ipip6_netlink_parms(data, &nt->parms); + + if (ipip6_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + err = ipip6_tunnel_create(dev); + if (err < 0) + return err; + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + err = ipip6_tunnel_update_6rd(nt, &ip6rd); +#endif + + return err; +} + +static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm p; + struct net *net = t->net; + struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + + if (dev == sitn->fb_tunnel_dev) + return -EINVAL; + + ipip6_netlink_parms(data, &p); + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + t = ipip6_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + ipip6_tunnel_update(t, &p); + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + return ipip6_tunnel_update_6rd(t, &ip6rd); +#endif + + return 0; +} + +static size_t ipip6_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(4) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(4) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_TOS */ + nla_total_size(1) + + /* IFLA_IPTUN_PMTUDISC */ + nla_total_size(1) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(2) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + +#ifdef CONFIG_IPV6_SIT_6RD + /* IFLA_IPTUN_6RD_PREFIX */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ + nla_total_size(4) + + /* IFLA_IPTUN_6RD_PREFIXLEN */ + nla_total_size(2) + + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ + nla_total_size(2) + +#endif + 0; +} + +static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct ip_tunnel_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || + nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || + nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, + !!(parm->iph.frag_off & htons(IP_DF))) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags)) + goto nla_put_failure; + +#ifdef CONFIG_IPV6_SIT_6RD + if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr), + &tunnel->ip6rd.prefix) || + nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, + tunnel->ip6rd.relay_prefix) || + nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, + tunnel->ip6rd.prefixlen) || + nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, + tunnel->ip6rd.relay_prefixlen)) + goto nla_put_failure; +#endif + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, + [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, + [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, +#ifdef CONFIG_IPV6_SIT_6RD + [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, + [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, + [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, +#endif +}; + +static void ipip6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + if (dev != sitn->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); } -static struct net_protocol sit_protocol = { +static struct rtnl_link_ops sit_link_ops __read_mostly = { + .kind = "sit", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip6_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip6_tunnel_setup, + .validate = ipip6_validate, + .newlink = ipip6_newlink, + .changelink = ipip6_changelink, + .get_size = ipip6_get_size, + .fill_info = ipip6_fill_info, + .dellink = ipip6_dellink, +}; + +static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, + .priority = 1, +}; + +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = ipip_rcv, + .err_handler = ipip6_err, + .priority = 2, }; -static void __exit sit_destroy_tunnels(void) +static void __net_exit sit_destroy_tunnels(struct net *net, + struct list_head *head) { + struct sit_net *sitn = net_generic(net, sit_net_id); + struct net_device *dev, *aux; int prio; + for_each_netdev_safe(net, dev, aux) + if (dev->rtnl_link_ops == &sit_link_ops) + unregister_netdevice_queue(dev, head); + for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { struct ip_tunnel *t; - while ((t = tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + + t = rtnl_dereference(sitn->tunnels[prio][h]); + while (t != NULL) { + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, + head); + t = rtnl_dereference(t->next); + } } } } -void __exit sit_cleanup(void) +static int __net_init sit_init_net(struct net *net) { - inet_del_protocol(&sit_protocol, IPPROTO_IPV6); + struct sit_net *sitn = net_generic(net, sit_net_id); + struct ip_tunnel *t; + int err; + + sitn->tunnels[0] = sitn->tunnels_wc; + sitn->tunnels[1] = sitn->tunnels_l; + sitn->tunnels[2] = sitn->tunnels_r; + sitn->tunnels[3] = sitn->tunnels_r_l; + + sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", + ipip6_tunnel_setup); + if (!sitn->fb_tunnel_dev) { + err = -ENOMEM; + goto err_alloc_dev; + } + dev_net_set(sitn->fb_tunnel_dev, net); + sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; + /* FB netdevice is special: we have one, and only one per netns. + * Allowing to move it to another netns is clearly unsafe. + */ + sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + + err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + if (err) + goto err_dev_free; + + ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); + + 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: + dev_put(sitn->fb_tunnel_dev); +err_dev_free: + ipip6_dev_free(sitn->fb_tunnel_dev); +err_alloc_dev: + return err; +} + +static void __net_exit sit_exit_net(struct net *net) +{ + LIST_HEAD(list); rtnl_lock(); - sit_destroy_tunnels(); - unregister_netdevice(ipip6_fb_tunnel_dev); + sit_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } -int __init sit_init(void) +static struct pernet_operations sit_net_ops = { + .init = sit_init_net, + .exit = sit_exit_net, + .id = &sit_net_id, + .size = sizeof(struct sit_net), +}; + +static void __exit sit_cleanup(void) +{ + rtnl_link_unregister(&sit_link_ops); + xfrm4_tunnel_deregister(&sit_handler, AF_INET6); + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); + + unregister_pernet_device(&sit_net_ops); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ +} + +static int __init sit_init(void) { int err; - printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n"); + pr_info("IPv6 over IPv4 tunneling driver\n"); - if (inet_add_protocol(&sit_protocol, IPPROTO_IPV6) < 0) { - printk(KERN_INFO "sit init: Can't add protocol\n"); - return -EAGAIN; + err = register_pernet_device(&sit_net_ops); + if (err < 0) + return err; + err = xfrm4_tunnel_register(&sit_handler, AF_INET6); + if (err < 0) { + pr_info("%s: can't register ip6ip4\n", __func__); + goto xfrm_tunnel_failed; } - - ipip6_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", - ipip6_tunnel_setup); - if (!ipip6_fb_tunnel_dev) { - err = -ENOMEM; - goto err1; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: can't register ip4ip4\n", __func__); + goto xfrm_tunnel4_failed; } + err = rtnl_link_register(&sit_link_ops); + if (err < 0) + goto rtnl_link_failed; - ipip6_fb_tunnel_dev->init = ipip6_fb_tunnel_init; - - if ((err = register_netdev(ipip6_fb_tunnel_dev))) - goto err2; - - out: +out: return err; - err2: - free_netdev(ipip6_fb_tunnel_dev); - err1: - inet_del_protocol(&sit_protocol, IPPROTO_IPV6); + +rtnl_link_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel4_failed: + xfrm4_tunnel_deregister(&sit_handler, AF_INET6); +xfrm_tunnel_failed: + unregister_pernet_device(&sit_net_ops); goto out; } + +module_init(sit_init); +module_exit(sit_cleanup); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("sit"); +MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c new file mode 100644 index 00000000000..a822b880689 --- /dev/null +++ b/net/ipv6/syncookies.c @@ -0,0 +1,272 @@ +/* + * IPv6 Syncookies implementation for the Linux kernel + * + * Authors: + * Glenn Griffin <ggriffin.kernel@gmail.com> + * + * Based on IPv4 implementation by Andi Kleen + * linux/net/ipv4/syncookies.c + * + * 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. + * + */ + +#include <linux/tcp.h> +#include <linux/random.h> +#include <linux/cryptohash.h> +#include <linux/kernel.h> +#include <net/ipv6.h> +#include <net/tcp.h> + +#define COOKIEBITS 24 /* Upper bits store count */ +#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) + +static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS]; + +/* RFC 2460, Section 8.3: + * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] + * + * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows + * using higher values than ipv4 tcp syncookies. + * The other values are chosen based on ethernet (1500 and 9k MTU), plus + * one that accounts for common encap (PPPoe) overhead. Table must be sorted. + */ +static __u16 const msstab[] = { + 1280 - 60, /* IPV6_MIN_MTU - 60 */ + 1480 - 60, + 1500 - 60, + 9000 - 60, +}; + +static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct sock *child; + + child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); + if (child) + inet_csk_reqsk_queue_add(sk, req, child); + else + reqsk_free(req); + + return child; +} + +static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], + ipv6_cookie_scratch); + +static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr, + __be16 sport, __be16 dport, u32 count, int c) +{ + __u32 *tmp; + + net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret)); + + tmp = __get_cpu_var(ipv6_cookie_scratch); + + /* + * we have 320 bits of information to hash, copy in the remaining + * 192 bits required for sha_transform, from the syncookie6_secret + * and overwrite the digest with the secret + */ + memcpy(tmp + 10, syncookie6_secret[c], 44); + memcpy(tmp, saddr, 16); + memcpy(tmp + 4, daddr, 16); + tmp[8] = ((__force u32)sport << 16) + (__force u32)dport; + tmp[9] = count; + sha_transform(tmp + 16, (__u8 *)tmp, tmp + 16 + 5); + + return tmp[17]; +} + +static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __be16 sport, __be16 dport, __u32 sseq, + __u32 data) +{ + u32 count = tcp_cookie_time(); + return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + + sseq + (count << COOKIEBITS) + + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) + & COOKIEMASK)); +} + +static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, + const struct in6_addr *daddr, __be16 sport, + __be16 dport, __u32 sseq) +{ + __u32 diff, count = tcp_cookie_time(); + + cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; + + diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); + if (diff >= MAX_SYNCOOKIE_AGE) + return (__u32)-1; + + return (cookie - + cookie_hash(saddr, daddr, sport, dport, count - diff, 1)) + & COOKIEMASK; +} + +u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, + const struct tcphdr *th, __u16 *mssp) +{ + int mssind; + const __u16 mss = *mssp; + + for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) + if (mss >= msstab[mssind]) + break; + + *mssp = msstab[mssind]; + + return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source, + th->dest, ntohl(th->seq), mssind); +} +EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); + +__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); + + tcp_synq_overflow(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); + + return __cookie_v6_init_sequence(iph, th, mssp); +} + +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, + __u32 cookie) +{ + __u32 seq = ntohl(th->seq) - 1; + __u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, + th->source, th->dest, seq); + + return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; +} +EXPORT_SYMBOL_GPL(__cookie_v6_check); + +struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_options_received tcp_opt; + struct inet_request_sock *ireq; + struct tcp_request_sock *treq; + struct ipv6_pinfo *np = inet6_sk(sk); + struct tcp_sock *tp = tcp_sk(sk); + const struct tcphdr *th = tcp_hdr(skb); + __u32 cookie = ntohl(th->ack_seq) - 1; + struct sock *ret = sk; + struct request_sock *req; + int mss; + struct dst_entry *dst; + __u8 rcv_wscale; + bool ecn_ok = false; + + if (!sysctl_tcp_syncookies || !th->ack || th->rst) + goto out; + + if (tcp_synq_no_recent_overflow(sk) || + (mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie)) == 0) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED); + goto out; + } + + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); + + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, 0, NULL); + + if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) + goto out; + + ret = NULL; + req = inet6_reqsk_alloc(&tcp6_request_sock_ops); + if (!req) + goto out; + + ireq = inet_rsk(req); + treq = tcp_rsk(req); + treq->listener = NULL; + + if (security_inet_conn_request(sk, skb, req)) + goto out_free; + + req->mss = mss; + ireq->ir_rmt_port = th->source; + ireq->ir_num = ntohs(th->dest); + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_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) { + atomic_inc(&skb->users); + ireq->pktopts = skb; + } + + ireq->ir_iif = sk->sk_bound_dev_if; + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); + + ireq->ir_mark = inet_request_mark(sk, skb); + + req->expires = 0UL; + req->num_retrans = 0; + ireq->ecn_ok = ecn_ok; + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->rcv_isn = ntohl(th->seq) - 1; + treq->snt_isn = cookie; + + /* + * We need to lookup the dst_entry to get the correct window size. + * This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten + * me if there is a preferred way. + */ + { + struct in6_addr *final_p, final; + struct flowi6 fl6; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.daddr = ireq->ir_v6_rmt_addr; + final_p = fl6_update_dst(&fl6, np->opt, &final); + fl6.saddr = ireq->ir_v6_loc_addr; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_mark = ireq->ir_mark; + fl6.fl6_dport = ireq->ir_rmt_port; + fl6.fl6_sport = inet_sk(sk)->inet_sport; + security_req_classify_flow(req, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) + goto out_free; + } + + req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); + tcp_select_initial_window(tcp_full_space(sk), req->mss, + &req->rcv_wnd, &req->window_clamp, + ireq->wscale_ok, &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); + + ireq->rcv_wscale = rcv_wscale; + + ret = get_cookie_sock(sk, skb, req, dst); +out: + return ret; +out_free: + reqsk_free(req); + return NULL; +} + diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 8eff9fa1e98..058f3eca2e5 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -7,116 +7,159 @@ #include <linux/mm.h> #include <linux/sysctl.h> -#include <linux/config.h> #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> +#include <net/inet_frag.h> -#ifdef CONFIG_SYSCTL - -static ctl_table ipv6_table[] = { - { - .ctl_name = NET_IPV6_ROUTE, - .procname = "route", - .maxlen = 0, - .mode = 0555, - .child = ipv6_route_table - }, - { - .ctl_name = NET_IPV6_ICMP, - .procname = "icmp", - .maxlen = 0, - .mode = 0555, - .child = ipv6_icmp_table - }, +static struct ctl_table ipv6_table_template[] = { { - .ctl_name = NET_IPV6_BINDV6ONLY, .procname = "bindv6only", - .data = &sysctl_ipv6_bindv6only, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec - }, - { - .ctl_name = NET_IPV6_IP6FRAG_HIGH_THRESH, - .procname = "ip6frag_high_thresh", - .data = &sysctl_ip6frag_high_thresh, + .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_LOW_THRESH, - .procname = "ip6frag_low_thresh", - .data = &sysctl_ip6frag_low_thresh, + .procname = "anycast_src_echo_reply", + .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_TIME, - .procname = "ip6frag_time", - .data = &sysctl_ip6frag_time, + .procname = "flowlabel_consistency", + .data = &init_net.ipv6.sysctl.flowlabel_consistency, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec }, { - .ctl_name = NET_IPV6_IP6FRAG_SECRET_INTERVAL, - .procname = "ip6frag_secret_interval", - .data = &sysctl_ip6frag_secret_interval, + .procname = "fwmark_reflect", + .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec }, + { } +}; + +static struct ctl_table ipv6_rotable[] = { { - .ctl_name = NET_IPV6_MLD_MAX_MSF, .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; -static struct ctl_table_header *ipv6_sysctl_header; +static int __net_init ipv6_sysctl_net_init(struct net *net) +{ + struct ctl_table *ipv6_table; + struct ctl_table *ipv6_route_table; + struct ctl_table *ipv6_icmp_table; + int err; -static ctl_table ipv6_net_table[] = { - { - .ctl_name = NET_IPV6, - .procname = "ipv6", - .mode = 0555, - .child = ipv6_table - }, - { .ctl_name = 0 } -}; + err = -ENOMEM; + ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), + GFP_KERNEL); + if (!ipv6_table) + goto out; + ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; + ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply; + ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; -static ctl_table ipv6_root_table[] = { - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, - .child = ipv6_net_table - }, - { .ctl_name = 0 } -}; + ipv6_route_table = ipv6_route_sysctl_init(net); + if (!ipv6_route_table) + goto out_ipv6_table; -void ipv6_sysctl_register(void) -{ - ipv6_sysctl_header = register_sysctl_table(ipv6_root_table, 0); + ipv6_icmp_table = ipv6_icmp_sysctl_init(net); + if (!ipv6_icmp_table) + goto out_ipv6_route_table; + + net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table); + if (!net->ipv6.sysctl.hdr) + goto out_ipv6_icmp_table; + + net->ipv6.sysctl.route_hdr = + register_net_sysctl(net, "net/ipv6/route", ipv6_route_table); + if (!net->ipv6.sysctl.route_hdr) + goto out_unregister_ipv6_table; + + net->ipv6.sysctl.icmp_hdr = + register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table); + if (!net->ipv6.sysctl.icmp_hdr) + goto out_unregister_route_table; + + err = 0; +out: + return err; +out_unregister_route_table: + unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); +out_unregister_ipv6_table: + unregister_net_sysctl_table(net->ipv6.sysctl.hdr); +out_ipv6_icmp_table: + kfree(ipv6_icmp_table); +out_ipv6_route_table: + kfree(ipv6_route_table); +out_ipv6_table: + kfree(ipv6_table); + goto out; } -void ipv6_sysctl_unregister(void) +static void __net_exit ipv6_sysctl_net_exit(struct net *net) { - unregister_sysctl_table(ipv6_sysctl_header); + struct ctl_table *ipv6_table; + struct ctl_table *ipv6_route_table; + struct ctl_table *ipv6_icmp_table; + + ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; + ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; + ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; + + unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); + unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); + unregister_net_sysctl_table(net->ipv6.sysctl.hdr); + + kfree(ipv6_table); + kfree(ipv6_route_table); + kfree(ipv6_icmp_table); } -#endif /* CONFIG_SYSCTL */ +static struct pernet_operations ipv6_sysctl_net_ops = { + .init = ipv6_sysctl_net_init, + .exit = ipv6_sysctl_net_exit, +}; + +static struct ctl_table_header *ip6_header; +int ipv6_sysctl_register(void) +{ + int err = -ENOMEM; + ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); + if (ip6_header == NULL) + goto out; + err = register_pernet_subsys(&ipv6_sysctl_net_ops); + if (err) + goto err_pernet; +out: + return err; + +err_pernet: + unregister_net_sysctl_table(ip6_header); + goto out; +} + +void ipv6_sysctl_unregister(void) +{ + unregister_net_sysctl_table(ip6_header); + unregister_pernet_subsys(&ipv6_sysctl_net_ops); +} diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d693cb988b7..229239ad96b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1,13 +1,11 @@ /* * TCP over IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * - * $Id: tcp_ipv6.c,v 1.144 2002/02/01 22:01:04 davem Exp $ - * - * Based on: + * Based on: * linux/net/ipv4/tcp.c * linux/net/ipv4/tcp_input.c * linux/net/ipv4/tcp_output.c @@ -25,8 +23,8 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/bottom_half.h> #include <linux/module.h> -#include <linux/config.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -40,7 +38,8 @@ #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> - +#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> @@ -48,6 +47,7 @@ #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> +#include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> @@ -56,493 +56,118 @@ #include <net/inet_ecn.h> #include <net/protocol.h> #include <net/xfrm.h> -#include <net/addrconf.h> #include <net/snmp.h> #include <net/dsfield.h> - -#include <asm/uaccess.h> +#include <net/timewait_sock.h> +#include <net/netdma.h> +#include <net/inet_common.h> +#include <net/secure_seq.h> +#include <net/tcp_memcontrol.h> +#include <net/busy_poll.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> -static void tcp_v6_send_reset(struct sk_buff *skb); -static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); -static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, - struct sk_buff *skb); - -static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static int tcp_v6_xmit(struct sk_buff *skb, int ipfragok); - -static struct tcp_func ipv6_mapped; -static struct tcp_func ipv6_specific; +#include <linux/crypto.h> +#include <linux/scatterlist.h> -static inline int tcp_v6_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb) -{ - const struct sock *sk2; - const struct hlist_node *node; - - /* We must walk the whole port owner list in this case. -DaveM */ - sk_for_each_bound(sk2, node, &tb->owners) { - if (sk != sk2 && - (!sk->sk_bound_dev_if || - !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && - (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; - } +static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb); +static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); - return node != NULL; -} +static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -/* Grrr, addr_type already calculated by caller, but I don't want - * to add some silly "cookie" argument to this method just for that. - * But it doesn't matter, the recalculation is in the rarest path - * this function ever takes. - */ -static int tcp_v6_get_port(struct sock *sk, unsigned short snum) +static const struct inet_connection_sock_af_ops ipv6_mapped; +static const struct inet_connection_sock_af_ops ipv6_specific; +#ifdef CONFIG_TCP_MD5SIG +static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; +static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; +#else +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, + const struct in6_addr *addr) { - struct inet_bind_hashbucket *head; - struct inet_bind_bucket *tb; - struct hlist_node *node; - int ret; - - local_bh_disable(); - if (snum == 0) { - int low = sysctl_local_port_range[0]; - int high = sysctl_local_port_range[1]; - int remaining = (high - low) + 1; - int rover; - - spin_lock(&tcp_hashinfo.portalloc_lock); - if (tcp_hashinfo.port_rover < low) - rover = low; - else - rover = tcp_hashinfo.port_rover; - do { rover++; - if (rover > high) - rover = low; - head = &tcp_hashinfo.bhash[inet_bhashfn(rover, tcp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) - if (tb->port == rover) - goto next; - break; - next: - spin_unlock(&head->lock); - } while (--remaining > 0); - tcp_hashinfo.port_rover = rover; - spin_unlock(&tcp_hashinfo.portalloc_lock); - - /* Exhausted local port range during search? It is not - * possible for us to be holding one of the bind hash - * locks if this test triggers, because if 'remaining' - * drops to zero, we broke out of the do/while loop at - * the top level, not from the 'break;' statement. - */ - ret = 1; - if (unlikely(remaining <= 0)) - goto fail; - - /* OK, here is the one we will use. */ - snum = rover; - } else { - head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) - if (tb->port == snum) - goto tb_found; - } - tb = NULL; - goto tb_not_found; -tb_found: - if (tb && !hlist_empty(&tb->owners)) { - if (tb->fastreuse > 0 && sk->sk_reuse && - sk->sk_state != TCP_LISTEN) { - goto success; - } else { - ret = 1; - if (tcp_v6_bind_conflict(sk, tb)) - goto fail_unlock; - } - } -tb_not_found: - ret = 1; - if (tb == NULL) { - tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, snum); - if (tb == NULL) - goto fail_unlock; - } - if (hlist_empty(&tb->owners)) { - if (sk->sk_reuse && sk->sk_state != TCP_LISTEN) - tb->fastreuse = 1; - else - tb->fastreuse = 0; - } else if (tb->fastreuse && - (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) - tb->fastreuse = 0; - -success: - if (!inet_csk(sk)->icsk_bind_hash) - inet_bind_hash(sk, tb, snum); - BUG_TRAP(inet_csk(sk)->icsk_bind_hash == tb); - ret = 0; - -fail_unlock: - spin_unlock(&head->lock); -fail: - local_bh_enable(); - return ret; + return NULL; } +#endif -static __inline__ void __tcp_v6_hash(struct sock *sk) +static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { - struct hlist_head *list; - rwlock_t *lock; - - BUG_TRAP(sk_unhashed(sk)); - - if (sk->sk_state == TCP_LISTEN) { - list = &tcp_hashinfo.listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &tcp_hashinfo.lhash_lock; - inet_listen_wlock(&tcp_hashinfo); - } else { - unsigned int hash; - sk->sk_hash = hash = inet6_sk_ehashfn(sk); - hash &= (tcp_hashinfo.ehash_size - 1); - list = &tcp_hashinfo.ehash[hash].chain; - lock = &tcp_hashinfo.ehash[hash].lock; - write_lock(lock); - } - - __sk_add_node(sk, list); - sock_prot_inc_use(sk->sk_prot); - write_unlock(lock); + struct dst_entry *dst = skb_dst(skb); + const struct rt6_info *rt = (const struct rt6_info *)dst; + + dst_hold(dst); + sk->sk_rx_dst = dst; + inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; + if (rt->rt6i_node) + inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum; } - static void tcp_v6_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->af_specific == &ipv6_mapped) { + if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) { tcp_prot.hash(sk); return; } local_bh_disable(); - __tcp_v6_hash(sk); + __inet6_hash(sk, NULL); local_bh_enable(); } } -/* - * Open request hash tables. - */ - -static u32 tcp_v6_synq_hash(const struct in6_addr *raddr, const u16 rport, const u32 rnd) +static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { - u32 a, b, c; - - a = raddr->s6_addr32[0]; - b = raddr->s6_addr32[1]; - c = raddr->s6_addr32[2]; - - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; - c += rnd; - __jhash_mix(a, b, c); - - a += raddr->s6_addr32[3]; - b += (u32) rport; - __jhash_mix(a, b, c); - - return c & (TCP_SYNQ_HSIZE - 1); -} - -static struct request_sock *tcp_v6_search_req(const struct sock *sk, - struct request_sock ***prevp, - __u16 rport, - struct in6_addr *raddr, - struct in6_addr *laddr, - int