summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/ah6.c3
-rw-r--r--net/ipv6/esp6.c2
-rw-r--r--net/ipv6/exthdrs.c4
-rw-r--r--net/ipv6/icmp.c12
-rw-r--r--net/ipv6/ip6_fib.c5
-rw-r--r--net/ipv6/ip6_output.c26
-rw-r--r--net/ipv6/ipcomp6.c2
-rw-r--r--net/ipv6/ndisc.c6
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c88
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c36
-rw-r--r--net/ipv6/raw.c5
-rw-r--r--net/ipv6/route.c235
-rw-r--r--net/ipv6/sit.c15
-rw-r--r--net/ipv6/tcp_ipv6.c37
-rw-r--r--net/ipv6/udp.c3
-rw-r--r--net/ipv6/xfrm6_policy.c10
16 files changed, 242 insertions, 247 deletions
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index f1a4a2c28ed3..49d4d26bda88 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -35,6 +35,7 @@
#include <linux/pfkeyv2.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
@@ -621,7 +622,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n",
ntohl(ah->spi), &iph->daddr);
-
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index db1521fcda5b..89a615ba84f8 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -39,6 +39,7 @@
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
@@ -442,6 +443,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return;
pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n",
ntohl(esph->spi), &iph->daddr);
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 6447dc49429f..fa3d9c328092 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -791,14 +791,14 @@ static int ipv6_renew_option(void *ohdr,
if (ohdr) {
memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr));
*hdr = (struct ipv6_opt_hdr *)*p;
- *p += CMSG_ALIGN(ipv6_optlen(*(struct ipv6_opt_hdr **)hdr));
+ *p += CMSG_ALIGN(ipv6_optlen(*hdr));
}
} else {
if (newopt) {
if (copy_from_user(*p, newopt, newoptlen))
return -EFAULT;
*hdr = (struct ipv6_opt_hdr *)*p;
- if (ipv6_optlen(*(struct ipv6_opt_hdr **)hdr) > newoptlen)
+ if (ipv6_optlen(*hdr) > newoptlen)
return -EINVAL;
*p += CMSG_ALIGN(newoptlen);
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 091a2971c7b7..5247d5c211f9 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -188,14 +188,14 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
} else {
struct rt6_info *rt = (struct rt6_info *)dst;
int tmo = net->ipv6.sysctl.icmpv6_time;
+ struct inet_peer *peer;
/* Give more bandwidth to wider prefixes. */
if (rt->rt6i_dst.plen < 128)
tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
- res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo);
+ peer = rt6_get_peer_create(rt);
+ res = inet_peer_xrlim_allow(peer, tmo);
}
dst_release(dst);
return res;
@@ -649,7 +649,6 @@ static int icmpv6_rcv(struct sk_buff *skb)
struct net_device *dev = skb->dev;
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
- const struct ipv6hdr *orig_hdr;
struct icmp6hdr *hdr;
u8 type;
@@ -661,7 +660,7 @@ static int icmpv6_rcv(struct sk_buff *skb)
XFRM_STATE_ICMP))
goto drop_no_count;
- if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(*orig_hdr)))
+ if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
goto drop_no_count;
nh = skb_network_offset(skb);
@@ -722,9 +721,6 @@ static int icmpv6_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto discard_it;
hdr = icmp6_hdr(skb);
- orig_hdr = (struct ipv6hdr *) (hdr + 1);
- rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev,
- ntohl(hdr->icmp6_mtu));
/*
* Drop through to notify
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index fbd4afff05fa..a83bf067bdc5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -197,6 +197,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
table->tb6_id = id;
table->tb6_root.leaf = net->ipv6.ip6_null_entry;
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+ inet_peer_base_init(&table->tb6_peers);
}
return table;
@@ -1633,6 +1634,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+ inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl),
@@ -1643,6 +1645,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry;
net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
+ inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
#endif
fib6_tables_init(net);
@@ -1666,8 +1669,10 @@ static void fib6_net_exit(struct net *net)
del_timer_sync(&net->ipv6.ip6_fib_timer);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers);
kfree(net->ipv6.fib6_local_tbl);
#endif
+ inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers);
kfree(net->ipv6.fib6_main_tbl);
kfree(net->ipv6.fib_table_hash);
kfree(net->ipv6.rt6_stats);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index decc21d19c53..a233a7ccbc3a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -83,19 +83,6 @@ int ip6_local_out(struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(ip6_local_out);
