diff options
Diffstat (limited to 'net/ipv6')
41 files changed, 866 insertions, 633 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d9da5eb9dcb2..e92ad8455c63 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2031,8 +2031,8 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) #if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) if (dev->type == ARPHRD_SIT) { + const struct net_device_ops *ops = dev->netdev_ops; struct ifreq ifr; - mm_segment_t oldfs; struct ip_tunnel_parm p; err = -EADDRNOTAVAIL; @@ -2048,9 +2048,14 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg) p.iph.ttl = 64; ifr.ifr_ifru.ifru_data = (__force void __user *)&p; - oldfs = get_fs(); set_fs(KERNEL_DS); - err = dev->do_ioctl(dev, &ifr, SIOCADDTUNNEL); - set_fs(oldfs); + if (ops->ndo_do_ioctl) { + mm_segment_t oldfs = get_fs(); + + set_fs(KERNEL_DS); + err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); + set_fs(oldfs); + } else + err = -EOPNOTSUPP; if (err == 0) { err = -ENOBUFS; @@ -2988,9 +2993,8 @@ static void if6_seq_stop(struct seq_file *seq, void *v) static int if6_seq_show(struct seq_file *seq, void *v) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v; - seq_printf(seq, - NIP6_SEQFMT " %02x %02x %02x %02x %8s\n", - NIP6(ifp->addr), + seq_printf(seq, "%pi6 %02x %02x %02x %02x %8s\n", + &ifp->addr, ifp->idev->dev->ifindex, ifp->prefix_len, ifp->scope, @@ -4033,8 +4037,8 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.forwarding, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &addrconf_sysctl_forward, - .strategy = &addrconf_sysctl_forward_strategy, + .proc_handler = addrconf_sysctl_forward, + .strategy = addrconf_sysctl_forward_strategy, }, { .ctl_name = NET_IPV6_HOP_LIMIT, @@ -4050,7 +4054,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.mtu6, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ACCEPT_RA, @@ -4058,7 +4062,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_ra, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ACCEPT_REDIRECTS, @@ -4066,7 +4070,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_redirects, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_AUTOCONF, @@ -4074,7 +4078,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.autoconf, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_DAD_TRANSMITS, @@ -4082,7 +4086,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.dad_transmits, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_RTR_SOLICITS, @@ -4090,7 +4094,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.rtr_solicits, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_RTR_SOLICIT_INTERVAL, @@ -4098,8 +4102,8 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.rtr_solicit_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_RTR_SOLICIT_DELAY, @@ -4107,8 +4111,8 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.rtr_solicit_delay, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_FORCE_MLD_VERSION, @@ -4116,7 +4120,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.force_mld_version, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_PRIVACY { @@ -4125,7 +4129,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.use_tempaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_TEMP_VALID_LFT, @@ -4133,7 +4137,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.temp_valid_lft, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_TEMP_PREFERED_LFT, @@ -4141,7 +4145,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.temp_prefered_lft, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_REGEN_MAX_RETRY, @@ -4149,7 +4153,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_MAX_DESYNC_FACTOR, @@ -4157,7 +4161,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.max_desync_factor, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { @@ -4166,7 +4170,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.max_addresses, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ACCEPT_RA_DEFRTR, @@ -4174,7 +4178,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_ra_defrtr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ACCEPT_RA_PINFO, @@ -4182,7 +4186,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_ROUTER_PREF { @@ -4191,7 +4195,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_ra_rtr_pref, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_RTR_PROBE_INTERVAL, @@ -4199,8 +4203,8 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.rtr_probe_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, #ifdef CONFIG_IPV6_ROUTE_INFO { @@ -4209,7 +4213,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif #endif @@ -4219,7 +4223,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ACCEPT_SOURCE_ROUTE, @@ -4227,7 +4231,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_source_route, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD { @@ -4236,7 +4240,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.optimistic_dad, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif @@ -4247,7 +4251,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.mc_forwarding, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif { @@ -4256,7 +4260,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.disable_ipv6, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = CTL_UNNUMBERED, @@ -4264,7 +4268,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.accept_dad, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = 0, /* sentinel */ diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 08909039d87b..6ff73c4c126a 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -186,10 +186,8 @@ u32 ipv6_addr_label(struct net *net, label = p ? p->label : IPV6_ADDR_LABEL_DEFAULT; rcu_read_unlock(); - ADDRLABEL(KERN_DEBUG "%s(addr=" NIP6_FMT ", type=%d, ifindex=%d) => %08x\n", - __func__, - NIP6(*addr), type, ifindex, - label); + ADDRLABEL(KERN_DEBUG "%s(addr=%pI6, type=%d, ifindex=%d) => %08x\n", + __func__, addr, type, ifindex, label); return label; } @@ -203,11 +201,8 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, struct ip6addrlbl_entry *newp; int addrtype; - ADDRLABEL(KERN_DEBUG "%s(prefix=" NIP6_FMT ", prefixlen=%d, ifindex=%d, label=%u)\n", - __func__, - NIP6(*prefix), prefixlen, - ifindex, - (unsigned int)label); + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u)\n", + __func__, prefix, prefixlen, ifindex, (unsigned int)label); addrtype = ipv6_addr_type(prefix) & (IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK); @@ -294,12 +289,9 @@ static int ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp; int ret = 0; - ADDRLABEL(KERN_DEBUG "%s(prefix=" NIP6_FMT ", prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n", - __func__, - NIP6(*prefix), prefixlen, - ifindex, - (unsigned int)label, - replace); + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n", + __func__, prefix, prefixlen, ifindex, (unsigned int)label, + replace); newp = ip6addrlbl_alloc(net, prefix, prefixlen, ifindex, label); if (IS_ERR(newp)) @@ -321,10 +313,8 @@ static int __ip6addrlbl_del(struct net *net, struct hlist_node *pos, *n; int ret = -ESRCH; - ADDRLABEL(KERN_DEBUG "%s(prefix=" NIP6_FMT ", prefixlen=%d, ifindex=%d)\n", - __func__, - NIP6(*prefix), prefixlen, - ifindex); + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", + __func__, prefix, prefixlen, ifindex); hlist_for_each_entry_safe(p, pos, n, &ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && @@ -347,10 +337,8 @@ static int ip6addrlbl_del(struct net *net, struct in6_addr prefix_buf; int ret; - ADDRLABEL(KERN_DEBUG "%s(prefix=" NIP6_FMT ", prefixlen=%d, ifindex=%d)\n", - __func__, - NIP6(*prefix), prefixlen, - ifindex); + ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", + __func__, prefix, prefixlen, ifindex); ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); spin_lock(&ip6addrlbl_table.lock); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 01edac888510..437b750b98fd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -637,7 +637,7 @@ int inet6_sk_rebuild_header(struct sock *sk) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { sk->sk_err_soft = -err; return err; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2ff0c8233e47..52449f7a1b71 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -407,6 +407,7 @@ out: static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; @@ -415,12 +416,12 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/" NIP6_FMT "\n", - ntohl(ah->spi), NIP6(iph->daddr)); + NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n", + ntohl(ah->spi), &iph->daddr); xfrm_state_put(x); } @@ -509,9 +510,7 @@ static void ah6_destroy(struct xfrm_state *x) return; kfree(ahp->work_icv); - ahp->work_icv = NULL; crypto_free_hash(ahp->tfm); - ahp->tfm = NULL; kfree(ahp); } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 8336cd81cb4f..1ae58bec1de0 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -512,11 +512,9 @@ static int ac6_seq_show(struct seq_file *seq, void *v) struct ifacaddr6 *im = (struct ifacaddr6 *)v; struct ac6_iter_state *state = ac6_seq_private(seq); - seq_printf(seq, - "%-4d %-15s " NIP6_SEQFMT " %5d\n", + seq_printf(seq, "%-4d %-15s %pi6 %5d\n", state->dev->ifindex, state->dev->name, - NIP6(im->aca_addr), - im->aca_users); + &im->aca_addr, im->aca_users); return 0; } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index e44deb8d4df2..e2bdc6d83a43 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -175,7 +175,8 @@ ipv4_connected: if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index b181b08fb761..c2f250150db1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -356,6 +356,7 @@ static u32 esp6_get_mtu(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, __be32 info) { + struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; @@ -364,11 +365,11 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, type != ICMPV6_PKT_TOOBIG) return; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/" NIP6_FMT "\n", - ntohl(esph->spi), NIP6(iph->daddr)); + printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%pI6\n", + ntohl(esph->spi), &iph->daddr); xfrm_state_put(x); } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 6bfffec2371c..1c7f400a3cfe 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -219,7 +219,7 @@ static int ipv6_dest_hao(struct sk_buff *skb, int optoff) if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { LIMIT_NETDEBUG( - KERN_DEBUG "hao is not an unicast addr: " NIP6_FMT "\n", NIP6(hao->addr)); + KERN_DEBUG "hao is not an unicast addr: %pI6\n", &hao->addr); goto discard; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 9b7d19ae5ced..4f433847d95f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -233,7 +233,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6h->icmp6_cksum = 0; if (skb_queue_len(&sk->sk_write_queue) == 1) { - skb->csum = csum_partial((char *)icmp6h, + skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, @@ -246,7 +246,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct tmp_csum = csum_add(tmp_csum, skb->csum); } - tmp_csum = csum_partial((char *)icmp6h, + tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, @@ -427,7 +427,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, /* No need to clone since we're just using its address. */ dst2 = dst; - err = xfrm_lookup(&dst, &fl, sk, 0); + err = xfrm_lookup(net, &dst, &fl, sk, 0); switch (err) { case 0: if (dst != dst2) @@ -446,7 +446,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, if (ip6_dst_lookup(sk, &dst2, &fl)) goto relookup_failed; - err = xfrm_lookup(&dst2, &fl, sk, XFRM_LOOKUP_ICMP); + err = xfrm_lookup(net, &dst2, &fl, sk, XFRM_LOOKUP_ICMP); switch (err) { case 0: dst_release(dst); @@ -552,7 +552,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto out; - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) goto out; if (ipv6_addr_is_multicast(&fl.fl6_dst)) @@ -646,9 +646,10 @@ static int icmpv6_rcv(struct sk_buff *skb) int type; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { + struct sec_path *sp = skb_sec_path(skb); int nh; - if (!