iif) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; - - for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)]; - (req = *prev) != NULL; - prev = &req->dl_next) { - const struct tcp6_request_sock *treq = tcp6_rsk(req); - - if (inet_rsk(req)->rmt_port == rport && - req->rsk_ops->family == AF_INET6 && - ipv6_addr_equal(&treq->rmt_addr, raddr) && - ipv6_addr_equal(&treq->loc_addr, laddr) && - (!treq->iif || treq->iif == iif)) { - BUG_TRAP(req->sk == NULL); - *prevp = prev; - return req; - } - } - - return NULL; + return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } -static __inline__ u16 tcp_v6_check(struct tcphdr *th, int len, - struct in6_addr *saddr, - struct in6_addr *daddr, - unsigned long base) -{ - return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); -} - -static __u32 tcp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) -{ - if (skb->protocol == htons(ETH_P_IPV6)) { - return secure_tcpv6_sequence_number(skb->nh.ipv6h->daddr.s6_addr32, - skb->nh.ipv6h->saddr.s6_addr32, - skb->h.th->dest, - skb->h.th->source); - } else { - return secure_tcp_sequence_number(skb->nh.iph->daddr, - skb->nh.iph->saddr, - skb->h.th->dest, - skb->h.th->source); - } -} - -static int __tcp_v6_check_established(struct sock *sk, const __u16 lport, - struct inet_timewait_sock **twp) -{ - struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - const struct in6_addr *daddr = &np->rcv_saddr; - const struct in6_addr *saddr = &np->daddr; - const int dif = sk->sk_bound_dev_if; - const u32 ports = INET_COMBINED_PORTS(inet->dport, lport); - unsigned int hash = inet6_ehashfn(daddr, inet->num, saddr, inet->dport); - struct inet_ehash_bucket *head = inet_ehash_bucket(&tcp_hashinfo, hash); - struct sock *sk2; - const struct hlist_node *node; - struct inet_timewait_sock *tw; - - prefetch(head->chain.first); - write_lock(&head->lock); - - /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &(head + tcp_hashinfo.ehash_size)->chain) { - const struct tcp6_timewait_sock *tcp6tw = tcp6_twsk(sk2); - - tw = inet_twsk(sk2); - - if(*((__u32 *)&(tw->tw_dport)) == ports && - sk2->sk_family == PF_INET6 && - ipv6_addr_equal(&tcp6tw->tw_v6_daddr, saddr) && - ipv6_addr_equal(&tcp6tw->tw_v6_rcv_saddr, daddr) && - sk2->sk_bound_dev_if == sk->sk_bound_dev_if) { - const struct tcp_timewait_sock *tcptw = tcp_twsk(sk2); - struct tcp_sock *tp = tcp_sk(sk); - - if (tcptw->tw_ts_recent_stamp && - (!twp || - (sysctl_tcp_tw_reuse && - xtime.tv_sec - tcptw->tw_ts_recent_stamp > 1))) { - /* See comment in tcp_ipv4.c */ - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (!tp->write_seq) - tp->write_seq = 1; - tp->rx_opt.ts_recent = tcptw->tw_ts_recent; - tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; - sock_hold(sk2); - goto unique; - } else - goto not_unique; - } - } - tw = NULL; - - /* And established part... */ - sk_for_each(sk2, node, &head->chain) { - if (INET6_MATCH(sk2, hash, saddr, daddr, ports, dif)) - goto not_unique; - } - -unique: - BUG_TRAP(sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); - sk->sk_hash = hash; - sock_prot_inc_use(sk->sk_prot); - write_unlock(&head->lock); - - if (twp) { - *twp = tw; - NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); - } else if (tw) { - /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw, &tcp_death_row); - NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); - - inet_twsk_put(tw); - } - return 0; - -not_unique: - write_unlock(&head->lock); - return -EADDRNOTAVAIL; -} - -static inline u32 tcpv6_port_offset(const struct sock *sk) -{ - const struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - - return secure_tcpv6_port_ephemeral(np->rcv_saddr.s6_addr32, - np->daddr.s6_addr32, - inet->dport); -} - -static int tcp_v6_hash_connect(struct sock *sk) -{ - unsigned short snum = inet_sk(sk)->num; - struct inet_bind_hashbucket *head; - struct inet_bind_bucket *tb; - int ret; - - if (!snum) { - int low = sysctl_local_port_range[0]; - int high = sysctl_local_port_range[1]; - int range = high - low; - int i; - int port; - static u32 hint; - u32 offset = hint + tcpv6_port_offset(sk); - struct hlist_node *node; - struct inet_timewait_sock *tw = NULL; - - local_bh_disable(); - for (i = 1; i <= range; i++) { - port = low + (i + offset) % range; - head = &tcp_hashinfo.bhash[inet_bhashfn(port, tcp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - - /* Does not bother with rcv_saddr checks, - * because the established check is already - * unique enough. - */ - inet_bind_bucket_for_each(tb, node, &head->chain) { - if (tb->port == port) { - BUG_TRAP(!hlist_empty(&tb->owners)); - if (tb->fastreuse >= 0) - goto next_port; - if (!__tcp_v6_check_established(sk, - port, - &tw)) - goto ok; - goto next_port; - } - } - - tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, port); - if (!tb) { - spin_unlock(&head->lock); - break; - } - tb->fastreuse = -1; - goto ok; - - next_port: - spin_unlock(&head->lock); - } - local_bh_enable(); - - return -EADDRNOTAVAIL; - -ok: - hint += i; - - /* Head lock still held and bh's disabled */ - inet_bind_hash(sk, tb, port); - if (sk_unhashed(sk)) { - inet_sk(sk)->sport = htons(port); - __tcp_v6_hash(sk); - } - spin_unlock(&head->lock); - - if (tw) { - inet_twsk_deschedule(tw, &tcp_death_row); - inet_twsk_put(tw); - } - - ret = 0; - goto out; - } - - head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)]; - tb = inet_csk(sk)->icsk_bind_hash; - spin_lock_bh(&head->lock); - - if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - __tcp_v6_hash(sk); - spin_unlock_bh(&head->lock); - return 0; - } else { - spin_unlock(&head->lock); - /* No definite answer... Walk to established hash table */ - ret = __tcp_v6_check_established(sk, snum, NULL); -out: - local_bh_enable(); - return ret; - } -} - -static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, +static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct in6_addr *saddr = NULL, *final_p = NULL, final; - struct flowi fl; + struct in6_addr *saddr = NULL, *final_p, final; + struct rt6_info *rt; + struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; - if (addr_len < SIN6_LEN_RFC2133) + if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - if (usin->sin6_family != AF_INET6) - return(-EAFNOSUPPORT); + if (usin->sin6_family != AF_INET6) + return -EAFNOSUPPORT; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; - IP6_ECN_flow_init(fl.fl6_flowlabel); - if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) { + fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; + IP6_ECN_flow_init(fl6.flowlabel); + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); fl6_sock_release(flowlabel); } } /* - * connect() to INADDR_ANY means loopback (BSD'ism). - */ - - if(ipv6_addr_any(&usin->sin6_addr)) - usin->sin6_addr.s6_addr[15] = 0x1; + * connect() to INADDR_ANY means loopback (BSD'ism). + */ + + if (ipv6_addr_any(&usin->sin6_addr)) + usin->sin6_addr.s6_addr[15] = 0x1; addr_type = ipv6_addr_type(&usin->sin6_addr); - if(addr_type & IPV6_ADDR_MULTICAST) + if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { @@ -564,21 +189,21 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (tp->rx_opt.ts_recent_stamp && - !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) { + !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; tp->write_seq = 0; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); - np->flow_label = fl.fl6_flowlabel; + sk->sk_v6_daddr = usin->sin6_addr; + np->flow_label = fl6.flowlabel; /* * TCP over IPv4 */ if (addr_type == IPV6_ADDR_MAPPED) { - u32 exthdrlen = tp->ext_header_len; + u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; SOCK_DEBUG(sk, "connect: ipv4 mapped\n"); @@ -590,84 +215,89 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; - tp->af_specific = &ipv6_mapped; + icsk->icsk_af_ops = &ipv6_mapped; sk->sk_backlog_rcv = tcp_v4_do_rcv; +#ifdef CONFIG_TCP_MD5SIG + tp->af_specific = &tcp_sock_ipv6_mapped_specific; +#endif err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { - tp->ext_header_len = exthdrlen; - tp->af_specific = &ipv6_specific; + icsk->icsk_ext_hdr_len = exthdrlen; + icsk->icsk_af_ops = &ipv6_specific; sk->sk_backlog_rcv = tcp_v6_do_rcv; +#ifdef CONFIG_TCP_MD5SIG + tp->af_specific = &tcp_sock_ipv6_specific; +#endif goto failure; } else { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), - inet->saddr); - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), - inet->rcv_saddr); + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &sk->sk_v6_rcv_saddr); } return err; } - if (!ipv6_addr_any(&np->rcv_saddr)) - saddr = &np->rcv_saddr; - - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, - (saddr ? saddr : &np->saddr)); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto failure; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.daddr = sk->sk_v6_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; + fl6.fl6_sport = inet->inet_sport; - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + final_p = fl6_update_dst(&fl6, np->opt, &final); + + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto failure; + } if (saddr == NULL) { - saddr = &fl.fl6_src; - ipv6_addr_copy(&np->rcv_saddr, saddr); + saddr = &fl6.saddr; + sk->sk_v6_rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); - inet->rcv_saddr = LOOPBACK4_IPV6; + np->saddr = *saddr; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; - ip6_dst_store(sk, dst, NULL); - sk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); + sk->sk_gso_type = SKB_GSO_TCPV6; + __ip6_dst_store(sk, dst, NULL, NULL); - tp->ext_header_len = 0; + rt = (struct rt6_info *) dst; + if (tcp_death_row.sysctl_tw_recycle && + !tp->rx_opt.ts_recent_stamp && + ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr)) + tcp_fetch_timewait_stamp(sk, dst); + + icsk->icsk_ext_hdr_len = 0; if (np->opt) - tp->ext_header_len = np->opt->opt_flen + np->opt->opt_nflen; + icsk->icsk_ext_hdr_len = (np->opt->opt_flen + + np->opt->opt_nflen); tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); - err = tcp_v6_hash_connect(sk); + err = inet6_hash_connect(&tcp_death_row, sk); if (err) goto late_failure; - if (!tp->write_seq) + if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, - inet->sport, - inet->dport); + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); err = tcp_connect(sk); if (err) @@ -679,97 +309,105 @@ late_failure: tcp_set_state(sk, TCP_CLOSE); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } +static void tcp_v6_mtu_reduced(struct sock *sk) +{ + struct dst_entry *dst; + + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + + dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + if (!dst) + return; + + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + tcp_sync_mss(sk, dst_mtu(dst)); + tcp_simple_retransmit(sk); + } +} + static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + u8 type, u8 code, int offset, __be32 info) { - struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct ipv6_pinfo *np; struct sock *sk; int err; - struct tcp_sock *tp; - __u32 seq; + struct tcp_sock *tp; + struct request_sock *fastopen; + __u32 seq, snd_una; + struct net *net = dev_net(skb->dev); - sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr, - th->source, skb->dev->ifindex); + sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr, + th->dest, &hdr->saddr, th->source, skb->dev->ifindex); if (sk == NULL) { - ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); return; } if (sk->sk_state == TCP_TIME_WAIT) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); - if (sock_owned_by_user(sk)) - NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); + if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; + if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto out; + } + tp = tcp_sk(sk); - seq = ntohl(th->seq); + seq = ntohl(th->seq); + /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ + fastopen = tp->fastopen_rsk; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt)) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + !between(seq, snd_una, tp->snd_nxt)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); - if (type == ICMPV6_PKT_TOOBIG) { - struct dst_entry *dst = NULL; - - if (sock_owned_by_user(sk)) - goto out; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) - goto out; - - /* icmp should have updated the destination cache entry */ - dst = __sk_dst_check(sk, np->dst_cookie); - - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct flowi fl; + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - /* BUGGG_FUTURE: Again, it is not clear how - to handle rthdr case. Ignore this complexity - for now. - */ - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; - - if ((err = ip6_dst_lookup(sk, &dst, &fl))) { - sk->sk_err_soft = -err; - goto out; - } + if (dst) + dst->ops->redirect(dst, sk, skb); + goto out; + } - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { - sk->sk_err_soft = -err; - goto out; - } + if (type == ICMPV6_PKT_TOOBIG) { + /* We are not interested in TCP_LISTEN and open_requests + * (SYN-ACKs send out by Linux are always <576bytes so + * they should go through unfragmented). + */ + if (sk->sk_state == TCP_LISTEN) + goto out; - } else - dst_hold(dst); + if (!ip6_sk_accept_pmtu(sk)) + goto out; - if (tp->pmtu_cookie > dst_mtu(dst)) { - tcp_sync_mss(sk, dst_mtu(dst)); - tcp_simple_retransmit(sk); - } /* else let the usual retransmit timer handle it */ - dst_release(dst); + tp->mtu_info = ntohl(info); + if (!sock_owned_by_user(sk)) + tcp_v6_mtu_reduced(sk); + else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, + &tp->tsq_flags)) + sock_hold(sk); goto out; } @@ -782,29 +420,34 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sock_owned_by_user(sk)) goto out; - req = tcp_v6_search_req(sk, &prev, th->dest, &hdr->daddr, - &hdr->saddr, inet6_iif(skb)); + req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, + &hdr->saddr, inet6_iif(skb)); if (!req) goto out; /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ - BUG_TRAP(req->sk == NULL); + WARN_ON(req->sk != NULL); if (seq != tcp_rsk(req)->snt_isn) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: - case TCP_SYN_RECV: /* Cannot happen. - It can, it SYNs are crossed. --ANK */ + case TCP_SYN_RECV: + /* Only in fast or simultaneous open. If a fast open socket is + * is already accepted it is treated as a connected one below. + */ + if (fastopen && fastopen->sk == NULL) + break; + if (!sock_owned_by_user(sk)) { - TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ @@ -826,200 +469,293 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, + struct flowi6 *fl6, + struct request_sock *req, + u16 queue_mapping, + struct tcp_fastopen_cookie *foc) { - struct tcp6_request_sock *treq = tcp6_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); - struct sk_buff * skb; - struct ipv6_txoptions *opt = NULL; - struct in6_addr * final_p = NULL, final; - struct flowi fl; - int err = -1; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.fl6_flowlabel = 0; - fl.oif = treq->iif; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; - - if (dst == NULL) { - opt = np->opt; - if (opt == NULL && - np->rxopt.bits.osrcrt == 2 && - treq->pktopts) { - struct sk_buff *pktopts = treq->pktopts; - struct inet6_skb_parm *rxopt = IP6CB(pktopts); - if (rxopt->srcrt) - opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(pktopts->nh.raw + rxopt->srcrt)); - } + struct sk_buff *skb; + int err = -ENOMEM; - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + /* First, grab a route. */ + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) + goto done; - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto done; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) - goto done; - } + skb = tcp_make_synack(sk, dst, req, foc); - skb = tcp_make_synack(sk, dst, req); if (skb) { - struct tcphdr *th = skb->h.th; + __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, + &ireq->ir_v6_rmt_addr); - th->check = tcp_v6_check(th, skb->len, - &treq->loc_addr, &treq->rmt_addr, - csum_partial((char *)th, skb->len, skb->csum)); + fl6->daddr = ireq->ir_v6_rmt_addr; + if (np->repflow && (ireq->pktopts != NULL)) + fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); - if (err == NET_XMIT_CN) - err = 0; + skb_set_queue_mapping(skb, queue_mapping); + err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); + err = net_xmit_eval(err); } done: - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); return err; } +static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) +{ + struct flowi6 fl6; + int res; + + res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL); + if (!res) { + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } + return res; +} + static void tcp_v6_reqsk_destructor(struct request_sock *req) { - if (tcp6_rsk(req)->pktopts) - kfree_skb(tcp6_rsk(req)->pktopts); + kfree_skb(inet_rsk(req)->pktopts); } -static struct request_sock_ops tcp6_request_sock_ops = { - .family = AF_INET6, - .obj_size = sizeof(struct tcp6_request_sock), - .rtx_syn_ack = tcp_v6_send_synack, - .send_ack = tcp_v6_reqsk_send_ack, - .destructor = tcp_v6_reqsk_destructor, - .send_reset = tcp_v6_send_reset -}; +#ifdef CONFIG_TCP_MD5SIG +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, + const struct in6_addr *addr) +{ + return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6); +} -static int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb) +static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, + struct sock *addr_sk) { - struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_skb_parm *opt = IP6CB(skb); - - if (np->rxopt.all) { - if ((opt->hop && (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || - ((IPV6_FLOWINFO_MASK & *(u32*)skb->nh.raw) && np->rxopt.bits.rxflow) || - (opt->srcrt && (np->rxopt.bits.srcrt || np->rxopt.bits.osrcrt)) || - ((opt->dst1 || opt->dst0) && (np->rxopt.bits.dstopts || np->rxopt.bits.odstopts))) - return 1; - } - return 0; + return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } +static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, + struct request_sock *req) +{ + return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr); +} -static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, - struct sk_buff *skb) +static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, + int optlen) { - struct ipv6_pinfo *np = inet6_sk(sk); + struct tcp_md5sig cmd; + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; - if (skb->ip_summed == CHECKSUM_HW) { - th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); - skb->csum = offsetof(struct tcphdr, check); - } else { - th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, - csum_partial((char *)th, th->doff<<2, - skb->csum)); - } -} + if (optlen < sizeof(cmd)) + return -EINVAL; + if (copy_from_user(&cmd, optval, sizeof(cmd))) + return -EFAULT; -static void tcp_v6_send_reset(struct sk_buff *skb) -{ - struct tcphdr *th = skb->h.th, *t1; - struct sk_buff *buff; - struct flowi fl; + if (sin6->sin6_family != AF_INET6) + return -EINVAL; - if (th->rst) - return; + if (!cmd.tcpm_keylen) { + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], + AF_INET); + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, + AF_INET6); + } - if (!ipv6_unicast_destination(skb)) - return; + if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) + return -EINVAL; - /* - * We need to grab some memory, and put together an RST, - * and then put it into the queue to be sent. - */ + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], + AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); - buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr), - GFP_ATOMIC); - if (buff == NULL) - return; + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, + AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); +} - skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)); +static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, + const struct in6_addr *daddr, + const struct in6_addr *saddr, int nbytes) +{ + struct tcp6_pseudohdr *bp; + struct scatterlist sg; + + bp = &hp->md5_blk.ip6; + /* 1. TCP pseudo-header (RFC2460) */ + bp->saddr = *saddr; + bp->daddr = *daddr; + bp->protocol = cpu_to_be32(IPPROTO_TCP); + bp->len = cpu_to_be32(nbytes); + + sg_init_one(&sg, bp, sizeof(*bp)); + return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp)); +} - t1 = (struct tcphdr *) skb_push(buff,sizeof(struct tcphdr)); +static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, + const struct in6_addr *daddr, struct in6_addr *saddr, + const struct tcphdr *th) +{ + struct tcp_md5sig_pool *hp; + struct hash_desc *desc; + + hp = tcp_get_md5sig_pool(); + if (!hp) + goto clear_hash_noput; + desc = &hp->md5_desc; + + if (crypto_hash_init(desc)) + goto clear_hash; + if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2)) + goto clear_hash; + if (tcp_md5_hash_header(hp, th)) + goto clear_hash; + if (tcp_md5_hash_key(hp, key)) + goto clear_hash; + if (crypto_hash_final(desc, md5_hash)) + goto clear_hash; + + tcp_put_md5sig_pool(); + return 0; - /* Swap the send and the receive. */ - memset(t1, 0, sizeof(*t1)); - t1->dest = th->source; - t1->source = th->dest; - t1->doff = sizeof(*t1)/4; - t1->rst = 1; - - if(th->ack) { - t1->seq = th->ack_seq; +clear_hash: + tcp_put_md5sig_pool(); +clear_hash_noput: + memset(md5_hash, 0, 16); + return 1; +} + +static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, + 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; + const struct tcphdr *th = tcp_hdr(skb); + + if (sk) { + saddr = &inet6_sk(sk)->saddr; + daddr = &sk->sk_v6_daddr; + } else if (req) { + saddr = &inet_rsk(req)->ir_v6_loc_addr; + daddr = &inet_rsk(req)->ir_v6_rmt_addr; } else { - t1->ack = 1; - t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin - + skb->len - (th->doff<<2)); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + saddr = &ip6h->saddr; + daddr = &ip6h->daddr; } - buff->csum = csum_partial((char *)t1, sizeof(*t1), 0); - - memset(&fl, 0, sizeof(fl)); - ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr); - ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr); - - t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst, - sizeof(*t1), IPPROTO_TCP, - buff->csum); + hp = tcp_get_md5sig_pool(); + if (!hp) + goto clear_hash_noput; + desc = &hp->md5_desc; + + if (crypto_hash_init(desc)) + goto clear_hash; + + if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, skb->len)) + goto clear_hash; + if (tcp_md5_hash_header(hp, th)) + goto clear_hash; + if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) + goto clear_hash; + if (tcp_md5_hash_key(hp, key)) + goto clear_hash; + if (crypto_hash_final(desc, md5_hash)) + goto clear_hash; + + tcp_put_md5sig_pool(); + return 0; - fl.proto = IPPROTO_TCP; - fl.oif = inet6_iif(skb); - fl.fl_ip_dport = t1->dest; - fl.fl_ip_sport = t1->source; +clear_hash: + tcp_put_md5sig_pool(); +clear_hash_noput: + memset(md5_hash, 0, 16); + return 1; +} - /* sk = NULL, but it is safe for now. RST socket required. */ - if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) { +static int tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) +{ + const __u8 *hash_location = NULL; + struct tcp_md5sig_key *hash_expected; + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); + int genhash; + u8 newhash[16]; + + hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr); + hash_location = tcp_parse_md5sig_option(th); + + /* We've parsed the options - do we have a hash? */ + if (!hash_expected && !hash_location) + return 0; - if ((xfrm_lookup(&buff->dst, &fl, NULL, 0)) < 0) - return; + if (hash_expected && !hash_location) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + return 1; + } - ip6_xmit(NULL, buff, &fl, NULL, 0); - TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(TCP_MIB_OUTRSTS); - return; + if (!hash_expected && hash_location) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); + return 1; } - kfree_skb(buff); + /* check the signature */ + genhash = tcp_v6_md5_hash_skb(newhash, + hash_expected, + NULL, NULL, skb); + + if (genhash || memcmp(hash_location, newhash, 16) != 0) { + net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", + genhash ? "failed" : "mismatch", + &ip6h->saddr, ntohs(th->source), + &ip6h->daddr, ntohs(th->dest)); + return 1; + } + return 0; } +#endif + +struct request_sock_ops tcp6_request_sock_ops __read_mostly = { + .family = AF_INET6, + .obj_size = sizeof(struct tcp6_request_sock), + .rtx_syn_ack = tcp_v6_rtx_synack, + .send_ack = tcp_v6_reqsk_send_ack, + .destructor = tcp_v6_reqsk_destructor, + .send_reset = tcp_v6_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, +}; -static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts) +#ifdef CONFIG_TCP_MD5SIG +static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { + .md5_lookup = tcp_v6_reqsk_md5_lookup, + .calc_md5_hash = tcp_v6_md5_hash_skb, +}; +#endif + +static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, + u32 tsval, u32 tsecr, int oif, + struct tcp_md5sig_key *key, int rst, u8 tclass, + u32 label) { - struct tcphdr *th = skb->h.th, *t1; + const struct tcphdr *th = tcp_hdr(skb); + struct tcphdr *t1; struct sk_buff *buff; - struct flowi fl; - int tot_len = sizeof(struct tcphdr); + struct flowi6 fl6; + struct net *net = dev_net(skb_dst(skb)->dev); + struct sock *ctl_sk = net->ipv6.tcp_sk; + unsigned int tot_len = sizeof(struct tcphdr); + struct dst_entry *dst; + __be32 *topt; - if (ts) - tot_len += 3*4; + if (tsecr) + tot_len += TCPOLEN_TSTAMP_ALIGNED; +#ifdef CONFIG_TCP_MD5SIG + if (key) + tot_len += TCPOLEN_MD5SIG_ALIGNED; +#endif buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); @@ -1028,205 +764,381 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); - t1 = (struct tcphdr *) skb_push(buff,tot_len); + t1 = (struct tcphdr *) skb_push(buff, tot_len); + skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); t1->dest = th->source; t1->source = th->dest; - t1->doff = tot_len/4; + t1->doff = tot_len / 4; t1->seq = htonl(seq); t1->ack_seq = htonl(ack); - t1->ack = 1; + t1->ack = !rst || !th->ack; + t1->rst = rst; t1->window = htons(win); - - if (ts) { - u32 *ptr = (u32*)(t1 + 1); - *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | - (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - *ptr++ = htonl(tcp_time_stamp); - *ptr = htonl(ts); + + topt = (__be32 *)(t1 + 1); + + if (tsecr) { + *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *topt++ = htonl(tsval); + *topt++ = htonl(tsecr); } - buff->csum = csum_partial((char *)t1, tot_len, 0); +#ifdef CONFIG_TCP_MD5SIG + if (key) { + *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); + tcp_v6_md5_hash_hdr((__u8 *)topt, key, + &ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, t1); + } +#endif - memset(&fl, 0, sizeof(fl)); - ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr); - ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr); + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = ipv6_hdr(skb)->saddr; + fl6.saddr = ipv6_hdr(skb)->daddr; + fl6.flowlabel = label; + + buff->ip_summed = CHECKSUM_PARTIAL; + buff->csum = 0; + + __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); + + fl6.flowi6_proto = IPPROTO_TCP; + if (rt6_need_strict(&fl6.daddr) && !oif) + fl6.flowi6_oif = inet6_iif(skb); + else + fl6.flowi6_oif = oif; + fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); + fl6.fl6_dport = t1->dest; + fl6.fl6_sport = t1->source; + security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); + + /* Pass a socket to ip6_dst_lookup either it is for RST + * Underlying function will use this to retrieve the network + * namespace + */ + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + if (!IS_ERR(dst)) { + skb_dst_set(buff, dst); + 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); + return; + } - t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst, - tot_len, IPPROTO_TCP, - buff->csum); + kfree_skb(buff); +} - fl.proto = IPPROTO_TCP; - fl.oif = inet6_iif(skb); - fl.fl_ip_dport = t1->dest; - fl.fl_ip_sport = t1->source; +static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +{ + const struct tcphdr *th = tcp_hdr(skb); + u32 seq = 0, ack_seq = 0; + struct tcp_md5sig_key *key = NULL; +#ifdef CONFIG_TCP_MD5SIG + const __u8 *hash_location = NULL; + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; +#endif + int oif; - if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) { - if ((xfrm_lookup(&buff->dst, &fl, NULL, 0)) < 0) - return; - ip6_xmit(NULL, buff, &fl, NULL, 0); - TCP_INC_STATS_BH(TCP_MIB_OUTSEGS); + if (th->rst) + return; + + if (!ipv6_unicast_destination(skb)) return; + +#ifdef CONFIG_TCP_MD5SIG + hash_location = tcp_parse_md5sig_option(th); + if (!sk && hash_location) { + /* + * active side is lost. Try to find listening socket through + * source port, and then find md5 key through listening socket. + * we are not loose security here: + * Incoming packet is checked with md5 hash with finding key, + * no RST generated if md5 hash doesn't match. + */ + sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), + &tcp_hashinfo, &ipv6h->saddr, + th->source, &ipv6h->daddr, + ntohs(th->source), inet6_iif(skb)); + if (!sk1) + return; + + rcu_read_lock(); + key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr); + if (!key) + goto release_sk1; + + genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto release_sk1; + } else { + key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL; } +#endif - kfree_skb(buff); + if (th->ack) + seq = ntohl(th->ack_seq); + else + ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - + (th->doff << 2); + + oif = sk ? sk->sk_bound_dev_if : 0; + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); + +#ifdef CONFIG_TCP_MD5SIG +release_sk1: + if (sk1) { + rcu_read_unlock(); + sock_put(sk1); + } +#endif +} + +static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, + u32 win, u32 tsval, u32 tsecr, int oif, + struct tcp_md5sig_key *key, u8 tclass, + u32 label) +{ + tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass, + label); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) { struct inet_timewait_sock *tw = inet_twsk(sk); - const struct tcp_timewait_sock *tcptw = tcp_twsk(sk); + struct tcp_timewait_sock *tcptw = tcp_twsk(sk); 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_time_stamp + tcptw->tw_ts_offset, + tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), + tw->tw_tclass, (tw->tw_flowlabel << 12)); inet_twsk_put(tw); } -static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) +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); + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV + * sk->sk_state == TCP_SYN_RECV -> for Fast Open. + */ + tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? + tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + tcp_rsk(req)->rcv_nxt, + req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), + 0, 0); } -static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) +static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) { struct request_sock *req, **prev; - const struct tcphdr *th = skb->h.th; + const struct tcphdr *th = tcp_hdr(skb); struct sock *nsk; /* Find possible connection requests. */ - req = tcp_v6_search_req(sk, &prev, th->source, &skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr, inet6_iif(skb)); + req = inet6_csk_search_req(sk, &prev, th->source, + &ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, inet6_iif(skb)); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); - nsk = __inet6_lookup_established(&tcp_hashinfo, &skb->nh.ipv6h->saddr, - th->source, &skb->nh.ipv6h->daddr, - ntohs(th->dest), inet6_iif(skb)); + nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, + &ipv6_hdr(skb)->saddr, th->source, + &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); if (nsk) { if (nsk->sk_state != TCP_TIME_WAIT) { bh_lock_sock(nsk); return nsk; } - inet_twsk_put((struct inet_timewait_sock *)nsk); + inet_twsk_put(inet_twsk(nsk)); return NULL; } -#if 0 /*def CONFIG_SYN_COOKIES*/ - if (!th->rst && !th->syn && th->ack) - sk = cookie_v6_check(sk, skb, &(IPCB(skb)->opt)); +#ifdef CONFIG_SYN_COOKIES + if (!th->syn) + sk = cookie_v6_check(sk, skb); #endif return sk; } -static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - const u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); - - reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, TCP_TIMEOUT_INIT); - inet_csk_reqsk_queue_added(sk, TCP_TIMEOUT_INIT); -} - - /* FIXME: this is substantially similar to the ipv4 code. * Can some kind of merge be done? -- erics */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { - struct tcp6_request_sock *treq; - struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_options_received tmp_opt; + struct request_sock *req; + struct inet_request_sock *ireq; + struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req = NULL; __u32 isn = TCP_SKB_CB(skb)->when; + struct dst_entry *dst = NULL; + struct tcp_fastopen_cookie foc = { .len = -1 }; + bool want_cookie = false, fastopen; + struct flowi6 fl6; + int err; if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) - goto drop; + goto drop; - /* - * There are no SYN attacks on IPv6, yet... - */ - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { - if (net_ratelimit()) - printk(KERN_INFO "TCPv6: dropping request, synflood is possible\n"); - goto drop; + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { + want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); + if (!want_cookie) + goto drop; } - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } - req = reqsk_alloc(&tcp6_request_sock_ops); + req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) goto drop; +#ifdef CONFIG_TCP_MD5SIG + tcp_rsk(req)->af_specific = &tcp_request_sock_ipv6_ops; +#endif + tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); - tcp_parse_options(skb, &tmp_opt, 0); + if (want_cookie && !tmp_opt.saw_tstamp) + tcp_clear_options(&tmp_opt); tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); - treq = tcp6_rsk(req); - ipv6_addr_copy(&treq->rmt_addr, &skb->nh.ipv6h->saddr); - ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr); - TCP_ECN_create_request(req, skb->h.th); - treq->pktopts = NULL; - if (ipv6_opt_accepted(sk, skb) || - np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || - np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { - atomic_inc(&skb->users); - treq->pktopts = skb; - } - treq->iif = sk->sk_bound_dev_if; + ireq = inet_rsk(req); + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + if (!want_cookie || tmp_opt.tstamp_ok) + TCP_ECN_create_request(req, skb, sock_net(sk)); + + ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_mark = inet_request_mark(sk, skb); /* 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); + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); + + if (!isn) { + if (ipv6_opt_accepted(sk, skb) || + np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || + np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || + np->repflow) { + atomic_inc(&skb->users); + ireq->pktopts = skb; + } - if (isn == 0) - isn = tcp_v6_init_sequence(sk,skb); + if (want_cookie) { + isn = cookie_v6_init_sequence(sk, skb, &req->mss); + req->cookie_ts = tmp_opt.tstamp_ok; + goto have_isn; + } - tcp_rsk(req)->snt_isn = isn; + /* VJ's idea. We save last timestamp seen + * from the destination in peer table, when entering + * state TIME-WAIT, and check against it before + * accepting new connection request. + * + * If "isn" is not zero, this request hit alive + * timewait bucket, so that all the necessary checks + * are made in the function processing timewait state. + */ + if (tmp_opt.saw_tstamp && + tcp_death_row.sysctl_tw_recycle && + (dst = inet6_csk_route_req(sk, &fl6, req)) != NULL) { + if (!tcp_peer_is_proven(req, dst, true)) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); + goto drop_and_release; + } + } + /* Kill the following clause, if you dislike this way. */ + else if (!sysctl_tcp_syncookies && + (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (sysctl_max_syn_backlog >> 2)) && + !tcp_peer_is_proven(req, dst, false)) { + /* Without syncookies last quarter of + * backlog is filled with destinations, + * proven to be alive. + * It means that we continue to communicate + * to destinations, already remembered + * to the moment of synflood. + */ + LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n", + &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source)); + goto drop_and_release; + } - if (tcp_v6_send_synack(sk, req, NULL)) - goto drop; + isn = tcp_v6_init_sequence(skb); + } +have_isn: - tcp_v6_synq_add(sk, req); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_release; + if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL) + goto drop_and_free; + + tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_openreq_init_rwin(req, sk, dst); + fastopen = !want_cookie && + tcp_try_fastopen(sk, skb, req, &foc, dst); + err = tcp_v6_send_synack(sk, dst, &fl6, req, + skb_get_queue_mapping(skb), &foc); + if (!fastopen) { + if (err || want_cookie) + goto drop_and_free; + + tcp_rsk(req)->listener = NULL; + inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + } return 0; +drop_and_release: + dst_release(dst); +drop_and_free: + reqsk_free(req); drop: - if (req) - reqsk_free(req); - - TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ } -static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) { - struct tcp6_request_sock *treq = tcp6_rsk(req); + struct inet_request_sock *ireq; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; - struct ipv6_txoptions *opt; +#ifdef CONFIG_TCP_MD5SIG + struct tcp_md5sig_key *key; +#endif + struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* @@ -1235,7 +1147,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst); - if (newsk == NULL) + if (newsk == NULL) return NULL; newtcp6sk = (struct tcp6_sock *)newsk; @@ -1247,20 +1159,27 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), - newinet->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newsk->sk_v6_rcv_saddr = newnp->saddr; - newtp->af_specific = &ipv6_mapped; + inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; +#ifdef CONFIG_TCP_MD5SIG + newtp->af_specific = &tcp_sock_ipv6_mapped_specific; +#endif + + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); - newnp->mcast_hops = skb->nh.ipv6h->hop_limit; + newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1269,57 +1188,28 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ /* It is tricky place. Until this moment IPv4 tcp - worked with IPv6 af_tcp.af_specific. + worked with IPv6 icsk.icsk_af_ops. Sync it now. */ - tcp_sync_mss(newsk, newtp->pmtu_cookie); + tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } - opt = np->opt; + ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto out_overflow; - if (np->rxopt.bits.osrcrt == 2 && - opt == NULL && treq->pktopts) { - struct inet6_skb_parm *rxopt = IP6CB(treq->pktopts); - if (rxopt->srcrt) - opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(treq->pktopts->nh.raw + rxopt->srcrt)); - } - - if (dst == NULL) { - struct in6_addr *final_p = NULL, final; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } - ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; - - if (ip6_dst_lookup(sk, &dst, &fl)) + if (!dst) { + dst = inet6_csk_route_req(sk, &fl6, req); + if (!dst) goto out; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) - goto out; - } + } newsk = tcp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto out; + goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -1327,9 +1217,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * comment in that function for the gory details. -acme */ - ip6_dst_store(newsk, dst, NULL); - newsk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); + newsk->sk_gso_type = SKB_GSO_TCPV6; + __ip6_dst_store(newsk, dst, NULL, NULL); + inet6_sk_rx_dst_set(newsk, skb); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; @@ -1340,32 +1230,38 @@ 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); - newsk->sk_bound_dev_if = treq->iif; + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; + newnp->saddr = ireq->ir_v6_loc_addr; + newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; + newsk->sk_bound_dev_if = ireq->ir_iif; - /* Now IPv6 options... + /* Now IPv6 options... First: no IPv4 options. */ - newinet->opt = NULL; + newinet->inet_opt = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (treq->pktopts != NULL) { - newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); - kfree_skb(treq->pktopts); - treq->pktopts = NULL; + if (ireq->pktopts != NULL) { + newnp->pktoptions = skb_clone(ireq->pktopts, + sk_gfp_atomic(sk, GFP_ATOMIC)); + consume_skb(ireq->pktopts); + ireq->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); } newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); - newnp->mcast_hops = skb->nh.ipv6h->hop_limit; + newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1373,59 +1269,58 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, but we make one more one thing there: reattach optmem to newsk. */ - if (opt) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt) + newnp->opt = ipv6_dup_options(newsk, np->opt); - newtp->ext_header_len = 0; + inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt) - newtp->ext_header_len = newnp->opt->opt_nflen + - newnp->opt->opt_flen; + inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + + newnp->opt->opt_flen); tcp_sync_mss(newsk, dst_mtu(dst)); - newtp->advmss = dst_metric(dst, RTAX_ADVMSS); + newtp->advmss = dst_metric_advmss(dst); + if (tcp_sk(sk)->rx_opt.user_mss && + tcp_sk(sk)->rx_opt.user_mss < newtp->advmss) + newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; + tcp_initialize_rcv_mss(newsk); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; + +#ifdef CONFIG_TCP_MD5SIG + /* Copy over the MD5 key from the original socket */ + key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr); + if (key != NULL) { + /* We're using one, so create a matching key + * on the newsk structure. If we fail to get + * memory, then we end up not copying the key + * across. Shucks. + */ + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, + AF_INET6, key->key, key->keylen, + sk_gfp_atomic(sk, GFP_ATOMIC)); + } +#endif - __tcp_v6_hash(newsk); - inet_inherit_port(&tcp_hashinfo, sk, newsk); + if (__inet_inherit_port(sk, newsk) < 0) { + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); + goto out; + } + __inet6_hash(newsk, NULL); return newsk; out_overflow: - NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); -out: - NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); - if (opt && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +out_nonewsk: dst_release(dst); +out: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; } -static int tcp_v6_checksum_init(struct sk_buff *skb) -{ - if (skb->ip_summed == CHECKSUM_HW) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr,skb->csum)) - return 0; - LIMIT_NETDEBUG(KERN_DEBUG "hw tcp v6 csum failed\n"); - } - if (skb->len <= 76) { - if (tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr,skb_checksum(skb, 0, skb->len, 0))) - return -1; - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else { - skb->csum = ~tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr,0); - } - return 0; -} - /* The socket must have it's spinlock held when we get * here. * @@ -1451,7 +1346,12 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb, 0)) +#ifdef CONFIG_TCP_MD5SIG + if (tcp_v6_inbound_md5_hash(sk, skb)) + goto discard; +#endif + + if (sk_filter(sk, skb)) goto discard; /* @@ -1470,25 +1370,33 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. - --ANK (980728) + --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - TCP_CHECK_TIMER(sk); - if (tcp_rcv_established(sk, skb, skb->h.th, skb->len)) - goto reset; - TCP_CHECK_TIMER(sk); + struct dst_entry *dst = sk->sk_rx_dst; + + sock_rps_save_rxhash(sk, skb); + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + dst_release(dst); + sk->sk_rx_dst = NULL; + } + } + + tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len); if (opt_skb) goto ipv6_pktoptions; return 0; } - if (skb->len < (skb->h.th->doff<<2) || tcp_checksum_complete(skb)) + if (skb->len < tcp_hdrlen(skb) || tcp_checksum_complete(skb)) goto csum_err; - if (sk->sk_state == TCP_LISTEN) { + if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_hnd_req(sk, skb); if (!nsk) goto discard; @@ -1498,32 +1406,33 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * otherwise we just shortcircuit this and continue with * the new socket.. */ - if(nsk != sk) { + if (nsk != sk) { + sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) __kfree_skb(opt_skb); return 0; } - } + } else + sock_rps_save_rxhash(sk, skb); - TCP_CHECK_TIMER(sk); - if (tcp_rcv_state_process(sk, skb, skb->h.th, skb->len)) + if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) goto reset; - TCP_CHECK_TIMER(sk); if (opt_skb) goto ipv6_pktoptions; return 0; reset: - tcp_v6_send_reset(skb); + tcp_v6_send_reset(sk, skb); discard: if (opt_skb) __kfree_skb(opt_skb); kfree_skb(skb); return 0; csum_err: - TCP_INC_STATS_BH(TCP_MIB_INERRS); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); goto discard; @@ -1541,7 +1450,11 @@ ipv6_pktoptions: if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) np->mcast_oif = inet6_iif(opt_skb); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) - np->mcast_hops = opt_skb->nh.ipv6h->hop_limit; + np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; + if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) + np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); + if (np->repflow) + np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1551,17 +1464,17 @@ ipv6_pktoptions: } } - if (opt_skb) - kfree_skb(opt_skb); + kfree_skb(opt_skb); return 0; } -static int tcp_v6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) +static int tcp_v6_rcv(struct sk_buff *skb) { - struct sk_buff *skb = *pskb; - struct tcphdr *th; + const struct tcphdr *th; + const struct ipv6hdr *hdr; struct sock *sk; int ret; + struct net *net = dev_net(skb->dev); if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -1569,35 +1482,32 @@ static int tcp_v6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) /* * Count it even if it's bad. */ - TCP_INC_STATS_BH(TCP_MIB_INSEGS); + TCP_INC_STATS_BH(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; - th = skb->h.th; + th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr)/4) goto bad_packet; if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; - if ((skb->ip_summed != CHECKSUM_UNNECESSARY && - tcp_v6_checksum_init(skb) < 0)) - goto bad_packet; + if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) + goto csum_error; - th = skb->h.th; + th = tcp_hdr(skb); + hdr = ipv6_hdr(skb); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + 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(skb->nh.ipv6h); + TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; - sk = __inet6_lookup(&tcp_hashinfo, &skb->nh.ipv6h->saddr, th->source, - &skb->nh.ipv6h->daddr, ntohs(th->dest), - inet6_iif(skb)); - + sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest); if (!sk) goto no_tcp_socket; @@ -1605,21 +1515,41 @@ process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; + if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) { + NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP); + goto discard_and_relse; + } + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; + sk_mark_napi_id(sk, skb); skb->dev = NULL; - bh_lock_sock(sk); + bh_lock_sock_nested(sk); ret = 0; if (!sock_owned_by_user(sk)) { - if (!tcp_prequeue(sk, skb)) +#ifdef CONFIG_NET_DMA + struct tcp_sock *tp = tcp_sk(sk); + if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list) + tp->ucopy.dma_chan = net_dma_find_channel(); + if (tp->ucopy.dma_chan) ret = tcp_v6_do_rcv(sk, skb); - } else - sk_add_backlog(sk, skb); + else +#endif + { + if (!tcp_prequeue(sk, skb)) + ret = tcp_v6_do_rcv(sk, skb); + } + } else if (unlikely(sk_add_backlog(sk, skb, + sk->sk_rcvbuf + sk->sk_sndbuf))) { + bh_unlock_sock(sk); + NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP); + goto discard_and_relse; + } bh_unlock_sock(sk); sock_put(sk); @@ -1630,18 +1560,15 @@ no_tcp_socket: goto discard_it; if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { +csum_error: + TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); bad_packet: - TCP_INC_STATS_BH(TCP_MIB_INERRS); + TCP_INC_STATS_BH(net, TCP_MIB_INERRS); } else { - tcp_v6_send_reset(skb); + tcp_v6_send_reset(NULL, skb); } discard_it: - - /* - * Discard frame - */ - kfree_skb(skb); return 0; @@ -1651,24 +1578,27 @@ discard_and_relse: do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - inet_twsk_put((struct inet_timewait_sock *)sk); + inet_twsk_put(inet_twsk(sk)); goto discard_it; } - if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { - TCP_INC_STATS_BH(TCP_MIB_INERRS); - inet_twsk_put((struct inet_timewait_sock *)sk); - goto discard_it; + if (skb->len < (th->doff<<2)) { + inet_twsk_put(inet_twsk(sk)); + goto bad_packet; + } + if (tcp_checksum_complete(skb)) { + inet_twsk_put(inet_twsk(sk)); + goto csum_error; } - switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk, - skb, th)) { + switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2; - sk2 = inet6_lookup_listener(&tcp_hashinfo, - &skb->nh.ipv6h->daddr, + sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + &ipv6_hdr(skb)->saddr, th->source, + &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); if (sk2 != NULL) { struct inet_timewait_sock *tw = inet_twsk(sk); @@ -1684,175 +1614,112 @@ do_time_wait: break; case TCP_TW_RST: goto no_tcp_socket; - case TCP_TW_SUCCESS:; + case TCP_TW_SUCCESS: + ; } goto discard_it; } -static int tcp_v6_rebuild_header(struct sock *sk) -{ - int err; - struct dst_entry *dst; - struct ipv6_pinfo *np = inet6_sk(sk); - - dst = __sk_dst_check(sk, np->dst_cookie); - - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct in6_addr *final_p = NULL, final; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl6_flowlabel = np->flow_label; - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } - - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) { - sk->sk_route_caps = 0; - return err; - } - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { - sk->sk_err_soft = -err; - return err; - } - - ip6_dst_store(sk, dst, NULL); - sk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); - } - - return 0; -} - -static int tcp_v6_xmit(struct sk_buff *skb, int ipfragok) +static void tcp_v6_early_demux(struct sk_buff *skb) { - struct sock *sk = skb->sk; - struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi fl; - struct dst_entry *dst; - struct in6_addr *final_p = NULL, final; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl6_flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_sport = inet->sport; - fl.fl_ip_dport = inet->dport; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + const struct ipv6hdr *hdr; + const struct tcphdr *th; + struct sock *sk; - dst = __sk_dst_check(sk, np->dst_cookie); + if (skb->pkt_type != PACKET_HOST) + return; - if (dst == NULL) { - int err = ip6_dst_lookup(sk, &dst, &fl); + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) + return; - if (err) { - sk->sk_err_soft = -err; - return err; - } + hdr = ipv6_hdr(skb); + th = tcp_hdr(skb); - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); + if (th->doff < sizeof(struct tcphdr) / 4) + return; - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { - sk->sk_route_caps = 0; - return err; + sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + inet6_iif(skb)); + if (sk) { + skb->sk = sk; + skb->destructor = sock_edemux; + if (sk->sk_state != TCP_TIME_WAIT) { + struct dst_entry *dst = sk->sk_rx_dst; + + if (dst) + dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + if (dst && + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) + skb_dst_set_noref(skb, dst); } - - ip6_dst_store(sk, dst, NULL); - sk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); } - - skb->dst = dst_clone(dst); - - /* Restore final destination back after routing done */ - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - - return ip6_xmit(sk, skb, &fl, np->opt, 0); } -static void v6_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; - - sin6->sin6_family = AF_INET6; - ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); - sin6->sin6_port = inet_sk(sk)->dport; - /* We do not store received flowlabel for TCP */ - sin6->sin6_flowinfo = 0; - sin6->sin6_scope_id = 0; - if (sk->sk_bound_dev_if && - ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin6->sin6_scope_id = sk->sk_bound_dev_if; -} +static struct timewait_sock_ops tcp6_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct tcp6_timewait_sock), + .twsk_unique = tcp_twsk_unique, + .twsk_destructor = tcp_twsk_destructor, +}; -static int tcp_v6_remember_stamp(struct sock *sk) -{ - /* Alas, not yet... */ - return 0; -} +static const struct inet_connection_sock_af_ops ipv6_specific = { + .queue_xmit = inet6_csk_xmit, + .send_check = tcp_v6_send_check, + .rebuild_header = inet6_sk_rebuild_header, + .sk_rx_dst_set = inet6_sk_rx_dst_set, + .conn_request = tcp_v6_conn_request, + .syn_recv_sock = tcp_v6_syn_recv_sock, + .net_header_len = sizeof(struct ipv6hdr), + .net_frag_header_len = sizeof(struct frag_hdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6), + .bind_conflict = inet6_csk_bind_conflict, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif +}; -static struct tcp_func ipv6_specific = { - .queue_xmit = tcp_v6_xmit, - .send_check = tcp_v6_send_check, - .rebuild_header = tcp_v6_rebuild_header, - .conn_request = tcp_v6_conn_request, - .