-/* dev_loopback_xmit for use with netfilter. */
-static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
-{
- skb_reset_mac_header(newskb);
- __skb_pull(newskb, skb_network_offset(newskb));
- newskb->pkt_type = PACKET_LOOPBACK;
- newskb->ip_summed = CHECKSUM_UNNECESSARY;
- WARN_ON(!skb_dst(newskb));
-
- netif_rx_ni(newskb);
- return 0;
-}
-
static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -121,7 +108,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
newskb, NULL, newskb->dev,
- ip6_dev_loopback_xmit);
+ dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
IP6_INC_STATS(dev_net(dev), idev,
@@ -463,6 +450,7 @@ int ip6_forward(struct sk_buff *skb)
*/
if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
+ struct inet_peer *peer;
struct rt6_info *rt;
/*
@@ -476,13 +464,12 @@ int ip6_forward(struct sk_buff *skb)
else
target = &hdr->daddr;
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
+ peer = rt6_get_peer_create(rt);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
- if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
+ if (inet_peer_xrlim_allow(peer, 1*HZ))
ndisc_send_redirect(skb, target);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
@@ -603,11 +590,8 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
int old, new;
if (rt && !(rt->dst.flags & DST_NOPEER)) {
- struct inet_peer *peer;
+ struct inet_peer *peer = rt6_get_peer_create(rt);
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
- peer = rt->rt6i_peer;
if (peer) {
fhdr->identification = htonl(inet_getid(peer, 0));
return;
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 5cb75bfe45b1..92832385a8ef 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -46,6 +46,7 @@
#include <linux/list.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
@@ -74,6 +75,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n",
spi, &iph->daddr);
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 54f62d3b8dd6..69a6330dea91 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1472,6 +1472,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.ndisc_sk;
int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr);
+ struct inet_peer *peer;
struct sk_buff *buff;
struct icmp6hdr *icmph;
struct in6_addr saddr_buf;
@@ -1518,9 +1519,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
"Redirect: destination is not a neighbour\n");
goto release;
}
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
- if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
+ peer = rt6_get_peer_create(rt);
+ if (!inet_peer_xrlim_allow(peer, 1*HZ))
goto release;
if (dev->addr_len) {
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 3224ef90a21a..fca10da80ea7 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -333,37 +333,75 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>");
-static int __init nf_conntrack_l3proto_ipv6_init(void)
+static int ipv6_net_init(struct net *net)
{
int ret = 0;
- need_conntrack();
- nf_defrag_ipv6_enable();
-
- ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp6);
+ ret = nf_conntrack_l4proto_register(net,
+ &nf_conntrack_l4proto_tcp6);
if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register tcp.\n");
- return ret;
+ printk(KERN_ERR "nf_conntrack_l4proto_tcp6: protocol register failed\n");
+ goto out;
}
-
- ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp6);
+ ret = nf_conntrack_l4proto_register(net,
+ &nf_conntrack_l4proto_udp6);
if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register udp.\n");
- goto cleanup_tcp;
+ printk(KERN_ERR "nf_conntrack_l4proto_udp6: protocol register failed\n");
+ goto cleanup_tcp6;
}
-
- ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmpv6);
+ ret = nf_conntrack_l4proto_register(net,
+ &nf_conntrack_l4proto_icmpv6);
if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register icmpv6.\n");
- goto cleanup_udp;
+ printk(KERN_ERR "nf_conntrack_l4proto_icmp6: protocol register failed\n");
+ goto cleanup_udp6;
}
-
- ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv6);
+ ret = nf_conntrack_l3proto_register(net,
+ &nf_conntrack_l3proto_ipv6);
if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register ipv6\n");
+ printk(KERN_ERR "nf_conntrack_l3proto_ipv6: protocol register failed\n");
goto cleanup_icmpv6;
}
+ return 0;
+ cleanup_icmpv6:
+ nf_conntrack_l4proto_unregister(net,
+ &nf_conntrack_l4proto_icmpv6);
+ cleanup_udp6:
+ nf_conntrack_l4proto_unregister(net,
+ &nf_conntrack_l4proto_udp6);
+ cleanup_tcp6:
+ nf_conntrack_l4proto_unregister(net,
+ &nf_conntrack_l4proto_tcp6);
+ out:
+ return ret;
+}
+static void ipv6_net_exit(struct net *net)
+{
+ nf_conntrack_l3proto_unregister(net,
+ &nf_conntrack_l3proto_ipv6);
+ nf_conntrack_l4proto_unregister(net,
+ &nf_conntrack_l4proto_icmpv6);
