diff options
Diffstat (limited to 'net/ipv6')
48 files changed, 1787 insertions, 1081 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ef5eaad44851..deb4101a2a81 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -175,9 +175,16 @@ config IPV6_TUNNEL If unsure, say N. +config IPV6_MULTIPLE_TABLES + bool "IPv6: Multiple Routing Tables" + depends on IPV6 && EXPERIMENTAL + select FIB_RULES + ---help--- + Support multiple routing tables. + config IPV6_SUBTREES bool "IPv6: source address based routing" - depends on IPV6 && EXPERIMENTAL + depends on IPV6_MULTIPLE_TABLES ---help--- Enable routing by source address or prefix. @@ -189,17 +196,3 @@ config IPV6_SUBTREES If unsure, say N. -config IPV6_MULTIPLE_TABLES - bool "IPv6: Multiple Routing Tables" - depends on IPV6 && EXPERIMENTAL - select FIB_RULES - ---help--- - Support multiple routing tables. - -config IPV6_ROUTE_FWMARK - bool "IPv6: use netfilter MARK value as routing key" - depends on IPV6_MULTIPLE_TABLES && NETFILTER - ---help--- - If you say Y here, you will be able to specify different routes for - packets with different mark values (see iptables(8), MARK target). - diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index addcc011bc01..8bacda109b7f 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -5,8 +5,8 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.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 \ + route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.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 inet6_connection_sock.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b312a5f7a759..a5e8d207a51b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -232,7 +232,7 @@ static inline unsigned ipv6_addr_scope2type(unsigned scope) int __ipv6_addr_type(const struct in6_addr *addr) { - u32 st; + __be32 st; st = addr->s6_addr32[0]; @@ -1164,7 +1164,7 @@ record_it: int ipv6_get_saddr(struct dst_entry *dst, struct in6_addr *daddr, struct in6_addr *saddr) { - return ipv6_dev_get_saddr(dst ? ((struct rt6_info *)dst)->rt6i_idev->dev : NULL, daddr, saddr); + return ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, daddr, saddr); } @@ -3098,10 +3098,9 @@ static inline int rt_scope(int ifa_scope) static inline int inet6_ifaddr_msgsize(void) { - return nlmsg_total_size(sizeof(struct ifaddrmsg) + - nla_total_size(16) + - nla_total_size(sizeof(struct ifa_cacheinfo)) + - 128); + return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + nla_total_size(16) /* IFA_ADDRESS */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); } static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, @@ -3329,10 +3328,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWADDR, 0); - if (err < 0) { - kfree_skb(skb); - goto errout_ifa; - } + /* failure implies BUG in inet6_ifaddr_msgsize() */ + BUG_ON(err < 0); err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); errout_ifa: @@ -3351,10 +3348,8 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) goto errout; err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); - if (err < 0) { - kfree_skb(skb); - goto errout; - } + /* failure implies BUG in inet6_ifaddr_msgsize() */ + BUG_ON(err < 0); err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); errout: @@ -3365,6 +3360,8 @@ errout: static void inline 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; @@ -3397,80 +3394,76 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; } -/* Maximum length of ifinfomsg attributes */ -#define INET6_IFINFO_RTA_SPACE \ - RTA_SPACE(IFNAMSIZ) /* IFNAME */ + \ - RTA_SPACE(MAX_ADDR_LEN) /* ADDRESS */ + \ - RTA_SPACE(sizeof(u32)) /* MTU */ + \ - RTA_SPACE(sizeof(int)) /* LINK */ + \ - RTA_SPACE(0) /* PROTINFO */ + \ - RTA_SPACE(sizeof(u32)) /* FLAGS */ + \ - RTA_SPACE(sizeof(struct ifla_cacheinfo)) /* CACHEINFO */ + \ - RTA_SPACE(sizeof(__s32[DEVCONF_MAX])) /* CONF */ +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( /* IFLA_PROTINFO */ + nla_total_size(4) /* IFLA_INET6_FLAGS */ + + nla_total_size(sizeof(struct ifla_cacheinfo)) + + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ + ); +} static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, u32 pid, u32 seq, int event, unsigned int flags) { - 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; - - 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; - - RTA_PUT(skb, IFLA_IFNAME, strlen(dev->name)+1, dev->name); + struct net_device *dev = idev->dev; + struct nlattr *conf; + struct ifinfomsg *hdr; + struct nlmsghdr *nlh; + void *protoinfo; + struct ifla_cacheinfo ci; + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); + if (nlh == NULL) + return -ENOBUFS; + + 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; + + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); if (dev->addr_len) - RTA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); + NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - RTA_PUT(skb, IFLA_MTU, sizeof(mtu), &mtu); + NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); if (dev->ifindex != dev->iflink) - RTA_PUT(skb, IFLA_LINK, sizeof(int), &dev->iflink); - - subattr = (struct rtattr*)skb->tail; + NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); - RTA_PUT(skb, IFLA_PROTINFO, 0, NULL); + protoinfo = nla_nest_start(skb, IFLA_PROTINFO); + if (protoinfo == NULL) + goto nla_put_failure; - /* return the device flags */ - RTA_PUT(skb, IFLA_INET6_FLAGS, sizeof(__u32), &idev->if_flags); + NLA_PUT_U32(skb, IFLA_INET6_FLAGS, idev->if_flags); - /* return interface cacheinfo */ 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); + NLA_PUT(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci); + + conf = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); + if (conf == NULL) + goto nla_put_failure; + ipv6_store_devconf(&idev->cnf, nla_data(conf), nla_len(conf)); /* XXX - Statistics/MC not implemented */ - subattr->rta_len = skb->tail - (u8*)subattr; - nlh->nlmsg_len = skb->tail - b; - kfree(array); - return skb->len; + nla_nest_end(skb, protoinfo); + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - kfree(array); - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) @@ -3501,18 +3494,15 @@ 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; - int payload = sizeof(struct ifinfomsg) + INET6_IFINFO_RTA_SPACE; int err = -ENOBUFS; - skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC); + 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) { - kfree_skb(skb); - goto errout; - } + /* failure implies BUG in inet6_if_nlmsg_size() */ + BUG_ON(err < 0); err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); errout: @@ -3520,22 +3510,26 @@ errout: rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err); } -/* Maximum length of prefix_cacheinfo attributes */ -#define INET6_PREFIX_RTA_SPACE \ - RTA_SPACE(sizeof(((struct prefix_info *)NULL)->prefix)) /* ADDRESS */ + \ - RTA_SPACE(sizeof(struct prefix_cacheinfo)) /* CACHEINFO */ +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 pid, 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, pid, seq, event, sizeof(*pmsg), flags); + if (nlh == NULL) + return -ENOBUFS; + + pmsg = nlmsg_data(nlh); pmsg->prefix_family = AF_INET6; pmsg->prefix_pad1 = 0; pmsg->prefix_pad2 = 0; @@ -3543,44 +3537,37 @@ 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); + NLA_PUT(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix); ci.preferred_time = ntohl(pinfo->prefered); ci.valid_time = ntohl(pinfo->valid); - RTA_PUT(skb, PREFIX_CACHEINFO, sizeof(ci), &ci); + NLA_PUT(skb, PREFIX_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; - int payload = sizeof(struct prefixmsg) + INET6_PREFIX_RTA_SPACE; int err = -ENOBUFS; - skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC); + 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) { - kfree_skb(skb); - goto errout; - } + /* failure implies BUG in inet6_prefix_nlmsg_size() */ + BUG_ON(err < 0); err = rtnl_notify(skb, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); errout: @@ -3982,10 +3969,9 @@ static void addrconf_sysctl_register(struct inet6_dev *idev, struct ipv6_devconf struct addrconf_sysctl_table *t; char *dev_name = NULL; - 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; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 858cae29581c..87c8f54872b7 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -49,6 +49,7 @@ #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/protocol.h> @@ -221,7 +222,7 @@ lookup_protocol: * the user to assign a number at socket * creation time automatically shares. */ - inet->sport = ntohs(inet->num); + inet->sport = htons(inet->num); sk->sk_prot->hash(sk); } if (sk->sk_prot->init) { @@ -341,7 +342,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = ntohs(inet->num); + inet->sport = htons(inet->num); inet->dport = 0; inet->daddr = 0; out: @@ -678,7 +679,7 @@ int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb) if (np->rxopt.all) { if ((opt->hop && (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || - ((IPV6_FLOWINFO_MASK & *(u32*)skb->nh.raw) && + ((IPV6_FLOWINFO_MASK & *(__be32*)skb->nh.raw) && np->rxopt.bits.rxflow) || (opt->srcrt && (np->rxopt.bits.srcrt || np->rxopt.bits.osrcrt)) || @@ -737,8 +738,13 @@ static int __init init_ipv6_mibs(void) if (snmp6_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib), __alignof__(struct udp_mib)) < 0) goto err_udp_mib; + if (snmp6_mib_init((void **)udplite_stats_in6, sizeof (struct udp_mib), + __alignof__(struct udp_mib)) < 0) + goto err_udplite_mib; return 0; +err_udplite_mib: + snmp6_mib_free((void **)udp_stats_in6); err_udp_mib: snmp6_mib_free((void **)icmpv6_statistics); err_icmp_mib: @@ -753,6 +759,7 @@ static void cleanup_ipv6_mibs(void) snmp6_mib_free((void **)ipv6_statistics); snmp6_mib_free((void **)icmpv6_statistics); snmp6_mib_free((void **)udp_stats_in6); + snmp6_mib_free((void **)udplite_stats_in6); } static int __init inet6_init(void) @@ -780,10 +787,14 @@ 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) @@ -837,6 +848,8 @@ static int __init inet6_init(void) 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; @@ -862,6 +875,7 @@ static int __init inet6_init(void) /* Init v6 transport protocols. */ udpv6_init(); + udplitev6_init(); tcpv6_init(); ipv6_packet_init(); @@ -879,6 +893,8 @@ proc_if6_fail: proc_anycast6_fail: ipv6_misc_proc_exit(); proc_misc6_fail: + udplite6_proc_exit(); +proc_udplite6_fail: udp6_proc_exit(); proc_udp6_fail: tcp6_proc_exit(); @@ -902,6 +918,8 @@ out_unregister_sock: sock_unregister(PF_INET6); 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: @@ -919,6 +937,7 @@ static void __exit inet6_exit(void) ac6_proc_exit(); ipv6_misc_proc_exit(); udp6_proc_exit(); + udplite6_proc_exit(); tcp6_proc_exit(); raw6_proc_exit(); #endif diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index b0d83e8e4252..12c5a4dec09e 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -354,10 +354,9 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, ah_hlen)) goto out; - tmp_hdr = kmalloc(hdr_len, GFP_ATOMIC); + tmp_hdr = kmemdup(skb->nh.raw, hdr_len, GFP_ATOMIC); if (!tmp_hdr) goto out; - memcpy(tmp_hdr, skb->nh.raw, hdr_len); if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len, XFRM_POLICY_IN)) goto free_out; skb->nh.ipv6h->priority = 0; @@ -397,7 +396,7 @@ out: } static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7206747022fc..5c94fea90e97 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -207,7 +207,7 @@ out: } void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, - u16 port, u32 info, u8 *payload) + __be16 port, u32 info, u8 *payload) { struct ipv6_pinfo *np = inet6_sk(sk); struct icmp6hdr *icmph = (struct icmp6hdr *)skb->h.raw; @@ -318,13 +318,13 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) ipv6_addr_copy(&sin->sin6_addr, (struct in6_addr *)(skb->nh.raw + serr->addr_offset)); if (np->sndflow) - sin->sin6_flowinfo = *(u32*)(skb->nh.raw + serr->addr_offset - 24) & IPV6_FLOWINFO_MASK; + sin->sin6_flowinfo = *(__be32*)(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; } else { ipv6_addr_set(&sin->sin6_addr, 0, 0, htonl(0xffff), - *(u32*)(skb->nh.raw + serr->addr_offset)); + *(__be32*)(skb->nh.raw + serr->addr_offset)); } } @@ -397,12 +397,12 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } if (np->rxopt.bits.rxtclass) { - int tclass = (ntohl(*(u32 *)skb->nh.ipv6h) >> 20) & 0xff; + int tclass = (ntohl(*(__be32 *)skb->nh.ipv6h) >> 20) & 0xff; 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; + if (np->rxopt.bits.rxflow && (*(__be32*)skb->nh.raw & IPV6_FLOWINFO_MASK)) { + __be32 flowinfo = *(__be32*)skb->nh.raw & IPV6_FLOWINFO_MASK; put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } @@ -560,12 +560,12 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, } if (fl->fl6_flowlabel&IPV6_FLOWINFO_MASK) { - if ((fl->fl6_flowlabel^*(u32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { + if ((fl->fl6_flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { err = -EINVAL; goto exit_f; } } - fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(u32 *)CMSG_DATA(cmsg); + fl->fl6_flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); break; case IPV6_2292HOPOPTS: diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index e78680a9985b..25dcf69cd807 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -256,7 +256,7 @@ static u32 esp6_get_max_size(struct xfrm_state *x, int mtu) } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ipv6_esp_hdr *esph = (struct ipv6_esp_hdr*)(skb->data+offset); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 88c96b10684c..0711f92d6a12 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -284,10 +284,12 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp) #ifdef CONFIG_IPV6_MIP6 __u16 dstbuf; #endif + struct dst_entry *dst; 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); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } @@ -298,7 +300,9 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp) dstbuf = opt->dst1; #endif + dst = dst_clone(skb->dst); if (ip6_parse_tlv(tlvprocdestopt_lst, skbp)) { + dst_release(dst); skb = *skbp; skb->h.raw += ((skb->h.raw[1]+1)<<3); opt = IP6CB(skb); @@ -310,7 +314,8 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp) return 1; } - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); + dst_release(dst); return -1; } @@ -365,7 +370,8 @@ static int ipv6_rthdr_rcv(struct sk_buff **skbp) 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); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } @@ -374,7 +380,8 @@ static int ipv6_rthdr_rcv(struct sk_buff **skbp) if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr) || skb->pkt_type != PACKET_HOST) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -388,7 +395,8 @@ looped_back: * processed by own */ if (!addr) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -410,7 +418,8 @@ looped_back: switch (hdr->type) { case IPV6_SRCRT_TYPE_0: if (hdr->hdrlen & 0x01) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw); return -1; } @@ -419,14 +428,16 @@ looped_back: case IPV6_SRCRT_TYPE_2: /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } break; #endif default: - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb->nh.raw); return -1; } @@ -439,7 +450,8 @@ looped_back: n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->segments_left) - skb->nh.raw); return -1; } @@ -449,12 +461,14 @@ looped_back: */ 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); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); return -1; } + kfree_skb(skb); *skbp = skb = skb2; opt = IP6CB(skb2); hdr = (struct ipv6_rt_hdr *) skb2->h.raw; @@ -475,12 +489,14 @@ looped_back: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&skb->nh.ipv6h->saddr, IPPROTO_ROUTING) < 0) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } if (!ipv6_chk_home_addr(addr)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -491,7 +507,8 @@ looped_back: } if (ipv6_addr_is_multicast(addr)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -510,7 +527,8 @@ looped_back: if (skb->dst->dev->flags&IFF_LOOPBACK) { if (skb->nh.ipv6h->hop_limit <= 1) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0, skb->dev); kfree_skb(skb); @@ -632,24 +650,25 @@ static int ipv6_hop_jumbo(struct sk_buff **skbp, int optoff) if (skb->nh.raw[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); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); goto drop; } - pkt_len = ntohl(*(u32*)(skb->nh.raw+optoff+2)); + pkt_len = ntohl(*(__be32*)(skb->nh.raw+optoff+2)); if (pkt_len <= IPV6_MAXPLEN) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2); return 0; } if (skb->nh.ipv6h->payload_len) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff); return 0; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 315bc1fbec3f..21cbbbddaf4d 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -77,7 +77,7 @@ 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), diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index d8c1057e8b00..0862809ffcf7 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -25,10 +25,6 @@ struct fib6_rule struct fib_rule common; struct rt6key src; struct rt6key dst; -#ifdef CONFIG_IPV6_ROUTE_FWMARK - u32 fwmark; - u32 fwmask; -#endif u8 tclass; }; @@ -67,7 +63,7 @@ struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, fib_rule_put(arg.rule); if (arg.result) - return (struct dst_entry *) arg.result; + return arg.result; dst_hold(&ip6_null_entry.u.dst); return &ip6_null_entry.u.dst; @@ -117,32 +113,26 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; - if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) + if (r->dst.plen && + !ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) return 0; - if ((flags & RT6_LOOKUP_F_HAS_SADDR) && - !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) - return 0; + if (r->src.plen) { + if (!(flags & RT6_LOOKUP_F_HAS_SADDR) || + !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) + return 0; + } if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff)) return 0; -#ifdef CONFIG_IPV6_ROUTE_FWMARK - if ((r->fwmark ^ fl->fl6_fwmark) & r->fwmask) - return 0; -#endif - return 1; } static struct nla_policy fib6_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, - [FRA_PRIORITY] = { .type = NLA_U32 }, + FRA_GENERIC_POLICY, [FRA_SRC] = { .len = sizeof(struct in6_addr) }, [FRA_DST] = { .len = sizeof(struct in6_addr) }, - [FRA_FWMARK] = { .type = NLA_U32 }, - [FRA_FWMASK] = { .type = NLA_U32 }, - [FRA_TABLE] = { .type = NLA_U32 }, }; static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, @@ -152,8 +142,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, int err = -EINVAL; struct fib6_rule *rule6 = (struct fib6_rule *) rule; - if (frh->src_len > 128 || frh->dst_len > 128 || - (frh->tos & ~IPV6_FLOWINFO_MASK)) + if (frh->src_len > 128 || frh->dst_len > 128) goto errout; if (rule->action == FR_ACT_TO_TBL) { @@ -174,23 +163,6 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, nla_memcpy(&rule6->dst.addr, tb[FRA_DST], sizeof(struct in6_addr)); -#ifdef CONFIG_IPV6_ROUTE_FWMARK - if (tb[FRA_FWMARK]) { - rule6->fwmark = nla_get_u32(tb[FRA_FWMARK]); - if (rule6->fwmark) { - /* - * if the mark value is non-zero, - * all bits are compared by default - * unless a mask is explicitly specified. - */ - rule6->fwmask = 0xFFFFFFFF; - } - } - - if (tb[FRA_FWMASK]) - rule6->fwmask = nla_get_u32(tb[FRA_FWMASK]); -#endif - rule6->src.plen = frh->src_len; rule6->dst.plen = frh->dst_len; rule6->tclass = frh->tos; @@ -222,14 +194,6 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr))) return 0; -#ifdef CONFIG_IPV6_ROUTE_FWMARK - if (tb[FRA_FWMARK] && (rule6->fwmark != nla_get_u32(tb[FRA_FWMARK]))) - return 0; - - if (tb[FRA_FWMASK] && (rule6->fwmask != nla_get_u32(tb[FRA_FWMASK]))) - return 0; -#endif - return 1; } @@ -251,14 +215,6 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, NLA_PUT(skb, FRA_SRC, sizeof(struct in6_addr), &rule6->src.addr); -#ifdef CONFIG_IPV6_ROUTE_FWMARK - if (rule6->fwmark) - NLA_PUT_U32(skb, FRA_FWMARK, rule6->fwmark); - - if (rule6->fwmask || rule6->fwmark) - NLA_PUT_U32(skb, FRA_FWMASK, rule6->fwmask); -#endif - return 0; nla_put_failure: @@ -275,6 +231,12 @@ static u32 fib6_rule_default_pref(void) 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 struct fib_rules_ops fib6_rules_ops = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), @@ -284,6 +246,7 @@ static struct fib_rules_ops fib6_rules_ops = { .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, .rules_list = &fib6_rules, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4ec876066b3f..3dcc4b7f41b4 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -177,7 +177,8 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type, */ dst = ip6_route_output(sk, fl); if (dst->error) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(ip6_dst_idev(dst), + IPSTATS_MIB_OUTNOROUTES); } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { res = 1; } else { @@ -233,7 +234,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct len, fl->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); @@ -241,13 +242,11 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct tmp_csum = csum_partial((char *)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(&fl->fl6_src, + &fl->fl6_dst, + len, fl->proto, + tmp_csum); } - if (icmp6h->icmp6_cksum == 0) - icmp6h->icmp6_cksum = -1; ip6_push_pending_frames(sk); out: return err; @@ -263,7 +262,7 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st { 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); @@ -555,7 +554,7 @@ out: icmpv6_xmit_unlock(); } -static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info) +static void icmpv6_notify(struct sk_buff *skb, int type, int code, __be32 info) { struct in6_addr *saddr, *daddr; struct inet6_protocol *ipprot; @@ -637,8 +636,8 @@ static int icmpv6_rcv(struct sk_buff **pskb) break; /* fall through */ case CHECKSUM_NONE: - skb->csum = ~csum_ipv6_magic(saddr, daddr, skb->len, - IPPROTO_ICMPV6, 0); + skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len, + IPPROTO_ICMPV6, 0)); if (__skb_checksum_complete(skb)) { LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [" NIP6_FMT " > " NIP6_FMT "]\n", NIP6(*saddr), NIP6(*daddr)); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 827f41d1478b..c700302ad51a 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -52,20 +52,20 @@ EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); /* * request_sock (formerly open request) hash tables. */ -static u32 inet6_synq_hash(const struct in6_addr *raddr, const u16 rport, +static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, const u32 rnd, const u16 synq_hsize) { - u32 a = raddr->s6_addr32[0]; - u32 b = raddr->s6_addr32[1]; - u32 c = raddr->s6_addr32[2]; + u32 a = (__force u32)raddr->s6_addr32[0]; + u32 b = (__force u32)raddr->s6_addr32[1]; + u32 c = (__force u32)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; + a += (__force u32)raddr->s6_addr32[3]; + b += (__force u32)rport; __jhash_mix(a, b, c); return c & (synq_hsize - 1); @@ -73,7 +73,7 @@ static u32 inet6_synq_hash(const struct in6_addr *raddr, const u16 rport, struct request_sock *inet6_csk_search_req(const struct sock *sk, struct request_sock ***prevp, - const __u16 rport, + const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, const int iif) @@ -139,9 +139,8 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr); -int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) +int inet6_csk_xmit(struct sk_buff *skb, struct sock *sk, int ipfragok) { - struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct flowi fl; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 8accd1fbeeda..b7e5bae0e347 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(__inet6_hash); */ struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, - const u16 sport, + const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif) @@ -146,8 +146,8 @@ struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, 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, + const struct in6_addr *saddr, const __be16 sport, + const struct in6_addr *daddr, const __be16 dport, const int dif) { struct sock *sk; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 8fcae7a6510b..bf526115e518 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -139,9 +139,9 @@ static __inline__ u32 fib6_new_sernum(void) * test bit */ -static __inline__ int addr_bit_set(void *token, int fn_bit) +static __inline__ __be32 addr_bit_set(void *token, int fn_bit) { - __u32 *addr = token; + __be32 *addr = token; return htonl(1 << ((~fn_bit)&0x1F)) & addr[fn_bit>>5]; } @@ -169,7 +169,6 @@ static __inline__ void rt6_release(struct rt6_info *rt) static struct fib6_table fib6_main_tbl = { .tb6_id = RT6_TABLE_MAIN, - .tb6_lock = RW_LOCK_UNLOCKED, .tb6_root = { .leaf = &ip6_null_entry, .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, @@ -187,6 +186,12 @@ static void fib6_link_table(struct fib6_table *tb) { unsigned int h; + /* + * 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); + h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1); /* @@ -199,7 +204,6 @@ static void fib6_link_table(struct fib6_table *tb) #ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table fib6_local_tbl = { .tb6_id = RT6_TABLE_LOCAL, - .tb6_lock = RW_LOCK_UNLOCKED, .tb6_root = { .leaf = &ip6_null_entry, .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, @@ -213,7 +217,6 @@ static struct fib6_table *fib6_alloc_table(u32 id) table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table != NULL) { table->tb6_id = id; - table->tb6_lock = RW_LOCK_UNLOCKED; table->tb6_root.leaf = &ip6_null_entry; table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; } @@ -431,7 +434,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, 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"); @@ -826,7 +829,7 @@ 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; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1d672b0547f2..624fae251f4e 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -61,7 +61,7 @@ static DEFINE_RWLOCK(ip6_fl_lock); static DEFINE_RWLOCK(ip6_sk_fl_lock); -static __inline__ struct ip6_flowlabel * __fl_lookup(u32 label) +static __inline__ struct ip6_flowlabel * __fl_lookup(__be32 label) { struct ip6_flowlabel *fl; @@ -72,7 +72,7 @@ static __inline__ struct ip6_flowlabel * __fl_lookup(u32 label) return NULL; } -static struct ip6_flowlabel * fl_lookup(u32 label) +static struct ip6_flowlabel * fl_lookup(__be32 label) { struct ip6_flowlabel *fl; @@ -153,7 +153,7 @@ static void ip6_fl_gc(unsigned long dummy) write_unlock(&ip6_fl_lock); } -static int fl_intern(struct ip6_flowlabel *fl, __u32 label) +static int fl_intern(struct ip6_flowlabel *fl, __be32 label) { fl->label = label & IPV6_FLOWLABEL_MASK; @@ -182,7 +182,7 @@ static int fl_intern(struct ip6_flowlabel *fl, __u32 label) /* 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); @@ -330,8 +330,10 @@ fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int * fl->share = freq->flr_share; addr_type = ipv6_addr_type(&freq->flr_dst); if ((addr_type&IPV6_ADDR_MAPPED) - || addr_type == IPV6_ADDR_ANY) + || addr_type == IPV6_ADDR_ANY) { + err = -EINVAL; goto done; + } ipv6_addr_copy(&fl->dst, &freq->flr_dst); atomic_set(&fl->users, 1); switch (fl->share) { @@ -587,6 +589,8 @@ static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flo while (!fl) { if (++state->bucket <= FL_HASH_MASK) fl = fl_ht[state->bucket]; + else + break; } return fl; } @@ -623,9 +627,13 @@ static void ip6fl_seq_stop(struct seq_file *seq, void *v) read_unlock_bh(&ip6_fl_lock); } -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) { + 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 " NIP6_SEQFMT " %-4d\n", (unsigned)ntohl(fl->label), @@ -636,17 +644,7 @@ static void ip6fl_fl_seq_show(struct seq_file *seq, struct ip6_flowlabel *fl) (long)(fl->expires - jiffies)/HZ, NIP6(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_printf(seq, "%-5s %-1s %-6s %-6s %-6s %-8s %-32s %s\n", - "Label", "S", "Owner", "Users", "Linger", "Expires", "Dst", "Opt"); - else - ip6fl_fl_seq_show(seq, v); return 0; } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 6b8e6d76a58b..ad0b8abcdf4b 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -60,14 +60,22 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt { struct ipv6hdr *hdr; u32 pkt_len; + struct inet6_dev *idev; - if (skb->pkt_type == PACKET_OTHERHOST) - goto drop; + if (skb->pkt_type == PACKET_OTHERHOST) { + kfree_skb(skb); + return 0; + } + + rcu_read_lock(); - IP6_INC_STATS_BH(IPSTATS_MIB_INRECEIVES); + idev = __in6_dev_get(skb->dev); + + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INRECEIVES); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { - IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS); + rcu_read_unlock(); goto out; } @@ -84,7 +92,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt * 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 ? ip6_dst_idev(skb->dst)->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; @@ -104,7 +112,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (pkt_len + sizeof(struct ipv6hdr) > skb->len) goto truncated; if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS); goto drop; } hdr = skb->nh.ipv6h; @@ -112,17 +120,21 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (hdr->nexthdr == NEXTHDR_HOP) { if (ipv6_parse_hopopts(&skb) < 0) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS); + rcu_read_unlock(); return 0; } } + rcu_read_unlock(); + return NF_HOOK(PF_INET6,NF_IP6_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); truncated: - IP6_INC_STATS_BH(IPSTATS_MIB_INTRUNCATEDPKTS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INTRUNCATEDPKTS); err: - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INHDRERRORS); drop: + rcu_read_unlock(); kfree_skb(skb); out: return 0; @@ -140,6 +152,7 @@ static inline int ip6_input_finish(struct sk_buff *skb) unsigned int nhoff; int nexthdr; u8 hash; + struct inet6_dev *idev; /* * Parse extension headers @@ -147,6 +160,7 @@ static inline int ip6_input_finish(struct sk_buff *skb) rcu_read_lock(); resubmit: + idev = ip6_dst_idev(skb->dst); if (!pskb_pull(skb, skb->h.raw - skb->data)) goto discard; nhoff = IP6CB(skb)->nhoff; @@ -185,24 +199,24 @@ resubmit: if (ret > 0) goto resubmit; else if (ret == 0) - IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDELIVERS); } else { if (!raw_sk) { if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - IP6_INC_STATS_BH(IPSTATS_MIB_INUNKNOWNPROTOS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INUNKNOWNPROTOS); icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_UNK_NEXTHDR, nhoff, skb->dev); } } else - IP6_INC_STATS_BH(IPSTATS_MIB_INDELIVERS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDELIVERS); kfree_skb(skb); } rcu_read_unlock(); return 0; discard: - IP6_INC_STATS_BH(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS); rcu_read_unlock(); kfree_skb(skb); return 0; @@ -219,7 +233,7 @@ int ip6_mc_input(struct sk_buff *skb) struct ipv6hdr *hdr; int deliver; - IP6_INC_STATS_BH(IPSTATS_MIB_INMCASTPKTS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INMCASTPKTS); hdr = skb->nh.ipv6h; deliver = likely(!(skb->dev->flags & (IFF_PROMISC|IFF_ALLMULTI))) || diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 66716911962e..e05ecbb1412d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -88,7 +88,7 @@ static inline int ip6_output_finish(struct sk_buff *skb) } else if (dst->neighbour) return dst->neighbour->output(skb); - IP6_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; @@ -118,6 +118,7 @@ static int ip6_output2(struct sk_buff *skb) if (ipv6_addr_is_multicast(&skb->nh.ipv6h->daddr)) { struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct inet6_dev *idev = ip6_dst_idev(skb->dst); if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && ipv6_chk_mcast_addr(dev, &skb->nh.ipv6h->daddr, @@ -133,13 +134,13 @@ static int ip6_output2(struct sk_buff *skb) ip6_dev_loopback_xmit); if (skb->nh.ipv6h->hop_limit == 0) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTMCASTPKTS); } return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb,NULL, skb->dev,ip6_output_finish); @@ -182,12 +183,14 @@ 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(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); return -ENOBUFS; } + kfree_skb(skb); + skb = skb2; if (sk) skb_set_owner_w(skb, sk); } @@ -217,7 +220,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, if (tclass < 0) tclass = 0; - *(u32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; + *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -230,7 +233,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, mtu = dst_mtu(dst); if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) { - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTREQUESTS); return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, dst_output); } @@ -239,7 +243,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, 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); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } @@ -267,7 +271,7 @@ int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, hdr = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); skb->nh.ipv6h = hdr; - *(u32*)hdr = htonl(0x60000000); + *(__be32*)hdr = htonl(0x60000000); hdr->payload_len = htons(len); hdr->nexthdr = proto; @@ -373,7 +377,7 @@ int ip6_forward(struct sk_buff *skb) goto error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } @@ -406,7 +410,7 @@ int ip6_forward(struct sk_buff *skb) skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0, skb->dev); - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; @@ -419,13 +423,13 @@ int ip6_forward(struct sk_buff *skb) if (proxied > 0) return ip6_input(skb); else if (proxied < 0) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { - IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } dst = skb->dst; @@ -464,14 +468,14 @@ int ip6_forward(struct sk_buff *skb) /* 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); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS); + IP6_INC_STATS_BH(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(ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } @@ -481,11 +485,11 @@ int ip6_forward(struct sk_buff *skb) hdr->hop_limit--; - IP6_INC_STATS_BH(IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); return