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v6_remember_stamp, - .net_header_len = sizeof(struct ipv6hdr), - - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = v6_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) +#ifdef CONFIG_TCP_MD5SIG +static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { + .md5_lookup = tcp_v6_md5_lookup, + .calc_md5_hash = tcp_v6_md5_hash_skb, + .md5_parse = tcp_v6_parse_md5_keys, }; +#endif /* * TCP over IPv4 via INET6 API */ - -static struct tcp_func ipv6_mapped = { - .queue_xmit = ip_queue_xmit, - .send_check = tcp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = tcp_v6_conn_request, - .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v4_remember_stamp, - .net_header_len = sizeof(struct iphdr), - - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = v6_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) +static const struct inet_connection_sock_af_ops ipv6_mapped = { + .queue_xmit = ip_queue_xmit, + .send_check = tcp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .sk_rx_dst_set = inet_sk_rx_dst_set, + .conn_request = tcp_v6_conn_request, + .syn_recv_sock = tcp_v6_syn_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6), + .bind_conflict = inet6_csk_bind_conflict, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif }; - +#ifdef CONFIG_TCP_MD5SIG +static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { + .md5_lookup = tcp_v4_md5_lookup, + .calc_md5_hash = tcp_v4_md5_hash_skb, + .md5_parse = tcp_v6_parse_md5_keys, +}; +#endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. @@ -1860,100 +1727,72 @@ static struct tcp_func ipv6_mapped = { static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - - skb_queue_head_init(&tp->out_of_order_queue); - tcp_init_xmit_timers(sk); - tcp_prequeue_init(tp); - - icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; - - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - tp->snd_cwnd = 2; - - /* See draft-stevens-tcpca-spec-01 for discussion of the - * initialization of these values. - */ - tp->snd_ssthresh = 0x7fffffff; - tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; - - tp->reordering = sysctl_tcp_reordering; - sk->sk_state = TCP_CLOSE; + tcp_init_sock(sk); - tp->af_specific = &ipv6_specific; - icsk->icsk_ca_ops = &tcp_init_congestion_ops; - sk->sk_write_space = sk_stream_write_space; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + icsk->icsk_af_ops = &ipv6_specific; - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - - atomic_inc(&tcp_sockets_allocated); +#ifdef CONFIG_TCP_MD5SIG + tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; +#endif return 0; } -static int tcp_v6_destroy_sock(struct sock *sk) +static void tcp_v6_destroy_sock(struct sock *sk) { tcp_v4_destroy_sock(sk); - return inet6_destroy_sock(sk); + inet6_destroy_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) +static void get_openreq6(struct seq_file *seq, + const struct sock *sk, struct request_sock *req, int i, kuid_t uid) { - struct in6_addr *dest, *src; int ttd = req->expires - jiffies; + const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; + const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; - src = &tcp6_rsk(req)->loc_addr; - dest = &tcp6_rsk(req)->rmt_addr; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], - ntohs(inet_sk(sk)->sport), + inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], - ntohs(inet_rsk(req)->rmt_port), + ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, - 0,0, /* could print option size, but that is af dependent. */ - 1, /* timers active (only the expire timer) */ - jiffies_to_clock_t(ttd), - req->retrans, - uid, - 0, /* non standard timer */ + 0, 0, /* could print option size, but that is af dependent. */ + 1, /* timers active (only the expire timer) */ + jiffies_to_clock_t(ttd), + req->num_timeout, + from_kuid_munged(seq_user_ns(seq), uid), + 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __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); + struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; - dest = &np->daddr; - src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -1971,61 +1810,61 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %u %u %u %u %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - tp->write_seq-tp->snd_una, tp->rcv_nxt-tp->copied_seq, + sp->sk_state, + tp->write_seq-tp->snd_una, + (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, - sock_i_uid(sp), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, - icsk->icsk_rto, - icsk->icsk_ack.ato, - (icsk->icsk_ack.quick << 1 ) | icsk->icsk_ack.pingpong, - tp->snd_cwnd, tp->snd_ssthresh>=0xFFFF?-1:tp->snd_ssthresh + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), + (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, + tp->snd_cwnd, + sp->sk_state == TCP_LISTEN ? + (fastopenq ? fastopenq->max_qlen : 0) : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } -static void get_timewait6_sock(struct seq_file *seq, +static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { - struct in6_addr *dest, *src; + const struct in6_addr *dest, *src; __u16 destp, srcp; - struct tcp6_timewait_sock *tcp6tw = tcp6_twsk((struct sock *)tw); - int ttd = tw->tw_ttd - jiffies; + s32 delta = tw->tw_ttd - inet_tw_time_stamp(); - if (ttd < 0) - ttd = 0; - - dest = &tcp6tw->tw_v6_daddr; - src = &tcp6tw->tw_v6_rcv_saddr; + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw); } -#ifdef CONFIG_PROC_FS static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; + struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -2041,39 +1880,58 @@ static int tcp6_seq_show(struct seq_file *seq, void *v) switch (st->state) { case TCP_SEQ_STATE_LISTENING: case TCP_SEQ_STATE_ESTABLISHED: - get_tcp6_sock(seq, v, st->num); + if (sk->sk_state == TCP_TIME_WAIT) + get_timewait6_sock(seq, v, st->num); + else + get_tcp6_sock(seq, v, st->num); break; case TCP_SEQ_STATE_OPENREQ: get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid); break; - case TCP_SEQ_STATE_TIME_WAIT: - get_timewait6_sock(seq, v, st->num); - break; } out: return 0; } -static struct file_operations tcp6_seq_fops; +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 = { - .owner = THIS_MODULE, .name = "tcp6", .family = AF_INET6, - .seq_show = tcp6_seq_show, - .seq_fops = &tcp6_seq_fops, + .seq_fops = &tcp6_afinfo_seq_fops, + .seq_ops = { + .show = tcp6_seq_show, + }, }; -int __init tcp6_proc_init(void) +int __net_init tcp6_proc_init(struct net *net) { - return tcp_proc_register(&tcp6_seq_afinfo); + return tcp_proc_register(net, &tcp6_seq_afinfo); } -void tcp6_proc_exit(void) +void tcp6_proc_exit(struct net *net) { - tcp_proc_unregister(&tcp6_seq_afinfo); + tcp_proc_unregister(net, &tcp6_seq_afinfo); } #endif +static void tcp_v6_clear_sk(struct sock *sk, int size) +{ + struct inet_sock *inet = inet_sk(sk); + + /* we do not want to clear pinet6 field, because of RCU lookups */ + sk_prot_clear_nulls(sk, offsetof(struct inet_sock, pinet6)); + + size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); + memset(&inet->pinet6 + 1, 0, size); +} + struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, @@ -2087,13 +1945,17 @@ struct proto tcpv6_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, - .sendmsg = tcp_sendmsg, .recvmsg = tcp_recvmsg, + .sendmsg = tcp_sendmsg, + .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, + .release_cb = tcp_release_cb, + .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, - .unhash = tcp_unhash, - .get_port = tcp_v6_get_port, + .unhash = inet_unhash, + .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, @@ -2103,11 +1965,23 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), - .twsk_obj_size = sizeof(struct tcp6_timewait_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, + .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, + .h.hashinfo = &tcp_hashinfo, + .no_autobind = true, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_tcp_setsockopt, + .compat_getsockopt = compat_tcp_getsockopt, +#endif +#ifdef CONFIG_MEMCG_KMEM + .proto_cgroup = tcp_proto_cgroup, +#endif + .clear_sk = tcp_v6_clear_sk, }; -static struct inet6_protocol tcpv6_protocol = { +static const struct inet6_protocol tcpv6_protocol = { + .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, @@ -2118,15 +1992,61 @@ static struct inet_protosw tcpv6_protosw = { .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .capability = -1, - .no_check = 0, - .flags = INET_PROTOSW_PERMANENT, + .flags = INET_PROTOSW_PERMANENT | + INET_PROTOSW_ICSK, }; -void __init tcpv6_init(void) +static int __net_init tcpv6_net_init(struct net *net) +{ + return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, + SOCK_RAW, IPPROTO_TCP, net); +} + +static void __net_exit tcpv6_net_exit(struct net *net) +{ + inet_ctl_sock_destroy(net->ipv6.tcp_sk); +} + +static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) { + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); +} + +static struct pernet_operations tcpv6_net_ops = { + .init = tcpv6_net_init, + .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, +}; + +int __init tcpv6_init(void) +{ + int ret; + + ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP); + if (ret) + goto out; + /* register inet6 protocol */ - if (inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP) < 0) - printk(KERN_ERR "tcpv6_init: Could not register protocol\n"); - inet6_register_protosw(&tcpv6_protosw); + ret = inet6_register_protosw(&tcpv6_protosw); + if (ret) + goto out_tcpv6_protocol; + + ret = register_pernet_subsys(&tcpv6_net_ops); + if (ret) + goto out_tcpv6_protosw; +out: + return ret; + +out_tcpv6_protosw: + inet6_unregister_protosw(&tcpv6_protosw); +out_tcpv6_protocol: + inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + goto out; +} + +void tcpv6_exit(void) +{ + unregister_pernet_subsys(&tcpv6_net_ops); + inet6_unregister_protosw(&tcpv6_protosw); + inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c new file mode 100644 index 00000000000..01b0ff9a0c2 --- /dev/null +++ b/net/ipv6/tcpv6_offload.c @@ -0,0 +1,93 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * 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. + * + * TCPv6 GSO/GRO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/tcp.h> +#include <net/ip6_checksum.h> +#include "ip6_offload.h" + +static int tcp_v6_gso_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + struct tcphdr *th; + + if (!pskb_may_pull(skb, sizeof(*th))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + th = tcp_hdr(skb); + + th->check = 0; + skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); + return 0; +} + +static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + __wsum wsum; + + /* Don't bother verifying checksum if we're going to flush anyway. */ + if (NAPI_GRO_CB(skb)->flush) + goto skip_csum; + + wsum = NAPI_GRO_CB(skb)->csum; + + switch (skb->ip_summed) { + case CHECKSUM_NONE: + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), + wsum); + + /* fall through */ + + case CHECKSUM_COMPLETE: + if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, + wsum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + +skip_csum: + return tcp_gro_receive(head, skb); +} + +static int tcp6_gro_complete(struct sk_buff *skb, int thoff) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, + &iph->daddr, 0); + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + + return tcp_gro_complete(skb); +} + +static const struct net_offload tcpv6_offload = { + .callbacks = { + .gso_send_check = tcp_v6_gso_send_check, + .gso_segment = tcp_gso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, +}; + +int __init tcpv6_offload_init(void) +{ + return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); +} diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c new file mode 100644 index 00000000000..2c4e4c5c761 --- /dev/null +++ b/net/ipv6/tunnel6.c @@ -0,0 +1,185 @@ +/* + * Copyright (C)2003,2004 USAGI/WIDE Project + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + * + * Authors Mitsuru KANDA <mk@linux-ipv6.org> + * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> + */ + +#define pr_fmt(fmt) "IPv6: " fmt + +#include <linux/icmpv6.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm6_tunnel __rcu *tunnel6_handlers __read_mostly; +static struct xfrm6_tunnel __rcu *tunnel46_handlers __read_mostly; +static DEFINE_MUTEX(tunnel6_mutex); + +int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family) +{ + struct xfrm6_tunnel __rcu **pprev; + struct xfrm6_tunnel *t; + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&tunnel6_mutex); + + for (pprev = (family == AF_INET6) ? &tunnel6_handlers : &tunnel46_handlers; + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&tunnel6_mutex))) != NULL; + pprev = &t->next) { + if (t->priority > priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&tunnel6_mutex); + + return ret; +} + +EXPORT_SYMBOL(xfrm6_tunnel_register); + +int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) +{ + struct xfrm6_tunnel __rcu **pprev; + struct xfrm6_tunnel *t; + int ret = -ENOENT; + + mutex_lock(&tunnel6_mutex); + + for (pprev = (family == AF_INET6) ? &tunnel6_handlers : &tunnel46_handlers; + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&tunnel6_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + mutex_unlock(&tunnel6_mutex); + + synchronize_net(); + + return ret; +} + +EXPORT_SYMBOL(xfrm6_tunnel_deregister); + +#define for_each_tunnel_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +static int tunnel6_rcv(struct sk_buff *skb) +{ + struct xfrm6_tunnel *handler; + + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto drop; + + for_each_tunnel_rcu(tunnel6_handlers, handler) + if (!handler->handler(skb)) + return 0; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + +drop: + kfree_skb(skb); + return 0; +} + +static int tunnel46_rcv(struct sk_buff *skb) +{ + struct xfrm6_tunnel *handler; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto drop; + + for_each_tunnel_rcu(tunnel46_handlers, handler) + if (!handler->handler(skb)) + return 0; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + +drop: + kfree_skb(skb); + return 0; +} + +static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_tunnel *handler; + + for_each_tunnel_rcu(tunnel6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static const struct inet6_protocol tunnel6_protocol = { + .handler = tunnel6_rcv, + .err_handler = tunnel6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +static const struct inet6_protocol tunnel46_protocol = { + .handler = tunnel46_rcv, + .err_handler = tunnel6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +static int __init tunnel6_init(void) +{ + if (inet6_add_protocol(&tunnel6_protocol, IPPROTO_IPV6)) { + pr_err("%s: can't add protocol\n", __func__); + return -EAGAIN; + } + if (inet6_add_protocol(&tunnel46_protocol, IPPROTO_IPIP)) { + pr_err("%s: can't add protocol\n", __func__); + inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); + return -EAGAIN; + } + return 0; +} + +static void __exit tunnel6_fini(void) +{ + if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) + pr_err("%s: can't remove protocol\n", __func__); + if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) + pr_err("%s: can't remove protocol\n", __func__); +} + +module_init(tunnel6_init); +module_exit(tunnel6_fini); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index bf9519341fd..7092ff78fd8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1,14 +1,12 @@ /* * UDP over IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Authors: - * Pedro Roque <roque@di.fc.ul.pt> + * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/udp.c * - * $Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $ - * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which @@ -23,12 +21,10 @@ * 2 of the License, or (at your option) any later version. */ -#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> @@ -36,309 +32,524 @@ #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/init.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/slab.h> #include <asm/uaccess.h> -#include <net/sock.h> -#include <net/snmp.h> - -#include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_route.h> -#include <net/addrconf.h> -#include <net/ip.h> -#include <net/udp.h> #include <net/raw.h> -#include <net/inet_common.h> #include <net/tcp_states.h> - #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/inet6_hashtables.h> +#include <net/busy_poll.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <trace/events/skb.h> +#include "udp_impl.h" + +static unsigned int udp6_ehashfn(struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) +{ + static u32 udp6_ehash_secret __read_mostly; + static u32 udp_ipv6_hash_secret __read_mostly; -DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly; + u32 lhash, fhash; -/* Grrr, addr_type already calculated by caller, but I don't want - * to add some silly "cookie" argument to this method just for that. - */ -static int udp_v6_get_port(struct sock *sk, unsigned short snum) + net_get_random_once(&udp6_ehash_secret, + sizeof(udp6_ehash_secret)); + net_get_random_once(&udp_ipv6_hash_secret, + sizeof(udp_ipv6_hash_secret)); + + lhash = (__force u32)laddr->s6_addr32[3]; + fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); + + return __inet6_ehashfn(lhash, lport, fhash, fport, + udp_ipv6_hash_secret + net_hash_mix(net)); +} + +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { - struct sock *sk2; - struct hlist_node *node; - - write_lock_bh(&udp_hash_lock); - if (snum == 0) { - int best_size_so_far, best, result, i; - - if (udp_port_rover > sysctl_local_port_range[1] || - udp_port_rover < sysctl_local_port_range[0]) - udp_port_rover = sysctl_local_port_range[0]; - best_size_so_far = 32767; - best = result = udp_port_rover; - for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) { - int size; - struct hlist_head *list; - - list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)]; - if (hlist_empty(list)) { - if (result > sysctl_local_port_range[1]) - result = sysctl_local_port_range[0] + - ((result - sysctl_local_port_range[0]) & - (UDP_HTABLE_SIZE - 1)); - goto gotit; - } - size = 0; - sk_for_each(sk2, node, list) - if (++size >= best_size_so_far) - goto next; - best_size_so_far = size; - best = result; - next:; - } - result = best; - for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) { - if (result > sysctl_local_port_range[1]) - result = sysctl_local_port_range[0] - + ((result - sysctl_local_port_range[0]) & - (UDP_HTABLE_SIZE - 1)); - if (!udp_lport_inuse(result)) - break; - } - if (i >= (1 << 16) / UDP_HTABLE_SIZE) - goto fail; -gotit: - udp_port_rover = snum = result; - } else { - sk_for_each(sk2, node, - &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) { - if (inet_sk(sk2)->num == snum && - sk2 != sk && - (!sk2->sk_bound_dev_if || - !sk->sk_bound_dev_if || - sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - (!sk2->sk_reuse || !sk->sk_reuse) && - ipv6_rcv_saddr_equal(sk, sk2)) - goto fail; - } - } + const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); + int sk_ipv6only = ipv6_only_sock(sk); + int sk2_ipv6only = inet_v6_ipv6only(sk2); + int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); + int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; + + /* if both are mapped, treat as IPv4 */ + if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) + return (!sk2_ipv6only && + (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr || + sk->sk_rcv_saddr == sk2->sk_rcv_saddr)); + + if (addr_type2 == IPV6_ADDR_ANY && + !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) + return 1; + + if (addr_type == IPV6_ADDR_ANY && + !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) + return 1; + + if (sk2_rcv_saddr6 && + ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6)) + return 1; - inet_sk(sk)->num = snum; - if (sk_unhashed(sk)) { - sk_add_node(sk, &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]); - sock_prot_inc_use(sk->sk_prot); - } - write_unlock_bh(&udp_hash_lock); return 0; +} + +static unsigned int udp6_portaddr_hash(struct net *net, + const struct in6_addr *addr6, + unsigned int port) +{ + unsigned int hash, mix = net_hash_mix(net); -fail: - write_unlock_bh(&udp_hash_lock); - return 1; + if (ipv6_addr_any(addr6)) + hash = jhash_1word(0, mix); + else if (ipv6_addr_v4mapped(addr6)) + hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); + else + hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); + + return hash ^ port; +} + + +int udp_v6_get_port(struct sock *sk, unsigned short snum) +{ + unsigned int hash2_nulladdr = + udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); + unsigned int hash2_partial = + udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); + + /* precompute partial secondary hash */ + udp_sk(sk)->udp_portaddr_hash = hash2_partial; + return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } -static void udp_v6_hash(struct sock *sk) +static void udp_v6_rehash(struct sock *sk) { - BUG(); + u16 new_hash = udp6_portaddr_hash(sock_net(sk), + &sk->sk_v6_rcv_saddr, + inet_sk(sk)->inet_num); + + udp_lib_rehash(sk, new_hash); } -static void udp_v6_unhash(struct sock *sk) +static inline int compute_score(struct sock *sk, struct net *net, + unsigned short hnum, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif) { - write_lock_bh(&udp_hash_lock); - if (sk_del_node_init(sk)) { - inet_sk(sk)->num = 0; - sock_prot_dec_use(sk->sk_prot); + int score = -1; + + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && + sk->sk_family == PF_INET6) { + struct inet_sock *inet = inet_sk(sk); + + score = 0; + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score++; + } + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return -1; + score++; + } + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } } - write_unlock_bh(&udp_hash_lock); + return score; } -static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, - struct in6_addr *daddr, u16 dport, int dif) +#define SCORE2_MAX (1 + 1 + 1) +static inline int compute_score2(struct sock *sk, struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned short hnum, + int dif) { - struct sock *sk, *result = NULL; - struct hlist_node *node; - unsigned short hnum = ntohs(dport); - int badness = -1; + int score = -1; - read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) { + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && + sk->sk_family == PF_INET6) { struct inet_sock *inet = inet_sk(sk); - if (inet->num == hnum && sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - int score = 0; - if (inet->dport) { - if (inet->dport != sport) - continue; - score++; - } - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - continue; - score++; - } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) - continue; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score++; - } - if(score == 4) { - result = sk; - break; - } else if(score > badness) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return -1; + score = 0; + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score++; + } + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + + +/* called with read_rcu_lock() */ +static struct sock *udp6_lib_lookup2(struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned int hnum, int dif, + struct udp_hslot *hslot2, unsigned int slot2) +{ + struct sock *sk, *result; + struct hlist_nulls_node *node; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; + +begin: + result = NULL; + badness = -1; + udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + score = compute_score2(sk, net, saddr, sport, + daddr, hnum, dif); + if (score > badness) { + result = sk; + badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = udp6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } else if (score == SCORE2_MAX) + goto exact_match; + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) result = sk; - badness = score; + hash = next_pseudo_random32(hash); + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot2) + goto begin; + + if (result) { +exact_match: + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) + result = NULL; + else if (unlikely(compute_score2(result, net, saddr, sport, + daddr, hnum, dif) < badness)) { + sock_put(result); + goto begin; + } + } + return result; +} + +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) +{ + struct sock *sk, *result; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(dport); + unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; + + rcu_read_lock(); + if (hslot->count > 10) { + hash2 = udp6_portaddr_hash(net, daddr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp6_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, + hslot2, slot2); + if (!result) { + hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp6_lib_lookup2(net, saddr, sport, + &in6addr_any, hnum, dif, + hslot2, slot2); + } + rcu_read_unlock(); + return result; + } +begin: + result = NULL; + badness = -1; + sk_nulls_for_each_rcu(sk, node, &hslot->head) { + score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif); + if (score > badness) { + result = sk; + badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = udp6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } - if (result) - sock_hold(result); - read_unlock(&udp_hash_lock); + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begin; + + if (result) { + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) + result = NULL; + else if (unlikely(compute_score(result, net, hnum, saddr, sport, + daddr, dport, dif) < badness)) { + sock_put(result); + goto 