+ nf_conntrack_l4proto_unregister(net,
+ &nf_conntrack_l4proto_udp6);
+ nf_conntrack_l4proto_unregister(net,
+ &nf_conntrack_l4proto_tcp6);
+}
+
+static struct pernet_operations ipv6_net_ops = {
+ .init = ipv6_net_init,
+ .exit = ipv6_net_exit,
+};
+
+static int __init nf_conntrack_l3proto_ipv6_init(void)
+{
+ int ret = 0;
+
+ need_conntrack();
+ nf_defrag_ipv6_enable();
+
+ ret = register_pernet_subsys(&ipv6_net_ops);
+ if (ret < 0)
+ goto cleanup_pernet;
ret = nf_register_hooks(ipv6_conntrack_ops,
ARRAY_SIZE(ipv6_conntrack_ops));
if (ret < 0) {
@@ -374,13 +412,8 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
return ret;
cleanup_ipv6:
- nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
- cleanup_icmpv6:
- nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
- cleanup_udp:
- nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6);
- cleanup_tcp:
- nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
+ unregister_pernet_subsys(&ipv6_net_ops);
+ cleanup_pernet:
return ret;
}
@@ -388,10 +421,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void)
{
synchronize_net();
nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
- nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
- nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
- nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udp6);
- nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
+ unregister_pernet_subsys(&ipv6_net_ops);
}
module_init(nf_conntrack_l3proto_ipv6_init);
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 3e81904fbbcd..63ed0121836c 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -29,6 +29,11 @@
static unsigned int nf_ct_icmpv6_timeout __read_mostly = 30*HZ;
+static inline struct nf_icmp_net *icmpv6_pernet(struct net *net)
+{
+ return &net->ct.nf_ct_proto.icmpv6;
+}
+
static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
unsigned int dataoff,
struct nf_conntrack_tuple *tuple)
@@ -90,7 +95,7 @@ static int icmpv6_print_tuple(struct seq_file *s,
static unsigned int *icmpv6_get_timeouts(struct net *net)
{
- return &nf_ct_icmpv6_timeout;
+ return &icmpv6_pernet(net)->timeout;
}
/* Returns verdict for packet, or -1 for invalid. */
@@ -281,16 +286,18 @@ static int icmpv6_nlattr_tuple_size(void)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_cttimeout.h>
-static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], void *data)
+static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
+ struct net *net, void *data)
{
unsigned int *timeout = data;
+ struct nf_icmp_net *in = icmpv6_pernet(net);
if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) {
*timeout =
ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ;
} else {
/* Set default ICMPv6 timeout. */
- *timeout = nf_ct_icmpv6_timeout;
+ *timeout = in->timeout;
}
return 0;
}
@@ -315,11 +322,9 @@ icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = {
#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
#ifdef CONFIG_SYSCTL
-static struct ctl_table_header *icmpv6_sysctl_header;
static struct ctl_table icmpv6_sysctl_table[] = {
{
.procname = "nf_conntrack_icmpv6_timeout",
- .data = &nf_ct_icmpv6_timeout,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
@@ -328,6 +333,22 @@ static struct ctl_table icmpv6_sysctl_table[] = {
};
#endif /* CONFIG_SYSCTL */
+static int icmpv6_init_net(struct net *net)
+{
+ struct nf_icmp_net *in = icmpv6_pernet(net);
+ struct nf_proto_net *pn = (struct nf_proto_net *)in;
+ in->timeout = nf_ct_icmpv6_timeout;
+#ifdef CONFIG_SYSCTL
+ pn->ctl_table = kmemdup(icmpv6_sysctl_table,
+ sizeof(icmpv6_sysctl_table),
+ GFP_KERNEL);
+ if (!pn->ctl_table)
+ return -ENOMEM;
+ pn->ctl_table[0].data = &in->timeout;
+#endif
+ return 0;
+}
+
struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly =
{
.l3proto = PF_INET6,
@@ -355,8 +376,5 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly =
.nla_policy = icmpv6_timeout_nla_policy,
},
#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
-#ifdef CONFIG_SYSCTL
- .ctl_table_header = &icmpv6_sysctl_header,
- .ctl_table = icmpv6_sysctl_table,
-#endif
+ .init_net = icmpv6_init_net,
};
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 93d69836fded..43b0042f15f4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -328,9 +328,10 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
return;
harderr = icmpv6_err_convert(type, code, &err);
- if (type == ICMPV6_PKT_TOOBIG)
+ if (type == ICMPV6_PKT_TOOBIG) {
+ ip6_sk_update_pmtu(skb, sk, info);
harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
-
+ }
if (np->recverr) {
u8 *payload = skb->data;
if (!inet->hdrincl)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index dc60bf585966..c7ccc36ba63e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -99,10 +99,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
