aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig42
-rw-r--r--net/ipv4/Makefile4
-rw-r--r--net/ipv4/af_inet.c46
-rw-r--r--net/ipv4/ah4.c27
-rw-r--r--net/ipv4/arp.c25
-rw-r--r--net/ipv4/datagram.c11
-rw-r--r--net/ipv4/devinet.c110
-rw-r--r--net/ipv4/esp4.c104
-rw-r--r--net/ipv4/fib_frontend.c105
-rw-r--r--net/ipv4/fib_hash.c1133
-rw-r--r--net/ipv4/fib_lookup.h10
-rw-r--r--net/ipv4/fib_rules.c25
-rw-r--r--net/ipv4/fib_semantics.c257
-rw-r--r--net/ipv4/fib_trie.c272
-rw-r--r--net/ipv4/icmp.c240
-rw-r--r--net/ipv4/igmp.c45
-rw-r--r--net/ipv4/inet_connection_sock.c27
-rw-r--r--net/ipv4/inet_timewait_sock.c2
-rw-r--r--net/ipv4/inetpeer.c148
-rw-r--r--net/ipv4/ip_gre.c57
-rw-r--r--net/ipv4/ip_input.c2
-rw-r--r--net/ipv4/ip_output.c345
-rw-r--r--net/ipv4/ipip.c41
-rw-r--r--net/ipv4/ipmr.c79
-rw-r--r--net/ipv4/netfilter.c36
-rw-r--r--net/ipv4/netfilter/Kconfig13
-rw-r--r--net/ipv4/netfilter/Makefile1
-rw-r--r--net/ipv4/netfilter/arp_tables.c5
-rw-r--r--net/ipv4/netfilter/ip_tables.c5
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c7
-rw-r--r--net/ipv4/netfilter/ipt_LOG.c3
-rw-r--r--net/ipv4/netfilter/ipt_addrtype.c134
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c2
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c17
-rw-r--r--net/ipv4/netfilter/nf_nat_amanda.c8
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c33
-rw-r--r--net/ipv4/netfilter/nf_nat_snmp_basic.c9
-rw-r--r--net/ipv4/netfilter/nf_nat_standalone.c9
-rw-r--r--net/ipv4/raw.c39
-rw-r--r--net/ipv4/route.c1182
-rw-r--r--net/ipv4/syncookies.c25
-rw-r--r--net/ipv4/tcp.c20
-rw-r--r--net/ipv4/tcp_bic.c2
-rw-r--r--net/ipv4/tcp_cubic.c47
-rw-r--r--net/ipv4/tcp_highspeed.c2
-rw-r--r--net/ipv4/tcp_htcp.c2
-rw-r--r--net/ipv4/tcp_hybla.c2
-rw-r--r--net/ipv4/tcp_illinois.c2
-rw-r--r--net/ipv4/tcp_input.c9
-rw-r--r--net/ipv4/tcp_ipv4.c37
-rw-r--r--net/ipv4/tcp_lp.c2
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv4/tcp_scalable.c2
-rw-r--r--net/ipv4/tcp_timer.c3
-rw-r--r--net/ipv4/tcp_vegas.c2
-rw-r--r--net/ipv4/tcp_veno.c2
-rw-r--r--net/ipv4/tcp_westwood.c2
-rw-r--r--net/ipv4/tcp_yeah.c2
-rw-r--r--net/ipv4/udp.c139
-rw-r--r--net/ipv4/xfrm4_policy.c74
-rw-r--r--net/ipv4/xfrm4_state.c20
61 files changed, 1997 insertions, 3061 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index a5a1050595d..cbb505ba932 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -55,45 +55,9 @@ config IP_ADVANCED_ROUTER
If unsure, say N here.
-choice
- prompt "Choose IP: FIB lookup algorithm (choose FIB_HASH if unsure)"
- depends on IP_ADVANCED_ROUTER
- default ASK_IP_FIB_HASH
-
-config ASK_IP_FIB_HASH
- bool "FIB_HASH"
- ---help---
- Current FIB is very proven and good enough for most users.
-
-config IP_FIB_TRIE
- bool "FIB_TRIE"
- ---help---
- Use new experimental LC-trie as FIB lookup algorithm.
- This improves lookup performance if you have a large
- number of routes.
-
- LC-trie is a longest matching prefix lookup algorithm which
- performs better than FIB_HASH for large routing tables.
- But, it consumes more memory and is more complex.
-
- LC-trie is described in:
-
- IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
- IEEE Journal on Selected Areas in Communications, 17(6):1083-1092,
- June 1999
-
- An experimental study of compression methods for dynamic tries
- Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002.