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, + struct udp_table *udptable) +{ + struct sock *sk; + const struct ipv6hdr *iph = ipv6_hdr(skb); + + if (unlikely(sk = skb_steal_sock(skb))) + return sk; + return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + udptable); +} -static void udpv6_close(struct sock *sk, long timeout) +struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, int dif) { - sk_common_release(sk); + return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); } +EXPORT_SYMBOL_GPL(udp6_lib_lookup); + /* * This should be easy, if there is something there we * return it, otherwise we block. */ -static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, +int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct sk_buff *skb; - size_t copied; - int err; + struct sk_buff *skb; + unsigned int ulen, copied; + int peeked, off = 0; + int err; + int is_udplite = IS_UDPLITE(sk); + int is_udp4; + bool slow; - if (addr_len) - *addr_len=sizeof(struct sockaddr_in6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); + + if (np->rxpmtu && np->rxopt.bits.rxpmtu) + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: - skb = skb_recv_datagram(sk, flags, noblock, &err); + skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + &peeked, &off, &err); if (!skb) goto out; - copied = skb->len - sizeof(struct udphdr); - if (copied > len) { - copied = len; - msg->msg_flags |= MSG_TRUNC; - } - - if (skb->ip_summed==CHECKSUM_UNNECESSARY) { - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov, - copied); - } else if (msg->msg_flags&MSG_TRUNC) { - if ((unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) + ulen = skb->len - sizeof(struct udphdr); + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) + msg->msg_flags |= MSG_TRUNC; + + is_udp4 = (skb->protocol == htons(ETH_P_IP)); + + /* + * If checksum is needed at all, try to do it while copying the + * data. If the data is truncated, or if we only want a partial + * coverage checksum (UDP-Lite), do it before the copy. + */ + + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (udp_lib_checksum_complete(skb)) goto csum_copy_err; - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov, - copied); - } else { + } + + if (skb_csum_unnecessary(skb)) + err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), + msg->msg_iov, copied); + else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) goto csum_copy_err; } - if (err) + if (unlikely(err)) { + trace_kfree_skb(skb, udpv6_recvmsg); + if (!peeked) { + atomic_inc(&sk->sk_drops); + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, + is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, + is_udplite); + } goto out_free; + } + if (!peeked) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { - struct sockaddr_in6 *sin6; - - sin6 = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); sin6->sin6_family = AF_INET6; - sin6->sin6_port = skb->h.uh->source; + sin6->sin6_port = udp_hdr(skb)->source; sin6->sin6_flowinfo = 0; - sin6->sin6_scope_id = 0; - - if (skb->protocol == htons(ETH_P_IP)) - ipv6_addr_set(&sin6->sin6_addr, 0, 0, - htonl(0xffff), skb->nh.iph->saddr); - else { - ipv6_addr_copy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr); - if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - sin6->sin6_scope_id = IP6CB(skb)->iif; - } + if (is_udp4) { + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin6->sin6_addr); + sin6->sin6_scope_id = 0; + } else { + sin6->sin6_addr = ipv6_hdr(skb)->saddr; + sin6->sin6_scope_id = + ipv6_iface_scope_id(&sin6->sin6_addr, + IP6CB(skb)->iif); + } + *addr_len = sizeof(*sin6); } - if (skb->protocol == htons(ETH_P_IP)) { + + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); + + if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } else { if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); - } + ip6_datagram_recv_specific_ctl(sk, msg, skb); + } err = copied; if (flags & MSG_TRUNC) - err = skb->len - sizeof(struct udphdr); + err = ulen; out_free: - skb_free_datagram(sk, skb); + skb_free_datagram_locked(sk, skb); out: return err; csum_copy_err: - /* Clear queue. */ - if (flags&MSG_PEEK) { - int clear = 0; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); - clear = 1; + slow = lock_sock_fast(sk); + if (!skb_kill_datagram(sk, skb, flags)) { + if (is_udp4) { + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_CSUMERRORS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + } else { + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_CSUMERRORS, is_udplite); + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); } - spin_unlock_bh(&sk->sk_receive_queue.lock); - if (clear) - kfree_skb(skb); } + unlock_sock_fast(sk, slow); - skb_free_datagram(sk, skb); - - if (flags & MSG_DONTWAIT) { - UDP6_INC_STATS_USER(UDP_MIB_INERRORS); + if (noblock) return -EAGAIN; - } + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } -static void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) +void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info, + struct udp_table *udptable) { struct ipv6_pinfo *np; - struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; - struct net_device *dev = skb->dev; - struct in6_addr *saddr = &hdr->saddr; - struct in6_addr *daddr = &hdr->daddr; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; + const struct in6_addr *saddr = &hdr->saddr; + const struct in6_addr *daddr = &hdr->daddr; struct udphdr *uh = (struct udphdr*)(skb->data+offset); struct sock *sk; int err; - sk = udp_v6_lookup(daddr, uh->dest, saddr, uh->source, dev->ifindex); - + sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest, + saddr, uh->source, inet6_iif(skb), udptable); if (sk == NULL) return; + if (type == ICMPV6_PKT_TOOBIG) { + if (!ip6_sk_accept_pmtu(sk)) + goto out; + ip6_sk_update_pmtu(skb, sk, info); + } + if (type == NDISC_REDIRECT) { + ip6_sk_redirect(skb, sk); + goto out; + } + np = inet6_sk(sk); if (!icmpv6_err_convert(type, code, &err) && !np->recverr) @@ -356,197 +567,387 @@ out: sock_put(sk); } -static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { + int rc; + + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); + } + + rc = sock_queue_rcv_skb(sk, skb); + if (rc < 0) { + int is_udplite = IS_UDPLITE(sk); + + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; } + return 0; +} + +static __inline__ void udpv6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, u8 type, + u8 code, int offset, __be32 info ) +{ + __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); +} + +static struct static_key udpv6_encap_needed __read_mostly; +void udpv6_encap_enable(void) +{ + if (!static_key_enabled(&udpv6_encap_needed)) + static_key_slow_inc(&udpv6_encap_needed); +} +EXPORT_SYMBOL(udpv6_encap_enable); + +int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + struct udp_sock *up = udp_sk(sk); + int rc; + int is_udplite = IS_UDPLITE(sk); + + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + goto drop; + + if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + + /* + * This is an encapsulation socket so pass the skb to + * the socket's udp_encap_rcv() hook. Otherwise, just + * fall through and pass this up the UDP socket. + * up->encap_rcv() returns the following value: + * =0 if skb was successfully passed to the encap + * handler or was discarded by it. + * >0 if skb should be passed on to UDP. + * <0 if skb should be resubmitted as proto -N + */ + + /* if we're overly short, let UDP handle it */ + encap_rcv = ACCESS_ONCE(up->encap_rcv); + if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + int ret; + + /* Verify checksum before giving to encap */ + if (udp_lib_checksum_complete(skb)) + goto csum_error; + + ret = encap_rcv(sk, skb); + if (ret <= 0) { + UDP_INC_STATS_BH(sock_net(sk), + UDP_MIB_INDATAGRAMS, + is_udplite); + return -ret; + } + } + + /* FALLTHROUGH -- it's a UDP Packet */ + } + + /* + * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). + */ + if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { - if (skb->ip_summed != CHECKSUM_UNNECESSARY) { - if ((unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) { - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); - kfree_skb(skb); - return 0; + if (up->pcrlen == 0) { /* full coverage was set */ + LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage" + " %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); + goto drop; + } + if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { + LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d " + "too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); + goto drop; } - skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (sock_queue_rcv_skb(sk,skb)<0) { - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); - kfree_skb(skb); - return 0; + if (rcu_access_pointer(sk->sk_filter)) { + if (udp_lib_checksum_complete(skb)) + goto csum_error; } - UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS); - return 0; + + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); + goto drop; + } + + skb_dst_drop(skb); + + bh_lock_sock(sk); + rc = 0; + if (!sock_owned_by_user(sk)) + rc = __udpv6_queue_rcv_skb(sk, skb); + else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + bh_unlock_sock(sk); + goto drop; + } + bh_unlock_sock(sk); + + return rc; + +csum_error: + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); +drop: + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + return -1; } -static struct sock *udp_v6_mcast_next(struct sock *sk, - u16 loc_port, struct in6_addr *loc_addr, - u16 rmt_port, struct in6_addr *rmt_addr, +static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, + __be16 loc_port, const struct in6_addr *loc_addr, + __be16 rmt_port, const struct in6_addr *rmt_addr, int dif) { - struct hlist_node *node; - struct sock *s = sk; + struct hlist_nulls_node *node; unsigned short num = ntohs(loc_port); - sk_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); + sk_nulls_for_each_from(sk, node) { + struct inet_sock *inet = inet_sk(sk); - if (inet->num == num && s->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(s); - if (inet->dport) { - if (inet->dport != rmt_port) + if (!net_eq(sock_net(sk), net)) + continue; + + if (udp_sk(sk)->udp_port_hash == num && + sk->sk_family == PF_INET6) { + if (inet->inet_dport) { + if (inet->inet_dport != rmt_port) continue; } - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; - if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) continue; } - if(!inet6_mc_check(s, loc_addr, rmt_addr)) + if (!inet6_mc_check(sk, loc_addr, rmt_addr)) continue; - return s; + return sk; } } return NULL; } +static void flush_stack(struct sock **stack, unsigned int count, + struct sk_buff *skb, unsigned int final) +{ + struct sk_buff *skb1 = NULL; + struct sock *sk; + unsigned int i; + + for (i = 0; i < count; i++) { + sk = stack[i]; + if (likely(skb1 == NULL)) + skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); + if (!skb1) { + atomic_inc(&sk->sk_drops); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + } + + if (skb1 && udpv6_queue_rcv_skb(sk, skb1) <= 0) + skb1 = NULL; + } + if (unlikely(skb1)) + kfree_skb(skb1); +} + +static void udp6_csum_zero_error(struct sk_buff *skb) +{ + /* RFC 2460 section 8.1 says that we SHOULD log + * this error. Well, it is reasonable. + */ + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", + &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source), + &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest)); +} + /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. */ -static void udpv6_mcast_deliver(struct udphdr *uh, - struct in6_addr *saddr, struct in6_addr *daddr, - struct sk_buff *skb) +static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, + const struct in6_addr *saddr, const struct in6_addr *daddr, + struct udp_table *udptable) { - struct sock *sk, *sk2; + struct sock *sk, *stack[256 / sizeof(struct sock *)]; + const struct udphdr *uh = udp_hdr(skb); + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; + unsigned int i, count = 0; + + spin_lock(&hslot->lock); + sk = sk_nulls_head(&hslot->head); + dif = inet6_iif(skb); + sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); + while (sk) { + /* If zero checksum and no_check is not on for + * the socket then skip it. + */ + if (uh->check || udp_sk(sk)->no_check6_rx) + stack[count++] = sk; - read_lock(&udp_hash_lock); - sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); - dif = skb->dev->ifindex; - sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); - if (!sk) { - kfree_skb(skb); - goto out; + sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, + uh->source, saddr, dif); + if (unlikely(count == ARRAY_SIZE(stack))) { + if (!sk) + break; + flush_stack(stack, count, skb, ~0); + count = 0; + } } + /* + * before releasing the lock, we must take reference on sockets + */ + for (i = 0; i < count; i++) + sock_hold(stack[i]); + + spin_unlock(&hslot->lock); + + if (count) { + flush_stack(stack, count, skb, count - 1); - sk2 = sk; - while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr, - uh->source, saddr, dif))) { - struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); - if (buff) - udpv6_queue_rcv_skb(sk2, buff); + for (i = 0; i < count; i++) + sock_put(stack[i]); + } else { + kfree_skb(skb); } - udpv6_queue_rcv_skb(sk, skb); -out: - read_unlock(&udp_hash_lock); + return 0; } -static int udpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) +int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, + int proto) { - struct sk_buff *skb = *pskb; + struct net *net = dev_net(skb->dev); struct sock *sk; - struct udphdr *uh; - struct net_device *dev = skb->dev; - struct in6_addr *saddr, *daddr; + struct udphdr *uh; + const struct in6_addr *saddr, *daddr; u32 ulen = 0; if (!pskb_may_pull(skb, sizeof(struct udphdr))) - goto short_packet; + goto discard; - saddr = &skb->nh.ipv6h->saddr; - daddr = &skb->nh.ipv6h->daddr; - uh = skb->h.uh; + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + uh = udp_hdr(skb); ulen = ntohs(uh->len); - - /* Check for jumbo payload */ - if (ulen == 0) - ulen = skb->len; - - if (ulen > skb->len || ulen < sizeof(*uh)) + if (ulen > skb->len) goto short_packet; - if (uh->check == 0) { - /* RFC 2460 section 8.1 says that we SHOULD log - this error. Well, it is reasonable. - */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); - goto discard; - } + if (proto == IPPROTO_UDP) { + /* UDP validates ulen. */ - if (ulen < skb->len) { - if (pskb_trim_rcsum(skb, ulen)) - goto discard; - saddr = &skb->nh.ipv6h->saddr; - daddr = &skb->nh.ipv6h->daddr; - uh = skb->h.uh; - } + /* Check for jumbo payload */ + if (ulen == 0) + ulen = skb->len; - if (skb->ip_summed==CHECKSUM_HW) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - if (csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum)) { - LIMIT_NETDEBUG(KERN_DEBUG "udp v6 hw csum failure.\n"); - skb->ip_summed = CHECKSUM_NONE; + if (ulen < sizeof(*uh)) + goto short_packet; + + if (ulen < skb->len) { + if (pskb_trim_rcsum(skb, ulen)) + goto short_packet; + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; + uh = udp_hdr(skb); } } - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->csum = ~csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, 0); - /* - * Multicast receive code + if (udp6_csum_init(skb, uh, proto)) + goto csum_error; + + /* + * Multicast receive code */ - if (ipv6_addr_is_multicast(daddr)) { - udpv6_mcast_deliver(uh, saddr, daddr, skb); - return 0; - } + if (ipv6_addr_is_multicast(daddr)) + return __udp6_lib_mcast_deliver(net, skb, + saddr, daddr, udptable); /* Unicast */ - /* + /* * check socket cache ... must talk to Alan about his plans * for sock caches... i'll skip this for now. */ - sk = udp_v6_lookup(saddr, uh->source, daddr, uh->dest, dev->ifindex); + sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); + if (sk != NULL) { + int ret; + + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + udp6_csum_zero_error(skb); + goto csum_error; + } - if (sk == NULL) { - if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) - goto discard; + ret = udpv6_queue_rcv_skb(sk, skb); + sock_put(sk); - if (skb->ip_summed != CHECKSUM_UNNECESSARY && - (unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum))) - goto discard; - UDP6_INC_STATS_BH(UDP_MIB_NOPORTS); + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); + return 0; + } - kfree_skb(skb); - return(0); + if (!uh->check) { + udp6_csum_zero_error(skb); + goto csum_error; } - - /* deliver */ - - udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); - return(0); -short_packet: - if (net_ratelimit()) - printk(KERN_DEBUG "UDP: short packet: %d/%u\n", ulen, skb->len); + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto discard; + + if (udp_lib_checksum_complete(skb)) + goto csum_error; + + UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +short_packet: + LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", + proto == IPPROTO_UDPLITE ? "-Lite" : "", + saddr, + ntohs(uh->source), + ulen, + skb->len, + daddr, + ntohs(uh->dest)); + goto discard; +csum_error: + UDP6_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); + UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb(skb); - return(0); + return 0; +} + +static __inline__ int udpv6_rcv(struct sk_buff *skb) +{ + return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); } + /* * Throw away all pending data and cancel the corking. Socket is locked. */ @@ -554,24 +955,75 @@ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); - if (up->pending) { + if (up->pending == AF_INET) + udp_flush_pending_frames(sk); + else if (up->pending) { up->len = 0; up->pending = 0; ip6_flush_pending_frames(sk); - } + } +} + +/** + * udp6_hwcsum_outgoing - handle outgoing HW checksumming + * @sk: socket we are sending on + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + */ +static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int len) +{ + unsigned int offset; + struct udphdr *uh = udp_hdr(skb); + __wsum csum = 0; + + if (skb_queue_len(&sk->sk_write_queue) == 1) { + /* Only one fragment on the socket. */ + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0); + } else { + /* + * HW-checksum won't work as there are two or more + * fragments on the socket so that all csums of sk_buffs + * should be together + */ + offset = skb_transport_offset(skb); + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + + skb->ip_summed = CHECKSUM_NONE; + + skb_queue_walk(&sk->sk_write_queue, skb) { + csum = csum_add(csum, skb->csum); + } + + uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, + csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } } /* * Sending */ -static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up) +static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udphdr *uh; + struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct flowi *fl = &inet->cork.fl; + struct flowi6 *fl6; int err = 0; + int is_udplite = IS_UDPLITE(sk); + __wsum csum = 0; + + if (up->pending == AF_INET) + return udp_push_pending_frames(sk); + + fl6 = &inet->cork.fl.u.ip6; /* Grab the skbuff where UDP header space exists. */ if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) @@ -580,68 +1032,70 @@ static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up) /* * Create a UDP header */ - uh = skb->h.uh; - uh->source = fl->fl_ip_sport; - uh->dest = fl->fl_ip_dport; + uh = udp_hdr(skb); + uh->source = fl6->fl6_sport; + uh->dest = fl6->fl6_dport; uh->len = htons(up->len); uh->check = 0; - if (sk->sk_no_check == UDP_CSUM_NOXMIT) { + if (is_udplite) + csum = udplite_csum_outgoing(sk, skb); + else if (up->no_check6_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; - } - - if (skb_queue_len(&sk->sk_write_queue) == 1) { - skb->csum = csum_partial((char *)uh, - sizeof(struct udphdr), skb->csum); - uh->check = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - up->len, fl->proto, skb->csum); - } else { - u32 tmp_csum = 0; - - skb_queue_walk(&sk->sk_write_queue, skb) { - tmp_csum = csum_add(tmp_csum, skb->csum); - } - tmp_csum = csum_partial((char *)uh, - sizeof(struct udphdr), tmp_csum); - tmp_csum = csum_ipv6_magic(&fl->fl6_src, - &fl->fl6_dst, - up->len, fl->proto, tmp_csum); - uh->check = tmp_csum; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, + up->len); + goto send; + } else + csum = udp_csum_outgoing(sk, skb); - } + /* add protocol-dependent pseudo-header */ + uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, + up->len, fl6->flowi6_proto, csum); if (uh->check == 0) - uh->check = -1; + uh->check = CSUM_MANGLED_0; send: err = ip6_push_pending_frames(sk); + if (err) { + if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); out: up->len = 0; up->pending = 0; return err; } -static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, +int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name; - struct in6_addr *daddr, *final_p = NULL, final; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); + struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi *fl = &inet->cork.fl; + struct flowi6 fl6; struct dst_entry *dst; int addr_len = msg->msg_namelen; int ulen = len; int hlimit = -1; int tclass = -1; + int dontfrag = -1; int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int err; int connected = 0; + int is_udplite = IS_UDPLITE(sk); + int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); /* destination address check */ if (sin6) { @@ -667,15 +1121,15 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, } else if (!up->pending) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; - } else + daddr = &sk->sk_v6_daddr; + } else daddr = NULL; if (daddr) { - if (ipv6_addr_type(daddr) == IPV6_ADDR_MAPPED) { + if (ipv6_addr_v4mapped(daddr)) { struct sockaddr_in sin; sin.sin_family = AF_INET; - sin.sin_port = sin6 ? sin6->sin6_port : inet->dport; + sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport; sin.sin_addr.s_addr = daddr->s6_addr32[3]; msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); @@ -690,11 +1144,11 @@ do_udp_sendmsg: return udp_sendmsg(iocb, sk, msg, len); /* Rough check on arithmetic overflow, - better check is made in ip6_build_xmit + better check is made in ip6_append_data(). */ if (len > INT_MAX - sizeof(struct udphdr)) return -EMSGSIZE; - + if (up->pending) { /* * There are pending frames. @@ -713,22 +1167,21 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(fl, 0, sizeof(*fl)); + memset(&fl6, 0, sizeof(fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl->fl_ip_dport = sin6->sin6_port; + fl6.fl6_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (np->sndflow) { - fl->fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel); + fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - daddr = &flowlabel->dst; } } @@ -737,38 +1190,44 @@ do_udp_sendmsg: * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && - ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL) - fl->oif = sin6->sin6_scope_id; + __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) + fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl->fl_ip_dport = inet->dport; - daddr = &np->daddr; - fl->fl6_flowlabel = np->flow_label; + fl6.fl6_dport = inet->inet_dport; + daddr = &sk->sk_v6_daddr; + fl6.flowlabel = np->flow_label; connected = 1; } - if (!fl->oif) - fl->oif = sk->sk_bound_dev_if; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = sk->sk_bound_dev_if; + + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + + fl6.flowi6_mark = sk->sk_mark; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, fl, opt, &hlimit, &tclass); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl->fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl->fl6_flowlabel); + if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; } @@ -778,53 +1237,43 @@ do_udp_sendmsg: } if (opt == NULL) opt = np->opt; - opt = fl6_merge_options(&opt_space, flowlabel, opt); - - fl->proto = IPPROTO_UDP; - ipv6_addr_copy(&fl->fl6_dst, daddr); - if (ipv6_addr_any(&fl->fl6_src) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl->fl6_src, &np->saddr); - fl->fl_ip_sport = inet->sport; - - /* merge ip6_build_xmit from ip6_output */ - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl->fl6_dst); - ipv6_addr_copy(&fl->fl6_dst, rt0->addr); - final_p = &final; + if (flowlabel) + opt = fl6_merge_options(&opt_space, flowlabel, opt); + opt = ipv6_fixup_options(&opt_space, opt); + + fl6.flowi6_proto = sk->sk_protocol; + if (!ipv6_addr_any(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)) + fl6.saddr = np->saddr; + fl6.fl6_sport = inet->inet_sport; + + final_p = fl6_update_dst(&fl6, opt, &final); + if (final_p) connected = 0; - } - if (!fl->oif && ipv6_addr_is_multicast(&fl->fl6_dst)) { - fl->oif = np->mcast_oif; + if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { + fl6.flowi6_oif = np->mcast_oif; connected = 0; - } + } else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(sk, &dst, fl); - if (err) - goto out; - if (final_p) - ipv6_addr_copy(&fl->fl6_dst, final_p); + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if ((err = xfrm_lookup(&dst, fl, sk, 0)) < 0) + dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto out; - - if (hlimit < 0) { - if (ipv6_addr_is_multicast(&fl->fl6_dst)) - hlimit = np->mcast_hops; - else - hlimit = np->hop_limit; - if (hlimit < 0) - hlimit = dst_metric(dst, RTAX_HOPLIMIT); - if (hlimit < 0) - hlimit = ipv6_get_hoplimit(dst->dev); } - if (tclass < 0) { + if (hlimit < 0) + hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -844,34 +1293,55 @@ back_from_confirm: up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; - err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), hlimit, tclass, opt, fl, + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), hlimit, tclass, opt, &fl6, (struct rt6_info*)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) - err = udp_v6_push_pending_frames(sk, up); + err = udp_v6_push_pending_frames(sk); + else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) + up->pending = 0; if (dst) { if (connected) { ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl->fl6_dst, &np->daddr) ? - &np->daddr : NULL); + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl6.saddr, &np->saddr) ? + &np->saddr : +#endif + NULL); } else { dst_release(dst); } + dst = NULL; } if (err > 0) err = np->recverr ? net_xmit_errno(err) : 0; release_sock(sk); out: + dst_release(dst); fl6_sock_release(flowlabel); - if (!err) { - UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS); + if (!err) return len; + /* + * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting + * ENOBUFS might not be good (it's not tunable per se), but otherwise + * we don't have a good statistic (IpOutDiscards but it can be too many + * things). We could add another new stat but at least for now that + * seems like overkill. + */ + if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); } return err; @@ -883,105 +1353,65 @@ do_confirm: goto out; } -static int udpv6_destroy_sock(struct sock *sk) +void udpv6_destroy_sock(struct sock *sk) { + struct udp_sock *up = udp_sk(sk); lock_sock(sk); udp_v6_flush_pending_frames(sk); release_sock(sk); - inet6_destroy_sock(sk); + if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } - return 0; + inet6_destroy_sock(sk); } /* * Socket option code for UDP */ -static int udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) { - struct udp_sock *up = udp_sk(sk); - int val; - int err = 0; - - if (level != SOL_UDP) - return ipv6_setsockopt(sk, level, optname, optval, optlen); - - if(optlen<sizeof(int)) - return -EINVAL; - - if (get_user(val, (int __user *)optval)) - return -EFAULT; - - switch(optname) { - case UDP_CORK: - if (val != 0) { - up->corkflag = 1; - } else { - up->corkflag = 0; - lock_sock(sk); - udp_v6_push_pending_frames(sk, up); - release_sock(sk); - } - break; - - case UDP_ENCAP: - switch (val) { - case 0: - up->encap_type = val; - break; - default: - err = -ENOPROTOOPT; - break; - } - break; - - default: - err = -ENOPROTOOPT; - break; - }; - - return err; + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_v6_push_pending_frames); + return ipv6_setsockopt(sk, level, optname, optval, optlen); } -static int udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +#ifdef CONFIG_COMPAT +int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) { - struct udp_sock *up = udp_sk(sk); - int val, len; - - if (level != SOL_UDP) - return ipv6_getsockopt(sk, level, optname, optval, optlen); - - if(get_user(len,optlen)) - return -EFAULT; - - len = min_t(unsigned int, len, sizeof(int)); - - if(len < 0) - return -EINVAL; - - switch(optname) { - case UDP_CORK: - val = up->corkflag; - break; - - case UDP_ENCAP: - val = up->encap_type; - break; + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_setsockopt(sk, level, optname, optval, optlen, + udp_v6_push_pending_frames); + return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); +} +#endif - default: - return -ENOPROTOOPT; - }; +int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_getsockopt(sk, level, optname, optval, optlen); + return ipv6_getsockopt(sk, level, optname, optval, optlen); +} - if(put_user(len, optlen)) - return -EFAULT; - if(copy_to_user(optval, &val,len)) - return -EFAULT; - return 0; +#ifdef CONFIG_COMPAT +int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level == SOL_UDP || level == SOL_UDPLITE) + return udp_lib_getsockopt(sk, level, optname, optval, optlen); + return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); } +#endif -static struct inet6_protocol udpv6_protocol = { +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, @@ -989,87 +1419,90 @@ static struct inet6_protocol udpv6_protocol = { /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS - -static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket) +int udp6_seq_show(struct seq_file *seq, void *v) { - struct inet_sock *inet = inet_sk(sp); - struct ipv6_pinfo *np = inet6_sk(sp); - struct in6_addr *dest, *src; - __u16 destp, srcp; - - dest = &np->daddr; - src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); - seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n", - bucket, - src->s6_addr32[0], src->s6_addr32[1], - src->s6_addr32[2], src->s6_addr32[3], srcp, - dest->s6_addr32[0], dest->s6_addr32[1], - dest->s6_addr32[2], dest->s6_addr32[3], destp, - sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), - 0, 0L, 0, - sock_i_uid(sp), 0, - sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp); -} - -static int udp6_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_printf(seq, - " sl " - "local_address " - "remote_address " - "st tx_queue rx_queue tr tm->when retrnsmt" - " uid timeout inode\n"); - else - udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket); + if (v == SEQ_START_TOKEN) { + seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); + } else { + int bucket = ((struct udp_iter_state *)seq->private)->bucket; + struct inet_sock *inet = inet_sk(v); + __u16 srcp = ntohs(inet->inet_sport); + __u16 destp = ntohs(inet->inet_dport); + ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket); + } return 0; } -static struct file_operations udp6_seq_fops; +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 = { - .owner = THIS_MODULE, .name = "udp6", .family = AF_INET6, - .seq_show = udp6_seq_show, - .seq_fops = &udp6_seq_fops, + .udp_table = &udp_table, + .seq_fops = &udp6_afinfo_seq_fops, + .seq_ops = { + .show = udp6_seq_show, + }, }; -int __init udp6_proc_init(void) +int __net_init udp6_proc_init(struct net *net) { - return udp_proc_register(&udp6_seq_afinfo); + return udp_proc_register(net, &udp6_seq_afinfo); } -void udp6_proc_exit(void) { - udp_proc_unregister(&udp6_seq_afinfo); +void udp6_proc_exit(struct net *net) { + udp_proc_unregister(net, &udp6_seq_afinfo); } #endif /* CONFIG_PROC_FS */ +void udp_v6_clear_sk(struct sock *sk, int size) +{ + struct inet_sock *inet = inet_sk(sk); + + /* we do not want to clear pinet6 field, because of RCU lookups */ + sk_prot_clear_portaddr_nulls(sk, offsetof(struct inet_sock, pinet6)); + + size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); + memset(&inet->pinet6 + 1, 0, size); +} + /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { - .name = "UDPv6", - .owner = THIS_MODULE, - .close = udpv6_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udpv6_destroy_sock, - .setsockopt = udpv6_setsockopt, - .getsockopt = udpv6_getsockopt, - .sendmsg = udpv6_sendmsg, - .recvmsg = udpv6_recvmsg, - .backlog_rcv = udpv6_queue_rcv_skb, - .hash = udp_v6_hash, - .unhash = udp_v6_unhash, - .get_port = udp_v6_get_port, - .obj_size = sizeof(struct udp6_sock), + .name = "UDPv6", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .backlog_rcv = __udpv6_queue_rcv_skb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, + .get_port = udp_v6_get_port, + .memory_allocated = &udp_memory_allocated, + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem = &sysctl_udp_wmem_min, + .sysctl_rmem = &sysctl_udp_rmem_min, + .obj_size = sizeof(struct udp6_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udp_table, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif + .clear_sk = udp_v6_clear_sk, }; static struct inet_protosw udpv6_protosw = { @@ -1077,15 +1510,31 @@ static struct inet_protosw udpv6_protosw = { .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, - .capability =-1, - .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }; -void __init udpv6_init(void) +int __init udpv6_init(void) +{ + int ret; + + ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + if (ret) + goto out; + + ret = inet6_register_protosw(&udpv6_protosw); + if (ret) + goto out_udpv6_protocol; +out: + return ret; + +out_udpv6_protocol: + inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + goto out; +} + +void udpv6_exit(void) { - if (inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP) < 0) - printk(KERN_ERR "udpv6_init: Could not register protocol\n"); - inet6_register_protosw(&udpv6_protosw); + inet6_unregister_protosw(&udpv6_protosw); + inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); } diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h new file mode 100644 index 00000000000..c779c3c90b9 --- /dev/null +++ b/net/ipv6/udp_impl.h @@ -0,0 +1,38 @@ +#ifndef _UDP6_IMPL_H +#define _UDP6_IMPL_H +#include <net/udp.h> +#include <net/udplite.h> +#include <net/protocol.h> +#include <net/addrconf.h> +#include <net/inet_common.h> +#include <net/transp_v6.h> + +int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int); +void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, + __be32, struct udp_table *); + +int udp_v6_get_port(struct sock *sk, unsigned short snum); + +int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); +#ifdef CONFIG_COMPAT +int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); +int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +#endif +int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len); +int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len, int noblock, int flags, int *addr_len); +int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); +void udpv6_destroy_sock(struct sock *sk); + +void udp_v6_clear_sk(struct sock *sk, int size); + +#ifdef CONFIG_PROC_FS +int udp6_seq_show(struct seq_file *seq, void *v); +#endif +#endif /* _UDP6_IMPL_H */ diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c new file mode 100644 index 00000000000..0ae3d98f83e --- /dev/null +++ b/net/ipv6/udp_offload.c @@ -0,0 +1,140 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * 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. + * + * UDPv6 GSO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> +#include "ip6_offload.h" + +static int udp6_ufo_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + if (likely(!skb->encapsulation)) { + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + } + + return 0; +} + +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; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *packet_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + int tnl_hlen; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM | + SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_IPIP | + SKB_GSO_SIT | + SKB_GSO_MPLS) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + if (skb->encapsulation && skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) + segs = skb_udp_tunnel_segment(skb, features); + else { + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb_checksum_start_offset(skb); + csum = skb_checksum(skb, offset, skb->len - offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + tnl_hlen = skb_tnl_header_len(skb); + if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { + if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) + goto out; + } + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + + unfrag_ip6hlen + tnl_hlen; + packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; + memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); + + SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + fptr->identification = skb_shinfo(skb)->ip6_frag_id; + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + } + +out: + return segs; +} +static const struct net_offload udpv6_offload = { + .callbacks = { + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, + }, +}; + +int __init udp_offload_init(void) +{ + return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); +} diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c new file mode 100644 index 00000000000..9cf097e206e --- /dev/null +++ b/net/ipv6/udplite.c @@ -0,0 +1,139 @@ +/* + * UDPLITEv6 An implementation of the UDP-Lite protocol over IPv6. + * See also net/ipv4/udplite.c + * + * Authors: Gerrit Renker <gerrit@erg.abdn.ac.uk> + * + * Changes: + * Fixes: + * 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. + */ +#include <linux/export.h> +#include "udp_impl.h" + +static int udplitev6_rcv(struct sk_buff *skb) +{ + return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); +} + +static void udplitev6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); +} + +static const struct inet6_protocol udplitev6_protocol = { + .handler = udplitev6_rcv, + .err_handler = udplitev6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +struct proto udplitev6_prot = { + .name = "UDPLITEv6", + .owner = THIS_MODULE, + .close = udp_lib_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udplite_sk_init, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .backlog_rcv = udpv6_queue_rcv_skb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .get_port = udp_v6_get_port, + .obj_size = sizeof(struct udp6_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udplite_table, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif + .clear_sk = udp_v6_clear_sk, +}; + +static struct inet_protosw udplite6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_UDPLITE, + .prot = &udplitev6_prot, + .ops = &inet6_dgram_ops, + .flags = INET_PROTOSW_PERMANENT, +}; + +int __init udplitev6_init(void) +{ + int ret; + + ret = inet6_add_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); + if (ret) + goto out; + + ret = inet6_register_protosw(&udplite6_protosw); + if (ret) + goto out_udplitev6_protocol; +out: + return ret; + +out_udplitev6_protocol: + inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); + goto out; +} + +void udplitev6_exit(void) +{ + inet6_unregister_protosw(&udplite6_protosw); + inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); +} + +#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 = &udplite6_afinfo_seq_fops, + .seq_ops = { + .show = udp6_seq_show, + }, +}; + +static int __net_init udplite6_proc_init_net(struct net *net) +{ + return udp_proc_register(net, &udplite6_seq_afinfo); +} + +static void __net_exit udplite6_proc_exit_net(struct net *net) +{ + udp_proc_unregister(net, &udplite6_seq_afinfo); +} + +static struct pernet_operations udplite6_net_ops = { + .init = udplite6_proc_init_net, + .exit = udplite6_proc_exit_net, +}; + +int __init udplite6_proc_init(void) +{ + return register_pernet_subsys(&udplite6_net_ops); +} + +void udplite6_proc_exit(void) +{ + unregister_pernet_subsys(&udplite6_net_ops); +} +#endif diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 28c29d78338..f8c3cf842f5 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -11,140 +11,136 @@ #include <linux/module.h> #include <linux/string.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <net/ip.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> #include <net/ipv6.h> #include <net/xfrm.h> -static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) +int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb) { - struct ipv6hdr *outer_iph = skb->nh.ipv6h; - struct ipv6hdr *inner_iph = skb->h.ipv6h; + return xfrm6_extract_header(skb); +} - if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) - IP6_ECN_set_ce(inner_iph); +int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET6; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + return xfrm_input(skb, nexthdr, spi, 0); } +EXPORT_SYMBOL(xfrm6_rcv_spi); -int xfrm6_rcv_spi(struct sk_buff **pskb, unsigned int *nhoffp, u32 spi) +int xfrm6_transport_finish(struct sk_buff *skb, int async) { - struct sk_buff *skb = *pskb; - int err; - u32 seq; - struct sec_decap_state xfrm_vec[XFRM_MAX_DEPTH]; - struct xfrm_state *x; - int xfrm_nr = 0; - int decaps = 0; - int nexthdr; - unsigned int nhoff; - - nhoff = *nhoffp; - nexthdr = skb->nh.raw[nhoff]; - - seq = 0; - if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) - goto drop; - - do { - struct ipv6hdr *iph = skb->nh.ipv6h; + skb_network_header(skb)[IP6CB(skb)->nhoff] = + XFRM_MODE_SKB_CB(skb)->protocol; - if (xfrm_nr == XFRM_MAX_DEPTH) - goto drop; +#ifndef CONFIG_NETFILTER + if (!async) + return 1; +#endif - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, nexthdr, AF_INET6); - if (x == NULL) - goto drop; - spin_lock(&x->lock); - if (unlikely(x->km.state != XFRM_STATE_VALID)) - goto drop_unlock; - - if (x->props.replay_window && xfrm_replay_check(x, seq)) - goto drop_unlock; - - if (xfrm_state_check_expire(x)) - goto drop_unlock; - - nexthdr = x->type->input(x, &(xfrm_vec[xfrm_nr].decap), skb); - if (nexthdr <= 0) - goto drop_unlock; - - skb->nh.raw[nhoff] = nexthdr; - - if (x->props.replay_window) - xfrm_replay_advance(x, seq); - - x->curlft.bytes += skb->len; - x->curlft.packets++; - - spin_unlock(&x->lock); - - xfrm_vec[xfrm_nr++].xvec = x; - - if (x->props.mode) { /* XXX */ - if (nexthdr != IPPROTO_IPV6) - goto drop; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto drop; - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - goto drop; - if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(skb->nh.ipv6h, skb->h.ipv6h); - if (!(x->props.flags & XFRM_STATE_NOECN)) - ipip6_ecn_decapsulate(skb); - skb->mac.raw = memmove(skb->data - skb->mac_len, - skb->mac.raw, skb->mac_len); - skb->nh.raw = skb->data; - decaps = 1; - break; - } + ipv6_hdr(skb)->payload_len = htons(skb->len); + __skb_push(skb, skb->data - skb_network_header(skb)); - if ((err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) < 0) - goto drop; - } while (!err); + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + ip6_rcv_finish); + return -1; +} + +int xfrm6_rcv(struct sk_buff *skb) +{ + return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0); +} + +EXPORT_SYMBOL(xfrm6_rcv); + +int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, + xfrm_address_t *saddr, u8 proto) +{ + struct net *net = dev_net(skb->dev); + struct xfrm_state *x = NULL; + int i = 0; /* Allocate new secpath or COW existing one. */ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { struct sec_path *sp; + sp = secpath_dup(skb->sp); - if (!sp) + if (!sp) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; + } if (skb->sp) secpath_put(skb->sp); skb->sp = sp; } - if (xfrm_nr + skb->sp->len > XFRM_MAX_DEPTH) + if (1 + skb->sp->len == XFRM_MAX_DEPTH) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; + } - memcpy(skb->sp->x+skb->sp->len, xfrm_vec, xfrm_nr*sizeof(struct sec_decap_state)); - skb->sp->len += xfrm_nr; - skb->ip_summed = CHECKSUM_NONE; + for (i = 0; i < 3; i++) { + xfrm_address_t *dst, *src; - if (decaps) { - if (!(skb->dev->flags&IFF_LOOPBACK)) { - dst_release(skb->dst); - skb->dst = NULL; + switch (i) { + case 0: + dst = daddr; + src = saddr; + break; + case 1: + /* lookup state with wild-card source address */ + dst = daddr; + src = (xfrm_address_t *)&in6addr_any; + break; + default: + /* lookup state with wild-card addresses */ + dst = (xfrm_address_t *)&in6addr_any; + src = (xfrm_address_t *)&in6addr_any; + break; } - netif_rx(skb); - return -1; - } else { - return 1; + + x = xfrm_state_lookup_byaddr(net, skb->mark, dst, src, proto, AF_INET6); + if (!x) + continue; + + spin_lock(&x->lock); + + if ((!i || (x->props.flags & XFRM_STATE_WILDRECV)) && + likely(x->km.state == XFRM_STATE_VALID) && + !xfrm_state_check_expire(x)) { + spin_unlock(&x->lock); + if (x->type->input(x, skb) > 0) { + /* found a valid state */ + break; + } + } else + spin_unlock(&x->lock); + + xfrm_state_put(x); + x = NULL; } -drop_unlock: + if (!x) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); + xfrm_audit_state_notfound_simple(skb, AF_INET6); + goto drop; + } + + skb->sp->xvec[skb->sp->len++] = x; + + spin_lock(&x->lock); + + x->curlft.bytes += skb->len; + x->curlft.packets++; + spin_unlock(&x->lock); - xfrm_state_put(x); + + return 1; + drop: - while (--xfrm_nr >= 0) - xfrm_state_put(xfrm_vec[xfrm_nr].xvec); - kfree_skb(skb); return -1; } -EXPORT_SYMBOL(xfrm6_rcv_spi); - -int xfrm6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) -{ - return xfrm6_rcv_spi(pskb, nhoffp, 0); -} +EXPORT_SYMBOL(xfrm6_input_addr); diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c new file mode 100644 index 00000000000..9949a356d62 --- /dev/null +++ b/net/ipv6/xfrm6_mode_beet.c @@ -0,0 +1,131 @@ +/* + * xfrm6_mode_beet.c - BEET mode encapsulation for IPv6. + * + * Copyright (c) 2006 Diego Beltrami <diego.beltrami@gmail.com> + * Miika Komu <miika@iki.fi> + * Herbert Xu <herbert@gondor.apana.org.au> + * Abhinav Pathak <abhinav.pathak@hiit.fi> + * Jeff Ahrenholz <ahrenholz@gmail.com> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/stringify.h> +#include <net/dsfield.h> +#include <net/dst.h> +#include <net/inet_ecn.h> +#include <net/ipv6.h> +#include <net/xfrm.h> + +static void xfrm6_beet_make_header(struct sk_buff *skb) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + + iph->version = 6; + + memcpy(iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, + sizeof(iph->flow_lbl)); + iph->nexthdr = XFRM_MODE_SKB_CB(skb)->protocol; + + ipv6_change_dsfield(iph, 0, XFRM_MODE_SKB_CB(skb)->tos); + iph->hop_limit = XFRM_MODE_SKB_CB(skb)->ttl; +} + +/* Add encapsulation header. + * + * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt. + */ +static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *top_iph; + struct ip_beet_phdr *ph; + int optlen, hdr_len; + + hdr_len = 0; + optlen = XFRM_MODE_SKB_CB(skb)->optlen; + if (unlikely(optlen)) + hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4); + + skb_set_network_header(skb, -x->props.header_len - hdr_len); + if (x->sel.family != AF_INET6) + skb->network_header += IPV4_BEET_PHMAXLEN; + skb->mac_header = skb->network_header + + offsetof(struct ipv6hdr, nexthdr); + skb->transport_header = skb->network_header + sizeof(*top_iph); + ph = (struct ip_beet_phdr *)__skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl-hdr_len); + + xfrm6_beet_make_header(skb); + + top_iph = ipv6_hdr(skb); + if (unlikely(optlen)) { + + BUG_ON(optlen < 0); + + ph->padlen = 4 - (optlen & 4); + ph->hdrlen = optlen / 8; + ph->nexthdr = top_iph->nexthdr; + if (ph->padlen) + memset(ph + 1, IPOPT_NOP, ph->padlen); + + top_iph->nexthdr = IPPROTO_BEETPH; + } + + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; + return 0; +} + +static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *ip6h; + int size = sizeof(struct ipv6hdr); + int err; + + err = skb_cow_head(skb, size + skb->mac_len); + if (err) + goto out; + + __skb_push(skb, size); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + + xfrm6_beet_make_header(skb); + + ip6h = ipv6_hdr(skb); + ip6h->payload_len = htons(skb->len - size); + ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6; + ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6; + err = 0; +out: + return err; +} + +static struct xfrm_mode xfrm6_beet_mode = { + .input2 = xfrm6_beet_input, + .input = xfrm_prepare_input, + .output2 = xfrm6_beet_output, + .output = xfrm6_prepare_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_BEET, + .flags = XFRM_MODE_FLAG_TUNNEL, +}; + +static int __init xfrm6_beet_init(void) +{ + return xfrm_register_mode(&xfrm6_beet_mode, AF_INET6); +} + +static void __exit xfrm6_beet_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_beet_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_beet_init); +module_exit(xfrm6_beet_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_BEET); diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c new file mode 100644 index 00000000000..0e015906f9c --- /dev/null +++ b/net/ipv6/xfrm6_mode_ro.c @@ -0,0 +1,83 @@ +/* + * xfrm6_mode_ro.c - Route optimization mode for IPv6. + * + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ +/* + * Authors: + * Noriaki TAKAMIYA @USAGI + * Masahide NAKAMURA @USAGI + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <linux/stringify.h> +#include <linux/time.h> +#include <net/ipv6.h> +#include <net/xfrm.h> + +/* Add route optimization header space. + * + * The IP header and mutable extension headers will be moved forward to make + * space for the route optimization header. + */ +static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + u8 *prevhdr; + int hdr_len; + + iph = ipv6_hdr(skb); + + hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); + skb_set_network_header(skb, -x->props.header_len); + skb->transport_header = skb->network_header + hdr_len; + __skb_pull(skb, hdr_len); + memmove(ipv6_hdr(skb), iph, hdr_len); + + x->lastused = get_seconds(); + + return 0; +} + +static struct xfrm_mode xfrm6_ro_mode = { + .output = xfrm6_ro_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_ROUTEOPTIMIZATION, +}; + +static int __init xfrm6_ro_init(void) +{ + return xfrm_register_mode(&xfrm6_ro_mode, AF_INET6); +} + +static void __exit xfrm6_ro_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_ro_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_ro_init); +module_exit(xfrm6_ro_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_ROUTEOPTIMIZATION); diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c new file mode 100644 index 00000000000..4e344105b3f --- /dev/null +++ b/net/ipv6/xfrm6_mode_transport.c @@ -0,0 +1,85 @@ +/* + * xfrm6_mode_transport.c - Transport mode encapsulation for IPv6. + * + * Copyright (C) 2002 USAGI/WIDE Project + * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/stringify.h> +#include <net/dst.h> +#include <net/ipv6.h> +#include <net/xfrm.h> + +/* Add encapsulation header. + * + * The IP header and mutable extension headers will be moved forward to make + * space for the encapsulation header. + */ +static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + u8 *prevhdr; + int hdr_len; + + iph = ipv6_hdr(skb); + + hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); + skb_set_network_header(skb, -x->props.header_len); + skb->transport_header = skb->network_header + hdr_len; + __skb_pull(skb, hdr_len); + memmove(ipv6_hdr(skb), iph, hdr_len); + return 0; +} + +/* Remove encapsulation header. + * + * The IP header will be moved over the top of the encapsulation header. + * + * On entry, skb->h shall point to where the IP header should be and skb->nh + * shall be set to where the IP header currently is. skb->data shall point + * to the start of the payload. + */ +static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) +{ + int ihl = skb->data - skb_transport_header(skb); + + if (skb->transport_header != skb->network_header) { + memmove(skb_transport_header(skb), + skb_network_header(skb), ihl); + skb->network_header = skb->transport_header; + } + ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - + sizeof(struct ipv6hdr)); + skb_reset_transport_header(skb); + return 0; +} + +static struct xfrm_mode xfrm6_transport_mode = { + .input = xfrm6_transport_input, + .output = xfrm6_transport_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_TRANSPORT, +}; + +static int __init xfrm6_transport_init(void) +{ + return xfrm_register_mode(&xfrm6_transport_mode, AF_INET6); +} + +static void __exit xfrm6_transport_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_transport_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_transport_init); +module_exit(xfrm6_transport_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TRANSPORT); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c new file mode 100644 index 00000000000..901ef6f8add --- /dev/null +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -0,0 +1,126 @@ +/* + * xfrm6_mode_tunnel.c - Tunnel mode encapsulation for IPv6. + * + * Copyright (C) 2002 USAGI/WIDE Project + * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au> + */ + +#include <linux/gfp.