if (!(rt->dst.flags & DST_HOST))
return NULL;
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
-
- peer = rt->rt6i_peer;
+ peer = rt6_get_peer_create(rt);
if (peer) {
u32 *old_p = __DST_METRICS_PTR(old);
unsigned long prev, new;
@@ -261,16 +258,19 @@ static struct rt6_info ip6_blk_hole_entry_template = {
#endif
/* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
+static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
- int flags)
+ int flags,
+ struct fib6_table *table)
{
- struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
+ struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
+ 0, 0, flags);
- if (rt)
+ if (rt) {
memset(&rt->rt6i_table, 0,
sizeof(*rt) - sizeof(struct dst_entry));
-
+ rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
+ }
return rt;
}
@@ -278,7 +278,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
- struct inet_peer *peer = rt->rt6i_peer;
if (!(rt->dst.flags & DST_HOST))
dst_destroy_metrics_generic(dst);
@@ -291,8 +290,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from)
dst_release(dst->from);
- if (peer) {
- rt->rt6i_peer = NULL;
+ if (rt6_has_peer(rt)) {
+ struct inet_peer *peer = rt6_peer_ptr(rt);
inet_putpeer(peer);
}
}
@@ -306,13 +305,20 @@ static u32 rt6_peer_genid(void)
void rt6_bind_peer(struct rt6_info *rt, int create)
{
+ struct inet_peer_base *base;
struct inet_peer *peer;
- peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
- if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
- inet_putpeer(peer);
- else
- rt->rt6i_peer_genid = rt6_peer_genid();
+ base = inetpeer_base_ptr(rt->_rt6i_peer);
+ if (!base)
+ return;
+
+ peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
+ if (peer) {
+ if (!rt6_set_peer(rt, peer))
+ inet_putpeer(peer);
+ else
+ rt->rt6i_peer_genid = rt6_peer_genid();
+ }
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -952,6 +958,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
if (rt) {
memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+ rt6_init_peer(rt, net->ipv6.peers);
new = &rt->dst;
@@ -996,7 +1003,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
if (rt->rt6i_peer_genid != rt6_peer_genid()) {
- if (!rt->rt6i_peer)
+ if (!rt6_has_peer(rt))
rt6_bind_peer(rt, 0);
rt->rt6i_peer_genid = rt6_peer_genid();
}
@@ -1042,7 +1049,10 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info*)dst;
+ dst_confirm(dst);
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
+ struct net *net = dev_net(dst->dev);
+
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU) {
u32 features = dst_metric(dst, RTAX_FEATURES);
@@ -1051,9 +1061,39 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
dst_metric_set(dst, RTAX_FEATURES, features);
}
dst_metric_set(dst, RTAX_MTU, mtu);
+ rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
}
+void ip6_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
+ int oif, __be32 mark)
+{
+ const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
+ struct dst_entry *dst;
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = mark;
+ fl6.flowi6_flags = FLOWI_FLAG_PRECOW_METRICS;
+ fl6.daddr = iph->daddr;
+ fl6.saddr = iph->saddr;
+ fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (!dst->error)
+ ip6_rt_update_pmtu(dst, ntohl(mtu));
+ dst_release(dst);
+}
+EXPORT_SYMBOL_GPL(ip6_update_pmtu);
+
+void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
+{
+ ip6_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
+
static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
@@ -1110,7 +1150,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
if (unlikely(!idev))
return ERR_PTR(-ENODEV);
- rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
+ rt = ip6_dst_alloc(net, dev, 0, NULL);
if (unlikely(!rt)) {
in6_dev_put(idev);
dst = ERR_PTR(-ENOMEM);
@@ -1292,7 +1332,7 @@ int ip6_route_add(struct fib6_config *cfg)
if (!table)
goto out;
- rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
+ rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
if (!rt) {
err = -ENOMEM;
@@ -1697,116 +1737,6 @@ out:
}
/*
- * Handle ICMP "packet too big" messages
- * i.e. Path MTU discovery
- */
-
-static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net *net, u32 pmtu, int ifindex)
-{
- struct rt6_info *rt, *nrt;
- int allfrag = 0;
-again:
- rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
- if (!rt)
- return;
-
- if (rt6_check_expired(rt)) {
- ip6_del_rt(rt);
- goto again;
- }
-
- if (pmtu >= dst_mtu(&rt->dst))
- goto out;
-
- if (pmtu < IPV6_MIN_MTU) {
- /*
- * According to RFC2460, PMTU is set to the IPv6 Minimum Link
- * MTU (1280) and a fragment header should always be included
- * after a node receiving Too Big message reporting PMTU is
- * less than the IPv6 Minimum Link MTU.