NF_HOOK(PF_INET6,NF_IP6_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); error: - IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); drop: kfree_skb(skb); return -EINVAL; @@ -499,12 +503,12 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) dst_release(to->dst); to->dst = dst_clone(from->dst); 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 */ nf_conntrack_put(to->nfct); to->nfct = from->nfct; @@ -571,7 +575,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; - u32 frag_id = 0; + __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; @@ -620,14 +624,13 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_shinfo(skb)->frag_list = NULL; /* BUILD HEADER */ - tmp_hdr = kmalloc(hlen, GFP_ATOMIC); + tmp_hdr = kmemdup(skb->nh.raw, hlen, GFP_ATOMIC); if (!tmp_hdr) { - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), 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); @@ -643,7 +646,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; skb->nh.ipv6h->payload_len = htons(first_len - sizeof(struct ipv6hdr)); - + + dst_hold(&rt->u.dst); for (;;) { /* Prepare header of the next frame, @@ -667,7 +671,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) err = output(skb); if(!err) - IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); + IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; @@ -680,7 +684,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) kfree(tmp_hdr); if (err == 0) { - IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); + IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGOKS); + dst_release(&rt->u.dst); return 0; } @@ -690,7 +695,8 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb; } - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGFAILS); + dst_release(&rt->u.dst); return err; } @@ -723,7 +729,8 @@ slow_path: if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_RESERVED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } @@ -784,15 +791,17 @@ slow_path: if (err) goto fail; - IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGCREATES); } + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_FRAGOKS); kfree_skb(skb); - IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); return err; fail: + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); - IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS); return err; } @@ -1265,7 +1274,7 @@ alloc_new_skb: return 0; error: inet->cork.length -= length; - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } @@ -1311,7 +1320,7 @@ int ip6_push_pending_frames(struct sock *sk) skb->nh.ipv6h = hdr = (struct ipv6hdr*) skb_push(skb, sizeof(struct ipv6hdr)); - *(u32*)hdr = fl->fl6_flowlabel | + *(__be32*)hdr = fl->fl6_flowlabel | htonl(0x60000000 | ((int)np->cork.tclass << 20)); if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) @@ -1326,7 +1335,7 @@ int ip6_push_pending_frames(struct sock *sk) skb->priority = sk->sk_priority; skb->dst = dst_clone(&rt->u.dst); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output); if (err) { if (err > 0) @@ -1357,7 +1366,8 @@ void ip6_flush_pending_frames(struct sock *sk) struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 84d7ebdb9d21..8d918348f5bb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -66,7 +66,7 @@ MODULE_LICENSE("GPL"); #define HASH_SIZE 32 -#define HASH(addr) (((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \ +#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \ (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) @@ -215,11 +215,10 @@ ip6ip6_tnl_unlink(struct ip6_tnl *t) * Create tunnel matching given parameters. * * Return: - * 0 on success + * 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 ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; @@ -236,11 +235,11 @@ ip6_tnl_create(struct ip6_tnl_parm *p, struct ip6_tnl **pt) break; } if (i == IP6_TNL_MAX) - return -ENOBUFS; + goto failed; } dev = alloc_netdev(sizeof (*t), name, ip6ip6_tnl_dev_setup); if (dev == NULL) - return -ENOMEM; + goto failed; t = netdev_priv(dev); dev->init = ip6ip6_tnl_dev_init; @@ -248,13 +247,13 @@ ip6_tnl_create(struct ip6_tnl_parm *p, struct ip6_tnl **pt) if ((err = register_netdevice(dev)) < 0) { free_netdev(dev); - return err; + goto failed; } dev_hold(dev); - ip6ip6_tnl_link(t); - *pt = t; - return 0; + return t; +failed: + return NULL; } /** @@ -268,32 +267,23 @@ ip6_tnl_create(struct ip6_tnl_parm *p, struct ip6_tnl **pt) * 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 *ip6ip6_tnl_locate(struct ip6_tnl_parm *p, int create) { struct in6_addr *remote = &p->raddr; struct in6_addr *local = &p->laddr; struct ip6_tnl *t; - if (p->proto != IPPROTO_IPV6) - return -EINVAL; - for (t = *ip6ip6_bucket(p); t; t = 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(p); } /** @@ -391,7 +381,7 @@ parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw) static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data; struct ip6_tnl *t; @@ -434,12 +424,9 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } 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 = parse_tlv_tnl_enc_lim(skb, skb->data); if (teli && teli == ntohl(info) - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; @@ -451,6 +438,10 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, "tunnel!\n", t->parms.name); rel_msg = 1; } + } else if (net_ratelimit()) { + printk(KERN_WARNING + "%s: Recipient unable to parse tunneled " + "packet!\n ", t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -470,6 +461,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_msg && pskb_may_pull(skb, offset + sizeof (*ipv6h))) { struct rt6_info *rt; struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) goto out; @@ -504,6 +496,27 @@ static inline void ip6ip6_ecn_decapsulate(struct ipv6hdr *outer_iph, if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) IP6_ECN_set_ce(inner_iph); } +static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) +{ + struct ip6_tnl_parm *p = &t->parms; + int ret = 0; + + if (p->flags & IP6_TNL_F_CAP_RCV) { + struct net_device *ldev = NULL; + + if (p->link) + ldev = dev_get_by_index(p->link); + + if ((ipv6_addr_is_multicast(&p->laddr) || + likely(ipv6_chk_addr(&p->laddr, ldev, 0))) && + likely(!ipv6_chk_addr(&p->raddr, NULL, 0))) + ret = 1; + + if (ldev) + dev_put(ldev); + } + return ret; +} /** * ip6ip6_rcv - decapsulate IPv6 packet and retransmit it locally @@ -528,7 +541,7 @@ ip6ip6_rcv(struct sk_buff *skb) goto discard; } - if (!(t->parms.flags & IP6_TNL_F_CAP_RCV)) { + if (!ip6_tnl_rcv_ctl(t)) { t->stat.rx_dropped++; read_unlock(&ip6ip6_lock); goto discard; @@ -542,6 +555,7 @@ ip6ip6_rcv(struct sk_buff *skb) skb->dev = t->dev; dst_release(skb->dst); skb->dst = NULL; + nf_reset(skb); if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6h, skb->nh.ipv6h); ip6ip6_ecn_decapsulate(ipv6h, skb); @@ -559,31 +573,23 @@ discard: return 0; } -static inline struct ipv6_txoptions *create_tel(__u8 encap_limit) -{ - struct ipv6_tlv_tnl_enc_lim *tel; - struct ipv6_txoptions *opt; - __u8 *raw; - - int opt_len = sizeof(*opt) + 8; - - if (!(opt = kzalloc(opt_len, GFP_ATOMIC))) { - return NULL; - } - 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; } /** @@ -606,6 +612,34 @@ ip6ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr) return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } +static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) +{ + struct ip6_tnl_parm *p = &t->parms; + int ret = 0; + + if (p->flags & IP6_TNL_F_CAP_XMIT) { + struct net_device *ldev = NULL; + + if (p->link) + ldev = dev_get_by_index(p->link); + + if (unlikely(!ipv6_chk_addr(&p->laddr, ldev, 0))) + printk(KERN_WARNING + "%s xmit: Local address not yet configured!\n", + p->name); + else if (!ipv6_addr_is_multicast(&p->raddr) && + unlikely(ipv6_chk_addr(&p->raddr, NULL, 0))) + printk(KERN_WARNING + "%s xmit: Routing loop! " + "Remote address found on this node!\n", + p->name); + else + ret = 1; + if (ldev) + dev_put(ldev); + } + return ret; +} /** * ip6ip6_tnl_xmit - encapsulate packet and send * @skb: the outgoing socket buffer @@ -625,8 +659,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->stat; struct ipv6hdr *ipv6h = skb->nh.ipv6h; - struct ipv6_txoptions *opt = NULL; int encap_limit = -1; + struct ipv6_tel_txoption opt; __u16 offset; struct flowi fl; struct dst_entry *dst; @@ -643,10 +677,9 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err; } if (skb->protocol != htons(ETH_P_IPV6) || - !(t->parms.flags & IP6_TNL_F_CAP_XMIT) || - ip6ip6_tnl_addr_conflict(t, ipv6h)) { + !ip6_tnl_xmit_ctl(t) || 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]; @@ -656,20 +689,17 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err; } encap_limit = tel->encap_limit - 1; - } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) { + } 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; dsfield = ipv6_get_dsfield(ipv6h); if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)) - fl.fl6_flowlabel |= (*(__u32 *) ipv6h & IPV6_TCLASS_MASK); + fl.fl6_flowlabel |= (*(__be32 *) 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; + fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); if ((dst = ip6_tnl_dst_check(t)) != NULL) dst_hold(dst); @@ -691,7 +721,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err_dst_release; } mtu = dst_mtu(dst) - sizeof (*ipv6h); - if (opt) { + if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } @@ -729,12 +759,13 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; - if (opt) - ipv6_push_nfrag_opts(skb, opt, &proto, NULL); - + if (encap_limit >= 0) { + init_tel_txopt(&opt, encap_limit); + ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); + } skb->nh.raw = skb_push(skb, sizeof(struct ipv6hdr)); ipv6h = skb->nh.ipv6h; - *(u32*)ipv6h = fl.fl6_flowlabel | htonl(0x60000000); + *(__be32*)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)); @@ -747,7 +778,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) 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) { + if (net_xmit_eval(err) == 0) { stats->tx_bytes += pkt_len; stats->tx_packets++; } else { @@ -755,9 +786,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) stats->tx_aborted_errors++; } ip6_tnl_dst_store(t, dst); - - kfree(opt); - t->recursion--; return 0; tx_err_link_failure: @@ -765,7 +793,6 @@ tx_err_link_failure: dst_link_failure(skb); tx_err_dst_release: dst_release(dst); - kfree(opt); tx_err: stats->tx_errors++; stats->tx_dropped++; @@ -777,39 +804,19 @@ tx_err: static void ip6_tnl_set_cap(struct ip6_tnl *t) { 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); + int ltype = ipv6_addr_type(&p->laddr); + int rtype = ipv6_addr_type(&p->raddr); p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV); - 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 (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; - } - if (ldev) - dev_put(ldev); + 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) + p->flags |= IP6_TNL_F_CAP_XMIT; + if (rtype&IPV6_ADDR_UNICAST) + p->flags |= IP6_TNL_F_CAP_RCV; } } @@ -843,8 +850,11 @@ static void ip6ip6_tnl_link_config(struct ip6_tnl *t) dev->iflink = p->link; 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(&p->raddr, &p->laddr, - p->link, 0); + p->link, strict); if (rt == NULL) return; @@ -919,26 +929,20 @@ static int ip6ip6_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; switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6ip6_fb_tnl_dev) { - if (copy_from_user(&p, - ifr->ifr_ifru.ifru_data, - sizeof (p))) { + 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 = netdev_priv(dev); - else if (err) - break; - } else + t = ip6ip6_tnl_locate(&p, 0); + } + if (t == NULL) t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof (p)); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) { err = -EFAULT; @@ -947,35 +951,36 @@ 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)) 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 = netdev_priv(dev); - } - if (!t && (err = ip6ip6_tnl_locate(&p, &t, create))) { + err = -EINVAL; + if (p.proto != IPPROTO_IPV6) break; - } - if (cmd == SIOCCHGTUNNEL) { - if (t->dev != dev) { - err = -EEXIST; - break; - } + t = ip6ip6_tnl_locate(&p, cmd == SIOCADDTUNNEL); + if (dev != ip6ip6_fb_tnl_dev && cmd == SIOCCHGTUNNEL) { + if (t != NULL) { + if (t->dev != dev) { + err = -EEXIST; + break; + } + } else + t = netdev_priv(dev); + 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; - } + if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof (p))) + err = -EFAULT; + + } else + err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); break; case SIOCDELTUNNEL: err = -EPERM; @@ -983,22 +988,18 @@ ip6ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; if (dev == ip6ip6_fb_tnl_dev) { - 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; - } - err = ip6ip6_tnl_locate(&p, &t, 0); - if (err) + err = -ENOENT; + if ((t = ip6ip6_tnl_locate(&p, 0)) == NULL) break; - if (t == netdev_priv(ip6ip6_fb_tnl_dev)) { - err = -EPERM; + err = -EPERM; + if (t->dev == ip6ip6_fb_tnl_dev) break; - } - } else { - t = netdev_priv(dev); + dev = t->dev; } - err = unregister_netdevice(t->dev); + err = unregister_netdevice(dev); break; default: err = -EINVAL; @@ -1149,6 +1150,20 @@ fail: return err; } +static void __exit ip6ip6_destroy_tunnels(void) +{ + int h; + struct ip6_tnl *t; + + for (h = 0; h < HASH_SIZE; h++) { + while ((t = tnls_r_l[h]) != NULL) + unregister_netdevice(t->dev); + } + + t = tnls_wc[0]; + unregister_netdevice(t->dev); +} + /** * ip6_tunnel_cleanup - free resources and unregister protocol **/ @@ -1158,7 +1173,9 @@ static void __exit ip6_tunnel_cleanup(void) if (xfrm6_tunnel_deregister(&ip6ip6_handler)) printk(KERN_INFO "ip6ip6 close: can't deregister tunnel\n"); - unregister_netdev(ip6ip6_fb_tnl_dev); + rtnl_lock(); + ip6ip6_destroy_tunnels(); + rtnl_unlock(); } module_init(ip6_tunnel_init); diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 71f59f18ede8..511730b67e97 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -176,7 +176,7 @@ out_ok: } static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { __be32 spi; struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index de6b91981b30..1eafcfc95e81 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -51,6 +51,7 @@ #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/udplite.h> #include <net/xfrm.h> #include <asm/uaccess.h> @@ -239,6 +240,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct sk_buff *pktopt; if (sk->sk_protocol != IPPROTO_UDP && + sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) break; @@ -276,11 +278,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sk->sk_family = PF_INET; 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_inc_use(prot); local_bh_enable(); - sk->sk_prot = &udp_prot; + sk->sk_prot = prot; sk->sk_socket->ops = &inet_dgram_ops; sk->sk_family = PF_INET; } @@ -813,6 +819,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_ADDRFORM: if (sk->sk_protocol != IPPROTO_UDP && + sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) return -EINVAL; if (sk->sk_state != TCP_ESTABLISHED) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 3b114e3fa2f8..a1c231a04ac2 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -83,7 +83,7 @@ struct mld2_grec { __u8 grec_type; __u8 grec_auxwords; - __u16 grec_nsrcs; + __be16 grec_nsrcs; struct in6_addr grec_mca; struct in6_addr grec_src[0]; }; @@ -91,18 +91,18 @@ struct mld2_grec { struct mld2_report { __u8 type; __u8 resv1; - __u16 csum; - __u16 resv2; - __u16 ngrec; + __sum16 csum; + __be16 resv2; + __be16 ngrec; struct mld2_grec grec[0]; }; struct mld2_query { __u8 type; __u8 code; - __u16 csum; - __u16 mrc; - __u16 resv1; + __sum16 csum; + __be16 mrc; + __be16 resv1; struct in6_addr mca; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 qrv:3, @@ -116,7 +116,7 @@ struct mld2_query { #error "Please fix <asm/byteorder.h>" #endif __u8 qqic; - __u16 nsrcs; + __be16 nsrcs; struct in6_addr srcs[0]; }; @@ -1465,7 +1465,7 @@ static void mld_sendpack(struct sk_buff *skb) struct inet6_dev *idev = in6_dev_get(skb->dev); int err; - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTREQUESTS); payload_len = skb->tail - (unsigned char *)skb->nh.ipv6h - sizeof(struct ipv6hdr); mldlen = skb->tail - skb->h.raw; @@ -1477,9 +1477,9 @@ static void mld_sendpack(struct sk_buff *skb) mld_dev_queue_xmit); if (!err) { ICMP6_INC_STATS(idev,ICMP6_MIB_OUTMSGS); - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTMCASTPKTS); } else - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS); if (likely(idev != NULL)) in6_dev_put(idev); @@ -1763,7 +1763,10 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + rcu_read_lock(); + IP6_INC_STATS(__in6_dev_get(dev), + IPSTATS_MIB_OUTREQUESTS); + rcu_read_unlock(); snd_addr = addr; if (type == ICMPV6_MGM_REDUCTION) { snd_addr = &all_routers; @@ -1777,7 +1780,10 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) skb = sock_alloc_send_skb(sk, LL_RESERVED_SPACE(dev) + full_len, 1, &err); if (skb == NULL) { - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + rcu_read_lock(); + IP6_INC_STATS(__in6_dev_get(dev), + IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return; } @@ -1816,9 +1822,9 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) else