(skb->sp && skb->sp->xvec[skb->sp->len - 1]->props.flags & + if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) goto drop_no_count; @@ -680,8 +681,8 @@ static int icmpv6_rcv(struct sk_buff *skb) 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)); + LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n", + saddr, daddr); goto discard_it; } } @@ -955,8 +956,8 @@ ctl_table ipv6_icmp_table_template[] = { .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies + .proc_handler = proc_dointvec_ms_jiffies, + .strategy = sysctl_ms_jiffies }, { .ctl_name = 0 }, }; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 16d43f20b32f..3c3732d50c1a 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -219,7 +219,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) { sk->sk_route_caps = 0; kfree_skb(skb); return err; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1646a5658255..8fe267feb81e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -25,26 +25,30 @@ void __inet6_hash(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - struct hlist_head *list; - rwlock_t *lock; WARN_ON(!sk_unhashed(sk)); if (sk->sk_state == TCP_LISTEN) { - list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &hashinfo->lhash_lock; - inet_listen_wlock(hashinfo); + struct inet_listen_hashbucket *ilb; + + ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + spin_lock(&ilb->lock); + __sk_nulls_add_node_rcu(sk, &ilb->head); + spin_unlock(&ilb->lock); } else { unsigned int hash; + struct hlist_nulls_head *list; + spinlock_t *lock; + sk->sk_hash = hash = inet6_sk_ehashfn(sk); list = &inet_ehash_bucket(hashinfo, hash)->chain; lock = inet_ehash_lockp(hashinfo, hash); - write_lock(lock); + spin_lock(lock); + __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); } - __sk_add_node(sk, list); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); } EXPORT_SYMBOL(__inet6_hash); @@ -63,77 +67,122 @@ struct sock *__inet6_lookup_established(struct net *net, const int dif) { struct sock *sk; - const struct hlist_node *node; + const struct hlist_nulls_node *node; const __portpair ports = INET_COMBINED_PORTS(sport, hnum); /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); - struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hashinfo, hash); + unsigned int slot = hash & (hashinfo->ehash_size - 1); + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; - prefetch(head->chain.first); - read_lock(lock); - sk_for_each(sk, node, &head->chain) { + + rcu_read_lock(); +begin: + sk_nulls_for_each_rcu(sk, node, &head->chain) { /* For IPV6 do the cheaper port and family tests first. */ - if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) - goto hit; /* You sunk my battleship! */ + if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + goto begintw; + if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + sock_put(sk); + goto begin; + } + goto out; + } } + if (get_nulls_value(node) != slot) + goto begin; + +begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ - sk_for_each(sk, node, &head->twchain) { - if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) - goto hit; + sk_nulls_for_each_rcu(sk, node, &head->twchain) { + if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { + sk = NULL; + goto out; + } + if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) { + sock_put(sk); + goto begintw; + } + goto out; + } } - read_unlock(lock); - return NULL; - -hit: - sock_hold(sk); - read_unlock(lock); + if (get_nulls_value(node) != slot) + goto begintw; + sk = NULL; +out: + rcu_read_unlock(); return sk; } EXPORT_SYMBOL(__inet6_lookup_established); +static int inline compute_score(struct sock *sk, struct net *net, + const unsigned short hnum, + const struct in6_addr *daddr, + const int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && + sk->sk_family == PF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + + score = 1; + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, const unsigned short hnum, const int dif) { struct sock *sk; - const struct hlist_node *node; - struct sock *result = NULL; - int score, hiscore = 0; - - read_lock(&hashinfo->lhash_lock); - sk_for_each(sk, node, - &hashinfo->listening_hash[inet_lhashfn(net, hnum)]) { - if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && - sk->sk_family == PF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); - - score = 1; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - continue; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score++; - } - if (score == 3) { - result = sk; - break; - } - if (score > hiscore) { - hiscore = score; - result = sk; - } + const struct hlist_nulls_node *node; + struct sock *result; + int score, hiscore; + unsigned int hash = inet_lhashfn(net, hnum); + struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; + + rcu_read_lock(); +begin: + result = NULL; + hiscore = -1; + sk_nulls_for_each(sk, node, &ilb->head) { + score = compute_score(sk, net, hnum, daddr, dif); + if (score > hiscore) { + hiscore = score; + result = sk; + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) + goto begin; + if (result) { + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score(result, net, hnum, daddr, + dif) < hiscore)) { + sock_put(result); + goto begin; } } - if (result) - sock_hold(result); - read_unlock(&hashinfo->lhash_lock); + rcu_read_unlock(); return result; } @@ -170,16 +219,15 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hinfo, hash); + spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; - const struct hlist_node *node; + const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; - prefetch(head->chain.first); - write_lock(lock); + spin_lock(lock); /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &head->twchain) { + sk_nulls_for_each(sk2, node, &head->twchain) { tw = inet_twsk(sk2); if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) { @@ -192,7 +240,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, tw = NULL; /* And established part... */ - sk_for_each(sk2, node, &head->chain) { + sk_nulls_for_each(sk2, node, &head->chain) { if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) goto not_unique; } @@ -203,10 +251,10 @@ unique: inet->num = lport; inet->sport = htons(lport); WARN_ON(!sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); + __sk_nulls_add_node_rcu(sk, &head->chain); sk->sk_hash = hash; + spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); if (twp != NULL) { *twp = tw; @@ -221,7 +269,7 @@ unique: return 0; not_unique: - write_unlock(lock); + spin_unlock(lock); return -EADDRNOTAVAIL; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 37a4e777e347..c62dd247774f 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -388,7 +388,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, fl->owner = current->pid; break; case IPV6_FL_S_USER: - fl->owner = current->euid; + fl->owner = current_euid(); break; default: err = -EINVAL; @@ -464,7 +464,7 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { - int err; + int uninitialized_var(err); struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_flowlabel_req freq; @@ -696,14 +696,14 @@ static int ip6fl_seq_show(struct seq_file *seq, void *v) else { struct ip6_flowlabel *fl = v; seq_printf(seq, - "%05X %-1d %-6d %-6d %-6ld %-8ld " NIP6_SEQFMT " %-4d\n", + "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", (unsigned)ntohl(fl->label), fl->share, (unsigned)fl->owner, atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, - NIP6(fl->dst), + &fl->dst, fl->opt ? fl->opt->opt_nflen : 0); } return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c77db0b95e26..4b15938bef4d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -137,7 +137,8 @@ static int ip6_output2(struct sk_buff *skb) struct inet6_dev *idev = ip6_dst_idev(skb->dst); if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && - ((mroute6_socket && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || + ((mroute6_socket(dev_net(dev)) && + !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); @@ -490,7 +491,7 @@ int ip6_forward(struct sk_buff *skb) We don't send redirects to frames decapsulated from IPsec. */ if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 && - !skb->sp) { + !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct rt6_info *rt; struct neighbour *n = dst->neighbour; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 64ce3d33d9c6..58e2b0d93758 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -74,8 +74,8 @@ MODULE_LICENSE("GPL"); (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \ (HASH_SIZE - 1)) -static int ip6_fb_tnl_dev_init(struct net_device *dev); -static int ip6_tnl_dev_init(struct net_device *dev); +static void ip6_fb_tnl_dev_init(struct net_device *dev); +static void ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static int ip6_tnl_net_id; @@ -249,7 +249,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) } t = netdev_priv(dev); - dev->init = ip6_tnl_dev_init; + ip6_tnl_dev_init(dev); t->parms = *p; if ((err = register_netdevice(dev)) < 0) @@ -846,6 +846,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, int encap_limit, __u32 *pmtu) { + struct net *net = dev_net(dev); struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); @@ -861,9 +862,9 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if ((dst = ip6_tnl_dst_check(t)) != NULL) dst_hold(dst); else { - dst = ip6_route_output(dev_net(dev), NULL, fl); + dst = ip6_route_output(net, NULL, fl); - if (dst->error || xfrm_lookup(&dst, fl, NULL, 0) < 0) + if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0) goto tx_err_link_failure; } @@ -1150,7 +1151,6 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters - * @active: != 0 if tunnel is ready for use * * Description: * ip6_tnl_change() updates the tunnel parameters @@ -1306,6 +1306,14 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return 0; } + +static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_uninit = ip6_tnl_dev_uninit, + .ndo_start_xmit = ip6_tnl_xmit, + .ndo_do_ioctl = ip6_tnl_ioctl, + .ndo_change_mtu = ip6_tnl_change_mtu, +}; + /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel @@ -1316,11 +1324,8 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static void ip6_tnl_dev_setup(struct net_device *dev) { - dev->uninit = ip6_tnl_dev_uninit; + dev->netdev_ops = &ip6_tnl_netdev_ops; dev->destructor = free_netdev; - dev->hard_start_xmit = ip6_tnl_xmit; - dev->do_ioctl = ip6_tnl_ioctl; - dev->change_mtu = ip6_tnl_change_mtu; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); @@ -1349,13 +1354,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) * @dev: virtual device associated with tunnel **/ -static int -ip6_tnl_dev_init(struct net_device *dev) +static void ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); ip6_tnl_dev_init_gen(dev); ip6_tnl_link_config(t); - return 