- */
- pmtu = IPV6_MIN_MTU;
- allfrag = 1;
- }
-
- /* New mtu received -> path was valid.
- They are sent only in response to data packets,
- so that this nexthop apparently is reachable. --ANK
- */
- dst_confirm(&rt->dst);
-
- /* Host route. If it is static, it would be better
- not to override it, but add new one, so that
- when cache entry will expire old pmtu
- would return automatically.
- */
- if (rt->rt6i_flags & RTF_CACHE) {
- dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&rt->dst, RTAX_FEATURES, features);
- }
- rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
- rt->rt6i_flags |= RTF_MODIFIED;
- goto out;
- }
-
- /* Network route.
- Two cases are possible:
- 1. It is connected route. Action: COW
- 2. It is gatewayed route or NONEXTHOP route. Action: clone it.
- */
- if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
- nrt = rt6_alloc_cow(rt, daddr, saddr);
- else
- nrt = rt6_alloc_clone(rt, daddr);
-
- if (nrt) {
- dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
- }
-
- /* According to RFC 1981, detecting PMTU increase shouldn't be
- * happened within 5 mins, the recommended timer is 10 mins.
- * Here this route expiration time is set to ip6_rt_mtu_expires
- * which is 10 mins. After 10 mins the decreased pmtu is expired
- * and detecting PMTU increase will be automatically happened.
- */
- rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires);
- nrt->rt6i_flags |= RTF_DYNAMIC;
- ip6_ins_rt(nrt);
- }
-out:
- dst_release(&rt->dst);
-}
-
-void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net_device *dev, u32 pmtu)
-{
- struct net *net = dev_net(dev);
-
- /*
- * RFC 1981 states that a node "MUST reduce the size of the packets it
- * is sending along the path" that caused the Packet Too Big message.
- * Since it's not possible in the general case to determine which
- * interface was used to send the original packet, we update the MTU
- * on the interface that will be used to send future packets. We also
- * update the MTU on the interface that received the Packet Too Big in
- * case the original packet was forced out that interface with
- * SO_BINDTODEVICE or similar. This is the next best thing to the
- * correct behaviour, which would be to update the MTU on all
- * interfaces.
- */
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
-}
-
-/*
* Misc support functions
*/
@@ -1814,8 +1744,8 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest)
{
struct net *net = dev_net(ort->dst.dev);
- struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
- ort->dst.dev, 0);
+ struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
+ ort->rt6i_table);
if (rt) {
rt->dst.input = ort->dst.input;
@@ -2099,8 +2029,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
bool anycast)
{
struct net *net = dev_net(idev->dev);
- struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
- net->loopback_dev, 0);
+ struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
int err;
if (!rt) {
@@ -2521,7 +2450,9 @@ static int rt6_fill_node(struct net *net,
else
expires = INT_MAX;
- peer = rt->rt6i_peer;
+ peer = NULL;
+ if (rt6_has_peer(rt))
+ peer = rt6_peer_ptr(rt);
ts = tsage = 0;
if (peer && peer->tcp_ts_stamp) {
ts = peer->tcp_ts;
@@ -2998,6 +2929,31 @@ static struct pernet_operations ip6_route_net_ops = {
.exit = ip6_route_net_exit,
};
+static int __net_init ipv6_inetpeer_init(struct net *net)
+{
+ struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL);
+
+ if (!bp)
+ return -ENOMEM;
+ inet_peer_base_init(bp);
+ net->ipv6.peers = bp;
+ return 0;
+}
+
+static void __net_exit ipv6_inetpeer_exit(struct net *net)
+{
+ struct inet_peer_base *bp = net->ipv6.peers;
+
+ net->ipv6.peers = NULL;
+ inetpeer_invalidate_tree(bp);
+ kfree(bp);
+}
+
+static struct pernet_operations ipv6_inetpeer_ops = {
+ .init = ipv6_inetpeer_init,
+ .exit = ipv6_inetpeer_exit,
+};
+
static struct notifier_block ip6_route_dev_notifier = {
.notifier_call = ip6_route_dev_notify,
.priority = 0,
@@ -3022,10 +2978,14 @@ int __init ip6_route_init(void)
if (ret)
goto out_dst_entries;
- ret = register_pernet_subsys(&ip6_route_net_ops);
+ ret = register_pernet_subsys(&ipv6_inetpeer_ops);
if (ret)
goto out_fib6_init;
+ ret = register_pernet_subsys(&ip6_route_net_ops);