ICMP6_INC_STATS(idev, ICMP6_MIB_OUTGROUPMEMBRESPONSES); ICMP6_INC_STATS(idev, ICMP6_MIB_OUTMSGS); - IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTMCASTPKTS); } else - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS); if (likely(idev != NULL)) in6_dev_put(idev); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 7ccdc8fc5a31..be7dd7db65d7 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -262,10 +262,10 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct sel.proto = fl->proto; sel.dport = xfrm_flowi_dport(fl); if (sel.dport) - sel.dport_mask = ~((__u16)0); + sel.dport_mask = htons(~0); sel.sport = xfrm_flowi_sport(fl); if (sel.sport) - sel.sport_mask = ~((__u16)0); + sel.sport_mask = htons(~0); sel.ifindex = fl->oif; err = km_report(IPPROTO_DSTOPTS, &sel, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0304b5fe8d6a..56ea92837307 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -472,7 +472,9 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, inc_opt = 0; } - skb = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), + skb = sock_alloc_send_skb(sk, + (MAX_HEADER + sizeof(struct ipv6hdr) + + len + LL_RESERVED_SPACE(dev)), 1, &err); if (skb == NULL) { @@ -513,7 +515,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, skb->dst = dst; idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(idev, 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); @@ -561,7 +563,9 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, if (send_llinfo) len += ndisc_opt_addr_space(dev); - skb = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), + skb = sock_alloc_send_skb(sk, + (MAX_HEADER + sizeof(struct ipv6hdr) + + len + LL_RESERVED_SPACE(dev)), 1, &err); if (skb == NULL) { ND_PRINTK0(KERN_ERR @@ -597,7 +601,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, /* send it! */ skb->dst = dst; idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(idev, 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); @@ -636,7 +640,9 @@ void ndisc_send_rs(struct net_device *dev, struct in6_addr *saddr, if (dev->addr_len) len += ndisc_opt_addr_space(dev); - skb = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), + skb = sock_alloc_send_skb(sk, + (MAX_HEADER + sizeof(struct ipv6hdr) + + len + LL_RESERVED_SPACE(dev)), 1, &err); if (skb == NULL) { ND_PRINTK0(KERN_ERR @@ -670,7 +676,7 @@ void ndisc_send_rs(struct net_device *dev, struct in6_addr *saddr, /* send it! */ skb->dst = dst; idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(idev, 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); @@ -967,8 +973,6 @@ static void ndisc_recv_na(struct sk_buff *skb) ipv6_devconf.forwarding && ipv6_devconf.proxy_ndp && pneigh_lookup(&nd_tbl, &msg->target, dev, 0)) { /* XXX: idev->cnf.prixy_ndp */ - WARN_ON(skb->dst != NULL && - ((struct rt6_info *)skb->dst)->rt6i_idev); goto out; } @@ -1263,10 +1267,11 @@ skip_defrtr: } 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 @@ -1448,7 +1453,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, rd_len &= ~0x7; len += rd_len; - buff = sock_alloc_send_skb(sk, MAX_HEADER + len + LL_RESERVED_SPACE(dev), + buff = sock_alloc_send_skb(sk, + (MAX_HEADER + sizeof(struct ipv6hdr) + + len + LL_RESERVED_SPACE(dev)), 1, &err); if (buff == NULL) { ND_PRINTK0(KERN_ERR @@ -1506,7 +1513,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, buff->dst = dst; idev = in6_dev_get(dst->dev); - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(idev, 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); @@ -1744,6 +1751,7 @@ int __init ndisc_init(struct net_proto_family *ops) void ndisc_cleanup(void) { + unregister_netdevice_notifier(&ndisc_netdev_notifier); #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 580b1aba6722..f6294e5bcb31 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -31,7 +31,7 @@ int ip6_route_me_harder(struct sk_buff *skb) #endif if (dst->error) { - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); return -EINVAL; @@ -80,11 +80,11 @@ static int nf_ip6_reroute(struct sk_buff **pskb, const struct nf_info *info) return 0; } -unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, +__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol) { struct ipv6hdr *ip6h = skb->nh.ipv6h; - unsigned int csum = 0; + __sum16 csum = 0; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -100,12 +100,13 @@ unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, } /* fall through */ case CHECKSUM_NONE: - skb->csum = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->csum = ~csum_unfold( + csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb->len - dataoff, protocol, csum_sub(0, skb_checksum(skb, 0, - dataoff, 0))); + dataoff, 0)))); csum = __skb_checksum_complete(skb); } return csum; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4bc4e5b33794..fc3e5eb4bc3f 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -6,7 +6,7 @@ menu "IPv6: Netfilter Configuration (EXPERIMENTAL)" depends on INET && IPV6 && NETFILTER && EXPERIMENTAL config NF_CONNTRACK_IPV6 - tristate "IPv6 support for new connection tracking (EXPERIMENTAL)" + tristate "IPv6 connection tracking support (EXPERIMENTAL)" depends on EXPERIMENTAL && NF_CONNTRACK ---help--- Connection tracking keeps a record of what packets have passed @@ -40,7 +40,7 @@ config IP6_NF_QUEUE To compile it as a module, choose M here. If unsure, say N. config IP6_NF_IPTABLES - tristate "IP6 tables support (required for filtering/masq/NAT)" + tristate "IP6 tables support (required for filtering)" depends on NETFILTER_XTABLES help ip6tables is a general, extensible packet identification framework. diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 9510c24ca8d2..d4d9f182441a 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -241,7 +241,7 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) 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->mark = entry->skb->mark; pmsg->hook = entry->info->hook; pmsg->hw_protocol = entry->skb->protocol; @@ -349,9 +349,10 @@ ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct ipq_queue_entry *e) 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 (diff < 0) { + if (pskb_trim(e->skb, v->data_len)) + return -ENOMEM; + } else if (diff > 0) { if (v->data_len > 0xFFFF) return -EINVAL; if (diff > skb_tailroom(e->skb)) { @@ -619,6 +620,7 @@ static ctl_table ipq_root_table[] = { { .ctl_name = 0 } }; +#ifdef CONFIG_PROC_FS static int ipq_get_info(char *buffer, char **start, off_t offset, int length) { @@ -652,6 +654,7 @@ ipq_get_info(char *buffer, char **start, off_t offset, int length) len = 0; return len; } +#endif /* CONFIG_PROC_FS */ static struct nf_queue_handler nfqh = { .name = "ip6_queue", diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 4ab368fa0b8f..f63fb86d7c7b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -111,7 +111,7 @@ ip6_packet_match(const struct sk_buff *skb, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, - int *fragoff) + int *fragoff, int *hotdrop) { size_t i; unsigned long ret; @@ -169,9 +169,11 @@ ip6_packet_match(const struct sk_buff *skb, unsigned short _frag_off; protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off); - if (protohdr < 0) + if (protohdr < 0) { + if (_frag_off == 0) + *hotdrop = 1; return 0; - + } *fragoff = _frag_off; dprintf("Packet protocol %hi ?= %s%hi.\n", @@ -290,7 +292,7 @@ ip6t_do_table(struct sk_buff **pskb, IP_NF_ASSERT(e); IP_NF_ASSERT(back); if (ip6_packet_match(*pskb, indev, outdev, &e->ipv6, - &protoff, &offset)) { + &protoff, &offset, &hotdrop)) { struct ip6t_entry_target *t; if (IP6T_MATCH_ITERATE(e, do_match, @@ -584,12 +586,19 @@ check_entry(struct ip6t_entry *e, const char *name, unsigned int size, return -EINVAL; } + if (e->target_offset + sizeof(struct ip6t_entry_target) > + e->next_offset) + return -EINVAL; + j = 0; ret = IP6T_MATCH_ITERATE(e, check_match, name, &e->ipv6, e->comefrom, &j); if (ret != 0) goto cleanup_matches; t = ip6t_get_target(e); + ret = -EINVAL; + if (e->target_offset + t->u.target_size > e->next_offset) + goto cleanup_matches; target = try_then_request_module(xt_find_target(AF_INET6, t->u.user.name, t->u.user.revision), @@ -749,19 +758,17 @@ translate_table(const char *name, } } - if (!mark_source_chains(newinfo, valid_hooks, entry0)) - return -ELOOP; - /* Finally, each sanity check must pass */ i = 0; ret = IP6T_ENTRY_ITERATE(entry0, newinfo->size, check_entry, name, size, &i); - if (ret != 0) { - IP6T_ENTRY_ITERATE(entry0, newinfo->size, - cleanup_entry, &i); - return ret; - } + if (ret != 0) + goto cleanup; + + ret = -ELOOP; + if (!mark_source_chains(newinfo, valid_hooks, entry0)) + goto cleanup; /* And one copy for every other CPU */ for_each_possible_cpu(i) { @@ -769,6 +776,9 @@ translate_table(const char *name, memcpy(newinfo->entries[i], entry0, newinfo->size); } + return 0; +cleanup: + IP6T_ENTRY_ITERATE(entry0, newinfo->size, cleanup_entry, &i); return ret; } @@ -1438,6 +1448,9 @@ static void __exit ip6_tables_fini(void) * 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 @@ -1461,32 +1474,33 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { if (target < 0) break; - return -1; + return -ENOENT; } hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr); if (hp == NULL) - return -1; + return -EBADMSG; if (nexthdr == NEXTHDR_FRAGMENT) { - unsigned short _frag_off, *fp; + unsigned short _frag_off; + __be16 *fp; fp = skb_header_pointer(skb, start+offsetof(struct frag_hdr, frag_off), sizeof(_frag_off), &_frag_off); if (fp == NULL) - return -1; + return -EBADMSG; _frag_off = ntohs(*fp) & ~0x7; if (_frag_off) { if (target < 0 && ((!ipv6_ext_hdr(hp->nexthdr)) || - nexthdr == NEXTHDR_NONE)) { + hp->nexthdr == NEXTHDR_NONE)) { if (fragoff) *fragoff = _frag_off; return hp->nexthdr; } - return -1; + return -ENOENT; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 0cf537d30185..33b1faa90d74 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -69,9 +69,9 @@ static void dump_packet(const struct nf_loginfo *info, /* 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, + (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, ih->hop_limit, - (ntohl(*(u_int32_t *)ih) & 0x000fffff)); + (ntohl(*(__be32 *)ih) & 0x000fffff)); fragment = 0; ptr = ip6hoff + sizeof(struct ipv6hdr); @@ -270,11 +270,15 @@ static void dump_packet(const struct nf_loginfo *info, } break; } - case IPPROTO_UDP: { + case IPPROTO_UDP: + case IPPROTO_UDPLITE: { struct udphdr _udph, *uh; - /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP "); + if (currenthdr == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + printk("PROTO=UDP " ); + else /* Max length: 14 "PROTO=UDPLITE " */ + printk("PROTO=UDPLITE "); if (fragment) break; @@ -436,13 +440,8 @@ ip6t_log_target(struct sk_buff **pskb, li.u.log.level = loginfo->level; li.u.log.logflags = loginfo->logflags; - if (loginfo->logflags & IP6T_LOG_NFLOG) - nf_log_packet(PF_INET6, hooknum, *pskb, in, out, &li, - "%s", loginfo->prefix); - else - ip6t_log_packet(PF_INET6, hooknum, *pskb, in, out, &li, - loginfo->prefix); - + ip6t_log_packet(PF_INET6, hooknum, *pskb, in, out, &li, + loginfo->prefix); return IP6T_CONTINUE; } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index ec1b1608156c..46486645eb75 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -54,9 +54,14 @@ match(const struct sk_buff *skb, const struct ip6t_ah *ahinfo = matchinfo; unsigned int ptr; unsigned int hdrlen = 0; + int err; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL) < 0) + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL); + if (err < 0) { + if (err != -ENOENT) + *hotdrop = 1; return 0; + } ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah); if (ah == NULL) { diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 78d9c8b9e28a..cd22eaaccdca 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -52,9 +52,14 @@ match(const struct sk_buff *skb, struct frag_hdr _frag, *fh; const struct ip6t_frag *fraginfo = matchinfo; unsigned int ptr; + int err; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL) < 0) + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL); + if (err < 0) { + if (err != -ENOENT) + *hotdrop = 1; return 0; + } fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag); if (fh == NULL) { diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index d32a205e3af2..3f25babe0440 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -65,9 +65,14 @@ match(const struct sk_buff *skb, u8 _opttype, *tp = NULL; u8 _optlen, *lp = NULL; unsigned int optlen; + int err; - if (ipv6_find_hdr(skb, &ptr, match->data, NULL) < 0) + err = ipv6_find_hdr(skb, &ptr, match->data, NULL); + if (err < 0) { + if (err != -ENOENT) + *hotdrop = 1; return 0; + } oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); if (oh == NULL) { diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index bcb2e168a5bc..54d7d14134fd 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -58,9 +58,14 @@ match(const struct sk_buff *skb, unsigned int hdrlen = 0; unsigned int ret = 0; struct in6_addr *ap, _addr; + int err; - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL) < 0) + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL); + if (err < 0) { + if (err != -ENOENT) + *hotdrop = 1; return 0; + } rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route); if (rh == NULL) { diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 386ea260e767..6250e86a6ddc 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -149,11 +149,10 @@ ip6t_local_hook(unsigned int hook, int (*okfn)(struct sk_buff *)) { - 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; #if 0 /* root is playing with raw sockets. */ @@ -165,10 +164,10 @@ ip6t_local_hook(unsigned int hook, } #endif - /* save source/dest address, nfmark, hoplimit, flowlabel, priority, */ + /* save source/dest address, mark, hoplimit, flowlabel, priority, */ memcpy(&saddr, &(*pskb)->nh.ipv6h->saddr, sizeof(saddr)); memcpy(&daddr, &(*pskb)->nh.ipv6h->daddr, sizeof(daddr)); - nfmark = (*pskb)->nfmark; + mark = (*pskb)->mark; hop_limit = (*pskb)->nh.ipv6h->hop_limit; /* flowlabel and prio (includes version, which shouldn't change either */ @@ -179,7 +178,7 @@ ip6t_local_hook(unsigned int hook, 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)->mark != mark || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) return ip6_route_me_harder(*pskb) == 0 ? ret : NF_DROP; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index e5e53fff9e38..a20615ffccff 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -33,7 +33,7 @@ #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> -#include <net/netfilter/nf_conntrack_protocol.h> +#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_core.h> @@ -43,8 +43,6 @@ #define DEBUGP(format, args...) #endif -DECLARE_PER_CPU(struct ip_conntrack_stat, nf_conntrack_stat); - static int ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple) { @@ -211,11 +209,6 @@ out: return nf_conntrack_confirm(pskb); } -extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb); -extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, - struct net_device *out, - int (*okfn)(struct sk_buff *)); static unsigned int ipv6_defrag(unsigned int hooknum, struct sk_buff **pskb, const struct net_device *in, @@ -331,26 +324,7 @@ static struct nf_hook_ops ipv6_conntrack_ops[] = { }; #ifdef CONFIG_SYSCTL - -/* From nf_conntrack_proto_icmpv6.c */ -extern unsigned int nf_ct_icmpv6_timeout; - -/* From nf_conntrack_reasm.c */ -extern unsigned int nf_ct_frag6_timeout; -extern unsigned int nf_ct_frag6_low_thresh; -extern unsigned int nf_ct_frag6_high_thresh; - -static struct ctl_table_header *nf_ct_ipv6_sysctl_header; - -static ctl_table nf_ct_sysctl_table[] = { - { - .ctl_name = NET_NF_CONNTRACK_ICMPV6_TIMEOUT, - .procname = "nf_conntrack_icmpv6_timeout", - .data = &nf_ct_icmpv6_timeout, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - }, +static ctl_table nf_ct_ipv6_sysctl_table[] = { { .ctl_name = NET_NF_CONNTRACK_FRAG6_TIMEOUT, .procname = "nf_conntrack_frag6_timeout", @@ -377,26 +351,6 @@ static ctl_table nf_ct_sysctl_table[] = { }, { .ctl_name = 0 } }; - -static ctl_table nf_ct_netfilter_table[] = { - { - .ctl_name = NET_NETFILTER, - .procname = "netfilter", - .mode = 0555, - .child = nf_ct_sysctl_table, - }, - { .ctl_name = 0 } -}; - -static ctl_table nf_ct_net_table[] = { - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, - .child = nf_ct_netfilter_table, - }, - { .ctl_name = 0 } -}; #endif #if defined(CONFIG_NF_CT_NETLINK) || \ @@ -454,16 +408,14 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .tuple_to_nfattr = ipv6_tuple_to_nfattr, .nfattr_to_tuple = ipv6_nfattr_to_tuple, #endif +#ifdef CONFIG_SYSCTL + .ctl_table_path = nf_net_netfilter_sysctl_path, + .ctl_table = nf_ct_ipv6_sysctl_table, +#endif .get_features = ipv6_get_features, .me = THIS_MODULE, }; -extern struct nf_conntrack_protocol nf_conntrack_protocol_tcp6; -extern struct nf_conntrack_protocol nf_conntrack_protocol_udp6; -extern struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6; -extern int nf_ct_frag6_init(void); -extern void nf_ct_frag6_cleanup(void); - MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); @@ -479,19 +431,19 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) printk("nf_conntrack_ipv6: can't initialize frag6.