0; } /** @@ -1365,8 +1368,7 @@ ip6_tnl_dev_init(struct net_device *dev) * Return: 0 **/ -static int -ip6_fb_tnl_dev_init(struct net_device *dev) +static void ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); @@ -1376,7 +1378,6 @@ ip6_fb_tnl_dev_init(struct net_device *dev) t->parms.proto = IPPROTO_IPV6; dev_hold(dev); ip6n->tnls_wc[0] = t; - return 0; } static struct xfrm6_tunnel ip4ip6_handler = { @@ -1428,10 +1429,10 @@ static int ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; - - ip6n->fb_tnl_dev->init = ip6_fb_tnl_dev_init; dev_net_set(ip6n->fb_tnl_dev, net); + ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); + err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0524769632e7..3c51b2d827f4 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -49,9 +49,6 @@ #include <net/addrconf.h> #include <linux/netfilter_ipv6.h> -struct sock *mroute6_socket; - - /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -62,22 +59,9 @@ static DEFINE_RWLOCK(mrt_lock); * Multicast router control variables */ -static struct mif_device vif6_table[MAXMIFS]; /* Devices */ -static int maxvif; - -#define MIF_EXISTS(idx) (vif6_table[idx].dev != NULL) - -static int mroute_do_assert; /* Set in PIM assert */ -#ifdef CONFIG_IPV6_PIMSM_V2 -static int mroute_do_pim; -#else -#define mroute_do_pim 0 -#endif - -static struct mfc6_cache *mfc6_cache_array[MFC6_LINES]; /* Forwarding cache */ +#define MIF_EXISTS(_net, _idx) ((_net)->ipv6.vif6_table[_idx].dev != NULL) static struct mfc6_cache *mfc_unres_queue; /* Queue of unresolved entries */ -static atomic_t cache_resolve_queue_len; /* Size of unresolved */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -93,8 +77,10 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache); -static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert); +static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, + mifi_t mifi, int assert); static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); +static void mroute_clean_tables(struct net *net); #ifdef CONFIG_IPV6_PIMSM_V2 static struct inet6_protocol pim6_protocol; @@ -106,19 +92,22 @@ static struct timer_list ipmr_expire_timer; #ifdef CONFIG_PROC_FS struct ipmr_mfc_iter { + struct seq_net_private p; struct mfc6_cache **cache; int ct; }; -static struct mfc6_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos) +static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, + struct ipmr_mfc_iter *it, loff_t pos) { struct mfc6_cache *mfc; - it->cache = mfc6_cache_array; + it->cache = net->ipv6.mfc6_cache_array; read_lock(&mrt_lock); - for (it->ct = 0; it->ct < ARRAY_SIZE(mfc6_cache_array); it->ct++) - for (mfc = mfc6_cache_array[it->ct]; mfc; mfc = mfc->next) + for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) + for (mfc = net->ipv6.mfc6_cache_array[it->ct]; + mfc; mfc = mfc->next) if (pos-- == 0) return mfc; read_unlock(&mrt_lock); @@ -126,7 +115,8 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos) it->cache = &mfc_unres_queue; spin_lock_bh(&mfc_unres_lock); for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) - if (pos-- == 0) + if (net_eq(mfc6_net(mfc), net) && + pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -142,17 +132,19 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos) */ struct ipmr_vif_iter { + struct seq_net_private p; int ct; }; -static struct mif_device *ip6mr_vif_seq_idx(struct ipmr_vif_iter *iter, +static struct mif_device *ip6mr_vif_seq_idx(struct net *net, + struct ipmr_vif_iter *iter, loff_t pos) { - for (iter->ct = 0; iter->ct < maxvif; ++iter->ct) { - if (!MIF_EXISTS(iter->ct)) + for (iter->ct = 0; iter->ct < net->ipv6.maxvif; ++iter->ct) { + if (!MIF_EXISTS(net, iter->ct)) continue; if (pos-- == 0) - return &vif6_table[iter->ct]; + return &net->ipv6.vif6_table[iter->ct]; } return NULL; } @@ -160,23 +152,26 @@ static struct mif_device *ip6mr_vif_seq_idx(struct ipmr_vif_iter *iter, static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { + struct net *net = seq_file_net(seq); + read_lock(&mrt_lock); - return (*pos ? ip6mr_vif_seq_idx(seq->private, *pos - 1) - : SEQ_START_TOKEN); + return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) + : SEQ_START_TOKEN; } static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; + struct net *net = seq_file_net(seq); ++*pos; if (v == SEQ_START_TOKEN) - return ip6mr_vif_seq_idx(iter, 0); + return ip6mr_vif_seq_idx(net, iter, 0); - while (++iter->ct < maxvif) { - if (!MIF_EXISTS(iter->ct)) + while (++iter->ct < net->ipv6.maxvif) { + if (!MIF_EXISTS(net, iter->ct)) continue; - return &vif6_table[iter->ct]; + return &net->ipv6.vif6_table[iter->ct]; } return NULL; } @@ -189,6 +184,8 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { + struct net *net = seq_file_net(seq); + if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); @@ -198,7 +195,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", - vif - vif6_table, + vif - net->ipv6.vif6_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); @@ -215,8 +212,8 @@ static struct seq_operations ip6mr_vif_seq_ops = { static int ip6mr_vif_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &ip6mr_vif_seq_ops, - sizeof(struct ipmr_vif_iter)); + return seq_open_net(inode, file, &ip6mr_vif_seq_ops, + sizeof(struct ipmr_vif_iter)); } static struct file_operations ip6mr_vif_fops = { @@ -224,24 +221,27 @@ static struct file_operations ip6mr_vif_fops = { .open = ip6mr_vif_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { - return (*pos ? ipmr_mfc_seq_idx(seq->private, *pos - 1) - : SEQ_START_TOKEN); + struct net *net = seq_file_net(seq); + + return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) + : SEQ_START_TOKEN; } static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct mfc6_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; + struct net *net = seq_file_net(seq); ++*pos; if (v == SEQ_START_TOKEN) - return ipmr_mfc_seq_idx(seq->private, 0); + return ipmr_mfc_seq_idx(net, seq->private, 0); if (mfc->next) return mfc->next; @@ -249,10 +249,10 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (it->cache == &mfc_unres_queue) goto end_of_list; - BUG_ON(it->cache != mfc6_cache_array); + BUG_ON(it->cache != net->ipv6.mfc6_cache_array); - while (++it->ct < ARRAY_SIZE(mfc6_cache_array)) { - mfc = mfc6_cache_array[it->ct]; + while (++it->ct < MFC6_LINES) { + mfc = net->ipv6.mfc6_cache_array[it->ct]; if (mfc) return mfc; } @@ -277,16 +277,18 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; + struct net *net = seq_file_net(seq); if (it->cache == &mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == mfc6_cache_array) + else if (it->cache == net->ipv6.mfc6_cache_array) read_unlock(&mrt_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; + struct net *net = seq_file_net(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -297,23 +299,28 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) const struct mfc6_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; - seq_printf(seq, - NIP6_FMT " " NIP6_FMT " %-3d %8ld %8ld %8ld", - NIP6(mfc->mf6c_mcastgrp), NIP6(mfc->mf6c_origin), - mfc->mf6c_parent, - mfc->mfc_un.res.pkt, - mfc->mfc_un.res.bytes, - mfc->mfc_un.res.wrong_if); + seq_printf(seq, "%pI6 %pI6 %-3hd", + &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, + mfc->mf6c_parent); if (it->cache != &mfc_unres_queue) { + seq_printf(seq, " %8lu %8lu %8lu", + mfc->mfc_un.res.pkt, + mfc->mfc_un.res.bytes, + mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++) { - if (MIF_EXISTS(n) && + if (MIF_EXISTS(net, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->mfc_un.res.ttls[n]); } + } else { + /* unresolved mfc_caches don't contain + * pkt, bytes and wrong_if values + */ + seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } @@ -329,8 +336,8 @@ static struct seq_operations ipmr_mfc_seq_ops = { static int ipmr_mfc_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &ipmr_mfc_seq_ops, - sizeof(struct ipmr_mfc_iter)); + return seq_open_net(inode, file, &ipmr_mfc_seq_ops, + sizeof(struct ipmr_mfc_iter)); } static struct file_operations ip6mr_mfc_fops = { @@ -338,18 +345,19 @@ static struct file_operations ip6mr_mfc_fops = { .open = ipmr_mfc_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; #endif #ifdef CONFIG_IPV6_PIMSM_V2 -static int reg_vif_num = -1; static int pim6_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct ipv6hdr *encap; struct net_device *reg_dev = NULL; + struct net *net = dev_net(skb->dev); + int reg_vif_num = net->ipv6.mroute_reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; @@ -372,7 +380,7 @@ static int pim6_rcv(struct sk_buff *skb) read_lock(&mrt_lock); if (reg_vif_num >= 0) - reg_dev = vif6_table[reg_vif_num].dev; + reg_dev = net->ipv6.vif6_table[reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -408,25 +416,32 @@ static struct inet6_protocol pim6_protocol = { static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { + struct net *net = dev_net(dev); + read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ip6mr_cache_report(skb, reg_vif_num, MRT6MSG_WHOLEPKT); + ip6mr_cache_report(net, skb, net->ipv6.mroute_reg_vif_num, + MRT6MSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); return 0; } +static const struct net_device_ops reg_vif_netdev_ops = { + .ndo_start_xmit = reg_vif_xmit, +}; + static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8; dev->flags = IFF_NOARP; - dev->hard_start_xmit = reg_vif_xmit; + dev->netdev_ops = ®_vif_netdev_ops; dev->destructor = free_netdev; } -static struct net_device *ip6mr_reg_vif(void) +static struct net_device *ip6mr_reg_vif(struct net *net) { struct net_device *dev; @@ -434,6 +449,8 @@ static struct net_device *ip6mr_reg_vif(void) if (dev == NULL) return NULL; + dev_net_set(dev, net); + if (register_netdevice(dev)) { free_netdev(dev); return NULL; @@ -460,14 +477,14 @@ failure: * Delete a VIF entry */ -static int mif6_delete(int vifi) +static int mif6_delete(struct net *net, int vifi) { struct mif_device *v; struct net_device *dev; - if (vifi < 0 || vifi >= maxvif) + if (vifi < 0 || vifi >= net->ipv6.maxvif) return -EADDRNOTAVAIL; - v = &vif6_table[vifi]; + v = &net->ipv6.vif6_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -479,17 +496,17 @@ static int mif6_delete(int vifi) } #ifdef CONFIG_IPV6_PIMSM_V2 - if (vifi == reg_vif_num) - reg_vif_num = -1; + if (vifi == net->ipv6.mroute_reg_vif_num) + net->ipv6.mroute_reg_vif_num = -1; #endif - if (vifi + 1 == maxvif) { + if (vifi + 1 == net->ipv6.maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { - if (MIF_EXISTS(tmp)) + if (MIF_EXISTS(net, tmp)) break; } - maxvif = tmp + 1; + net->ipv6.maxvif = tmp + 1; } write_unlock_bh(&mrt_lock); @@ -503,6 +520,12 @@ static int mif6_delete(int vifi) return 0; } +static inline void ip6mr_cache_free(struct mfc6_cache *c) +{ + release_net(mfc6_net(c)); + kmem_cache_free(mrt_cachep, c); +} + /* Destroy an unresolved cache entry, killing queued skbs and reporting error to netlink readers. */ @@ -510,8 +533,9 @@ static int mif6_delete(int vifi) static void ip6mr_destroy_unres(struct mfc6_cache *c) { struct sk_buff *skb; + struct net *net = mfc6_net(c); - atomic_dec(&cache_resolve_queue_len); + atomic_dec(&net->ipv6.cache_resolve_queue_len); while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { @@ -520,12 +544,12 @@ static void ip6mr_destroy_unres(struct mfc6_cache *c) nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT; - rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else