+ if (ret)
+ goto out_register_inetpeer;
+
ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
/* Registering of the loopback is done before this portion of code,
@@ -3072,6 +3032,8 @@ out_fib6_init_late:
fib6_cleanup_late();
out_register_subsys:
unregister_pernet_subsys(&ip6_route_net_ops);
+out_register_inetpeer:
+ unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_fib6_init:
fib6_gc_cleanup();
out_dst_entries:
@@ -3087,6 +3049,7 @@ void ip6_route_cleanup(void)
fib6_rules_cleanup();
xfrm6_fini();
fib6_gc_cleanup();
+ unregister_pernet_subsys(&ipv6_inetpeer_ops);
unregister_pernet_subsys(&ip6_route_net_ops);
dst_entries_destroy(&ip6_dst_blackhole_ops);
kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 60415711563f..49aea94c9be3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -527,9 +527,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -551,7 +548,17 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
skb->dev,
iph->daddr,
iph->saddr);
- if (t == NULL || t->parms.iph.daddr == 0)
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+ err = 0;
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0)
goto out;
err = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3a9aec29581a..26a88623940b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -415,6 +415,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
} else
dst_hold(dst);
+ dst->ops->update_pmtu(dst, ntohl(info));
+
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
@@ -522,7 +524,6 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
done:
if (opt && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
- dst_release(dst);
return err;
}
@@ -1733,42 +1734,24 @@ do_time_wait:
goto discard_it;
}
-static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it)
+static struct inet_peer *tcp_v6_get_peer(struct sock *sk)
{
struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
- struct inet_peer *peer;
-
- if (!rt ||
- !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) {
- peer = inet_getpeer_v6(&np->daddr, 1);
- *release_it = true;
- } else {
- if (!rt->rt6i_peer)
- rt6_bind_peer(rt, 1);
- peer = rt->rt6i_peer;
- *release_it = false;
- }
-
- return peer;
-}
-
-static void *tcp_v6_tw_get_peer(struct sock *sk)
-{
- const struct inet6_timewait_sock *tw6 = inet6_twsk(sk);
- const struct inet_timewait_sock *tw = inet_twsk(sk);
- if (tw->tw_family == AF_INET)
- return tcp_v4_tw_get_peer(sk);
-
- return inet_getpeer_v6(&tw6->tw_v6_daddr, 1);
+ /* If we don't have a valid cached route, or we're doing IP
+ * options which make the IPv6 header destination address
+ * different from our peer's, do not bother with this.
+ */
+ if (!rt || !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr))
+ return NULL;
+ return rt6_get_peer_create(rt);
}
static struct timewait_sock_ops tcp6_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct tcp6_timewait_sock),
.twsk_unique = tcp_twsk_unique,
.twsk_destructor= tcp_twsk_destructor,
- .twsk_getpeer = tcp_v6_tw_get_peer,
};
static const struct inet_connection_sock_af_ops ipv6_specific = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f05099fc5901..051ad481973f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -479,6 +479,9 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (sk == NULL)
return;
+ if (type == ICMPV6_PKT_TOOBIG)
+ ip6_sk_update_pmtu(skb, sk, info);
+
np = inet6_sk(sk);
if (!icmpv6_err_convert(type, code, &err) && !np->recverr)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 8625fba96db9..d7494845efbf 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -99,9 +99,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
if (!xdst->u.rt6.rt6i_idev)
return -ENODEV;
- xdst->u.rt6.rt6i_peer = rt->rt6i_peer;
- if (rt->rt6i_peer)
- atomic_inc(&rt->rt6i_peer->refcnt);
+ rt6_transfer_peer(&xdst->u.rt6, rt);
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
@@ -223,8 +221,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
- if (likely(xdst->u.rt6.rt6i_peer))
- inet_putpeer(xdst->u.rt6.rt6i_peer);
+ if (rt6_has_peer(&xdst->u.rt6)) {
+ struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
+ inet_putpeer(peer);
+ }
xfrm_dst_destroy(xdst);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-27 06:56:21 +0000