\n"); return ret; } - ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_tcp6); + ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6); if (ret < 0) { printk("nf_conntrack_ipv6: can't register tcp.\n"); goto cleanup_frag6; } - ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_udp6); + ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6); if (ret < 0) { printk("nf_conntrack_ipv6: can't register udp.\n"); goto cleanup_tcp; } - ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_icmpv6); + ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmpv6); if (ret < 0) { printk("nf_conntrack_ipv6: can't register icmpv6.\n"); goto cleanup_udp; @@ -510,28 +462,16 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) "hook.\n"); goto cleanup_ipv6; } -#ifdef CONFIG_SYSCTL - nf_ct_ipv6_sysctl_header = register_sysctl_table(nf_ct_net_table, 0); - if (nf_ct_ipv6_sysctl_header == NULL) { - printk("nf_conntrack: can't register to sysctl.\n"); - ret = -ENOMEM; - goto cleanup_hooks; - } -#endif return ret; -#ifdef CONFIG_SYSCTL - cleanup_hooks: - nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); -#endif cleanup_ipv6: nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); cleanup_icmpv6: - nf_conntrack_protocol_unregister(&nf_conntrack_protocol_icmpv6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); cleanup_udp: - nf_conntrack_protocol_unregister(&nf_conntrack_protocol_udp6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); cleanup_tcp: - nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); cleanup_frag6: nf_ct_frag6_cleanup(); return ret; @@ -540,14 +480,11 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) static void __exit nf_conntrack_l3proto_ipv6_fini(void) { synchronize_net(); -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(nf_ct_ipv6_sysctl_header); -#endif nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); - nf_conntrack_protocol_unregister(&nf_conntrack_protocol_icmpv6); - nf_conntrack_protocol_unregister(&nf_conntrack_protocol_udp6); - nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6); nf_ct_frag6_cleanup(); } diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 34d447208ffd..3905cacc69af 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -29,11 +29,11 @@ #include <linux/seq_file.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack_tuple.h> -#include <net/netfilter/nf_conntrack_protocol.h> +#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h> -unsigned long nf_ct_icmpv6_timeout __read_mostly = 30*HZ; +static unsigned long nf_ct_icmpv6_timeout __read_mostly = 30*HZ; #if 0 #define DEBUGP printk @@ -142,9 +142,6 @@ static int icmpv6_new(struct nf_conn *conntrack, return 1; } -extern int -nf_ct_ipv6_skip_exthdr(struct sk_buff *skb, int start, u8 *nexthdrp, int len); -extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6; static int icmpv6_error_message(struct sk_buff *skb, unsigned int icmp6off, @@ -155,7 +152,7 @@ icmpv6_error_message(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h; struct icmp6hdr _hdr, *hp; unsigned int inip6off; - struct nf_conntrack_protocol *inproto; + struct nf_conntrack_l4proto *inproto; u_int8_t inprotonum; unsigned int inprotoff; @@ -185,7 +182,7 @@ icmpv6_error_message(struct sk_buff *skb, return -NF_ACCEPT; } - inproto = __nf_ct_proto_find(PF_INET6, inprotonum); + inproto = __nf_ct_l4proto_find(PF_INET6, inprotonum); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuple(skb, inip6off, inprotoff, PF_INET6, inprotonum, @@ -290,7 +287,7 @@ static int icmpv6_nfattr_to_tuple(struct nfattr *tb[], tuple->dst.u.icmp.code = *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMPV6_CODE-1]); tuple->src.u.icmp.id = - *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_ICMPV6_ID-1]); + *(__be16 *)NFA_DATA(tb[CTA_PROTO_ICMPV6_ID-1]); if (tuple->dst.u.icmp.type < 128 || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) @@ -301,10 +298,27 @@ static int icmpv6_nfattr_to_tuple(struct nfattr *tb[], } #endif -struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6 = +#ifdef CONFIG_SYSCTL +static struct ctl_table_header *icmpv6_sysctl_header; +static struct ctl_table icmpv6_sysctl_table[] = { + { + .ctl_name = NET_NF_CONNTRACK_ICMPV6_TIMEOUT, + .procname = "nf_conntrack_icmpv6_timeout", + .data = &nf_ct_icmpv6_timeout, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + }, + { + .ctl_name = 0 + } +}; +#endif /* CONFIG_SYSCTL */ + +struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = { .l3proto = PF_INET6, - .proto = IPPROTO_ICMPV6, + .l4proto = IPPROTO_ICMPV6, .name = "icmpv6", .pkt_to_tuple = icmpv6_pkt_to_tuple, .invert_tuple = icmpv6_invert_tuple, @@ -318,6 +332,10 @@ struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6 = .tuple_to_nfattr = icmpv6_tuple_to_nfattr, .nfattr_to_tuple = icmpv6_nfattr_to_tuple, #endif +#ifdef CONFIG_SYSCTL + .ctl_table_header = &icmpv6_sysctl_header, + .ctl_table = icmpv6_sysctl_table, +#endif }; -EXPORT_SYMBOL(nf_conntrack_protocol_icmpv6); +EXPORT_SYMBOL(nf_conntrack_l4proto_icmpv6); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index bf93c1ea6be9..37e5fca923aa 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -72,7 +72,7 @@ struct nf_ct_frag6_queue struct hlist_node list; struct list_head lru_list; /* lru list member */ - __u32 id; /* fragment id */ + __be32 id; /* fragment id */ struct in6_addr saddr; struct in6_addr daddr; @@ -115,28 +115,28 @@ static __inline__ void fq_unlink(struct nf_ct_frag6_queue *fq) write_unlock(&nf_ct_frag6_lock); } -static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr, +static unsigned int ip6qhashfn(__be32 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]; + a = (__force u32)saddr->s6_addr32[0]; + b = (__force u32)saddr->s6_addr32[1]; + c = (__force u32)saddr->s6_addr32[2]; a += JHASH_GOLDEN_RATIO; b += JHASH_GOLDEN_RATIO; c += nf_ct_frag6_hash_rnd; __jhash_mix(a, b, c); - a += saddr->s6_addr32[3]; - b += daddr->s6_addr32[0]; - c += daddr->s6_addr32[1]; + a += (__force u32)saddr->s6_addr32[3]; + b += (__force u32)daddr->s6_addr32[0]; + c += (__force u32)daddr->s6_addr32[1]; __jhash_mix(a, b, c); - a += daddr->s6_addr32[2]; - b += daddr->s6_addr32[3]; - c += id; + a += (__force u32)daddr->s6_addr32[2]; + b += (__force u32)daddr->s6_addr32[3]; + c += (__force u32)id; __jhash_mix(a, b, c); return c & (FRAG6Q_HASHSZ - 1); @@ -338,7 +338,7 @@ static struct nf_ct_frag6_queue *nf_ct_frag6_intern(unsigned int hash, static struct nf_ct_frag6_queue * -nf_ct_frag6_create(unsigned int hash, u32 id, struct in6_addr *src, struct in6_addr *dst) +nf_ct_frag6_create(unsigned int hash, __be32 id, struct in6_addr *src, struct in6_addr *dst) { struct nf_ct_frag6_queue *fq; @@ -366,7 +366,7 @@ oom: } static __inline__ struct nf_ct_frag6_queue * -fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) { struct nf_ct_frag6_queue *fq; struct hlist_node *n; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index efee7a6301a8..35249d8487bb 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -49,6 +49,8 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) fold_prot_inuse(&tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", fold_prot_inuse(&udpv6_prot)); + seq_printf(seq, "UDPLITE6: inuse %d\n", + fold_prot_inuse(&udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", fold_prot_inuse(&rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", @@ -133,6 +135,14 @@ static struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_SENTINEL }; +static 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_SENTINEL +}; + static unsigned long fold_field(void *mib[], int offt) { @@ -161,11 +171,13 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) if (idev) { seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex); + snmp6_seq_show_item(seq, (void **)idev->stats.ipv6, snmp6_ipstats_list); 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); + snmp6_seq_show_item(seq, (void **)udplite_stats_in6, snmp6_udplite6_list); } return 0; } @@ -281,6 +293,9 @@ int snmp6_alloc_dev(struct inet6_dev *idev) if (!idev || !idev->dev) return -EINVAL; + if (snmp6_mib_init((void **)idev->stats.ipv6, sizeof(struct ipstats_mib), + __alignof__(struct ipstats_mib)) < 0) + goto err_ip; if (snmp6_mib_init((void **)idev->stats.icmpv6, sizeof(struct icmpv6_mib), __alignof__(struct icmpv6_mib)) < 0) goto err_icmp; @@ -288,12 +303,15 @@ int snmp6_alloc_dev(struct inet6_dev *idev) return 0; err_icmp: + snmp6_mib_free((void **)idev->stats.ipv6); +err_ip: return err; } int snmp6_free_dev(struct inet6_dev *idev) { snmp6_mib_free((void **)idev->stats.icmpv6); + snmp6_mib_free((void **)idev->stats.ipv6); return 0; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d09329ca3267..c2e629d6aea4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -220,7 +220,7 @@ 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; @@ -290,7 +290,7 @@ out: void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, u32 info) + int type, int code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -370,9 +370,9 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->csum = ~csum_ipv6_magic(&skb->nh.ipv6h->saddr, + skb->csum = ~csum_unfold(csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, - skb->len, inet->num, 0); + skb->len, inet->num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { @@ -479,8 +479,8 @@ 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; @@ -530,16 +530,15 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, /* 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, + csum = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, total_len, fl->proto, tmp_csum); - if (tmp_csum == 0) - tmp_csum = -1; + if (csum == 0 && fl->proto == IPPROTO_UDP) + csum = CSUM_MANGLED_0; - csum = tmp_csum; if (skb_store_bits(skb, offset, &csum, 2)) BUG(); @@ -586,7 +585,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, if (err) goto error_fault; - IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS); + IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) @@ -600,11 +599,11 @@ error_fault: err = -EFAULT; kfree_skb(skb); error: - IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); return err; } -static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) +static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) { struct iovec *iov; u8 __user *type = NULL; @@ -616,7 +615,7 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) int i; if (!msg->msg_iov) - return; + return 0; for (i = 0; i < msg->msg_iovlen; i++) { iov = &msg->msg_iov[i]; @@ -638,8 +637,9 @@ 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(fl->fl_icmp_type, type) || + get_user(fl->fl_icmp_code, code)) + return -EFAULT; probed = 1; } break; @@ -650,7 +650,8 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) /* check if type field is readable or not. */ if (iov->iov_len > 2 - len) { u8 __user *p = iov->iov_base; - get_user(fl->fl_mh_type, &p[2 - len]); + if (get_user(fl->fl_mh_type, &p[2 - len])) + return -EFAULT; probed = 1; } else len += iov->iov_len; @@ -664,6 +665,7 @@ 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, @@ -787,7 +789,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, opt = ipv6_fixup_options(&opt_space, opt); fl.proto = proto; - rawv6_probe_proto_opt(&fl, msg); + err = rawv6_probe_proto_opt(&fl, msg); + if (err) + goto out; ipv6_addr_copy(&fl.fl6_dst, daddr); if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index f39bbedd1327..6f9a9046510f 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -47,6 +47,7 @@ #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> @@ -76,7 +77,7 @@ struct frag_queue struct hlist_node list; struct list_head lru_list; /* lru list member */ - __u32 id; /* fragment id */ + __be32 id; /* fragment id */ struct in6_addr saddr; struct in6_addr daddr; @@ -124,28 +125,28 @@ static __inline__ void fq_unlink(struct frag_queue *fq) * 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 ip6qhashfn(u32 id, struct in6_addr *saddr, +static unsigned int ip6qhashfn(__be32 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]; + a = (__force u32)saddr->s6_addr32[0]; + b = (__force u32)saddr->s6_addr32[1]; + c = (__force u32)saddr->s6_addr32[2]; a += JHASH_GOLDEN_RATIO; b += JHASH_GOLDEN_RATIO; c += ip6_frag_hash_rnd; __jhash_mix(a, b, c); - a += saddr->s6_addr32[3]; - b += daddr->s6_addr32[0]; - c += daddr->s6_addr32[1]; + a += (__force u32)saddr->s6_addr32[3]; + b += (__force u32)daddr->s6_addr32[0]; + c += (__force u32)daddr->s6_addr32[1]; __jhash_mix(a, b, c); - a += daddr->s6_addr32[2]; - b += daddr->s6_addr32[3]; - c += id; + a += (__force u32)daddr->s6_addr32[2]; + b += (__force u32)daddr->s6_addr32[3]; + c += (__force u32)id; __jhash_mix(a, b, c); return c & (IP6Q_HASHSZ - 1); @@ -257,7 +258,7 @@ static __inline__ void fq_kill(struct frag_queue *fq) } } -static void ip6_evictor(void) +static void ip6_evictor(struct inet6_dev *idev) { struct frag_queue *fq; struct list_head *tmp; @@ -284,14 +285,14 @@ static void ip6_evictor(void) spin_unlock(&fq->lock); fq_put(fq, &work); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS); } } static void ip6_frag_expire(unsigned long data) { struct frag_queue *fq = (struct frag_queue *) data; - struct net_device *dev; + struct net_device *dev = NULL; spin_lock(&fq->lock); @@ -300,17 +301,19 @@ static void ip6_frag_expire(unsigned long data) fq_kill(fq); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + dev = dev_get_by_index(fq->iif); + if (!dev) + goto out; + + rcu_read_lock(); + IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); + IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + rcu_read_unlock(); /* Don't send error if the first segment did not arrive. */ if (!(fq->last_in&FIRST_IN) || !fq->fragments) goto out; - dev = dev_get_by_index(fq->iif); - if (!dev) - goto out; - /* But use as source device on which LAST ARRIVED segment was received. And do not use fq->dev @@ -318,8 +321,9 @@ static void ip6_frag_expire(unsigned long data) */ fq->fragments->dev = dev; icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev); - dev_put(dev); out: + if (dev) + dev_put(dev); spin_unlock(&fq->lock); fq_put(fq, NULL); } @@ -366,7 +370,8 @@ static struct frag_queue *ip6_frag_intern(struct frag_queue *fq_in) static struct frag_queue * -ip6_frag_create(u32 id, struct in6_addr *src, struct in6_addr *dst) +ip6_frag_create(__be32 id, struct in6_addr *src, struct in6_addr *dst, + struct inet6_dev *idev) { struct frag_queue *fq; @@ -386,12 +391,13 @@ ip6_frag_create(u32 id, struct in6_addr *src, struct in6_addr *dst) return ip6_frag_intern(fq); oom: - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS); return NULL; } static __inline__ struct frag_queue * -fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst) +fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst, + struct inet6_dev *idev) { struct frag_queue *fq; struct hlist_node *n; @@ -410,7 +416,7 @@ fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst) } read_unlock(&ip6_frag_lock); - return ip6_frag_create(id, src, dst); + return ip6_frag_create(id, src, dst, idev); } @@ -428,7 +434,8 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, ((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb,ICMPV6_HDR_FIELD, (u8*)&fhdr->frag_off - skb->nh.raw); return; } @@ -455,7 +462,8 @@ 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); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), + IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, payload_len)); return; @@ -571,7 +579,7 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, return; err: - IP6_INC_STATS(IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); } @@ -665,7 +673,9 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum); - IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS); + rcu_read_lock(); + IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMOKS); + rcu_read_unlock(); fq->fragments = NULL; return 1; @@ -677,7 +687,9 @@ out_oom: if (net_ratelimit()) printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n"); out_fail: - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + rcu_read_lock(); + IP6_INC_STATS_BH(__in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + rcu_read_unlock(); return -1; } @@ -691,16 +703,16 @@ static int ipv6_frag_rcv(struct sk_buff **skbp) hdr = skb->nh.ipv6h; - IP6_INC_STATS_BH(IPSTATS_MIB_REASMREQDS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ if (hdr->payload_len==0) { - IP6_INC_STATS(IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), 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); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb->h.raw-skb->nh.raw); return -1; } @@ -711,16 +723,17 @@ static int ipv6_frag_rcv(struct sk_buff **skbp) 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); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8*)fhdr - skb->nh.raw; return 1; } if (atomic_read(&ip6_frag_mem) > sysctl_ip6frag_high_thresh) - ip6_evictor(); + ip6_evictor(ip6_dst_idev(skb->dst)); - if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr)) != NULL) { + if ((fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr, + ip6_dst_idev(skb->dst))) != NULL) { int ret = -1; spin_lock(&fq->lock); @@ -736,7 +749,7 @@ static int ipv6_frag_rcv(struct sk_buff **skbp) return ret; } - IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); + IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d6b4b4f48d18..9f80518aacbd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,6 +141,10 @@ struct rt6_info ip6_null_entry = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sk_buff *skb); +static int ip6_pkt_blk_hole(struct sk_buff *skb); + struct rt6_info ip6_prohibit_entry = { .u = { .dst = { @@ -150,8 +154,8 @@ struct rt6_info ip6_prohibit_entry = { .obsolete = -1, .error = -EACCES, .