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/stringify.h> +#include <net/dsfield.h> +#include <net/dst.h> +#include <net/inet_ecn.h> +#include <net/ip6_route.h> +#include <net/ipv6.h> +#include <net/xfrm.h> + +static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) +{ + const struct ipv6hdr *outer_iph = ipv6_hdr(skb); + struct ipv6hdr *inner_iph = ipipv6_hdr(skb); + + if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) + IP6_ECN_set_ce(inner_iph); +} + +/* Add encapsulation header. + * + * The top IP header will be constructed per RFC 2401. + */ +static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct ipv6hdr *top_iph; + int dsfield; + + skb_set_network_header(skb, -x->props.header_len); + skb->mac_header = skb->network_header + + offsetof(struct ipv6hdr, nexthdr); + skb->transport_header = skb->network_header + sizeof(*top_iph); + top_iph = ipv6_hdr(skb); + + top_iph->version = 6; + + memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, + sizeof(top_iph->flow_lbl)); + top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family); + + if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP) + dsfield = 0; + else + dsfield = XFRM_MODE_SKB_CB(skb)->tos; + dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos); + if (x->props.flags & XFRM_STATE_NOECN) + dsfield &= ~INET_ECN_MASK; + ipv6_change_dsfield(top_iph, 0, dsfield); + top_iph->hop_limit = ip6_dst_hoplimit(dst->child); + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; + return 0; +} + +#define for_each_input_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) + + +static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) +{ + int err = -EINVAL; + + if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) + goto out; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto out; + + err = skb_unclone(skb, GFP_ATOMIC); + if (err) + goto out; + + if (x->props.flags & XFRM_STATE_DECAP_DSCP) + ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), + ipipv6_hdr(skb)); + if (!(x->props.flags & XFRM_STATE_NOECN)) + ipip6_ecn_decapsulate(skb); + + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + + err = 0; + +out: + return err; +} + +static struct xfrm_mode xfrm6_tunnel_mode = { + .input2 = xfrm6_mode_tunnel_input, + .input = xfrm_prepare_input, + .output2 = xfrm6_mode_tunnel_output, + .output = xfrm6_prepare_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_TUNNEL, + .flags = XFRM_MODE_FLAG_TUNNEL, +}; + +static int __init xfrm6_mode_tunnel_init(void) +{ + return xfrm_register_mode(&xfrm6_tunnel_mode, AF_INET6); +} + +static void __exit xfrm6_mode_tunnel_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_tunnel_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_mode_tunnel_init); +module_exit(xfrm6_mode_tunnel_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TUNNEL); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 6b9867717d1..433672d07d0 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -2,143 +2,173 @@ * xfrm6_output.c - Common IPsec encapsulation code for IPv6. * Copyright (C) 2002 USAGI/WIDE Project * Copyright (c) 2004 Herbert Xu <herbert@gondor.apana.org.au> - * + * * 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. */ +#include <linux/if_ether.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/skbuff.h> -#include <linux/spinlock.h> #include <linux/icmpv6.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> +#include <linux/netfilter_ipv6.h> +#include <net/dst.h> #include <net/ipv6.h> +#include <net/ip6_route.h> #include <net/xfrm.h> -/* Add encapsulation header. - * - * In transport mode, the IP header and mutable extension headers will be moved - * forward to make space for the encapsulation header. - * - * In tunnel mode, the top IP header will be constructed per RFC 2401. - * The following fields in it shall be filled in by x->type->output: - * payload_len - * - * On exit, skb->h will be set to the start of the encapsulation header to be - * filled in by x->type->output and skb->nh will be set to the nextheader field - * of the extension header directly preceding the encapsulation header, or in - * its absence, that of the top IP header. The value of skb->data will always - * point to the top IP header. - */ -static void xfrm6_encap(struct sk_buff *skb) +int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, + u8 **prevhdr) { - struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; - struct ipv6hdr *iph, *top_iph; - int dsfield; + return ip6_find_1stfragopt(skb, prevhdr); +} + +EXPORT_SYMBOL(xfrm6_find_1stfragopt); - skb_push(skb, x->props.header_len); - iph = skb->nh.ipv6h; +static int xfrm6_local_dontfrag(struct sk_buff *skb) +{ + int proto; + struct sock *sk = skb->sk; - if (!x->props.mode) { - u8 *prevhdr; - int hdr_len; + if (sk) { + if (sk->sk_family != AF_INET6) + return 0; - hdr_len = ip6_find_1stfragopt(skb, &prevhdr); - skb->nh.raw = prevhdr - x->props.header_len; - skb->h.raw = skb->data + hdr_len; - memmove(skb->data, iph, hdr_len); - return; + proto = sk->sk_protocol; + if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) + return inet6_sk(sk)->dontfrag; } - skb->nh.raw = skb->data; - top_iph = skb->nh.ipv6h; - skb->nh.raw = &top_iph->nexthdr; - skb->h.ipv6h = top_iph + 1; - - top_iph->version = 6; - top_iph->priority = iph->priority; - top_iph->flow_lbl[0] = iph->flow_lbl[0]; - top_iph->flow_lbl[1] = iph->flow_lbl[1]; - top_iph->flow_lbl[2] = iph->flow_lbl[2]; - dsfield = ipv6_get_dsfield(top_iph); - dsfield = INET_ECN_encapsulate(dsfield, dsfield); - if (x->props.flags & XFRM_STATE_NOECN) - dsfield &= ~INET_ECN_MASK; - ipv6_change_dsfield(top_iph, 0, dsfield); - top_iph->nexthdr = IPPROTO_IPV6; - top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT); - ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); + 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); +} + +void xfrm6_local_error(struct sk_buff *skb, u32 mtu) +{ + struct flowi6 fl6; + const struct ipv6hdr *hdr; + struct sock *sk = skb->sk; + + hdr = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb); + fl6.fl6_dport = inet_sk(sk)->inet_dport; + fl6.daddr = hdr->daddr; + + ipv6_local_error(sk, EMSGSIZE, &fl6, mtu); } static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); mtu = dst_mtu(dst); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if (skb->len > mtu) { + if (!skb->ignore_df && skb->len > mtu) { skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev); + + if (xfrm6_local_dontfrag(skb)) + xfrm6_local_rxpmtu(skb, mtu); + else if (skb->sk) + xfrm_local_error(skb, mtu); + else + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ret = -EMSGSIZE; } return ret; } -int xfrm6_output(struct sk_buff *skb) +int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; int err; - - if (skb->ip_summed == CHECKSUM_HW) { - err = skb_checksum_help(skb, 0); - if (err) - goto error_nolock; - } - if (x->props.mode) { - err = xfrm6_tunnel_check_size(skb); - if (err) - goto error_nolock; - } - - spin_lock_bh(&x->lock); - err = xfrm_state_check(x, skb); + err = xfrm6_tunnel_check_size(skb); if (err) - goto error; + return err; + + XFRM_MODE_SKB_CB(skb)->protocol = ipv6_hdr(skb)->nexthdr; - xfrm6_encap(skb); + return xfrm6_extract_header(skb); +} - err = x->type->output(x, skb); +int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + err = xfrm_inner_extract_output(x, skb); if (err) - goto error; + return err; + + skb->ignore_df = 1; + + return x->outer_mode->output2(x, skb); +} +EXPORT_SYMBOL(xfrm6_prepare_output); + +int xfrm6_output_finish(struct sk_buff *skb) +{ + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + skb->protocol = htons(ETH_P_IPV6); + +#ifdef CONFIG_NETFILTER + IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; +#endif - x->curlft.bytes += skb->len; - x->curlft.packets++; + return xfrm_output(skb); +} - spin_unlock_bh(&x->lock); +static int __xfrm6_output(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + int mtu; - skb->nh.raw = skb->data; - - if (!(skb->dst = dst_pop(dst))) { - err = -EHOSTUNREACH; - goto error_nolock; +#ifdef CONFIG_NETFILTER + if (!x) { + IP6CB(skb)->flags |= IP6SKB_REROUTED; + return dst_output(skb); + } +#endif + + if (skb->protocol == htons(ETH_P_IPV6)) + mtu = ip6_skb_dst_mtu(skb); + else + mtu = dst_mtu(skb_dst(skb)); + + if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { + xfrm6_local_rxpmtu(skb, mtu); + return -EMSGSIZE; + } else if (!skb->ignore_df && skb->len > mtu && skb->sk) { + xfrm_local_error(skb, mtu); + return -EMSGSIZE; } - err = NET_XMIT_BYPASS; - -out_exit: - return err; -error: - spin_unlock_bh(&x->lock); -error_nolock: - kfree_skb(skb); - goto out_exit; + + if (x->props.mode == XFRM_MODE_TUNNEL && + ((skb->len > mtu && !skb_is_gso(skb)) || + dst_allfrag(skb_dst(skb)))) { + return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); + } + return x->outer_mode->afinfo->output_finish(skb); +} + +int xfrm6_output(struct sock *sk, struct sk_buff *skb) +{ + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, + NULL, skb_dst(skb)->dev, __xfrm6_output, + !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index cf1d91e74c8..2a0bbda2c76 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -8,257 +8,234 @@ * IPv6 support * YOSHIFUJI Hideaki * Split up af-specific portion - * + * */ -#include <asm/bug.h> -#include <linux/compiler.h> -#include <linux/config.h> +#include <linux/err.h> +#include <linux/kernel.h> #include <linux/netdevice.h> #include <net/addrconf.h> +#include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#if IS_ENABLED(CONFIG_IPV6_MIP6) +#include <net/mip6.h> +#endif -static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static struct xfrm_type_map xfrm6_type_map = { .lock = RW_LOCK_UNLOCKED }; - -static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl) +static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr) { - int err = 0; - *dst = (struct xfrm_dst*)ip6_route_output(NULL, fl); - if (!*dst) - err = -ENETUNREACH; - return err; + struct flowi6 fl6; + struct dst_entry *dst; + int err; + + memset(&fl6, 0, sizeof(fl6)); + memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); + if (saddr) + memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); + + dst = ip6_route_output(net, NULL, &fl6); + + err = dst->error; + if (dst->error) { + dst_release(dst); + dst = ERR_PTR(err); + } + + return dst; } -static struct dst_entry * -__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) +static int xfrm6_get_saddr(struct net *net, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; + struct net_device *dev; - /* Still not clear if we should set fl->fl6_{src,dst}... */ - read_lock_bh(&policy->lock); - for (dst = policy->bundles; dst; dst = dst->next) { - struct xfrm_dst *xdst = (struct xfrm_dst*)dst; - struct in6_addr fl_dst_prefix, fl_src_prefix; - - ipv6_addr_prefix(&fl_dst_prefix, - &fl->fl6_dst, - xdst->u.rt6.rt6i_dst.plen); - ipv6_addr_prefix(&fl_src_prefix, - &fl->fl6_src, - xdst->u.rt6.rt6i_src.plen); - if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) && - ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) && - xfrm_bundle_ok(xdst, fl, AF_INET6)) { - dst_clone(dst); - break; - } - } - read_unlock_bh(&policy->lock); - return dst; + dst = xfrm6_dst_lookup(net, 0, NULL, daddr); + if (IS_ERR(dst)) + return -EHOSTUNREACH; + + dev = ip6_dst_idev(dst)->dev; + ipv6_dev_get_saddr(dev_net(dev), dev, + (struct in6_addr *)&daddr->a6, 0, + (struct in6_addr *)&saddr->a6); + dst_release(dst); + return 0; } -/* Allocate chain of dst_entry's, attach known xfrm's, calculate - * all the metrics... Shortly, bundle a bundle. - */ +static int xfrm6_get_tos(const struct flowi *fl) +{ + return 0; +} -static int -__xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx, - struct flowi *fl, struct dst_entry **dst_p) +static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst) { - struct dst_entry *dst, *dst_prev; - struct rt6_info *rt0 = (struct rt6_info*)(*dst_p); - struct rt6_info *rt = rt0; - struct in6_addr *remote = &fl->fl6_dst; - struct in6_addr *local = &fl->fl6_src; - struct flowi fl_tunnel = { - .nl_u = { - .ip6_u = { - .saddr = *local, - .daddr = *remote - } - } - }; - int i; - int err = 0; - int header_len = 0; - int trailer_len = 0; - - dst = dst_prev = NULL; - dst_hold(&rt->u.dst); - - for (i = 0; i < nx; i++) { - struct dst_entry *dst1 = dst_alloc(&xfrm6_dst_ops); - struct xfrm_dst *xdst; - int tunnel = 0; - - if (unlikely(dst1 == NULL)) { - err = -ENOBUFS; - dst_release(&rt->u.dst); - goto error; - } + struct rt6_info *rt = (struct rt6_info *)xdst; - if (!dst) - dst = dst1; - else { - dst_prev->child = dst1; - dst1->flags |= DST_NOHASH; - dst_clone(dst1); - } + rt6_init_peer(rt, net->ipv6.peers); +} - xdst = (struct xfrm_dst *)dst1; - xdst->route = &rt->u.dst; +static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, + int nfheader_len) +{ + if (dst->ops->family == AF_INET6) { + struct rt6_info *rt = (struct rt6_info*)dst; if (rt->rt6i_node) - xdst->route_cookie = rt->rt6i_node->fn_sernum; - - dst1->next = dst_prev; - dst_prev = dst1; - if (xfrm[i]->props.mode) { - remote = (struct in6_addr*)&xfrm[i]->id.daddr; - local = (struct in6_addr*)&xfrm[i]->props.saddr; - tunnel = 1; - } - header_len += xfrm[i]->props.header_len; - trailer_len += xfrm[i]->props.trailer_len; - - if (tunnel) { - ipv6_addr_copy(&fl_tunnel.fl6_dst, remote); - ipv6_addr_copy(&fl_tunnel.fl6_src, local); - err = xfrm_dst_lookup((struct xfrm_dst **) &rt, - &fl_tunnel, AF_INET6); - if (err) - goto error; - } else - dst_hold(&rt->u.dst); + path->path_cookie = rt->rt6i_node->fn_sernum; } - dst_prev->child = &rt->u.dst; - dst->path = &rt->u.dst; - if (rt->rt6i_node) - ((struct xfrm_dst *)dst)->path_cookie = rt->rt6i_node->fn_sernum; - - *dst_p = dst; - dst = dst_prev; - - dst_prev = *dst_p; - i = 0; - for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) { - struct xfrm_dst *x = (struct xfrm_dst*)dst_prev; - - dst_prev->xfrm = xfrm[i++]; - dst_prev->dev = rt->u.dst.dev; - if (rt->u.dst.dev) - dev_hold(rt->u.dst.dev); - dst_prev->obsolete = -1; - dst_prev->flags |= DST_HOST; - dst_prev->lastuse = jiffies; - dst_prev->header_len = header_len; - dst_prev->trailer_len = trailer_len; - memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics)); - - /* Copy neighbour for reachability confirmation */ - dst_prev->neighbour = neigh_clone(rt->u.dst.neighbour); - dst_prev->input = rt->u.dst.input; - dst_prev->output = xfrm6_output; - /* Sheit... I remember I did this right. Apparently, - * it was magically lost, so this code needs audit */ - x->u.rt6.rt6i_flags = rt0->rt6i_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL); - x->u.rt6.rt6i_metric = rt0->rt6i_metric; - x->u.rt6.rt6i_node = rt0->rt6i_node; - x->u.rt6.rt6i_gateway = rt0->rt6i_gateway; - memcpy(&x->u.rt6.rt6i_gateway, &rt0->rt6i_gateway, sizeof(x->u.rt6.rt6i_gateway)); - x->u.rt6.rt6i_dst = rt0->rt6i_dst; - x->u.rt6.rt6i_src = rt0->rt6i_src; - x->u.rt6.rt6i_idev = rt0->rt6i_idev; - in6_dev_hold(rt0->rt6i_idev); - header_len -= x->u.dst.xfrm->props.header_len; - trailer_len -= x->u.dst.xfrm->props.trailer_len; - } + path->u.rt6.rt6i_nfheader_len = nfheader_len; - xfrm_init_pmtu(dst); return 0; +} -error: - if (dst) - dst_free(dst); - return err; +static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, + const struct flowi *fl) +{ + struct rt6_info *rt = (struct rt6_info*)xdst->route; + + xdst->u.dst.dev = dev; + dev_hold(dev); + + xdst->u.rt6.rt6i_idev = in6_dev_get(dev); + if (!xdst->u.rt6.rt6i_idev) { + dev_put(dev); + return -ENODEV; + } + + rt6_transfer_peer(&xdst->u.rt6, rt); + + /* Sheit... I remember I did this right. Apparently, + * it was magically lost, so this code needs audit */ + xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | + RTF_LOCAL); + xdst->u.rt6.rt6i_metric = rt->rt6i_metric; + xdst->u.rt6.rt6i_node = rt->rt6i_node; + if (rt->rt6i_node) + xdst->route_cookie = rt->rt6i_node->fn_sernum; + xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; + xdst->u.rt6.rt6i_dst = rt->rt6i_dst; + xdst->u.rt6.rt6i_src = rt->rt6i_src; + + return 0; } static inline void -_decode_session6(struct sk_buff *skb, struct flowi *fl) +_decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) { - u16 offset = sizeof(struct ipv6hdr); - struct ipv6hdr *hdr = skb->nh.ipv6h; - struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); - u8 nexthdr = skb->nh.ipv6h->nexthdr; - - memset(fl, 0, sizeof(struct flowi)); - ipv6_addr_copy(&fl->fl6_dst, &hdr->daddr); - ipv6_addr_copy(&fl->fl6_src, &hdr->saddr); + struct flowi6 *fl6 = &fl->u.ip6; + int onlyproto = 0; + u16 offset = skb_network_header_len(skb); + const struct ipv6hdr *hdr = ipv6_hdr(skb); + struct ipv6_opt_hdr *exthdr; + const unsigned char *nh = skb_network_header(skb); + u8 nexthdr = nh[IP6CB(skb)->nhoff]; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; + + memset(fl6, 0, sizeof(struct flowi6)); + fl6->flowi6_mark = skb->mark; + fl6->flowi6_oif = reverse ? skb->skb_iif : oif; + + 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)) { + nh = skb_network_header(skb); + exthdr = (struct ipv6_opt_hdr *)(nh + offset); - while (pskb_may_pull(skb, skb->nh.raw + offset + 1 - skb->data)) { switch (nexthdr) { + case NEXTHDR_FRAGMENT: + onlyproto = 1; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: offset += ipv6_optlen(exthdr); nexthdr = exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); + exthdr = (struct ipv6_opt_hdr *)(nh + offset); break; case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: - if (pskb_may_pull(skb, skb->nh.raw + offset + 4 - skb->data)) { - u16 *ports = (u16 *)exthdr; + case IPPROTO_DCCP: + if (!onlyproto && (nh + offset + 4 < skb->data || + pskb_may_pull(skb, nh + offset + 4 - skb->data))) { + __be16 *ports = (__be16 *)exthdr; - fl->fl_ip_sport = ports[0]; - fl->fl_ip_dport = ports[1]; + fl6->fl6_sport = ports[!!reverse]; + fl6->fl6_dport = ports[!reverse]; } - fl->proto = nexthdr; + fl6->flowi6_proto = nexthdr; return; case IPPROTO_ICMPV6: - if (pskb_may_pull(skb, skb->nh.raw + offset + 2 - skb->data)) { + if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { u8 *icmp = (u8 *)exthdr; - fl->fl_icmp_type = icmp[0]; - fl->fl_icmp_code = icmp[1]; + fl6->fl6_icmp_type = icmp[0]; + fl6->fl6_icmp_code = icmp[1]; } - fl->proto = nexthdr; + fl6->flowi6_proto = nexthdr; return; +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPPROTO_MH: + if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { + struct ip6_mh *mh; + mh = (struct ip6_mh *)exthdr; + + fl6->fl6_mh_type = mh->ip6mh_type; + } + fl6->flowi6_proto = nexthdr; + return; +#endif + /* XXX Why are there these headers? */ case IPPROTO_AH: case IPPROTO_ESP: case IPPROTO_COMP: default: - fl->fl_ipsec_spi = 0; - fl->proto = nexthdr; + fl6->fl6_ipsec_spi = 0; + fl6->flowi6_proto = nexthdr; return; - }; + } } } -static inline int xfrm6_garbage_collect(void) +static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - read_lock(&xfrm6_policy_afinfo.lock); - xfrm6_policy_afinfo.garbage_collect(); - read_unlock(&xfrm6_policy_afinfo.lock); - return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); + + xfrm6_policy_afinfo.garbage_collect(net); + return dst_entries_get_fast(ops) > ops->gc_thresh * 2; } -static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) +static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, mtu); + path->ops->update_pmtu(path, sk, skb, mtu); +} + +static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + struct dst_entry *path = xdst->route; + + path->ops->redirect(path, sk, skb); } static void xfrm6_dst_destroy(struct dst_entry *dst) @@ -267,6 +244,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); + dst_destroy_metrics_generic(dst); + if (rt6_has_peer(&xdst->u.rt6)) { + struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6); + inet_putpeer(peer); + } xfrm_dst_destroy(xdst); } @@ -280,7 +262,8 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xdst = (struct xfrm_dst *)dst; if (xdst->u.rt6.rt6i_idev->dev == dev) { - struct inet6_dev *loopback_idev = in6_dev_get(&loopback_dev); + struct inet6_dev *loopback_idev = + in6_dev_get(dev_net(dev)->loopback_dev); BUG_ON(!loopback_idev); do { @@ -298,29 +281,33 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, static struct dst_ops xfrm6_dst_ops = { .family = AF_INET6, - .protocol = __constant_htons(ETH_P_IPV6), + .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .redirect = xfrm6_redirect, + .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, - .gc_thresh = 1024, - .entry_size = sizeof(struct xfrm_dst), + .local_out = __ip6_local_out, + .gc_thresh = 32768, }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .family = AF_INET6, - .lock = RW_LOCK_UNLOCKED, - .type_map = &xfrm6_type_map, .dst_ops = &xfrm6_dst_ops, .dst_lookup = xfrm6_dst_lookup, - .find_bundle = __xfrm6_find_bundle, - .bundle_create = __xfrm6_bundle_create, + .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, + .get_tos = xfrm6_get_tos, + .init_dst = xfrm6_init_dst, + .init_path = xfrm6_init_path, + .fill_dst = xfrm6_fill_dst, + .blackhole_route = ip6_blackhole_route, }; -static void __init xfrm6_policy_init(void) +static int __init xfrm6_policy_init(void) { - xfrm_policy_register_afinfo(&xfrm6_policy_afinfo); + return xfrm_policy_register_afinfo(&xfrm6_policy_afinfo); } static void xfrm6_policy_fini(void) @@ -328,15 +315,103 @@ static void xfrm6_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo); } -void __init xfrm6_init(void) +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm6_policy_table[] = { + { + .procname = "xfrm6_gc_thresh", + .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static int __net_init xfrm6_net_init(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = xfrm6_policy_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh; + } + + hdr = register_net_sysctl(net, "net/ipv6", table); + if (!hdr) + goto err_reg; + + net->ipv6.sysctl.xfrm6_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit xfrm6_net_exit(struct net *net) { - xfrm6_policy_init(); - xfrm6_state_init(); + struct ctl_table *table; + + if (net->ipv6.sysctl.xfrm6_hdr == NULL) + return; + + table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations xfrm6_net_ops = { + .init = xfrm6_net_init, + .exit = xfrm6_net_exit, +}; +#endif + +int __init xfrm6_init(void) +{ + int ret; + + dst_entries_init(&xfrm6_dst_ops); + + ret = xfrm6_policy_init(); + if (ret) { + dst_entries_destroy(&xfrm6_dst_ops); + goto out; + } + ret = xfrm6_state_init(); + if (ret) + goto out_policy; + + ret = xfrm6_protocol_init(); + if (ret) + goto out_state; + +#ifdef CONFIG_SYSCTL + register_pernet_subsys(&xfrm6_net_ops); +#endif +out: + return ret; +out_state: + xfrm6_state_fini(); +out_policy: + xfrm6_policy_fini(); + goto out; } void xfrm6_fini(void) { - //xfrm6_input_fini(); +#ifdef CONFIG_SYSCTL + unregister_pernet_subsys(&xfrm6_net_ops); +#endif + xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); + dst_entries_destroy(&xfrm6_dst_ops); } diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c new file mode 100644 index 00000000000..54d13f8dbba --- /dev/null +++ b/net/ipv6/xfrm6_protocol.c @@ -0,0 +1,279 @@ +/* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/xfrm4_protocol.c + * + * 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. + */ + +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <linux/icmpv6.h> +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; +static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; +static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; +static DEFINE_MUTEX(xfrm6_protocol_mutex); + +static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp6_handlers; + case IPPROTO_AH: + return &ah6_handlers; + case IPPROTO_COMP: + return &ipcomp6_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm6_protocol *handler; + struct xfrm6_protocol __rcu **head = proto_handlers(protocol); + + if (!head) + return 0; + + for_each_protocol_rcu(*proto_handlers(protocol), handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm6_rcv_cb); + +static int xfrm6_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(esp6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(esp6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static int xfrm6_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(ah6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(ah6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static int xfrm6_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(ipcomp6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(ipcomp6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static const struct inet6_protocol esp6_protocol = { + .handler = xfrm6_esp_rcv, + .err_handler = xfrm6_esp_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static const struct inet6_protocol ah6_protocol = { + .handler = xfrm6_ah_rcv, + .err_handler = xfrm6_ah_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static const struct inet6_protocol ipcomp6_protocol = { + .handler = xfrm6_ipcomp_rcv, + .err_handler = xfrm6_ipcomp_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static struct xfrm_input_afinfo xfrm6_input_afinfo = { + .family = AF_INET6, + .owner = THIS_MODULE, + .callback = xfrm6_rcv_cb, +}; + +static inline const struct inet6_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp6_protocol; + case IPPROTO_AH: + return &ah6_protocol; + case IPPROTO_COMP: + return &ipcomp6_protocol; + } + + return NULL; +} + +int xfrm6_protocol_register(struct xfrm6_protocol *handler, + unsigned char protocol) +{ + struct xfrm6_protocol __rcu **pprev; + struct xfrm6_protocol *t; + bool add_netproto = false; + int ret = -EEXIST; + int priority = handler->priority; + + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + + mutex_lock(&xfrm6_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm6_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm6_protocol_mutex); + + if (add_netproto) { + if (inet6_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm6_protocol_register); + +int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, + unsigned char protocol) +{ + struct