- <http://www.csc.kth.se/~snilsson/software/dyntrie2/>
-
-endchoice
-
-config IP_FIB_HASH
- def_bool ASK_IP_FIB_HASH || !IP_ADVANCED_ROUTER
-
config IP_FIB_TRIE_STATS
bool "FIB TRIE statistics"
- depends on IP_FIB_TRIE
+ depends on IP_ADVANCED_ROUTER
---help---
Keep track of statistics on structure of FIB TRIE table.
Useful for testing and measuring TRIE performance.
@@ -140,6 +104,9 @@ config IP_ROUTE_VERBOSE
handled by the klogd daemon which is responsible for kernel messages
("man klogd").
+config IP_ROUTE_CLASSID
+ bool
+
config IP_PNP
bool "IP: kernel level autoconfiguration"
help
@@ -657,4 +624,3 @@ config TCP_MD5SIG
on the Internet.
If unsure, say N.
-
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 4978d22f9a7..0dc772d0d12 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -10,12 +10,10 @@ obj-y := route.o inetpeer.o protocol.o \
tcp_minisocks.o tcp_cong.o \
datagram.o raw.o udp.o udplite.o \
arp.o icmp.o devinet.o af_inet.o igmp.o \
- fib_frontend.o fib_semantics.o \
+ fib_frontend.o fib_semantics.o fib_trie.o \
inet_fragment.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
-obj-$(CONFIG_IP_FIB_HASH) += fib_hash.o
-obj-$(CONFIG_IP_FIB_TRIE) += fib_trie.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 45b89d7bda5..807d83c02ef 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1101,23 +1101,20 @@ int sysctl_ip_dynaddr __read_mostly;
static int inet_sk_reselect_saddr(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
- int err;
- struct rtable *rt;
__be32 old_saddr = inet->inet_saddr;
- __be32 new_saddr;
__be32 daddr = inet->inet_daddr;
+ struct rtable *rt;
+ __be32 new_saddr;
if (inet->opt && inet->opt->srr)
daddr = inet->opt->faddr;
/* Query new route. */
- err = ip_route_connect(&rt, daddr, 0,
- RT_CONN_FLAGS(sk),
- sk->sk_bound_dev_if,
- sk->sk_protocol,
- inet->inet_sport, inet->inet_dport, sk, 0);
- if (err)
- return err;
+ rt = ip_route_connect(daddr, 0, RT_CONN_FLAGS(sk),
+ sk->sk_bound_dev_if, sk->sk_protocol,
+ inet->inet_sport, inet->inet_dport, sk, false);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
sk_setup_caps(sk, &rt->dst);
@@ -1160,25 +1157,16 @@ int inet_sk_rebuild_header(struct sock *sk)
daddr = inet->inet_daddr;
if (inet->opt && inet->opt->srr)
daddr = inet->opt->faddr;
-{
- struct flowi fl = {
- .oif = sk->sk_bound_dev_if,
- .mark = sk->sk_mark,
- .fl4_dst = daddr,
- .fl4_src = inet->inet_saddr,
- .fl4_tos = RT_CONN_FLAGS(sk),
- .proto = sk->sk_protocol,
- .flags = inet_sk_flowi_flags(sk),
- .fl_ip_sport = inet->inet_sport,
- .fl_ip_dport = inet->inet_dport,
- };
-
- security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0);
-}
- if (!err)
+ rt = ip_route_output_ports(sock_net(sk), sk, daddr, inet->inet_saddr,
+ inet->inet_dport, inet->inet_sport,
+ sk->sk_protocol, RT_CONN_FLAGS(sk),
+ sk->sk_bound_dev_if);
+ if (!IS_ERR(rt)) {
+ err = 0;
sk_setup_caps(sk, &rt->dst);
- else {
+ } else {
+ err = PTR_ERR(rt);
+
/* Routing failed... */
sk->sk_route_caps = 0;
/*
@@ -1231,7 +1219,7 @@ out:
return err;
}
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
struct iphdr *iph;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 86961bec70a..4286fd3cc0e 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -201,11 +201,14 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
top_iph->ttl = 0;
top_iph->check = 0;
- ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
+ if (x->props.flags & XFRM_STATE_ALIGN4)
+ ah->hdrlen = (XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
+ else
+ ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2;
ah->reserved = 0;
ah->spi = x->id.spi;
- ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output);
+ ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
sg_init_table(sg, nfrags);
skb_to_sgvec(skb, sg, 0, skb->len);
@@ -299,9 +302,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
nexthdr = ah->nexthdr;
ah_hlen = (ah->hdrlen + 2) << 2;
- if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
- ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
- goto out;
+ if (x->props.flags & XFRM_STATE_ALIGN4) {
+ if (ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_full_len) &&
+ ah_hlen != XFRM_ALIGN4(sizeof(*ah) + ahp->icv_trunc_len))
+ goto out;
+ } else {
+ if (ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_full_len) &&
+ ah_hlen != XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len))