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_discard, - .output = ip6_pkt_discard_out, + .input = ip6_pkt_prohibit, + .output = ip6_pkt_prohibit_out, .ops = &ip6_dst_ops, .path = (struct dst_entry*)&ip6_prohibit_entry, } @@ -170,8 +174,8 @@ struct rt6_info ip6_blk_hole_entry = { .obsolete = -1, .error = -EINVAL, .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_discard, - .output = ip6_pkt_discard_out, + .input = ip6_pkt_blk_hole, + .output = ip6_pkt_blk_hole, .ops = &ip6_dst_ops, .path = (struct dst_entry*)&ip6_blk_hole_entry, } @@ -326,6 +330,8 @@ static int inline rt6_check_neigh(struct rt6_info *rt) read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) m = 2; + else if (!(neigh->nud_state & NUD_FAILED)) + m = 1; read_unlock_bh(&neigh->lock); } return m; @@ -343,9 +349,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif n = rt6_check_neigh(rt); - if (n > 1) - m |= 16; - else if (!n && strict & RT6_LOOKUP_F_REACHABLE) + if (!n && (strict & RT6_LOOKUP_F_REACHABLE)) return -1; return m; } @@ -376,10 +380,11 @@ static struct rt6_info *rt6_select(struct rt6_info **head, int oif, continue; if (m > mpri) { - rt6_probe(match); + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(match); match = rt; mpri = m; - } else { + } else if (strict & RT6_LOOKUP_F_REACHABLE) { rt6_probe(rt); } } @@ -435,7 +440,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (pref == ICMPV6_ROUTER_PREF_INVALID) pref = ICMPV6_ROUTER_PREF_MEDIUM; - lifetime = htonl(rinfo->lifetime); + lifetime = ntohl(rinfo->lifetime); if (lifetime == 0xffffffff) { /* infinity */ } else if (lifetime > 0x7fffffff/HZ) { @@ -484,7 +489,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, do { \ if (rt == &ip6_null_entry) { \ struct fib6_node *pn; \ - while (fn) { \ + while (1) { \ if (fn->fn_flags & RTN_TL_ROOT) \ goto out; \ pn = fn->parent; \ @@ -529,13 +534,17 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, .nl_u = { .ip6_u = { .daddr = *daddr, - /* TODO: saddr */ }, }, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; + if (saddr) { + memcpy(&fl.fl6_src, saddr, sizeof(*saddr)); + flags |= RT6_LOOKUP_F_HAS_SADDR; + } + dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup); if (dst->error == 0) return (struct rt6_info *) dst; @@ -614,8 +623,6 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; - if (rt->rt6i_flags & RTF_REJECT) - rt->u.dst.error = ort->u.dst.error; rt->u.dst.flags |= DST_HOST; rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop); } @@ -630,7 +637,7 @@ static struct rt6_info *ip6_pol_route_input(struct fib6_table *table, int strict = 0; int attempts = 3; int err; - int reachable = RT6_LOOKUP_F_REACHABLE; + int reachable = ipv6_devconf.forwarding ? 0 : RT6_LOOKUP_F_REACHABLE; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -697,21 +704,22 @@ out2: void ip6_route_input(struct sk_buff *skb) { struct ipv6hdr *iph = skb->nh.ipv6h; + int flags = RT6_LOOKUP_F_HAS_SADDR; struct flowi fl = { .iif = skb->dev->ifindex, .nl_u = { .ip6_u = { .daddr = iph->daddr, .saddr = iph->saddr, -#ifdef CONFIG_IPV6_ROUTE_FWMARK - .fwmark = skb->nfmark, -#endif - .flowlabel = (* (u32 *) iph)&IPV6_FLOWINFO_MASK, + .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK, }, }, + .mark = skb->mark, .proto = iph->nexthdr, }; - int flags = rt6_need_strict(&iph->daddr) ? RT6_LOOKUP_F_IFACE : 0; + + if (rt6_need_strict(&iph->daddr)) + flags |= RT6_LOOKUP_F_IFACE; skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input); } @@ -724,7 +732,7 @@ static struct rt6_info *ip6_pol_route_output(struct fib6_table *table, int strict = 0; int attempts = 3; int err; - int reachable = RT6_LOOKUP_F_REACHABLE; + int reachable = ipv6_devconf.forwarding ? 0 : RT6_LOOKUP_F_REACHABLE; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -794,6 +802,9 @@ struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) if (rt6_need_strict(&fl->fl6_dst)) flags |= RT6_LOOKUP_F_IFACE; + if (!ipv6_addr_any(&fl->fl6_src)) + flags |= RT6_LOOKUP_F_HAS_SADDR; + return fib6_rule_lookup(fl, flags, ip6_pol_route_output); } @@ -929,7 +940,7 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev, fib6_force_start_gc(); out: - return (struct dst_entry *)rt; + return &rt->u.dst; } int ndisc_dst_gc(int *more) @@ -1212,7 +1223,7 @@ out: if (idev) in6_dev_put(idev); if (rt) - dst_free((struct dst_entry *) rt); + dst_free(&rt->u.dst); return err; } @@ -1345,6 +1356,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, struct in6_addr *gateway, struct net_device *dev) { + int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl = { .fl = { .oif = dev->ifindex, @@ -1357,7 +1369,9 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, }, .gateway = *gateway, }; - int flags = rt6_need_strict(dest) ? RT6_LOOKUP_F_IFACE : 0; + + if (rt6_need_strict(dest)) + flags |= RT6_LOOKUP_F_IFACE; return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect); } @@ -1527,6 +1541,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) rt->u.dst.output = ort->u.dst.output; memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); + rt->u.dst.error = ort->u.dst.error; rt->u.dst.dev = ort->u.dst.dev; if (rt->u.dst.dev) dev_hold(rt->u.dst.dev); @@ -1730,24 +1745,50 @@ 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 inline int ip6_pkt_drop(struct sk_buff *skb, int code) { int type = ipv6_addr_type(&skb->nh.ipv6h->daddr); if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED) - IP6_INC_STATS(IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INADDRERRORS); - IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOROUTE, 0, skb->dev); + IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTNOROUTES); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev); kfree_skb(skb); return 0; } +static int ip6_pkt_discard(struct sk_buff *skb) +{ + return ip6_pkt_drop(skb, ICMPV6_NOROUTE); +} + static int ip6_pkt_discard_out(struct sk_buff *skb) { skb->dev = skb->dst->dev; return ip6_pkt_discard(skb); } +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + +static int ip6_pkt_prohibit(struct sk_buff *skb) +{ + return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED); +} + +static int ip6_pkt_prohibit_out(struct sk_buff *skb) +{ + skb->dev = skb->dst->dev; + return ip6_pkt_prohibit(skb); +} + +static int ip6_pkt_blk_hole(struct sk_buff *skb) +{ + kfree_skb(skb); + return 0; +} + +#endif + /* * Allocate a dst for local (unicast / anycast) address. */ @@ -1781,7 +1822,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, 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); + dst_free(&rt->u.dst); return ERR_PTR(-ENOMEM); } @@ -1965,6 +2006,20 @@ int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return ip6_route_add(&cfg); } +static inline size_t rt6_nlmsg_size(void) +{ + 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 */ + + nla_total_size(sizeof(struct rta_cacheinfo)); +} + static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, @@ -1972,7 +2027,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, { struct rtmsg *rtm; struct nlmsghdr *nlh; - struct rta_cacheinfo ci; + long expires; u32 table; if (prefix) { /* user wants prefix routes only */ @@ -2046,18 +2101,11 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); NLA_PUT_U32(skb, RTA_PRIORITY, 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; - NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); + + expires = rt->rt6i_expires ? rt->rt6i_expires - jiffies : 0; + if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, + expires, rt->u.dst.error) < 0) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2159,7 +2207,6 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) struct sk_buff *skb; u32 pid = 0, seq = 0; struct nlmsghdr *nlh = NULL; - int payload = sizeof(struct rtmsg) + 256; int err = -ENOBUFS; if (info) { @@ -2169,15 +2216,13 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) seq = nlh->nlmsg_seq; } - skb = nlmsg_new(nlmsg_total_size(payload), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); if (skb == NULL) goto errout; err = rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0); - if (err < 0) { - kfree_skb(skb); - goto errout; - } + /* failure implies BUG in rt6_nlmsg_size() */ + BUG_ON(err < 0); err = rtnl_notify(skb, pid, RTNLGRP_IPV6_ROUTE, nlh, gfp_any()); errout: @@ -2205,7 +2250,6 @@ struct rt6_proc_arg 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++; @@ -2215,38 +2259,28 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) 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 ", + arg->len += sprintf(arg->buffer + arg->len, + NIP6_SEQFMT " %02x ", + NIP6(rt->rt6i_dst.addr), 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 ", + arg->len += sprintf(arg->buffer + arg->len, + NIP6_SEQFMT " %02x ", + NIP6(rt->rt6i_src.addr), rt->rt6i_src.plen); #else - sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000 00 "); - arg->len += 36; + arg->len += sprintf(arg->buffer + arg->len, + "00000000000000000000000000000000 00 "); #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; - } + arg->len += sprintf(arg->buffer + arg->len, + NIP6_SEQFMT, + NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key))); } else { - sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000"); - arg->len += 32; + arg->len += sprintf(arg->buffer + arg->len, + "00000000000000000000000000000000"); } arg->len += sprintf(arg->buffer + arg->len, " %08x %08x %08x %08x %8s\n", diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index dc5765b62b87..77b7b0911438 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -60,7 +60,7 @@ */ #define HASH_SIZE 16 -#define HASH(addr) ((addr^(addr>>4))&0xF) +#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) static int ipip6_fb_tunnel_init(struct net_device *dev); static int ipip6_tunnel_init(struct net_device *dev); @@ -76,7 +76,7 @@ static struct ip_tunnel **tunnels[4] = { tunnels_wc, tunnels_l, tunnels_r, tunne static DEFINE_RWLOCK(ipip6_lock); -static struct ip_tunnel * ipip6_tunnel_lookup(u32 remote, u32 local) +static struct ip_tunnel * ipip6_tunnel_lookup(__be32 remote, __be32 local) { unsigned h0 = HASH(remote); unsigned h1 = HASH(local); @@ -102,8 +102,8 @@ static struct ip_tunnel * ipip6_tunnel_lookup(u32 remote, u32 local) static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t) { - u32 remote = t->parms.iph.daddr; - u32 local = t->parms.iph.saddr; + __be32 remote = t->parms.iph.daddr; + __be32 local = t->parms.iph.saddr; unsigned h = 0; int prio = 0; @@ -144,8 +144,8 @@ static void ipip6_tunnel_link(struct ip_tunnel *t) static struct ip_tunnel * ipip6_tunnel_locate(struct ip_tunnel_parm *parms, int create) { - u32 remote = parms->iph.daddr; - u32 local = parms->iph.saddr; + __be32 remote = parms->iph.daddr; + __be32 local = parms->iph.saddr; struct ip_tunnel *t, **tp, *nt; struct net_device *dev; unsigned h = 0; @@ -405,9 +405,9 @@ out: /* Returns the embedded IPv4 address if the IPv6 address comes from 6to4 (RFC 3056) addr space */ -static inline u32 try_6to4(struct in6_addr *v6dst) +static inline __be32 try_6to4(struct in6_addr *v6dst) { - u32 dst = 0; + __be32 dst = 0; if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ @@ -432,7 +432,7 @@ static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) 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; + __be32 dst = tiph->daddr; int mtu; struct in6_addr *addr6; int addr_type; @@ -809,7 +809,7 @@ static void __exit sit_destroy_tunnels(void) } } -void __exit sit_cleanup(void) +static void __exit sit_cleanup(void) { inet_del_protocol(&sit_protocol, IPPROTO_IPV6); @@ -819,7 +819,7 @@ void __exit sit_cleanup(void) rtnl_unlock(); } -int __init sit_init(void) +static int __init sit_init(void) { int err; @@ -853,3 +853,5 @@ int __init sit_init(void) module_init(sit_init); module_exit(sit_cleanup); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("sit0"); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4c2a7c0cafef..c25e930c2c69 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -66,10 +66,13 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/crypto.h> +#include <linux/scatterlist.h> + /* Socket used for sending RSTs and ACKs */ static struct socket *tcp6_socket; -static void tcp_v6_send_reset(struct sk_buff *skb); +static void tcp_v6_send_reset(struct sock *sk, 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, int len, struct sk_buff *skb); @@ -78,6 +81,10 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static struct inet_connection_sock_af_ops ipv6_mapped; static struct inet_connection_sock_af_ops ipv6_specific; +#ifdef CONFIG_TCP_MD5SIG +static struct tcp_sock_af_ops tcp_sock_ipv6_specific; +static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; +#endif static int tcp_v6_get_port(struct sock *sk, unsigned short snum) { @@ -98,27 +105,20 @@ static void tcp_v6_hash(struct sock *sk) } } -static __inline__ u16 tcp_v6_check(struct tcphdr *th, int len, +static __inline__ __sum16 tcp_v6_check(struct tcphdr *th, int len, struct in6_addr *saddr, struct in6_addr *daddr, - unsigned long base) + __wsum base) { return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); } -static __u32 tcp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) +static __u32 tcp_v6_init_sequence(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); - } + 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); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, @@ -215,6 +215,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 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)); @@ -222,6 +225,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 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), @@ -310,7 +316,7 @@ failure: } static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); @@ -509,8 +515,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); err = ip6_xmit(sk, skb, &fl, opt, 0); - if (err == NET_XMIT_CN) - err = 0; + err = net_xmit_eval(err); } done: @@ -526,7 +531,396 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) kfree_skb(inet6_rsk(req)->pktopts); } -static struct request_sock_ops tcp6_request_sock_ops = { +#ifdef CONFIG_TCP_MD5SIG +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, + struct in6_addr *addr) +{ + struct tcp_sock *tp = tcp_sk(sk); + int i; + + BUG_ON(tp == NULL); + + if (!tp->md5sig_info || !tp->md5sig_info->entries6) + return NULL; + + for (i = 0; i < tp->md5sig_info->entries6; i++) { + if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, addr) == 0) + return (struct tcp_md5sig_key *)&tp->md5sig_info->keys6[i]; + } + return NULL; +} + +static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, + struct sock *addr_sk) +{ + return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->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, &inet6_rsk(req)->rmt_addr); +} + +static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, + char *newkey, u8 newkeylen) +{ + /* Add key to the list */ + struct tcp6_md5sig_key *key; + struct tcp_sock *tp = tcp_sk(sk); + struct tcp6_md5sig_key *keys; + + key = (struct tcp6_md5sig_key*) tcp_v6_md5_do_lookup(sk, peer); + if (key) { + /* modify existing entry - just update that one */ + kfree(key->key); + key->key = newkey; + key->keylen = newkeylen; + } else { + /* reallocate new list if current one is full. */ + if (!tp->md5sig_info) { + tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC); + if (!tp->md5sig_info) { + kfree(newkey); + return -ENOMEM; + } + } + tcp_alloc_md5sig_pool(); + if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) { + keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) * + (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC); + + if (!keys) { + tcp_free_md5sig_pool(); + kfree(newkey); + return -ENOMEM; + } + + if (tp->md5sig_info->entries6) + memmove(keys, tp->md5sig_info->keys6, + (sizeof (tp->md5sig_info->keys6[0]) * + tp->md5sig_info->entries6)); + + kfree(tp->md5sig_info->keys6); + tp->md5sig_info->keys6 = keys; + tp->md5sig_info->alloced6++; + } + + ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr, + peer); + tp->md5sig_info->keys6[tp->md5sig_info->entries6].key = newkey; + tp->md5sig_info->keys6[tp->md5sig_info->entries6].keylen = newkeylen; + + tp->md5sig_info->entries6++; + } + return 0; +} + +static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk, + u8 *newkey, __u8 newkeylen) +{ + return tcp_v6_md5_do_add(sk, &inet6_sk(addr_sk)->daddr, + newkey, newkeylen); +} + +static int tcp_v6_md5_do_del(struct sock *sk, struct in6_addr *peer) +{ + struct tcp_sock *tp = tcp_sk(sk); + int i; + + for (i = 0; i < tp->md5sig_info->entries6; i++) { + if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, peer) == 