kfree_skb(skb); } - kmem_cache_free(mrt_cachep, c); + ip6mr_cache_free(c); } @@ -553,7 +577,7 @@ static void ipmr_do_expire_process(unsigned long dummy) ip6mr_destroy_unres(c); } - if (atomic_read(&cache_resolve_queue_len)) + if (mfc_unres_queue != NULL) mod_timer(&ipmr_expire_timer, jiffies + expires); } @@ -564,7 +588,7 @@ static void ipmr_expire_process(unsigned long dummy) return; } - if (atomic_read(&cache_resolve_queue_len)) + if (mfc_unres_queue != NULL) ipmr_do_expire_process(dummy); spin_unlock(&mfc_unres_lock); @@ -575,13 +599,15 @@ static void ipmr_expire_process(unsigned long dummy) static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttls) { int vifi; + struct net *net = mfc6_net(cache); cache->mfc_un.res.minvif = MAXMIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); - for (vifi = 0; vifi < maxvif; vifi++) { - if (MIF_EXISTS(vifi) && ttls[vifi] && ttls[vifi] < 255) { + for (vifi = 0; vifi < net->ipv6.maxvif; vifi++) { + if (MIF_EXISTS(net, vifi) && + ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; @@ -591,15 +617,15 @@ static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttl } } -static int mif6_add(struct mif6ctl *vifc, int mrtsock) +static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; - struct mif_device *v = &vif6_table[vifi]; + struct mif_device *v = &net->ipv6.vif6_table[vifi]; struct net_device *dev; int err; /* Is vif busy ? */ - if (MIF_EXISTS(vifi)) + if (MIF_EXISTS(net, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { @@ -609,9 +635,9 @@ static int mif6_add(struct mif6ctl *vifc, int mrtsock) * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ - if (reg_vif_num >= 0) + if (net->ipv6.mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ip6mr_reg_vif(); + dev = ip6mr_reg_vif(net); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -623,7 +649,7 @@ static int mif6_add(struct mif6ctl *vifc, int mrtsock) break; #endif case 0: - dev = dev_get_by_index(&init_net, vifc->mif6c_pifi); + dev = dev_get_by_index(net, vifc->mif6c_pifi); if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); @@ -657,20 +683,22 @@ static int mif6_add(struct mif6ctl *vifc, int mrtsock) v->dev = dev; #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) - reg_vif_num = vifi; + net->ipv6.mroute_reg_vif_num = vifi; #endif - if (vifi + 1 > maxvif) - maxvif = vifi + 1; + if (vifi + 1 > net->ipv6.maxvif) + net->ipv6.maxvif = vifi + 1; write_unlock_bh(&mrt_lock); return 0; } -static struct mfc6_cache *ip6mr_cache_find(struct in6_addr *origin, struct in6_addr *mcastgrp) +static struct mfc6_cache *ip6mr_cache_find(struct net *net, + struct in6_addr *origin, + struct in6_addr *mcastgrp) { int line = MFC6_HASH(mcastgrp, origin); struct mfc6_cache *c; - for (c = mfc6_cache_array[line]; c; c = c->next) { + for (c = net->ipv6.mfc6_cache_array[line]; c; c = c->next) { if (ipv6_addr_equal(&c->mf6c_origin, origin) && ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) break; @@ -681,24 +709,24 @@ static struct mfc6_cache *ip6mr_cache_find(struct in6_addr *origin, struct in6_a /* * Allocate a multicast cache entry */ -static struct mfc6_cache *ip6mr_cache_alloc(void) +static struct mfc6_cache *ip6mr_cache_alloc(struct net *net) { - struct mfc6_cache *c = kmem_cache_alloc(mrt_cachep, GFP_KERNEL); + struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c == NULL) return NULL; - memset(c, 0, sizeof(*c)); c->mfc_un.res.minvif = MAXMIFS; + mfc6_net_set(c, net); return c; } -static struct mfc6_cache *ip6mr_cache_alloc_unres(void) +static struct mfc6_cache *ip6mr_cache_alloc_unres(struct net *net) { - struct mfc6_cache *c = kmem_cache_alloc(mrt_cachep, GFP_ATOMIC); + struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c == NULL) return NULL; - memset(c, 0, sizeof(*c)); skb_queue_head_init(&c->mfc_un.unres.unresolved); c->mfc_un.unres.expires = jiffies + 10 * HZ; + mfc6_net_set(c, net); return c; } @@ -727,7 +755,7 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; } - err = rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid); + err = rtnl_unicast(skb, mfc6_net(uc), NETLINK_CB(skb).pid); } else ip6_mr_forward(skb, c); } @@ -740,7 +768,8 @@ static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) * Called under mrt_lock. */ -static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert) +static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, + int assert) { struct sk_buff *skb; struct mrt6msg *msg; @@ -776,7 +805,7 @@ static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert) msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = MRT6MSG_WHOLEPKT; - msg->im6_mif = reg_vif_num; + msg->im6_mif = net->ipv6.mroute_reg_vif_num; msg->im6_pad = 0; ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); @@ -813,7 +842,7 @@ static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert) skb_pull(skb, sizeof(struct ipv6hdr)); } - if (mroute6_socket == NULL) { + if (net->ipv6.mroute6_sk == NULL) { kfree_skb(skb); return -EINVAL; } @@ -821,7 +850,8 @@ static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert) /* * Deliver to user space multicast routing algorithms */ - if ((ret = sock_queue_rcv_skb(mroute6_socket, skb)) < 0) { + ret = sock_queue_rcv_skb(net->ipv6.mroute6_sk, skb); + if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n"); kfree_skb(skb); @@ -835,14 +865,15 @@ static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert) */ static int -ip6mr_cache_unresolved(mifi_t mifi, struct sk_buff *skb) +ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) { int err; struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); for (c = mfc_unres_queue; c; c = c->next) { - if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && + if (net_eq(mfc6_net(c), net) && + ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) break; } @@ -852,8 +883,8 @@ ip6mr_cache_unresolved(mifi_t mifi, struct sk_buff *skb) * Create a new entry if allowable */ - if (atomic_read(&cache_resolve_queue_len) >= 10 || - (c = ip6mr_cache_alloc_unres()) == NULL) { + if (atomic_read(&net->ipv6.cache_resolve_queue_len) >= 10 || + (c = ip6mr_cache_alloc_unres(net)) == NULL) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); @@ -870,18 +901,19 @@ ip6mr_cache_unresolved(mifi_t mifi, struct sk_buff *skb) /* * Reflect first query at pim6sd */ - if ((err = ip6mr_cache_report(skb, mifi, MRT6MSG_NOCACHE)) < 0) { + err = ip6mr_cache_report(net, skb, mifi, MRT6MSG_NOCACHE); + if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); - kmem_cache_free(mrt_cachep, c); + ip6mr_cache_free(c); kfree_skb(skb); return err; } - atomic_inc(&cache_resolve_queue_len); + atomic_inc(&net->ipv6.cache_resolve_queue_len); c->next = mfc_unres_queue; mfc_unres_queue = c; @@ -907,21 +939,22 @@ ip6mr_cache_unresolved(mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct net *net, struct mf6cctl *mfc) { int line; struct mfc6_cache *c, **cp; line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &mfc6_cache_array[line]; (c = *cp) != NULL; cp = &c->next) { + for (cp = &net->ipv6.mfc6_cache_array[line]; + (c = *cp) != NULL; cp = &c->next) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { write_lock_bh(&mrt_lock); *cp = c->next; write_unlock_bh(&mrt_lock); - kmem_cache_free(mrt_cachep, c); + ip6mr_cache_free(c); return 0; } } @@ -932,19 +965,17 @@ static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; + struct net *net = dev_net(dev); struct mif_device *v; int ct; - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &vif6_table[0]; - for (ct = 0; ct < maxvif; ct++, v++) { + v = &net->ipv6.vif6_table[0]; + for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(ct); + mif6_delete(net, ct); } return NOTIFY_DONE; } @@ -957,6 +988,66 @@ static struct notifier_block ip6_mr_notifier = { * Setup for IP multicast routing */ +static int __net_init ip6mr_net_init(struct net *net) +{ + int err = 0; + net->ipv6.vif6_table = kcalloc(MAXMIFS, sizeof(struct mif_device), + GFP_KERNEL); + if (!net->ipv6.vif6_table) { + err = -ENOMEM; + goto fail; + } + + /* Forwarding cache */ + net->ipv6.mfc6_cache_array = kcalloc(MFC6_LINES, + sizeof(struct mfc6_cache *), + GFP_KERNEL); + if (!net->ipv6.mfc6_cache_array) { + err = -ENOMEM; + goto fail_mfc6_cache; + } + +#ifdef CONFIG_IPV6_PIMSM_V2 + net->ipv6.mroute_reg_vif_num = -1; +#endif + +#ifdef CONFIG_PROC_FS + err = -ENOMEM; + if (!proc_net_fops_create(net, "ip6_mr_vif", 0, &ip6mr_vif_fops)) + goto proc_vif_fail; + if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops)) + goto proc_cache_fail; +#endif + return 0; + +#ifdef CONFIG_PROC_FS +proc_cache_fail: + proc_net_remove(net, "ip6_mr_vif"); +proc_vif_fail: + kfree(net->ipv6.mfc6_cache_array); +#endif +fail_mfc6_cache: + kfree(net->ipv6.vif6_table); +fail: + return err; +} + +static void __net_exit ip6mr_net_exit(struct net *net) +{ +#ifdef CONFIG_PROC_FS + proc_net_remove(net, "ip6_mr_cache"); + proc_net_remove(net, "ip6_mr_vif"); +#endif + mroute_clean_tables(net); + kfree(net->ipv6.mfc6_cache_array); + kfree(net->ipv6.vif6_table); +} + +static struct pernet_operations ip6mr_net_ops = { + .init = ip6mr_net_init, + .exit = ip6mr_net_exit, +}; + int __init ip6_mr_init(void) { int err; @@ -968,43 +1059,32 @@ int __init ip6_mr_init(void) if (!mrt_cachep) return -ENOMEM; + err = register_pernet_subsys(&ip6mr_net_ops); + if (err) + goto reg_pernet_fail; + setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; -#ifdef CONFIG_PROC_FS - err = -ENOMEM; - if (!proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops)) - goto proc_vif_fail; - if (!proc_net_fops_create(&init_net, "ip6_mr_cache", - 0, &ip6mr_mfc_fops)) - goto proc_cache_fail; -#endif return 0; -#ifdef CONFIG_PROC_FS -proc_cache_fail: - proc_net_remove(&init_net, "ip6_mr_vif"); -proc_vif_fail: - unregister_netdevice_notifier(&ip6_mr_notifier); -#endif reg_notif_fail: del_timer(&ipmr_expire_timer); + unregister_pernet_subsys(&ip6mr_net_ops); +reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } void ip6_mr_cleanup(void) { -#ifdef CONFIG_PROC_FS - proc_net_remove(&init_net, "ip6_mr_cache"); - proc_net_remove(&init_net, "ip6_mr_vif"); -#endif unregister_netdevice_notifier(&ip6_mr_notifier); del_timer(&ipmr_expire_timer); + unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } -static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) +static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) { int line; struct mfc6_cache *uc, *c, **cp; @@ -1020,7 +1100,8 @@ static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &mfc6_cache_array[line]; (c = *cp) != NULL; cp = &c->next) { + for (cp = &net->ipv6.mfc6_cache_array[line]; + (c = *cp) != NULL; cp = &c->next) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) break; @@ -1039,7 +1120,7 @@ static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; - c = ip6mr_cache_alloc(); + c = ip6mr_cache_alloc(net); if (c == NULL) return -ENOMEM; @@ -1051,8 +1132,8 @@ static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - c->next = mfc6_cache_array[line]; - mfc6_cache_array[line] = c; + c->next = net->ipv6.mfc6_cache_array[line]; + net->ipv6.mfc6_cache_array[line] = c; write_unlock_bh(&mrt_lock); /* @@ -1062,19 +1143,21 @@ static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) spin_lock_bh(&mfc_unres_lock); for (cp = &mfc_unres_queue; (uc = *cp) != NULL; cp = &uc->next) { - if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && + if (net_eq(mfc6_net(uc), net) && + ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { *cp = uc->next; - if (atomic_dec_and_test(&cache_resolve_queue_len)) - del_timer(&ipmr_expire_timer); + atomic_dec(&net->ipv6.cache_resolve_queue_len); break; } } + if (mfc_unres_queue == NULL) + del_timer(&ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (uc) { ip6mr_cache_resolve(uc, c); - kmem_cache_free(mrt_cachep, uc); + ip6mr_cache_free(uc); } return 0; } @@ -1083,25 +1166,25 @@ static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct sock *sk) +static void mroute_clean_tables(struct net *net) { int i; /* * Shut down all active vif entries */ - for (i = 0; i < maxvif; i++) { - if (!(vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(i); + for (i = 0; i < net->ipv6.maxvif; i++) { + if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC)) + mif6_delete(net, i); } /* * Wipe the cache */ - for (i = 0; i < ARRAY_SIZE(mfc6_cache_array); i++) { + for (i = 0; i < MFC6_LINES; i++) { struct mfc6_cache *c, **cp; - cp = &mfc6_cache_array[i]; + cp = &net->ipv6.mfc6_cache_array[i]; while ((c = *cp) != NULL) { if (c->mfc_flags & MFC_STATIC) { cp = &c->next; @@ -1111,22 +1194,22 @@ static void mroute_clean_tables(struct sock *sk) *cp = c->next; write_unlock_bh(&mrt_lock); - kmem_cache_free(mrt_cachep, c); + ip6mr_cache_free(c); } } - if (atomic_read(&cache_resolve_queue_len) != 0) { - struct mfc6_cache *c; + if (atomic_read(&net->ipv6.cache_resolve_queue_len) != 0) { + struct mfc6_cache *c, **cp; spin_lock_bh(&mfc_unres_lock); - while (mfc_unres_queue != NULL) { - c = mfc_unres_queue; - mfc_unres_queue = c->next; - spin_unlock_bh(&mfc_unres_lock); - + cp = &mfc_unres_queue; + while ((c = *cp) != NULL) { + if (!net_eq(mfc6_net(c), net)) { + cp = &c->next; + continue; + } + *cp = c->next; ip6mr_destroy_unres(c); - - spin_lock_bh(&mfc_unres_lock); } spin_unlock_bh(&mfc_unres_lock); } @@ -1135,11 +1218,12 @@ static void mroute_clean_tables(struct sock *sk) static int ip6mr_sk_init(struct sock *sk) { int err = 0; + struct net *net = sock_net(sk); rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(mroute6_socket == NULL)) - mroute6_socket = sk; + if (likely(net->ipv6.mroute6_sk == NULL)) + net->ipv6.mroute6_sk = sk; else err = -EADDRINUSE; write_unlock_bh(&mrt_lock); @@ -1152,14 +1236,15 @@ static int ip6mr_sk_init(struct sock *sk) int ip6mr_sk_done(struct sock *sk) { int err = 0; + struct net *net = sock_net(sk); rtnl_lock(); - if (sk == mroute6_socket) { + if (sk == net->ipv6.mroute6_sk) { write_lock_bh(&mrt_lock); - mroute6_socket = NULL; + net->ipv6.mroute6_sk = NULL; write_unlock_bh(&mrt_lock); - mroute_clean_tables(sk); + mroute_clean_tables(net); } else err = -EACCES; rtnl_unlock(); @@ -1180,9 +1265,10 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; + struct net *net = sock_net(sk); if (optname != MRT6_INIT) { - if (sk != mroute6_socket && !capable(CAP_NET_ADMIN)) + if (sk != net->ipv6.mroute6_sk && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1207,7 +1293,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); - ret = mif6_add(&vif, sk == mroute6_socket); + ret = mif6_add(net, &vif, sk == net->ipv6.mroute6_sk); rtnl_unlock(); return ret; @@ -1217,7 +1303,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(mifi); + ret = mif6_delete(net, mifi); rtnl_unlock(); return ret; @@ -1233,9 +1319,10 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int return -EFAULT; rtnl_lock(); if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(&mfc); + ret = ip6mr_mfc_delete(net, &mfc); else - ret = ip6mr_mfc_add(&mfc, sk == mroute6_socket); + ret = ip6mr_mfc_add(net, &mfc, + sk == net->ipv6.mroute6_sk); rtnl_unlock(); return ret; @@ -1247,7 +1334,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int int v; if (get_user(v, (int __user *)optval)) return -EFAULT; - mroute_do_assert = !!v; + net->ipv6.mroute_do_assert = !!v; return 0; } @@ -1260,10 +1347,10 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int v = !!v; rtnl_lock(); ret = 0; - if (v != mroute_do_pim) { - mroute_do_pim = v; - mroute_do_assert = v; - if (mroute_do_pim) + if (v != net->ipv6.mroute_do_pim) { + net->ipv6.mroute_do_pim = v; + net->ipv6.mroute_do_assert = v; + if (net->ipv6.mroute_do_pim) ret = inet6_add_protocol(&pim6_protocol, IPPROTO_PIM); else @@ -1295,6 +1382,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, { int olr; int val; + struct net *net = sock_net(sk); switch (optname) { case MRT6_VERSION: @@ -1302,11 +1390,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: - val = mroute_do_pim; + val = net->ipv6.mroute_do_pim; break; #endif case MRT6_ASSERT: - val = mroute_do_assert; + val = net->ipv6.mroute_do_assert; break; default: return -ENOPROTOOPT; @@ -1336,16 +1424,17 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) struct sioc_mif_req6 vr; struct mif_device *vif; struct mfc6_cache *c; + struct net *net = sock_net(sk); switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.mifi >= maxvif) + if (vr.mifi >= net->ipv6.maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &vif6_table[vr.mifi]; - if (MIF_EXISTS(vr.mifi)) { + vif = &net->ipv6.vif6_table[vr.mifi]; + if (MIF_EXISTS(net, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1363,7 +1452,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; read_lock(&mrt_lock); - c = ip6mr_cache_find(&sr.src.sin6_addr, &sr.grp.sin6_addr); + c = ip6mr_cache_find(net, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; @@ -1396,7 +1485,8 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb) static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) { struct ipv6hdr *ipv6h; - struct mif_device *vif = &vif6_table[vifi]; + struct net *net = mfc6_net(c); + struct mif_device *vif = &net->ipv6.vif6_table[vifi]; struct net_device *dev; struct dst_entry *dst; struct flowi fl; @@ -1410,9 +1500,8 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - ip6mr_cache_report(skb, vifi, MRT6MSG_WHOLEPKT); - kfree_skb(skb); - return 0; + ip6mr_cache_report(net, skb, vifi, MRT6MSG_WHOLEPKT); + goto out_free; } #endif @@ -1425,7 +1514,7 @@ static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) } }; - dst = ip6_route_output(&init_net, NULL, &fl); + dst = ip6_route_output(net, NULL, &fl); if (!dst) goto out_free; @@ -1468,9 +1557,10 @@ out_free: static int ip6mr_find_vif(struct net_device *dev) { + struct net *net = dev_net(dev); int ct; - for (ct = maxvif - 1; ct >= 0; ct--) { - if (vif6_table[ct].dev == dev) + for (ct = net->ipv6.maxvif - 1; ct >= 0; ct--) { + if (net->ipv6.vif6_table[ct].dev == dev) break; } return ct; @@ -1480,6 +1570,7 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; + struct net *net = mfc6_net(cache); vif = cache->mf6c_parent; cache->mfc_un.res.pkt++; @@ -1488,29 +1579,30 @@ static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (vif6_table[vif].dev != skb->dev) { + if (net->ipv6.vif6_table[vif].dev != skb->dev) { int true_vifi; cache->mfc_un.res.wrong_if++; true_vifi = ip6mr_find_vif(skb->dev); - if (true_vifi >= 0 && mroute_do_assert && + if (true_vifi >= 0 && net->ipv6.mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ - (mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && + (net->ipv6.mroute_do_pim || + cache->mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { cache->mfc_un.res.last_assert = jiffies; - ip6mr_cache_report(skb, true_vifi, MRT6MSG_WRONGMIF); + ip6mr_cache_report(net, skb, true_vifi, MRT6MSG_WRONGMIF); } goto dont_forward; } - vif6_table[vif].pkt_in++; - vif6_table[vif].bytes_in += skb->len; + net->ipv6.vif6_table[vif].pkt_in++; + net->ipv6.vif6_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1543,9 +1635,11 @@ dont_forward: int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; + struct net *net = dev_net(skb->dev); read_lock(&mrt_lock); - cache = ip6mr_cache_find(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + cache = ip6mr_cache_find(net, + &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); /* * No usable cache entry @@ -1555,7 +1649,7 @@ int ip6_mr_input(struct sk_buff *skb) vif = ip6mr_find_vif(skb->dev); if (vif >= 0) { - int err = ip6mr_cache_unresolved(vif, skb); + int err = ip6mr_cache_unresolved(net, vif, skb); read_unlock(&mrt_lock); return err; @@ -1578,7 +1672,8 @@ ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) { int ct; struct rtnexthop *nhp; - struct net_device *dev = vif6_table[c->mf6c_parent].dev; + struct net *net = mfc6_net(c); + struct net_device *dev = net->ipv6.vif6_table[c->mf6c_parent].dev; u8 *b = skb_tail_pointer(skb); struct rtattr *mp_head; @@ -1594,7 +1689,7 @@ ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = vif6_table[ct].dev->ifindex; + nhp->rtnh_ifindex = net->ipv6.vif6_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } @@ -1608,14 +1703,15 @@ rtattr_failure: return -EMSGSIZE; } -int ip6mr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait) +int ip6mr_get_route(struct net *net, + struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb->dst; read_lock(&mrt_lock); - cache = ip6mr_cache_find(&rt->rt6i_src.addr, &rt->rt6i_dst.addr); + cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache) { struct sk_buff *skb2; @@ -1658,7 +1754,7 @@ int ip6mr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait) ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); - err = ip6mr_cache_unresolved(vif, skb2); + err = ip6mr_cache_unresolved(net, vif, skb2); read_unlock(&mrt_lock); return err; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 4545e4306862..3a0b3be7ece5 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -63,12 +63,12 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; spi = htonl(ntohs(ipcomph->cpi)); - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); + x = xfrm_state_lookup(&init_net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/" NIP6_FMT "\n", - spi, NIP6(iph->daddr)); + printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI6\n", + spi, &iph->daddr); xfrm_state_put(x); } @@ -76,7 +76,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct xfrm_state *t = NULL; - t = xfrm_state_alloc(); + t = xfrm_state_alloc(&init_net); if (!t) goto out; @@ -114,7 +114,7 @@ static int ipcomp6_tunnel_attach(struct xfrm_state *x) spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&x->props.saddr); if (spi) - t = xfrm_state_lookup((xfrm_address_t *)&x->id.daddr, + t = xfrm_state_lookup(&init_net, (xfrm_address_t *)&x->id.daddr, spi, IPPROTO_IPV6, AF_INET6); if (!t) { t = ipcomp6_tunnel_create(x); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2aa294be0c79..eeeaad2e8b5c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -395,6 +395,28 @@ sticky_done: break; } + case IPV6_PKTINFO: + { + struct in6_pktinfo pkt; + + if (optlen == 0) + goto e_inval; + else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL) + goto e_inval; + + if (copy_from_user(&pkt, optval, optlen)) { + retv = -EFAULT; + break; + } + if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if) + goto e_inval; + + np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex; + ipv6_addr_copy(&np->sticky_pktinfo.ipi6_addr, &pkt.ipi6_addr); + retv = 0; + break; + } + case IPV6_2292PKTOPTIONS: { struct ipv6_txoptions *opt = NULL; @@ -916,8 +938,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } else { if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if; - ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : + np->sticky_pktinfo.ipi6_ifindex; + np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) : + ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr)); put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { @@ -926,8 +950,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if; - ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : + np->sticky_pktinfo.ipi6_ifindex; + np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) : + ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr)); put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d7b3c6d398ae..a51fb33e6864 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -303,20 +303,23 @@ static struct inet6_dev *ip6_mc_find_dev(struct net *net, dev = dev_get_by_index(net, ifindex); if (!dev) - return NULL; + goto nodev; idev = in6_dev_get(dev); - if (!idev) { - dev_put(dev); - return NULL; - } + if (!idev) + goto release; read_lock_bh(&idev->lock); - if (idev->dead) { - read_unlock_bh(&idev->lock); - in6_dev_put(idev); - dev_put(dev); - return NULL; - } + if (idev->dead) + goto unlock_release; + return idev; + +unlock_release: + read_unlock_bh(&idev->lock); + in6_dev_put(idev); +release: + dev_put(dev); +nodev: + return NULL; } void ipv6_sock_mc_close(struct sock *sk) @@ -1466,7 +1469,7 @@ static void mld_sendpack(struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(&skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); if (err) goto err_out; @@ -1817,7 +1820,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) hdr->icmp6_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, - csum_partial((__u8 *) hdr, len, 0)); + csum_partial(hdr, len, 0)); idev = in6_dev_get(skb->dev); @@ -1831,7 +1834,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - err = xfrm_lookup(&skb->dst, &fl, NULL, 0); + err = xfrm_lookup(net, &skb->dst, &fl, NULL, 0); if (err) goto err_out; @@ -2430,9 +2433,9 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, - "%-4d %-15s " NIP6_SEQFMT " %5d %08X %ld\n", + "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, - NIP6(im->mca_addr), + &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags&MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_timer.expires-jiffies) : 0); @@ -2591,10 +2594,10 @@ static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) "Source Address", "INC", "EXC"); } else { seq_printf(seq, - "%3d %6.6s " NIP6_SEQFMT " " NIP6_SEQFMT " %6lu %6lu\n", + "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, - NIP6(state->im->mca_addr), - NIP6(psf->sf_addr), + &state->im->mca_addr, + &psf->sf_addr, psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 31295c8f6196..f995e19c87a9 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -205,6 +205,7 @@ static inline int mip6_report_rl_allow(struct timeval *stamp, static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl) { + struct net *net = xs_net(x); struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb; struct ipv6_destopt_hao *hao = NULL; struct xfrm_selector sel; @@ -247,7 +248,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct sel.sport_mask = htons(~0); sel.ifindex = fl->oif; - err = km_report(IPPROTO_DSTOPTS, &sel, + err = km_report(net, IPPROTO_DSTOPTS, &sel, (hao ? (xfrm_address_t *)&hao->addr : NULL)); out: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 172438320eec..3e2970841bd8 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -437,38 +437,20 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -/* - * Send a Neighbour Advertisement - */ -static void __ndisc_send(struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, const struct in6_addr *target, - int llinfo) +struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo) { - struct flowi fl; - struct dst_entry *dst; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; - struct inet6_dev *idev; int len; int err; - u8 *opt, type; - - type = icmp6h->icmp6_type; - - icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); - - dst = icmp6_dst_alloc(dev, neigh, daddr); - if (!dst) - return; - - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) - return; + u8 *opt; if (!dev->addr_len) llinfo = 0; @@ -485,8 +467,7 @@ static void __ndisc_send(struct net_device *dev, ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb.\n", __func__); - dst_release(dst); - return; + return NULL; } skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -510,9 +491,45 @@ static void __ndisc_send(struct net_device *dev, hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, IPPROTO_ICMPV6, - csum_partial((__u8 *) hdr, + csum_partial(hdr, len, 0)); + return skb; +} + +EXPORT_SYMBOL(ndisc_build_skb); + +void ndisc_send_skb(struct sk_buff *skb, + struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h) +{ + struct flowi fl; + struct dst_entry *dst; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.ndisc_sk; + struct inet6_dev *idev; + int err; + u8 type; + + type = icmp6h->icmp6_type; + + icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); + + dst = icmp6_dst_alloc(dev, neigh, daddr); + if (!dst) { + kfree_skb(skb); + return; + } + + err = xfrm_lookup(net, &dst, &fl, NULL, 0); + if (err < 0) { + kfree_skb(skb); + return; + } + skb->dst = dst; idev = in6_dev_get(dst->dev); @@ -529,6 +546,27 @@ static void __ndisc_send(struct net_device *dev, in6_dev_put(idev); } +EXPORT_SYMBOL(ndisc_send_skb); + +/* + * Send a Neighbour Discover packet + */ +static void __ndisc_send(struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, const struct in6_addr *target, + int llinfo) +{ + struct sk_buff *skb; + + skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo); + if (!skb) + return; + + ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h); +} + static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, @@ -647,11 +685,8 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) if ((probes -= neigh->parms->ucast_probes) < 0) { if (!(neigh->nud_state & NUD_VALID)) { - ND_PRINTK1(KERN_DEBUG - "%s(): trying to ucast probe in NUD_INVALID: " - NIP6_FMT "\n", - __func__, - NIP6(*target)); + ND_PRINTK1(KERN_DEBUG "%s(): trying to ucast probe in NUD_INVALID: %pI6\n", + __func__, target); } ndisc_send_ns(dev, neigh, target, target, saddr); } else if ((probes -= neigh->parms->app_probes) < 0) { @@ -912,8 +947,13 @@ static void ndisc_recv_na(struct sk_buff *skb) is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) + + We should not print the error if NA has been + received from loopback - it is just our own + unsolicited advertisement. */ - ND_PRINTK1(KERN_WARNING + if (skb->pkt_type != PACKET_LOOPBACK) + ND_PRINTK1(KERN_WARNING "ICMPv6 NA: someone advertises our address on %s!\n", ifp->idev->dev->name); in6_ifa_put(ifp); @@ -1489,7 +1529,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, if (dst == NULL) return; - err = xfrm_lookup(&dst, &fl, NULL, 0); + err = xfrm_lookup(net, &dst, &fl, NULL, 0); if (err) return; @@ -1577,7 +1617,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, icmph->icmp6_cksum = csum_ipv6_magic(&saddr_buf, &ipv6_hdr(skb)->saddr, len, IPPROTO_ICMPV6, - csum_partial((u8 *) icmph, len, 0)); + csum_partial(icmph, len, 0)); buff->dst = dst; idev = in6_dev_get(dst->dev); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index fd5b3a4e3329..834cea69fb53 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -29,7 +29,7 @@ int ip6_route_me_harder(struct sk_buff *skb) #ifdef CONFIG_XFRM if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, &fl, AF_INET6) == 0) - if (xfrm_lookup(&skb->dst, &fl, skb->sk, 0)) + if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) return -1; #endif @@ -56,6 +56,7 @@ EXPORT_SYMBOL(ip6_route_me_harder); struct ip6_rt_info { struct in6_addr daddr; struct in6_addr saddr; + u_int32_t mark; }; static void nf_ip6_saveroute(const struct sk_buff *skb, @@ -68,6 +69,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb, rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; + rt_info->mark = skb->mark; } } @@ -79,7 +81,8 @@ static int nf_ip6_reroute(struct sk_buff *skb, if (entry->hook == NF_INET_LOCAL_OUT) { struct ipv6hdr *iph = ipv6_hdr(skb); if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || - !ipv6_addr_equal(&iph->saddr, &rt_info->saddr)) + !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || + skb->mark != rt_info->mark) return ip6_route_me_harder(skb); } return 0; diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index caa441d09567..37adf5abc51e 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -61,7 +61,7 @@ static void dump_packet(const struct nf_loginfo *info, } /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ - printk("SRC=" NIP6_FMT " DST=" NIP6_FMT " ", NIP6(ih->saddr), NIP6(ih->daddr)); + printk("SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ printk("LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", @@ -364,8 +364,8 @@ static void dump_packet(const struct nf_loginfo *info, read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) printk("UID=%u GID=%u ", - skb->sk->sk_socket->file->f_uid, - skb->sk->sk_socket->file->f_gid); + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); } @@ -424,9 +424,8 @@ ip6t_log_packet(u_int8_t pf, if (skb->dev->type == ARPHRD_SIT) { const struct iphdr *iph = (struct iphdr *)skb_mac_header(skb); - printk("TUNNEL=%u.%u.%u.%u->%u.%u.%u.%u ", - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); + printk("TUNNEL=%pI4->%pI4 ", + &iph->saddr, &iph->daddr); } } else printk(" "); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 0981b4ccb8b1..5a2d0a41694a 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -97,7 +97,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) dst = ip6_route_output(net, NULL, &fl); if (dst == NULL) return; - if (dst->error || xfrm_lookup(&dst, &fl, NULL, 0)) + if (dst->error || xfrm_lookup(net, &dst, &fl, NULL, 0)) return; hh_len = (dst->dev->hard_header_len + 15)&~15; diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index b110a8a85a14..40d2e36d8fac 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -61,7 +61,7 @@ static struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6t_local_in_hook(unsigned int hook, +ip6t_in_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -72,17 +72,6 @@ ip6t_local_in_hook(unsigned int hook, } static unsigned int -ip6t_forward_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return ip6t_do_table(skb, hook, in, out, - dev_net(in)->ipv6.ip6table_filter); -} - -static unsigned int ip6t_local_out_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, @@ -105,14 +94,14 @@ ip6t_local_out_hook(unsigned int hook, static struct nf_hook_ops ip6t_ops[] __read_mostly = { { - .hook = ip6t_local_in_hook, + .hook = ip6t_in_hook, .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_FILTER, }, { - .hook = ip6t_forward_hook, + .hook = ip6t_in_hook, .