xfrm6_protocol __rcu **pprev; + struct xfrm6_protocol *t; + int ret = -ENOENT; + + if (!proto_handlers(protocol) || !netproto(protocol)) + return -EINVAL; + + mutex_lock(&xfrm6_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm6_protocol_mutex))) { + if (inet6_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm6_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm6_protocol_deregister); + +int __init xfrm6_protocol_init(void) +{ + return xfrm_input_register_afinfo(&xfrm6_input_afinfo); +} + +void xfrm6_protocol_fini(void) +{ + xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); +} diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index bf0d0abc387..3fc970135fc 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -8,33 +8,42 @@ * IPv6 support * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion - * + * */ #include <net/xfrm.h> #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> - -static struct xfrm_state_afinfo xfrm6_state_afinfo; +#include <net/addrconf.h> static void -__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { + const struct flowi6 *fl6 = &fl->u.ip6; + /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst); - ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src); - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = ~0; - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = ~0; - x->sel.prefixlen_d = 128; - x->sel.prefixlen_s = 128; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; + *(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); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET6; + sel->prefixlen_d = 128; + sel->prefixlen_s = 128; + sel->proto = fl6->flowi6_proto; + sel->ifindex = fl6->flowi6_oif; +} + +static void +xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) +{ x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); @@ -46,87 +55,140 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->props.family = AF_INET6; } -static struct xfrm_state * -__xfrm6_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto) +/* distribution counting sort function for xfrm_state and xfrm_tmpl */ +static int +__xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass) { - unsigned h = __xfrm6_spi_hash(daddr, spi, proto); - struct xfrm_state *x; - - list_for_each_entry(x, xfrm6_state_afinfo.state_byspi+h, byspi) { - if (x->props.family == AF_INET6 && - spi == x->id.spi && - ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) && - proto == x->id.proto) { - xfrm_state_hold(x); - return x; - } + int i; + int class[XFRM_MAX_DEPTH]; + int count[maxclass]; + + memset(count, 0, sizeof(count)); + + for (i = 0; i < n; i++) { + int c; + class[i] = c = cmp(src[i]); + count[c]++; } - return NULL; + + for (i = 2; i < maxclass; i++) + count[i] += count[i - 1]; + + for (i = 0; i < n; i++) { + dst[count[class[i] - 1]++] = src[i]; + src[i] = NULL; + } + + return 0; } -static struct xfrm_state * -__xfrm6_find_acq(u8 mode, u32 reqid, u8 proto, - xfrm_address_t *daddr, xfrm_address_t *saddr, - int create) +/* + * Rule for xfrm_state: + * + * rule 1: select IPsec transport except AH + * rule 2: select MIPv6 RO or inbound trigger + * rule 3: select IPsec transport AH + * rule 4: select IPsec tunnel + * rule 5: others + */ +static int __xfrm6_state_sort_cmp(void *p) { - struct xfrm_state *x, *x0; - unsigned h = __xfrm6_dst_hash(daddr); - - x0 = NULL; - - list_for_each_entry(x, xfrm6_state_afinfo.state_bydst+h, bydst) { - if (x->props.family == AF_INET6 && - ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) && - mode == x->props.mode && - proto == x->id.proto && - ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)x->props.saddr.a6) && - reqid == x->props.reqid && - x->km.state == XFRM_STATE_ACQ && - !x->id.spi) { - x0 = x; - break; - } + struct xfrm_state *v = p; + + switch (v->props.mode) { + case XFRM_MODE_TRANSPORT: + if (v->id.proto != IPPROTO_AH) + return 1; + else + return 3; +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case XFRM_MODE_ROUTEOPTIMIZATION: + case XFRM_MODE_IN_TRIGGER: + return 2; +#endif + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + return 4; } - if (!x0 && create && (x0 = xfrm_state_alloc()) != NULL) { - ipv6_addr_copy((struct in6_addr *)x0->sel.daddr.a6, - (struct in6_addr *)daddr); - ipv6_addr_copy((struct in6_addr *)x0->sel.saddr.a6, - (struct in6_addr *)saddr); - x0->sel.prefixlen_d = 128; - x0->sel.prefixlen_s = 128; - ipv6_addr_copy((struct in6_addr *)x0->props.saddr.a6, - (struct in6_addr *)saddr); - x0->km.state = XFRM_STATE_ACQ; - ipv6_addr_copy((struct in6_addr *)x0->id.daddr.a6, - (struct in6_addr *)daddr); - x0->id.proto = proto; - x0->props.family = AF_INET6; - x0->props.mode = mode; - x0->props.reqid = reqid; - x0->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES; - xfrm_state_hold(x0); - x0->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ; - add_timer(&x0->timer); - xfrm_state_hold(x0); - list_add_tail(&x0->bydst, xfrm6_state_afinfo.state_bydst+h); - wake_up(&km_waitq); + return 5; +} + +static int +__xfrm6_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n) +{ + return __xfrm6_sort((void **)dst, (void **)src, n, + __xfrm6_state_sort_cmp, 6); +} + +/* + * Rule for xfrm_tmpl: + * + * rule 1: select IPsec transport + * rule 2: select MIPv6 RO or inbound trigger + * rule 3: select IPsec tunnel + * rule 4: others + */ +static int __xfrm6_tmpl_sort_cmp(void *p) +{ + struct xfrm_tmpl *v = p; + switch (v->mode) { + case XFRM_MODE_TRANSPORT: + return 1; +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case XFRM_MODE_ROUTEOPTIMIZATION: + case XFRM_MODE_IN_TRIGGER: + return 2; +#endif + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + return 3; } - if (x0) - xfrm_state_hold(x0); - return x0; + return 4; +} + +static int +__xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n) +{ + return __xfrm6_sort((void **)dst, (void **)src, n, + __xfrm6_tmpl_sort_cmp, 5); +} + +int xfrm6_extract_header(struct sk_buff *skb) +{ + struct ipv6hdr *iph = ipv6_hdr(skb); + + XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); + XFRM_MODE_SKB_CB(skb)->id = 0; + XFRM_MODE_SKB_CB(skb)->frag_off = htons(IP_DF); + XFRM_MODE_SKB_CB(skb)->tos = ipv6_get_dsfield(iph); + XFRM_MODE_SKB_CB(skb)->ttl = iph->hop_limit; + XFRM_MODE_SKB_CB(skb)->optlen = 0; + memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl, + sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); + + return 0; } static struct xfrm_state_afinfo xfrm6_state_afinfo = { .family = AF_INET6, - .lock = RW_LOCK_UNLOCKED, + .proto = IPPROTO_IPV6, + .eth_proto = htons(ETH_P_IPV6), + .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, - .state_lookup = __xfrm6_state_lookup, - .find_acq = __xfrm6_find_acq, + .init_temprop = xfrm6_init_temprop, + .tmpl_sort = __xfrm6_tmpl_sort, + .state_sort = __xfrm6_state_sort, + .output = xfrm6_output, + .output_finish = xfrm6_output_finish, + .extract_input = xfrm6_extract_input, + .extract_output = xfrm6_extract_output, + .transport_finish = xfrm6_transport_finish, + .local_error = xfrm6_local_error, }; -void __init xfrm6_state_init(void) +int __init xfrm6_state_init(void) { - xfrm_state_register_afinfo(&xfrm6_state_afinfo); + return xfrm_state_register_afinfo(&xfrm6_state_afinfo); } void xfrm6_state_fini(void) diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index fbef7826a74..1c66465a42d 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -5,15 +5,14 @@ * 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. - * + * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * + * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> @@ -21,435 +20,251 @@ * Based on net/ipv4/xfrm4_tunnel.c * */ -#include <linux/config.h> #include <linux/module.h> #include <linux/xfrm.h> -#include <linux/list.h> +#include <linux/slab.h> +#include <linux/rculist.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipv6.h> -#include <net/protocol.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> +#include <linux/mutex.h> +#include <net/netns/generic.h> -#ifdef CONFIG_IPV6_XFRM6_TUNNEL_DEBUG -# define X6TDEBUG 3 -#else -# define X6TDEBUG 1 -#endif +#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256 +#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256 -#define X6TPRINTK(fmt, args...) printk(fmt, ## args) -#define X6TNOPRINTK(fmt, args...) do { ; } while(0) +#define XFRM6_TUNNEL_SPI_MIN 1 +#define XFRM6_TUNNEL_SPI_MAX 0xffffffff -#if X6TDEBUG >= 1 -# define X6TPRINTK1 X6TPRINTK -#else -# define X6TPRINTK1 X6TNOPRINTK -#endif +struct xfrm6_tunnel_net { + struct hlist_head spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE]; + struct hlist_head spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE]; + u32 spi; +}; -#if X6TDEBUG >= 3 -# define X6TPRINTK3 X6TPRINTK -#else -# define X6TPRINTK3 X6TNOPRINTK -#endif +static int xfrm6_tunnel_net_id __read_mostly; +static inline struct xfrm6_tunnel_net *xfrm6_tunnel_pernet(struct net *net) +{ + return net_generic(net, xfrm6_tunnel_net_id); +} /* - * xfrm_tunnel_spi things are for allocating unique id ("spi") + * xfrm_tunnel_spi things are for allocating unique id ("spi") * per xfrm_address_t. */ struct xfrm6_tunnel_spi { - struct hlist_node list_byaddr; - struct hlist_node list_byspi; - xfrm_address_t addr; - u32 spi; - atomic_t refcnt; -#ifdef XFRM6_TUNNEL_SPI_MAGIC - u32 magic; -#endif + struct hlist_node list_byaddr; + struct hlist_node list_byspi; + xfrm_address_t addr; + u32 spi; + atomic_t refcnt; + struct rcu_head rcu_head; }; -#ifdef CONFIG_IPV6_XFRM6_TUNNEL_DEBUG -# define XFRM6_TUNNEL_SPI_MAGIC 0xdeadbeef -#endif - -static DEFINE_RWLOCK(xfrm6_tunnel_spi_lock); - -static u32 xfrm6_tunnel_spi; +static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); -#define XFRM6_TUNNEL_SPI_MIN 1 -#define XFRM6_TUNNEL_SPI_MAX 0xffffffff +static struct kmem_cache *xfrm6_tunnel_spi_kmem __read_mostly; -static kmem_cache_t *xfrm6_tunnel_spi_kmem __read_mostly; - -#define XFRM6_TUNNEL_SPI_BYADDR_HSIZE 256 -#define XFRM6_TUNNEL_SPI_BYSPI_HSIZE 256 - -static struct hlist_head xfrm6_tunnel_spi_byaddr[XFRM6_TUNNEL_SPI_BYADDR_HSIZE]; -static struct hlist_head xfrm6_tunnel_spi_byspi[XFRM6_TUNNEL_SPI_BYSPI_HSIZE]; - -#ifdef XFRM6_TUNNEL_SPI_MAGIC -static int x6spi_check_magic(const struct xfrm6_tunnel_spi *x6spi, - const char *name) -{ - if (unlikely(x6spi->magic != XFRM6_TUNNEL_SPI_MAGIC)) { - X6TPRINTK3(KERN_DEBUG "%s(): x6spi object " - "at %p has corrupted magic %08x " - "(should be %08x)\n", - name, x6spi, x6spi->magic, XFRM6_TUNNEL_SPI_MAGIC); - return -1; - } - return 0; -} -#else -static int inline x6spi_check_magic(const struct xfrm6_tunnel_spi *x6spi, - const char *name) -{ - return 0; -} -#endif - -#define X6SPI_CHECK_MAGIC(x6spi) x6spi_check_magic((x6spi), __FUNCTION__) - - -static unsigned inline xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr) +static inline unsigned int xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *addr) { - unsigned h; - - X6TPRINTK3(KERN_DEBUG "%s(addr=%p)\n", __FUNCTION__, addr); + unsigned int h; - h = addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3]; + h = ipv6_addr_hash((const struct in6_addr *)addr); h ^= h >> 16; h ^= h >> 8; h &= XFRM6_TUNNEL_SPI_BYADDR_HSIZE - 1; - X6TPRINTK3(KERN_DEBUG "%s() = %u\n", __FUNCTION__, h); - return h; } -static unsigned inline xfrm6_tunnel_spi_hash_byspi(u32 spi) +static inline unsigned int xfrm6_tunnel_spi_hash_byspi(u32 spi) { return spi % XFRM6_TUNNEL_SPI_BYSPI_HSIZE; } - -static int xfrm6_tunnel_spi_init(void) -{ - int i; - - X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__); - - xfrm6_tunnel_spi = 0; - xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", - sizeof(struct xfrm6_tunnel_spi), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!xfrm6_tunnel_spi_kmem) { - X6TPRINTK1(KERN_ERR - "%s(): failed to allocate xfrm6_tunnel_spi_kmem\n", - __FUNCTION__); - return -ENOMEM; - } - - for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) - INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byaddr[i]); - for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) - INIT_HLIST_HEAD(&xfrm6_tunnel_spi_byspi[i]); - return 0; -} - -static void xfrm6_tunnel_spi_fini(void) -{ - int i; - - X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__); - - for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) { - if (!hlist_empty(&xfrm6_tunnel_spi_byaddr[i])) - goto err; - } - for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) { - if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i])) - goto err; - } - kmem_cache_destroy(xfrm6_tunnel_spi_kmem); - xfrm6_tunnel_spi_kmem = NULL; - return; -err: - X6TPRINTK1(KERN_ERR "%s(): table is not empty\n", __FUNCTION__); - return; -} - -static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) +static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos; - - X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr); - hlist_for_each_entry(x6spi, pos, - &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], + hlist_for_each_entry_rcu(x6spi, + &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { - if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { - X6SPI_CHECK_MAGIC(x6spi); - X6TPRINTK3(KERN_DEBUG "%s() = %p(%u)\n", __FUNCTION__, x6spi, x6spi->spi); + if (xfrm6_addr_equal(&x6spi->addr, saddr)) return x6spi; - } } - X6TPRINTK3(KERN_DEBUG "%s() = NULL(0)\n", __FUNCTION__); return NULL; } -u32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) +__be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; - X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr); - - read_lock_bh(&xfrm6_tunnel_spi_lock); - x6spi = __xfrm6_tunnel_spi_lookup(saddr); + rcu_read_lock_bh(); + x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); spi = x6spi ? x6spi->spi : 0; - read_unlock_bh(&xfrm6_tunnel_spi_lock); - return spi; + rcu_read_unlock_bh(); + return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup); -static u32 __xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) +static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi) { - u32 spi; + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos; - unsigned index; + int index = xfrm6_tunnel_spi_hash_byspi(spi); + + hlist_for_each_entry(x6spi, + &xfrm6_tn->spi_byspi[index], + list_byspi) { + if (x6spi->spi == spi) + return -1; + } + return index; +} - X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr); +static u32 __xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) +{ + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); + u32 spi; + struct xfrm6_tunnel_spi *x6spi; + int index; - if (xfrm6_tunnel_spi < XFRM6_TUNNEL_SPI_MIN || - xfrm6_tunnel_spi >= XFRM6_TUNNEL_SPI_MAX) - xfrm6_tunnel_spi = XFRM6_TUNNEL_SPI_MIN; + if (xfrm6_tn->spi < XFRM6_TUNNEL_SPI_MIN || + xfrm6_tn->spi >= XFRM6_TUNNEL_SPI_MAX) + xfrm6_tn->spi = XFRM6_TUNNEL_SPI_MIN; else - xfrm6_tunnel_spi++; - - for (spi = xfrm6_tunnel_spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) { - index = xfrm6_tunnel_spi_hash_byspi(spi); - hlist_for_each_entry(x6spi, pos, - &xfrm6_tunnel_spi_byspi[index], - list_byspi) { - if (x6spi->spi == spi) - goto try_next_1; - } - xfrm6_tunnel_spi = spi; - goto alloc_spi; -try_next_1:; + xfrm6_tn->spi++; + + for (spi = xfrm6_tn->spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) { + index = __xfrm6_tunnel_spi_check(net, spi); + if (index >= 0) + goto alloc_spi; } - for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tunnel_spi; spi++) { - index = xfrm6_tunnel_spi_hash_byspi(spi); - hlist_for_each_entry(x6spi, pos, - &xfrm6_tunnel_spi_byspi[index], - list_byspi) { - if (x6spi->spi == spi) - goto try_next_2; - } - xfrm6_tunnel_spi = spi; - goto alloc_spi; -try_next_2:; + for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tn->spi; spi++) { + index = __xfrm6_tunnel_spi_check(net, spi); + if (index >= 0) + goto alloc_spi; } spi = 0; goto out; alloc_spi: - X6TPRINTK3(KERN_DEBUG "%s(): allocate new spi for " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - __FUNCTION__, - NIP6(*(struct in6_addr *)saddr)); - x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, SLAB_ATOMIC); - if (!x6spi) { - X6TPRINTK1(KERN_ERR "%s(): kmem_cache_alloc() failed\n", - __FUNCTION__); + xfrm6_tn->spi = spi; + x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, GFP_ATOMIC); + if (!x6spi) goto out; - } -#ifdef XFRM6_TUNNEL_SPI_MAGIC - x6spi->magic = XFRM6_TUNNEL_SPI_MAGIC; -#endif + memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; atomic_set(&x6spi->refcnt, 1); - hlist_add_head(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]); + hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tn->spi_byspi[index]); index = xfrm6_tunnel_spi_hash_byaddr(saddr); - hlist_add_head(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]); - X6SPI_CHECK_MAGIC(x6spi); + hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tn->spi_byaddr[index]); out: - X6TPRINTK3(KERN_DEBUG "%s() = %u\n", __FUNCTION__, spi); return spi; } -u32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) +__be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; - X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr); - - write_lock_bh(&xfrm6_tunnel_spi_lock); - x6spi = __xfrm6_tunnel_spi_lookup(saddr); + spin_lock_bh(&xfrm6_tunnel_spi_lock); + x6spi = __xfrm6_tunnel_spi_lookup(net, saddr); if (x6spi) { atomic_inc(&x6spi->refcnt); spi = x6spi->spi; } else - spi = __xfrm6_tunnel_alloc_spi(saddr); - write_unlock_bh(&xfrm6_tunnel_spi_lock); - - X6TPRINTK3(KERN_DEBUG "%s() = %u\n", __FUNCTION__, spi); + spi = __xfrm6_tunnel_alloc_spi(net, saddr); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); - return spi; + return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi); -void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) +static void x6spi_destroy_rcu(struct rcu_head *head) { - struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos, *n; + kmem_cache_free(xfrm6_tunnel_spi_kmem, + container_of(head, struct xfrm6_tunnel_spi, rcu_head)); +} - X6TPRINTK3(KERN_DEBUG "%s(saddr=%p)\n", __FUNCTION__, saddr); +static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) +{ + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); + struct xfrm6_tunnel_spi *x6spi; + struct hlist_node *n; - write_lock_bh(&xfrm6_tunnel_spi_lock); + spin_lock_bh(&xfrm6_tunnel_spi_lock); - hlist_for_each_entry_safe(x6spi, pos, n, - &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], + hlist_for_each_entry_safe(x6spi, n, + &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { - if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { - X6TPRINTK3(KERN_DEBUG "%s(): x6spi object " - "for %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x " - "found at %p\n", - __FUNCTION__, - NIP6(*(struct in6_addr *)saddr), - x6spi); - X6SPI_CHECK_MAGIC(x6spi); + if (xfrm6_addr_equal(&x6spi->addr, saddr)) { if (atomic_dec_and_test(&x6spi->refcnt)) { - hlist_del(&x6spi->list_byaddr); - hlist_del(&x6spi->list_byspi); - kmem_cache_free(xfrm6_tunnel_spi_kmem, x6spi); + hlist_del_rcu(&x6spi->list_byaddr); + hlist_del_rcu(&x6spi->list_byspi); + call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); break; } } } - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); } -EXPORT_SYMBOL(xfrm6_tunnel_free_spi); - static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { - struct ipv6hdr *top_iph; - - top_iph = (struct ipv6hdr *)skb->data; - top_iph->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); - + skb_push(skb, -skb_network_offset(skb)); return 0; } -static int xfrm6_tunnel_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb) +static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - return 0; + return skb_network_header(skb)[IP6CB(skb)->nhoff]; } -static struct xfrm6_tunnel *xfrm6_tunnel_handler; -static DECLARE_MUTEX(xfrm6_tunnel_sem); - -int xfrm6_tunnel_register(struct xfrm6_tunnel *handler) +static int xfrm6_tunnel_rcv(struct sk_buff *skb) { - int ret; + struct net *net = dev_net(skb->dev); + const struct ipv6hdr *iph = ipv6_hdr(skb); + __be32 spi; - down(&xfrm6_tunnel_sem); - ret = 0; - if (xfrm6_tunnel_handler != NULL) - ret = -EINVAL; - if (!ret) - xfrm6_tunnel_handler = handler; - up(&xfrm6_tunnel_sem); - - return ret; -} - -EXPORT_SYMBOL(xfrm6_tunnel_register); - -int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler) -{ - int ret; - - down(&xfrm6_tunnel_sem); - ret = 0; - if (xfrm6_tunnel_handler != handler) - ret = -EINVAL; - if (!ret) - xfrm6_tunnel_handler = NULL; - up(&xfrm6_tunnel_sem); - - synchronize_net(); - - return ret; + spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr); + return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi); } -EXPORT_SYMBOL(xfrm6_tunnel_deregister); - -static int xfrm6_tunnel_rcv(struct sk_buff **pskb, unsigned int *nhoffp) -{ - struct sk_buff *skb = *pskb; - struct xfrm6_tunnel *handler = xfrm6_tunnel_handler; - struct ipv6hdr *iph = skb->nh.ipv6h; - u32 spi; - - /* device-like_ip6ip6_handler() */ - if (handler && handler->handler(pskb, nhoffp) == 0) - return 0; - - spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&iph->saddr); - return xfrm6_rcv_spi(pskb, nhoffp, spi); -} - -static void xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) +static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { - struct xfrm6_tunnel *handler = xfrm6_tunnel_handler; - - /* call here first for device-like ip6ip6 err handling */ - if (handler) { - handler->err_handler(skb, opt, type, code, offset, info); - return; - } - /* xfrm6_tunnel native err handling */ switch (type) { - case ICMPV6_DEST_UNREACH: + case ICMPV6_DEST_UNREACH: switch (code) { - case ICMPV6_NOROUTE: + case ICMPV6_NOROUTE: case ICMPV6_ADM_PROHIBITED: case ICMPV6_NOT_NEIGHBOUR: case ICMPV6_ADDR_UNREACH: case ICMPV6_PORT_UNREACH: default: - X6TPRINTK3(KERN_DEBUG - "xfrm6_tunnel: Destination Unreach.\n"); break; } break; case ICMPV6_PKT_TOOBIG: - X6TPRINTK3(KERN_DEBUG - "xfrm6_tunnel: Packet Too Big.\n"); break; case ICMPV6_TIME_EXCEED: switch (code) { case ICMPV6_EXC_HOPLIMIT: - X6TPRINTK3(KERN_DEBUG - "xfrm6_tunnel: Too small Hoplimit.\n"); break; case ICMPV6_EXC_FRAGTIME: - default: + default: break; } break; @@ -463,12 +278,13 @@ static void xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, default: break; } - return; + + return 0; } static int xfrm6_tunnel_init_state(struct xfrm_state *x) { - if (!x->props.mode) + if (x->props.mode != XFRM_MODE_TUNNEL) return -EINVAL; if (x->encap) @@ -481,10 +297,12 @@ static int xfrm6_tunnel_init_state(struct xfrm_state *x) static void xfrm6_tunnel_destroy(struct xfrm_state *x) { - xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr); + struct net *net = xs_net(x); + + xfrm6_tunnel_free_spi(net, (xfrm_address_t *)&x->props.saddr); } -static struct xfrm_type xfrm6_tunnel_type = { +static const struct xfrm_type xfrm6_tunnel_type = { .description = "IP6IP6", .owner = THIS_MODULE, .proto = IPPROTO_IPV6, @@ -494,50 +312,88 @@ static struct xfrm_type xfrm6_tunnel_type = { .output = xfrm6_tunnel_output, }; -static struct inet6_protocol xfrm6_tunnel_protocol = { +static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = { + .handler = xfrm6_tunnel_rcv, + .err_handler = xfrm6_tunnel_err, + .priority = 2, +}; + +static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = { .handler = xfrm6_tunnel_rcv, - .err_handler = xfrm6_tunnel_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, + .err_handler = xfrm6_tunnel_err, + .priority = 2, +}; + +static int __net_init xfrm6_tunnel_net_init(struct net *net) +{ + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); + unsigned int i; + + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) + INIT_HLIST_HEAD(&xfrm6_tn->spi_byaddr[i]); + for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) + INIT_HLIST_HEAD(&xfrm6_tn->spi_byspi[i]); + xfrm6_tn->spi = 0; + + return 0; +} + +static void __net_exit xfrm6_tunnel_net_exit(struct net *net) +{ +} + +static struct pernet_operations xfrm6_tunnel_net_ops = { + .init = xfrm6_tunnel_net_init, + .exit = xfrm6_tunnel_net_exit, + .id = &xfrm6_tunnel_net_id, + .size = sizeof(struct xfrm6_tunnel_net), }; static int __init xfrm6_tunnel_init(void) { - X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__); + int rv; - if (xfrm_register_type(&xfrm6_tunnel_type, AF_INET6) < 0) { - X6TPRINTK1(KERN_ERR - "xfrm6_tunnel init: can't add xfrm type\n"); - return -EAGAIN; - } - if (inet6_add_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6) < 0) { - X6TPRINTK1(KERN_ERR - "xfrm6_tunnel init(): can't add protocol\n"); - xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); - return -EAGAIN; - } - if (xfrm6_tunnel_spi_init() < 0) { - X6TPRINTK1(KERN_ERR - "xfrm6_tunnel init: failed to initialize spi\n"); - inet6_del_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6); - xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); - return -EAGAIN; - } + xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", + sizeof(struct xfrm6_tunnel_spi), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (!xfrm6_tunnel_spi_kmem) + return -ENOMEM; + rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); + if (rv < 0) + goto out_pernet; + rv = xfrm_register_type(&xfrm6_tunnel_type, AF_INET6); + if (rv < 0) + goto out_type; + rv = xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6); + if (rv < 0) + goto out_xfrm6; + rv = xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET); + if (rv < 0) + goto out_xfrm46; return 0; + +out_xfrm46: + xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); +out_xfrm6: + xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); +out_type: + unregister_pernet_subsys(&xfrm6_tunnel_net_ops); +out_pernet: + kmem_cache_destroy(xfrm6_tunnel_spi_kmem); + return rv; } static void __exit xfrm6_tunnel_fini(void) { - X6TPRINTK3(KERN_DEBUG "%s()\n", __FUNCTION__); - - xfrm6_tunnel_spi_fini(); - if (inet6_del_protocol(&xfrm6_tunnel_protocol, IPPROTO_IPV6) < 0) - X6TPRINTK1(KERN_ERR - "xfrm6_tunnel close: can't remove protocol\n"); - if (xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6) < 0) - X6TPRINTK1(KERN_ERR - "xfrm6_tunnel close: can't remove xfrm type\n"); + xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET); + xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); + xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); + unregister_pernet_subsys(&xfrm6_tunnel_net_ops); + kmem_cache_destroy(xfrm6_tunnel_spi_kmem); } module_init(xfrm6_tunnel_init); module_exit(xfrm6_tunnel_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6); |