0) { + /* Free the key */ + kfree(tp->md5sig_info->keys6[i].key); + tp->md5sig_info->entries6--; + + if (tp->md5sig_info->entries6 == 0) { + kfree(tp->md5sig_info->keys6); + tp->md5sig_info->keys6 = NULL; + + tcp_free_md5sig_pool(); + + return 0; + } else { + /* shrink the database */ + if (tp->md5sig_info->entries6 != i) + memmove(&tp->md5sig_info->keys6[i], + &tp->md5sig_info->keys6[i+1], + (tp->md5sig_info->entries6 - i) + * sizeof (tp->md5sig_info->keys6[0])); + } + } + } + return -ENOENT; +} + +static void tcp_v6_clear_md5_list (struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int i; + + if (tp->md5sig_info->entries6) { + for (i = 0; i < tp->md5sig_info->entries6; i++) + kfree(tp->md5sig_info->keys6[i].key); + tp->md5sig_info->entries6 = 0; + tcp_free_md5sig_pool(); + } + + kfree(tp->md5sig_info->keys6); + tp->md5sig_info->keys6 = NULL; + tp->md5sig_info->alloced6 = 0; + + if (tp->md5sig_info->entries4) { + for (i = 0; i < tp->md5sig_info->entries4; i++) + kfree(tp->md5sig_info->keys4[i].key); + tp->md5sig_info->entries4 = 0; + tcp_free_md5sig_pool(); + } + + kfree(tp->md5sig_info->keys4); + tp->md5sig_info->keys4 = NULL; + tp->md5sig_info->alloced4 = 0; +} + +static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, + int optlen) +{ + struct tcp_md5sig cmd; + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; + u8 *newkey; + + if (optlen < sizeof(cmd)) + return -EINVAL; + + if (copy_from_user(&cmd, optval, sizeof(cmd))) + return -EFAULT; + + if (sin6->sin6_family != AF_INET6) + return -EINVAL; + + if (!cmd.tcpm_keylen) { + if (!tcp_sk(sk)->md5sig_info) + return -ENOENT; + if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_MAPPED) + return tcp_v4_md5_do_del(sk, sin6->sin6_addr.s6_addr32[3]); + return tcp_v6_md5_do_del(sk, &sin6->sin6_addr); + } + + if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) + return -EINVAL; + + if (!tcp_sk(sk)->md5sig_info) { + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_info *p; + + p = kzalloc(sizeof(struct tcp_md5sig_info), GFP_KERNEL); + if (!p) + return -ENOMEM; + + tp->md5sig_info = p; + } + + newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + if (!newkey) + return -ENOMEM; + if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_MAPPED) { + return tcp_v4_md5_do_add(sk, sin6->sin6_addr.s6_addr32[3], + newkey, cmd.tcpm_keylen); + } + return tcp_v6_md5_do_add(sk, &sin6->sin6_addr, newkey, cmd.tcpm_keylen); +} + +static int tcp_v6_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key, + struct in6_addr *saddr, + struct in6_addr *daddr, + struct tcphdr *th, int protocol, + int tcplen) +{ + struct scatterlist sg[4]; + __u16 data_len; + int block = 0; + __sum16 cksum; + struct tcp_md5sig_pool *hp; + struct tcp6_pseudohdr *bp; + struct hash_desc *desc; + int err; + unsigned int nbytes = 0; + + hp = tcp_get_md5sig_pool(); + if (!hp) { + printk(KERN_WARNING "%s(): hash pool not found...\n", __FUNCTION__); + goto clear_hash_noput; + } + bp = &hp->md5_blk.ip6; + desc = &hp->md5_desc; + + /* 1. TCP pseudo-header (RFC2460) */ + ipv6_addr_copy(&bp->saddr, saddr); + ipv6_addr_copy(&bp->daddr, daddr); + bp->len = htonl(tcplen); + bp->protocol = htonl(protocol); + + sg_set_buf(&sg[block++], bp, sizeof(*bp)); + nbytes += sizeof(*bp); + + /* 2. TCP header, excluding options */ + cksum = th->check; + th->check = 0; + sg_set_buf(&sg[block++], th, sizeof(*th)); + nbytes += sizeof(*th); + + /* 3. TCP segment data (if any) */ + data_len = tcplen - (th->doff << 2); + if (data_len > 0) { + u8 *data = (u8 *)th + (th->doff << 2); + sg_set_buf(&sg[block++], data, data_len); + nbytes += data_len; + } + + /* 4. shared key */ + sg_set_buf(&sg[block++], key->key, key->keylen); + nbytes += key->keylen; + + /* Now store the hash into the packet */ + err = crypto_hash_init(desc); + if (err) { + printk(KERN_WARNING "%s(): hash_init failed\n", __FUNCTION__); + goto clear_hash; + } + err = crypto_hash_update(desc, sg, nbytes); + if (err) { + printk(KERN_WARNING "%s(): hash_update failed\n", __FUNCTION__); + goto clear_hash; + } + err = crypto_hash_final(desc, md5_hash); + if (err) { + printk(KERN_WARNING "%s(): hash_final failed\n", __FUNCTION__); + goto clear_hash; + } + + /* Reset header, and free up the crypto */ + tcp_put_md5sig_pool(); + th->check = cksum; +out: + return 0; +clear_hash: + tcp_put_md5sig_pool(); +clear_hash_noput: + memset(md5_hash, 0, 16); + goto out; +} + +static int tcp_v6_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key, + struct sock *sk, + struct dst_entry *dst, + struct request_sock *req, + struct tcphdr *th, int protocol, + int tcplen) +{ + struct in6_addr *saddr, *daddr; + + if (sk) { + saddr = &inet6_sk(sk)->saddr; + daddr = &inet6_sk(sk)->daddr; + } else { + saddr = &inet6_rsk(req)->loc_addr; + daddr = &inet6_rsk(req)->rmt_addr; + } + return tcp_v6_do_calc_md5_hash(md5_hash, key, + saddr, daddr, + th, protocol, tcplen); +} + +static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) +{ + __u8 *hash_location = NULL; + struct tcp_md5sig_key *hash_expected; + struct ipv6hdr *ip6h = skb->nh.ipv6h; + struct tcphdr *th = skb->h.th; + int length = (th->doff << 2) - sizeof (*th); + int genhash; + u8 *ptr; + u8 newhash[16]; + + hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr); + + /* If the TCP option is too short, we can short cut */ + if (length < TCPOLEN_MD5SIG) + return hash_expected ? 1 : 0; + + /* parse options */ + ptr = (u8*)(th + 1); + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch(opcode) { + case TCPOPT_EOL: + goto done_opts; + case TCPOPT_NOP: + length--; + continue; + default: + opsize = *ptr++; + if (opsize < 2 || opsize > length) + goto done_opts; + if (opcode == TCPOPT_MD5SIG) { + hash_location = ptr; + goto done_opts; + } + } + ptr += opsize - 2; + length -= opsize; + } + +done_opts: + /* do we have a hash as expected? */ + if (!hash_expected) { + if (!hash_location) + return 0; + if (net_ratelimit()) { + printk(KERN_INFO "MD5 Hash NOT expected but found " + "(" NIP6_FMT ", %u)->" + "(" NIP6_FMT ", %u)\n", + NIP6(ip6h->saddr), ntohs(th->source), + NIP6(ip6h->daddr), ntohs(th->dest)); + } + return 1; + } + + if (!hash_location) { + if (net_ratelimit()) { + printk(KERN_INFO "MD5 Hash expected but NOT found " + "(" NIP6_FMT ", %u)->" + "(" NIP6_FMT ", %u)\n", + NIP6(ip6h->saddr), ntohs(th->source), + NIP6(ip6h->daddr), ntohs(th->dest)); + } + return 1; + } + + /* check the signature */ + genhash = tcp_v6_do_calc_md5_hash(newhash, + hash_expected, + &ip6h->saddr, &ip6h->daddr, + th, sk->sk_protocol, + skb->len); + if (genhash || memcmp(hash_location, newhash, 16) != 0) { + if (net_ratelimit()) { + printk(KERN_INFO "MD5 Hash %s for " + "(" NIP6_FMT ", %u)->" + "(" NIP6_FMT ", %u)\n", + genhash ? "failed" : "mismatch", + NIP6(ip6h->saddr), ntohs(th->source), + NIP6(ip6h->daddr), ntohs(th->dest)); + } + return 1; + } + return 0; +} +#endif + +static 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_send_synack, @@ -535,9 +929,16 @@ static struct request_sock_ops tcp6_request_sock_ops = { .send_reset = tcp_v6_send_reset }; +#ifdef CONFIG_TCP_MD5SIG +static struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { + .md5_lookup = tcp_v6_reqsk_md5_lookup, +}; +#endif + 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 void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) @@ -547,7 +948,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); - skb->csum = offsetof(struct tcphdr, check); + skb->csum_offset = offsetof(struct tcphdr, check); } else { th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, csum_partial((char *)th, th->doff<<2, @@ -569,16 +970,20 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb) th->check = 0; th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, IPPROTO_TCP, 0); - skb->csum = offsetof(struct tcphdr, check); + skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; return 0; } -static void tcp_v6_send_reset(struct sk_buff *skb) +static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = skb->h.th, *t1; struct sk_buff *buff; struct flowi fl; + int tot_len = sizeof(*th); +#ifdef CONFIG_TCP_MD5SIG + struct tcp_md5sig_key *key; +#endif if (th->rst) return; @@ -586,25 +991,35 @@ static void tcp_v6_send_reset(struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) return; +#ifdef CONFIG_TCP_MD5SIG + if (sk) + key = tcp_v6_md5_do_lookup(sk, &skb->nh.ipv6h->daddr); + else + key = NULL; + + if (key) + tot_len += TCPOLEN_MD5SIG_ALIGNED; +#endif + /* * We need to grab some memory, and put together an RST, * and then put it into the queue to be sent. */ - buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr), + buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len, GFP_ATOMIC); if (buff == NULL) return; - skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)); + skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len); - t1 = (struct tcphdr *) skb_push(buff,sizeof(struct tcphdr)); + t1 = (struct tcphdr *) skb_push(buff, tot_len); /* 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->doff = tot_len / 4; t1->rst = 1; if(th->ack) { @@ -615,6 +1030,22 @@ static void tcp_v6_send_reset(struct sk_buff *skb) + skb->len - (th->doff<<2)); } +#ifdef CONFIG_TCP_MD5SIG + if (key) { + __be32 *opt = (__be32*)(t1 + 1); + opt[0] = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + tcp_v6_do_calc_md5_hash((__u8*)&opt[1], + key, + &skb->nh.ipv6h->daddr, + &skb->nh.ipv6h->saddr, + t1, IPPROTO_TCP, + tot_len); + } +#endif + buff->csum = csum_partial((char *)t1, sizeof(*t1), 0); memset(&fl, 0, sizeof(fl)); @@ -645,15 +1076,37 @@ static void tcp_v6_send_reset(struct sk_buff *skb) kfree_skb(buff); } -static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts) +static void tcp_v6_send_ack(struct tcp_timewait_sock *tw, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts) { struct tcphdr *th = skb->h.th, *t1; struct sk_buff *buff; struct flowi fl; int tot_len = sizeof(struct tcphdr); + __be32 *topt; +#ifdef CONFIG_TCP_MD5SIG + struct tcp_md5sig_key *key; + struct tcp_md5sig_key tw_key; +#endif + +#ifdef CONFIG_TCP_MD5SIG + if (!tw && skb->sk) { + key = tcp_v6_md5_do_lookup(skb->sk, &skb->nh.ipv6h->daddr); + } else if (tw && tw->tw_md5_keylen) { + tw_key.key = tw->tw_md5_key; + tw_key.keylen = tw->tw_md5_keylen; + key = &tw_key; + } else { + key = NULL; + } +#endif if (ts) 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); @@ -673,15 +1126,29 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 t1->ack_seq = htonl(ack); t1->ack = 1; t1->window = htons(win); + + topt = (__be32 *)(t1 + 1); 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++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + *topt++ = htonl(tcp_time_stamp); + *topt = htonl(ts); } +#ifdef CONFIG_TCP_MD5SIG + if (key) { + *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); + tcp_v6_do_calc_md5_hash((__u8 *)topt, + key, + &skb->nh.ipv6h->daddr, + &skb->nh.ipv6h->saddr, + t1, IPPROTO_TCP, + tot_len); + } +#endif + buff->csum = csum_partial((char *)t1, tot_len, 0); memset(&fl, 0, sizeof(fl)); @@ -712,9 +1179,9 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 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, + tcp_v6_send_ack(tcptw, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcptw->tw_ts_recent); @@ -723,7 +1190,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) { - tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); + tcp_v6_send_ack(NULL, skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } @@ -794,6 +1261,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) 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; @@ -822,7 +1293,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq->iif = inet6_iif(skb); if (isn == 0) - isn = tcp_v6_init_sequence(sk,skb); + isn = tcp_v6_init_sequence(skb); tcp_rsk(req)->snt_isn = isn; @@ -852,6 +1323,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct tcp_sock *newtp; struct sock *newsk; struct ipv6_txoptions *opt; +#ifdef CONFIG_TCP_MD5SIG + struct tcp_md5sig_key *key; +#endif if (skb->protocol == htons(ETH_P_IP)) { /* @@ -882,6 +1356,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, 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->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); @@ -1016,6 +1494,21 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; +#ifdef CONFIG_TCP_MD5SIG + /* Copy over the MD5 key from the original socket */ + if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != 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. + */ + char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); + if (newkey != NULL) + tcp_v6_md5_do_add(newsk, &inet6_sk(sk)->daddr, + newkey, key->keylen); + } +#endif + __inet6_hash(&tcp_hashinfo, newsk); inet_inherit_port(&tcp_hashinfo, sk, newsk); @@ -1031,7 +1524,7 @@ out: return NULL; } -static int tcp_v6_checksum_init(struct sk_buff *skb) +static __sum16 tcp_v6_checksum_init(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, @@ -1041,8 +1534,8 @@ static int tcp_v6_checksum_init(struct sk_buff *skb) } } - skb->csum = ~tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, - &skb->nh.ipv6h->daddr, 0); + skb->csum = ~csum_unfold(tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, 0)); if (skb->len <= 76) { return __skb_checksum_complete(skb); @@ -1075,6 +1568,11 @@ 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); +#ifdef CONFIG_TCP_MD5SIG + if (tcp_v6_inbound_md5_hash (sk, skb)) + goto discard; +#endif + if (sk_filter(sk, skb)) goto discard; @@ -1140,7 +1638,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; reset: - tcp_v6_send_reset(skb); + tcp_v6_send_reset(sk, skb); discard: if (opt_skb) __kfree_skb(opt_skb); @@ -1265,7 +1763,7 @@ no_tcp_socket: bad_packet: TCP_INC_STATS_BH(TCP_MIB_INERRS); } else { - tcp_v6_send_reset(skb); + tcp_v6_send_reset(NULL, skb); } discard_it: @@ -1344,6 +1842,15 @@ static struct inet_connection_sock_af_ops ipv6_specific = { #endif }; +#ifdef CONFIG_TCP_MD5SIG +static struct tcp_sock_af_ops tcp_sock_ipv6_specific = { + .md5_lookup = tcp_v6_md5_lookup, + .calc_md5_hash = tcp_v6_calc_md5_hash, + .md5_add = tcp_v6_md5_add_func, + .md5_parse = tcp_v6_parse_md5_keys, +}; +#endif + /* * TCP over IPv4 via INET6 API */ @@ -1366,6 +1873,15 @@ static struct inet_connection_sock_af_ops ipv6_mapped = { #endif }; +#ifdef CONFIG_TCP_MD5SIG +static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { + .md5_lookup = tcp_v4_md5_lookup, + .calc_md5_hash = tcp_v4_calc_md5_hash, + .md5_add = tcp_v6_md5_add_func, + .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. */ @@ -1405,6 +1921,10 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); +#ifdef CONFIG_TCP_MD5SIG + tp->af_specific = &tcp_sock_ipv6_specific; +#endif + sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -1415,6 +1935,11 @@ static int tcp_v6_init_sock(struct sock *sk) static int tcp_v6_destroy_sock(struct sock *sk) { +#ifdef CONFIG_TCP_MD5SIG + /* Clean up the MD5 key list */ + if (tcp_sk(sk)->md5sig_info) + tcp_v6_clear_md5_list(sk); +#endif tcp_v4_destroy_sock(sk); return inet6_destroy_sock(sk); } diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 0ef9a35798d1..918d07dd1219 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -104,7 +104,7 @@ drop: } static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct xfrm6_tunnel *handler; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e0c3934a7e4b..f52a5c3cc0a3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -38,26 +38,18 @@ #include <linux/skbuff.