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_FORWARD, diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index e91db16611d9..727b9530448a 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -56,9 +56,8 @@ static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple, static int ipv6_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "src=" NIP6_FMT " dst=" NIP6_FMT " ", - NIP6(*((struct in6_addr *)tuple->src.u3.ip6)), - NIP6(*((struct in6_addr *)tuple->dst.u3.ip6))); + return seq_printf(s, "src=%pI6 dst=%pI6 ", + tuple->src.u3.ip6, tuple->dst.u3.ip6); } /* diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 05726177903f..bd52151d31e9 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -253,7 +253,7 @@ static struct ctl_table icmpv6_sysctl_table[] = { .data = &nf_ct_icmpv6_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { .ctl_name = 0 diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 9967ac7a01a8..ed4d79a9e4a6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -80,7 +80,7 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .data = &nf_init_frags.timeout, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { .ctl_name = NET_NF_CONNTRACK_FRAG6_LOW_THRESH, @@ -88,7 +88,7 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .data = &nf_init_frags.low_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_NF_CONNTRACK_FRAG6_HIGH_THRESH, @@ -96,7 +96,7 @@ struct ctl_table nf_ct_ipv6_sysctl_table[] = { .data = &nf_init_frags.high_thresh, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = 0 } }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 2ba04d41dc25..61f6827e5906 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -860,7 +860,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index af12de071f4c..3c575118fca5 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -642,7 +642,7 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .data = &init_net.ipv6.frags.high_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV6_IP6FRAG_LOW_THRESH, @@ -650,7 +650,7 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV6_IP6FRAG_TIME, @@ -658,8 +658,8 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .data = &init_net.ipv6.frags.timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { } }; @@ -671,8 +671,8 @@ static struct ctl_table ip6_frags_ctl_table[] = { .data = &ip6_frags.secret_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { } }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 89dc69924340..18c486cf4987 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -108,7 +108,6 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .local_out = __ip6_local_out, - .entry_size = sizeof(struct rt6_info), .entries = ATOMIC_INIT(0), }; @@ -122,7 +121,6 @@ static struct dst_ops ip6_dst_blackhole_ops = { .destroy = ip6_dst_destroy, .check = ip6_dst_check, .update_pmtu = ip6_rt_blackhole_update_pmtu, - .entry_size = sizeof(struct rt6_info), .entries = ATOMIC_INIT(0), }; @@ -2196,7 +2194,7 @@ static int rt6_fill_node(struct net *net, if (iif) { #ifdef CONFIG_IPV6_MROUTE if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { - int err = ip6mr_get_route(skb, rtm, nowait); + int err = ip6mr_get_route(net, skb, rtm, nowait); if (err <= 0) { if (!nowait) { if (err == 0) @@ -2408,19 +2406,16 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) { struct seq_file *m = p_arg; - seq_printf(m, NIP6_SEQFMT " %02x ", NIP6(rt->rt6i_dst.addr), - rt->rt6i_dst.plen); + seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); #ifdef CONFIG_IPV6_SUBTREES - seq_printf(m, NIP6_SEQFMT " %02x ", NIP6(rt->rt6i_src.addr), - rt->rt6i_src.plen); + seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif if (rt->rt6i_nexthop) { - seq_printf(m, NIP6_SEQFMT, - NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key))); + seq_printf(m, "%pi6", rt->rt6i_nexthop->primary_key); } else { seq_puts(m, "00000000000000000000000000000000"); } @@ -2502,7 +2497,7 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, - .proc_handler = &ipv6_sysctl_rtcache_flush + .proc_handler = ipv6_sysctl_rtcache_flush }, { .ctl_name = NET_IPV6_ROUTE_GC_THRESH, @@ -2510,7 +2505,7 @@ ctl_table ipv6_route_table_template[] = { .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ROUTE_MAX_SIZE, @@ -2518,7 +2513,7 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL, @@ -2526,8 +2521,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_ROUTE_GC_TIMEOUT, @@ -2535,8 +2530,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_ROUTE_GC_INTERVAL, @@ -2544,8 +2539,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_ROUTE_GC_ELASTICITY, @@ -2553,8 +2548,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_ROUTE_MTU_EXPIRES, @@ -2562,8 +2557,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_ROUTE_MIN_ADVMSS, @@ -2571,8 +2566,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS, @@ -2580,8 +2575,8 @@ ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, + .proc_handler = proc_dointvec_ms_jiffies, + .strategy = sysctl_ms_jiffies, }, { .ctl_name = 0 } }; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b7a50e968506..d3467e563f02 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -62,8 +62,8 @@ #define HASH_SIZE 16 #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); +static void ipip6_fb_tunnel_init(struct net_device *dev); +static void ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static int sit_net_id; @@ -188,7 +188,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, } nt = netdev_priv(dev); - dev->init = ipip6_tunnel_init; + ipip6_tunnel_init(dev); + nt->parms = *parms; if (parms->i_flags & SIT_ISATAP) @@ -926,13 +927,17 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static const struct net_device_ops ipip6_netdev_ops = { + .ndo_uninit = ipip6_tunnel_uninit, + .ndo_start_xmit = ipip6_tunnel_xmit, + .ndo_do_ioctl = ipip6_tunnel_ioctl, + .ndo_change_mtu = ipip6_tunnel_change_mtu, +}; + static void ipip6_tunnel_setup(struct net_device *dev) { - dev->uninit = ipip6_tunnel_uninit; + dev->netdev_ops = &ipip6_netdev_ops; dev->destructor = free_netdev; - dev->hard_start_xmit = ipip6_tunnel_xmit; - dev->do_ioctl = ipip6_tunnel_ioctl; - dev->change_mtu = ipip6_tunnel_change_mtu; dev->type = ARPHRD_SIT; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -943,11 +948,9 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static int ipip6_tunnel_init(struct net_device *dev) +static void ipip6_tunnel_init(struct net_device *dev) { - struct ip_tunnel *tunnel; - - tunnel = netdev_priv(dev); + struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; strcpy(tunnel->parms.name, dev->name); @@ -956,11 +959,9 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - - return 0; } -static int ipip6_fb_tunnel_init(struct net_device *dev) +static void ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -977,7 +978,6 @@ static int ipip6_fb_tunnel_init(struct net_device *dev) dev_hold(dev); sitn->tunnels_wc[0] = tunnel; - return 0; } static struct xfrm_tunnel sit_handler = { @@ -1025,16 +1025,17 @@ static int sit_init_net(struct net *net) err = -ENOMEM; goto err_alloc_dev; } - - sitn->fb_tunnel_dev->init = ipip6_fb_tunnel_init; dev_net_set(sitn->fb_tunnel_dev, net); + ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; return 0; err_reg_dev: + dev_put(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: /* nothing */ diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 676c80b5b14b..711175e0571f 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -259,7 +259,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto out_free; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 587f8f60c489..9048fe7e7ea7 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -35,7 +35,7 @@ static ctl_table ipv6_table_template[] = { .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = 0 } }; @@ -47,7 +47,7 @@ static ctl_table ipv6_table[] = { .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = 0 } }; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6b356b7912a..8702b06cb60a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -260,7 +260,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) @@ -390,7 +391,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + if ((err = xfrm_lookup(net, &dst, &fl, sk, 0)) < 0) { sk->sk_err_soft = -err; goto out; } @@ -492,7 +493,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) goto done; if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto done; skb = tcp_make_synack(sk, dst, req); @@ -501,7 +502,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) th->check = tcp_v6_check(th, skb->len, &treq->loc_addr, &treq->rmt_addr, - csum_partial((char *)th, skb->len, skb->csum)); + csum_partial(th, skb->len, skb->csum)); ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); err = ip6_xmit(sk, skb, &fl, opt, 0); @@ -872,12 +873,10 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) 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", + printk(KERN_INFO "MD5 Hash %s for (%pI6, %u)->(%pI6, %u)\n", genhash ? "failed" : "mismatch", - NIP6(ip6h->saddr), ntohs(th->source), - NIP6(ip6h->daddr), ntohs(th->dest)); + &ip6h->saddr, ntohs(th->source), + &ip6h->daddr, ntohs(th->dest)); } return 1; } @@ -917,7 +916,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) 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, + csum_partial(th, th->doff<<2, skb->csum)); } } @@ -999,7 +998,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, } #endif - buff->csum = csum_partial((char *)t1, tot_len, 0); + buff->csum = csum_partial(t1, tot_len, 0); memset(&fl, 0, sizeof(fl)); ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr); @@ -1020,7 +1019,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, * namespace */ if (!ip6_dst_lookup(ctl_sk, &buff->dst, &fl)) { - if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { + if (xfrm_lookup(net, &buff->dst, &fl, NULL, 0) >= 0) { ip6_xmit(ctl_sk, buff, &fl, NULL, 0); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) @@ -1318,7 +1317,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto out; } @@ -1831,7 +1830,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - atomic_inc(&tcp_sockets_allocated); + percpu_counter_inc(&tcp_sockets_allocated); return 0; } @@ -2045,6 +2044,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = &tcp_hashinfo, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8b48512ebf6a..84b1a296eecb 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -54,62 +54,91 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal); } +static inline int compute_score(struct sock *sk, struct net *net, + unsigned short hnum, + struct in6_addr *saddr, __be16 sport, + struct in6_addr *daddr, __be16 dport, + int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && + sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_sock *inet = inet_sk(sk); + + score = 0; + if (inet->dport) { + if (inet->dport != sport) + return -1; + score++; + } + if (!ipv6_addr_any(&np->rcv_saddr)) { + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + return -1; + score++; + } + if (!ipv6_addr_any(&np->daddr)) { + if (!ipv6_addr_equal(&np->daddr, saddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + static struct sock *__udp6_lib_lookup(struct net *net, struct in6_addr *saddr, __be16 sport, struct in6_addr *daddr, __be16 dport, - int dif, struct hlist_head udptable[]) + int dif, struct udp_table *udptable) { - struct sock *sk, *result = NULL; - struct hlist_node *node; + struct sock *sk, *result; + struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - int badness = -1; - - read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udptable[udp_hashfn(net, hnum)]) { - struct inet_sock *inet = inet_sk(sk); - - if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && - sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - int score = 0; - if (inet->dport) { - if (inet->dport != sport) - continue; - score++; - } - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) - continue; - score++; - } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) - continue; - score++; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score++; - } - if (score == 4) { - result = sk; - break; - } else if (score > badness) { - result = sk; - badness = score; - } + unsigned int hash = udp_hashfn(net, hnum); + struct udp_hslot *hslot = &udptable->hash[hash]; + int score, badness; + + rcu_read_lock(); +begin: + result = NULL; + badness = -1; + sk_nulls_for_each_rcu(sk, node, &hslot->head) { + score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif); + if (score > badness) { + result = sk; + badness = score; } } - if (result) - sock_hold(result); - read_unlock(&udp_hash_lock); + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash) + goto begin; + + if (result) { + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score(result, net, hnum, saddr, sport, + daddr, dport, dif) < badness)) { + sock_put(result); + goto begin; + } + } + rcu_read_unlock(); return result; } static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, - struct hlist_head udptable[]) + struct udp_table *udptable) { struct sock *sk; struct ipv6hdr *iph = ipv6_hdr(skb); @@ -253,7 +282,7 @@ csum_copy_err: 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 udp_table *udptable) { struct ipv6_pinfo *np; struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data; @@ -289,7 +318,7 @@ static __inline__ void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __be32 info ) { - __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash); + __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) @@ -347,11 +376,11 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, __be16 rmt_port, struct in6_addr *rmt_addr, int dif) { - struct hlist_node *node; + struct hlist_nulls_node *node; struct sock *s = sk; unsigned short num = ntohs(loc_port); - sk_for_each_from(s, node) { + sk_nulls_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); if (!net_eq(sock_net(s), net)) @@ -388,14 +417,15 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, */ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, - struct hlist_head udptable[]) + struct udp_table *udptable) { struct sock *sk, *sk2; const struct udphdr *uh = udp_hdr(skb); + struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; int dif; - read_lock(&udp_hash_lock); - sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]); + spin_lock(&hslot->lock); + sk = sk_nulls_head(&hslot->head); dif = inet6_iif(skb); sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); if (!sk) { @@ -404,7 +434,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, } sk2 = sk; - while ((sk2 = udp_v6_mcast_next(net, sk_next(sk2), uh->dest, daddr, + while ((sk2 = udp_v6_mcast_next(net, sk_nulls_next(sk2), uh->dest, daddr, uh->source, saddr, dif))) { struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); if (buff) { @@ -423,7 +453,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, sk_add_backlog(sk, skb); bh_unlock_sock(sk); out: - read_unlock(&udp_hash_lock); + spin_unlock(&hslot->lock); return 0; } @@ -461,7 +491,7 @@ static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, return 0; } -int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], +int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { struct sock *sk; @@ -558,7 +588,7 @@ discard: static __inline__ int udpv6_rcv(struct sk_buff *skb) { - return __udp6_lib_rcv(skb, udp_hash, IPPROTO_UDP); + return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); } /* @@ -763,6 +793,9 @@ do_udp_sendmsg: if (!fl.oif) fl.oif = sk->sk_bound_dev_if; + if (!fl.oif) + fl.oif = np->sticky_pktinfo.ipi6_ifindex; + if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); @@ -819,7 +852,8 @@ do_udp_sendmsg: if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) { + err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT); + if (err < 0) { if (err == -EREMOTE) err = ip6_dst_blackhole(sk, &dst, &fl); if (err < 0) @@ -1022,7 +1056,7 @@ int udp6_seq_show(struct seq_file *seq, void *v) static struct udp_seq_afinfo udp6_seq_afinfo = { .name = "udp6", .family = AF_INET6, - .hashtable = udp_hash, + .udp_table = &udp_table, .seq_fops = { .owner = THIS_MODULE, }, @@ -1064,7 +1098,8 @@ struct proto udpv6_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp6_sock), - .h.udp_hash = udp_hash, + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 92dd7da766d8..23779208c334 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -7,9 +7,9 @@ #include <net/inet_common.h> #include <net/transp_v6.h> -extern int __udp6_lib_rcv(struct sk_buff *, struct hlist_head [], int ); +extern int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int ); extern void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, - int , int , int , __be32 , struct hlist_head []); + int , int , int , __be32 , struct udp_table *); extern int udp_v6_get_port(struct sock *sk, unsigned short snum); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 3cd1a1ac3d6c..ba162a824585 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -15,14 +15,14 @@ static int udplitev6_rcv(struct sk_buff *skb) { - return __udp6_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE); + return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); } static void udplitev6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __be32 info) { - __udp6_lib_err(skb, opt, type, code, offset, info, udplite_hash); + __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); } static struct inet6_protocol udplitev6_protocol = { @@ -49,7 +49,8 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .obj_size = sizeof(struct udp6_sock), - .h.udp_hash = udplite_hash, + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, @@ -95,7 +96,7 @@ void udplitev6_exit(void) static struct udp_seq_afinfo udplite6_seq_afinfo = { .name = "udplite6", .family = AF_INET6, - .hashtable = udplite_hash, + .udp_table = &udplite_table, .seq_fops = { .owner = THIS_MODULE, }, diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index a71c7ddcb41e..9084582d236b 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -58,6 +58,7 @@ EXPORT_SYMBOL(xfrm6_rcv); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto) { + struct net *net = dev_net(skb->dev); struct xfrm_state *x = NULL; int i = 0; @@ -67,7 +68,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, sp = secpath_dup(skb->sp); if (!sp) { - XFRM_INC_STATS(LINUX_MIB_XFRMINERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } if (skb->sp) @@ -76,7 +77,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, } if (1 + skb->sp->len == XFRM_MAX_DEPTH) { - XFRM_INC_STATS(LINUX_MIB_XFRMINBUFFERERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } @@ -100,7 +101,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, break; } - x = xfrm_state_lookup_byaddr(dst, src, proto, AF_INET6); + x = xfrm_state_lookup_byaddr(net, dst, src, proto, AF_INET6); if (!x) continue; @@ -122,7 +123,7 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, } if (!x) { - XFRM_INC_STATS(LINUX_MIB_XFRMINNOSTATES); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound_simple(skb, AF_INET6); goto drop; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 08e4cbbe3f04..97ab068e8ccc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -27,7 +27,8 @@ static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, +static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct flowi fl = {}; @@ -38,7 +39,7 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, if (saddr) memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src)); - dst = ip6_route_output(&init_net, NULL, &fl); + dst = ip6_route_output(net, NULL, &fl); err = dst->error; if (dst->error) { @@ -49,12 +50,13 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, return dst; } -static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) +static int xfrm6_get_saddr(struct net *net, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; struct net_device *dev; - dst = xfrm6_dst_lookup(0, NULL, daddr); + dst = xfrm6_dst_lookup(net, 0, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -144,6 +146,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev) static inline void _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) { + int onlyproto = 0; u16 offset = skb_network_header_len(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct ipv6_opt_hdr *exthdr; @@ -159,6 +162,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) exthdr = (struct ipv6_opt_hdr *)(nh + offset); switch (nexthdr) { + case NEXTHDR_FRAGMENT: + onlyproto = 1; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: @@ -172,7 +177,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: - if (pskb_may_pull(skb, nh + offset + 4 - skb->data)) { + if (!onlyproto && pskb_may_pull(skb, nh + offset + 4 - skb->data)) { __be16 *ports = (__be16 *)exthdr; fl->fl_ip_sport = ports[!!reverse]; @@ -182,7 +187,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) return; case IPPROTO_ICMPV6: - if (pskb_may_pull(skb, nh + offset + 2 - skb->data)) { + if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { u8 *icmp = (u8 *)exthdr; fl->fl_icmp_type = icmp[0]; @@ -193,7 +198,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) case IPPROTO_MH: - if (pskb_may_pull(skb, nh + offset + 3 - skb->data)) { + if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { struct ip6_mh *mh; mh = (struct ip6_mh *)exthdr; @@ -217,7 +222,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - xfrm6_policy_afinfo.garbage_collect(); + xfrm6_policy_afinfo.garbage_collect(&init_net); return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); } @@ -274,7 +279,6 @@ static struct dst_ops xfrm6_dst_ops = { .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, .gc_thresh = 1024, - .entry_size = sizeof(struct xfrm_dst), .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 60c78cfc2737..0e685b05496e 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -19,8 +19,6 @@ #include <net/ipv6.h> #include <net/addrconf.h> -static struct xfrm_state_afinfo xfrm6_state_afinfo; - static void __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, struct xfrm_tmpl *tmpl, diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index c2b278138604..80193db224d9 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -345,24 +345,23 @@ static struct xfrm6_tunnel xfrm46_tunnel_handler = { static int __init xfrm6_tunnel_init(void) { if (xfrm_register_type(&xfrm6_tunnel_type, AF_INET6) < 0) - return -EAGAIN; - - if (xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6)) { - xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); - return -EAGAIN; - } - if (xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET)) { - xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); - xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); - return -EAGAIN; - } - if (xfrm6_tunnel_spi_init() < 0) { - xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET); - xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); - xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); - return -EAGAIN; - } + goto err; + if (xfrm6_tunnel_register(&xfrm6_tunnel_handler, AF_INET6)) + goto unreg; + if (xfrm6_tunnel_register(&xfrm46_tunnel_handler, AF_INET)) + goto dereg6; + if (xfrm6_tunnel_spi_init() < 0) + goto dereg46; return 0; + +dereg46: + xfrm6_tunnel_deregister(&xfrm46_tunnel_handler, AF_INET); +dereg6: + xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); +unreg: + xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); +err: + return -EAGAIN; } static void __exit xfrm6_tunnel_fini(void) |