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 <linux/proc_fs.h> #include <linux/seq_file.h> +#include "udp_impl.h" DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly; @@ -66,23 +58,9 @@ static inline int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_get_port(sk, snum, ipv6_rcv_saddr_equal); } -static void udp_v6_hash(struct sock *sk) -{ - BUG(); -} - -static void udp_v6_unhash(struct sock *sk) -{ - write_lock_bh(&udp_hash_lock); - if (sk_del_node_init(sk)) { - inet_sk(sk)->num = 0; - sock_prot_dec_use(sk->sk_prot); - } - write_unlock_bh(&udp_hash_lock); -} - -static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, - struct in6_addr *daddr, u16 dport, int dif) +static struct sock *__udp6_lib_lookup(struct in6_addr *saddr, __be16 sport, + struct in6_addr *daddr, __be16 dport, + int dif, struct hlist_head udptable[]) { struct sock *sk, *result = NULL; struct hlist_node *node; @@ -90,7 +68,7 @@ static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, int badness = -1; read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) { + sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { struct inet_sock *inet = inet_sk(sk); if (inet->num == hnum && sk->sk_family == PF_INET6) { @@ -132,20 +110,11 @@ static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport, } /* - * - */ - -static void udpv6_close(struct sock *sk, long timeout) -{ - sk_common_release(sk); -} - -/* * 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) { @@ -153,7 +122,7 @@ static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; size_t copied; - int err; + int err, copy_only, is_udplite = IS_UDPLITE(sk); if (addr_len) *addr_len=sizeof(struct sockaddr_in6); @@ -172,15 +141,21 @@ try_again: 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 (__skb_checksum_complete(skb)) + /* + * Decide whether to checksum and/or copy data. + */ + copy_only = (skb->ip_summed==CHECKSUM_UNNECESSARY); + + if (is_udplite || (!copy_only && msg->msg_flags&MSG_TRUNC)) { + if (__udp_lib_checksum_complete(skb)) goto csum_copy_err; - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov, - copied); - } else { + copy_only = 1; + } + + if (copy_only) + 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; @@ -231,26 +206,26 @@ csum_copy_err: skb_kill_datagram(sk, skb, flags); if (flags & MSG_DONTWAIT) { - UDP6_INC_STATS_USER(UDP_MIB_INERRORS); + UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); return -EAGAIN; } 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, + int type, int code, int offset, __be32 info, + struct hlist_head 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; 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(daddr, uh->dest, + saddr, uh->source, inet6_iif(skb), udptable); if (sk == NULL) return; @@ -271,36 +246,60 @@ out: sock_put(sk); } -static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +static __inline__ void udpv6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, int type, + int code, int offset, __be32 info ) +{ + return __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash); +} + +int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) { + struct udp_sock *up = udp_sk(sk); int rc; - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); - return -1; - } + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + goto drop; - if (skb_checksum_complete(skb)) { - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); - kfree_skb(skb); - return 0; + /* + * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). + */ + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + + 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; + } } + if (udp_lib_checksum_complete(skb)) + goto drop; + if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) - UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS); - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); - kfree_skb(skb); - return 0; + UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, up->pcflag); + goto drop; } - UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS); + UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag); return 0; +drop: + UDP6_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag); + 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, + __be16 loc_port, struct in6_addr *loc_addr, + __be16 rmt_port, struct in6_addr *rmt_addr, int dif) { struct hlist_node *node; @@ -339,16 +338,16 @@ static struct sock *udp_v6_mcast_next(struct sock *sk, * 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 sk_buff *skb, struct in6_addr *saddr, + struct in6_addr *daddr, struct hlist_head udptable[]) { struct sock *sk, *sk2; + const struct udphdr *uh = skb->h.uh; int dif; read_lock(&udp_hash_lock); - sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); - dif = skb->dev->ifindex; + sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); + dif = inet6_iif(skb); sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); if (!sk) { kfree_skb(skb); @@ -365,9 +364,35 @@ static void udpv6_mcast_deliver(struct udphdr *uh, udpv6_queue_rcv_skb(sk, skb); out: read_unlock(&udp_hash_lock); + return 0; +} + +static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh) + +{ + 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"); + return 1; + } + if (skb->ip_summed == CHECKSUM_COMPLETE && + !csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, + skb->len, IPPROTO_UDP, skb->csum )) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (skb->ip_summed != CHECKSUM_UNNECESSARY) + skb->csum = ~csum_unfold(csum_ipv6_magic(&skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, + skb->len, IPPROTO_UDP, + 0)); + + return (UDP_SKB_CB(skb)->partial_cov = 0); } -static int udpv6_rcv(struct sk_buff **pskb) +int __udp6_lib_rcv(struct sk_buff **pskb, struct hlist_head udptable[], + int is_udplite) { struct sk_buff *skb = *pskb; struct sock *sk; @@ -384,44 +409,39 @@ static int udpv6_rcv(struct sk_buff **pskb) uh = skb->h.uh; ulen = ntohs(uh->len); + if (ulen > skb->len) + goto short_packet; - /* Check for jumbo payload */ - if (ulen == 0) - ulen = skb->len; + if(! is_udplite ) { /* UDP validates ulen. */ - if (ulen > skb->len || ulen < sizeof(*uh)) - goto short_packet; + /* Check for jumbo payload */ + if (ulen == 0) + ulen = skb->len; - 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 (ulen < sizeof(*uh)) + goto short_packet; - 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; - } + if (ulen < skb->len) { + if (pskb_trim_rcsum(skb, ulen)) + goto short_packet; + saddr = &skb->nh.ipv6h->saddr; + daddr = &skb->nh.ipv6h->daddr; + uh = skb->h.uh; + } - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (udp6_csum_init(skb, uh)) + goto discard; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->csum = ~csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, 0); + } else { /* UDP-Lite validates cscov. */ + if (udplite6_csum_init(skb, uh)) + goto discard; + } /* * 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(skb, saddr, daddr, udptable); /* Unicast */ @@ -429,15 +449,16 @@ static int udpv6_rcv(struct sk_buff **pskb) * 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(saddr, uh->source, + daddr, uh->dest, inet6_iif(skb), udptable); if (sk == NULL) { if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; - if (skb_checksum_complete(skb)) + if (udp_lib_checksum_complete(skb)) goto discard; - UDP6_INC_STATS_BH(UDP_MIB_NOPORTS); + UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, is_udplite); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); @@ -452,14 +473,20 @@ static int udpv6_rcv(struct sk_buff **pskb) return(0); short_packet: - if (net_ratelimit()) - printk(KERN_DEBUG "UDP: short packet: %d/%u\n", ulen, skb->len); + LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n", + is_udplite? "-Lite" : "", ulen, skb->len); discard: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS); + UDP6_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return(0); } + +static __inline__ int udpv6_rcv(struct sk_buff **pskb) +{ + return __udp6_lib_rcv(pskb, udp_hash, 0); +} + /* * Throw away all pending data and cancel the corking. Socket is locked. */ @@ -478,13 +505,15 @@ static void udp_v6_flush_pending_frames(struct sock *sk) * 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; int err = 0; + __wsum csum = 0; /* Grab the skbuff where UDP header space exists. */ if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) @@ -499,35 +528,17 @@ static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up) uh->len = htons(up->len); uh->check = 0; - if (sk->sk_no_check == UDP_CSUM_NOXMIT) { - 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; + if (up->pcflag) + csum = udplite_csum_outgoing(sk, skb); + else + csum = udp_csum_outgoing(sk, skb); - 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; - - } + /* add protocol-dependent pseudo-header */ + uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, + up->len, fl->proto, csum ); if (uh->check == 0) - uh->check = -1; + uh->check = CSUM_MANGLED_0; -send: err = ip6_push_pending_frames(sk); out: up->len = 0; @@ -535,7 +546,7 @@ out: 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; @@ -555,6 +566,8 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int err; int connected = 0; + int is_udplite = up->pcflag; + int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); /* destination address check */ if (sin6) { @@ -695,7 +708,7 @@ do_udp_sendmsg: opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); - fl.proto = IPPROTO_UDP; + fl.proto = sk->sk_protocol; 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); @@ -762,14 +775,15 @@ back_from_confirm: do_append_data: up->len += ulen; - err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl, (struct rt6_info*)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); 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; @@ -794,7 +808,7 @@ do_append_data: out: fl6_sock_release(flowlabel); if (!err) { - UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS); + UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); return len; } /* @@ -805,7 +819,7 @@ out: * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS); + UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); } return err; @@ -817,7 +831,7 @@ do_confirm: goto out; } -static int udpv6_destroy_sock(struct sock *sk) +int udpv6_destroy_sock(struct sock *sk) { lock_sock(sk); udp_v6_flush_pending_frames(sk); @@ -831,119 +845,41 @@ static int udpv6_destroy_sock(struct sock *sk) /* * Socket option code for UDP */ -static int do_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) -{ - struct udp_sock *up = udp_sk(sk); - int val; - int err = 0; - - 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; -} - -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, int optlen) { - if (level != SOL_UDP) - return ipv6_setsockopt(sk, level, optname, optval, optlen); - return do_udpv6_setsockopt(sk, level, optname, optval, optlen); + 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); } #ifdef CONFIG_COMPAT -static int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { - if (level != SOL_UDP) - return compat_ipv6_setsockopt(sk, level, optname, - optval, optlen); - return do_udpv6_setsockopt(sk, level, optname, optval, optlen); + 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 -static int do_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - struct udp_sock *up = udp_sk(sk); - int val, len; - - 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; - - default: - return -ENOPROTOOPT; - }; - - if(put_user(len, optlen)) - return -EFAULT; - if(copy_to_user(optval, &val,len)) - return -EFAULT; - return 0; -} - -static int udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - if (level != SOL_UDP) - return ipv6_getsockopt(sk, level, optname, optval, optlen); - return do_udpv6_getsockopt(sk, level, optname, optval, 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); } #ifdef CONFIG_COMPAT -static int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { - if (level != SOL_UDP) - return compat_ipv6_getsockopt(sk, level, optname, - optval, optlen); - return do_udpv6_getsockopt(sk, level, optname, optval, 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 @@ -984,7 +920,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket atomic_read(&sp->sk_refcnt), sp); } -static int udp6_seq_show(struct seq_file *seq, void *v) +int udp6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, @@ -1003,6 +939,7 @@ static struct udp_seq_afinfo udp6_seq_afinfo = { .owner = THIS_MODULE, .name = "udp6", .family = AF_INET6, + .hashtable = udp_hash, .seq_show = udp6_seq_show, .seq_fops = &udp6_seq_fops, }; @@ -1022,7 +959,7 @@ void udp6_proc_exit(void) { struct proto udpv6_prot = { .name = "UDPv6", .owner = THIS_MODULE, - .close = udpv6_close, + .close = udp_lib_close, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, @@ -1032,8 +969,8 @@ struct proto udpv6_prot = { .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, .backlog_rcv = udpv6_queue_rcv_skb, - .hash = udp_v6_hash, - .unhash = udp_v6_unhash, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .obj_size = sizeof(struct udp6_sock), #ifdef CONFIG_COMPAT diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h new file mode 100644 index 000000000000..ec9878899128 --- /dev/null +++ b/net/ipv6/udp_impl.h @@ -0,0 +1,34 @@ +#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> + +extern int __udp6_lib_rcv(struct sk_buff **, struct hlist_head [], int ); +extern void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, + int , int , int , __be32 , struct hlist_head []); + +extern int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +extern int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen); +#ifdef CONFIG_COMPAT +extern int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen); +extern int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +#endif +extern int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len); +extern int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len, + int noblock, int flags, int *addr_len); +extern int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb); +extern int udpv6_destroy_sock(struct sock *sk); + +#ifdef CONFIG_PROC_FS +extern int udp6_seq_show(struct seq_file *seq, void *v); +#endif +#endif /* _UDP6_IMPL_H */ diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c new file mode 100644 index 000000000000..629f97162fbc --- /dev/null +++ b/net/ipv6/udplite.c @@ -0,0 +1,105 @@ +/* + * UDPLITEv6 An implementation of the UDP-Lite protocol over IPv6. + * See also net/ipv4/udplite.c + * + * Version: $Id: udplite.c,v 1.9 2006/10/19 08:28:10 gerrit Exp $ + * + * 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 "udp_impl.h" + +DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6) __read_mostly; + +static int udplitev6_rcv(struct sk_buff **pskb) +{ + return __udp6_lib_rcv(pskb, udplite_hash, 1); +} + +static void udplitev6_err(struct sk_buff *skb, + struct inet6_skb_parm *opt, + int type, int code, int offset, __be32 info) +{ + return __udp6_lib_err(skb, opt, type, code, offset, info, udplite_hash); +} + +static struct inet6_protocol udplitev6_protocol = { + .handler = udplitev6_rcv, + .err_handler = udplitev6_err, + .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, +}; + +static int udplite_v6_get_port(struct sock *sk, unsigned short snum) +{ + return udplite_get_port(sk, snum, ipv6_rcv_saddr_equal); +} + +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 = udplite_v6_get_port, + .obj_size = sizeof(struct udp6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif +}; + +static struct inet_protosw udplite6_protosw = { + .type = SOCK_DGRAM, + .protocol = IPPROTO_UDPLITE, + .prot = &udplitev6_prot, + .ops = &inet6_dgram_ops, + .capability = -1, + .no_check = 0, + .flags = INET_PROTOSW_PERMANENT, +}; + +void __init udplitev6_init(void) +{ + if (inet6_add_protocol(&udplitev6_protocol, IPPROTO_UDPLITE) < 0) + printk(KERN_ERR "%s: Could not register.\n", __FUNCTION__); + + inet6_register_protosw(&udplite6_protosw); +} + +#ifdef CONFIG_PROC_FS +static struct file_operations udplite6_seq_fops; +static struct udp_seq_afinfo udplite6_seq_afinfo = { + .owner = THIS_MODULE, + .name = "udplite6", + .family = AF_INET6, + .hashtable = udplite_hash, + .seq_show = udp6_seq_show, + .seq_fops = &udplite6_seq_fops, +}; + +int __init udplite6_proc_init(void) +{ + return udp_proc_register(&udplite6_seq_afinfo); +} + +void udplite6_proc_exit(void) +{ + udp_proc_unregister(&udplite6_seq_afinfo); +} +#endif diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 73cee2ec07e8..8dffd4daae9c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -25,12 +25,14 @@ static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl) +static int xfrm6_dst_lookup(struct xfrm_dst **xdst, struct flowi *fl) { - int err = 0; - *dst = (struct xfrm_dst*)ip6_route_output(NULL, fl); - if (!*dst) - err = -ENETUNREACH; + struct dst_entry *dst = ip6_route_output(NULL, fl); + int err = dst->error; + if (!err) + *xdst = (struct xfrm_dst *) dst; + else + dst_release(dst); return err; } @@ -272,11 +274,12 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) break; case IPPROTO_UDP: + case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: if (pskb_may_pull(skb, skb->nh.raw + offset + 4 - skb->data)) { - u16 *ports = (u16 *)exthdr; + __be16 *ports = (__be16 *)exthdr; fl->fl_ip_sport = ports[0]; fl->fl_ip_dport = ports[1]; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 7af227bb1551..01a5c52a2be3 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -62,7 +62,7 @@ static unsigned inline xfrm6_tunnel_spi_hash_byaddr(xfrm_address_t *addr) { unsigned h; - h = addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3]; + h = (__force u32)(addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3]); h ^= h >> 16; h ^= h >> 8; h &= XFRM6_TUNNEL_SPI_BYADDR_HSIZE - 1; @@ -126,7 +126,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) return NULL; } -u32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) +__be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; @@ -135,7 +135,7 @@ u32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) x6spi = __xfrm6_tunnel_spi_lookup(saddr); spi = x6spi ? x6spi->spi : 0; read_unlock_bh(&xfrm6_tunnel_spi_lock); - return spi; + return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup); @@ -196,7 +196,7 @@ out: return spi; } -u32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) +__be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; u32 spi; @@ -210,7 +210,7 @@ u32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) spi = __xfrm6_tunnel_alloc_spi(saddr); write_unlock_bh(&xfrm6_tunnel_spi_lock); - return spi; + return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi); @@ -265,7 +265,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb) } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { /* xfrm6_tunnel native err handling */ switch (type) { |