+ goto out;
+ }
if (!pskb_may_pull(skb, ah_hlen))
goto out;
@@ -450,8 +459,12 @@ static int ah_init_state(struct xfrm_state *x)
BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
- x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
- ahp->icv_trunc_len);
+ if (x->props.flags & XFRM_STATE_ALIGN4)
+ x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) +
+ ahp->icv_trunc_len);
+ else
+ x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
+ ahp->icv_trunc_len);
if (x->props.mode == XFRM_MODE_TUNNEL)
x->props.header_len += sizeof(struct iphdr);
x->data = ahp;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7927589813b..090d273d786 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -433,14 +433,13 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
{
- struct flowi fl = { .fl4_dst = sip,
- .fl4_src = tip };
struct rtable *rt;
int flag = 0;
/*unsigned long now; */
struct net *net = dev_net(dev);
- if (ip_route_output_key(net, &rt, &fl) < 0)
+ rt = ip_route_output(net, sip, tip, 0, 0);
+ if (IS_ERR(rt))
return 1;
if (rt->dst.dev != dev) {
NET_INC_STATS_BH(net, LINUX_MIB_ARPFILTER);
@@ -1061,12 +1060,10 @@ static int arp_req_set(struct net *net, struct arpreq *r,
if (r->arp_flags & ATF_PERM)
r->arp_flags |= ATF_COM;
if (dev == NULL) {
- struct flowi fl = { .fl4_dst = ip,
- .fl4_tos = RTO_ONLINK };
- struct rtable *rt;
- err = ip_route_output_key(net, &rt, &fl);
- if (err != 0)
- return err;
+ struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
+
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
dev = rt->dst.dev;
ip_rt_put(rt);
if (!dev)
@@ -1177,7 +1174,6 @@ static int arp_req_delete_public(struct net *net, struct arpreq *r,
static int arp_req_delete(struct net *net, struct arpreq *r,
struct net_device *dev)
{
- int err;
__be32 ip;
if (r->arp_flags & ATF_PUBL)
@@ -1185,12 +1181,9 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
if (dev == NULL) {
- struct flowi fl = { .fl4_dst = ip,
- .fl4_tos = RTO_ONLINK };
- struct rtable *rt;
- err = ip_route_output_key(net, &rt, &fl);
- if (err != 0)
- return err;
+ struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
dev = rt->dst.dev;
ip_rt_put(rt);
if (!dev)
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 174be6caa5c..85bd24ca4f6 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -46,11 +46,12 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (!saddr)
saddr = inet->mc_addr;
}
- err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr,
- RT_CONN_FLAGS(sk), oif,
- sk->sk_protocol,
- inet->inet_sport, usin->sin_port, sk, 1);
- if (err) {
+ rt = ip_route_connect(usin->sin_addr.s_addr, saddr,
+ RT_CONN_FLAGS(sk), oif,
+ sk->sk_protocol,
+ inet->inet_sport, usin->sin_port, sk, true);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
if (err == -ENETUNREACH)
IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return err;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 748cb5b337b..6d85800daeb 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -51,6 +51,7 @@
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/slab.h>
+#include <linux/hash.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
@@ -92,6 +93,71 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
};
+/* inet_addr_hash's shifting is dependent upon this IN4_ADDR_HSIZE
+ * value. So if you change this define, make appropriate changes to
+ * inet_addr_hash as well.
+ */
+#define IN4_ADDR_HSIZE 256
+static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
+static DEFINE_SPINLOCK(inet_addr_hash_lock);
+
+static inline unsigned int inet_addr_hash(struct net *net, __be32 addr)
+{
+ u32 val = (__force u32) addr ^ hash_ptr(net, 8);
+
+ return ((val ^ (val >> 8) ^ (val >> 16) ^ (val >> 24)) &
+ (IN4_ADDR_HSIZE - 1));
+}
+
+static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
+{
+ unsigned int hash = inet_addr_hash(net, ifa->ifa_local);
+
+ spin_lock(&inet_addr_hash_lock);
+ hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
+ spin_unlock(&inet_addr_hash_lock);
+}
+
+static void inet_hash_remove(struct in_ifaddr *ifa)
+{
+ spin_lock(&inet_addr_hash_lock);
+ hlist_del_init_rcu(&ifa->hash);
+ spin_unlock(&inet_addr_hash_lock);
+}
+
+/**
+ * __ip_dev_find - find the first device with a given source address.
+ * @net: the net namespace
+ * @addr: the source address
+ * @devref: if true, take a reference on the found device
+ *
+ * If a caller uses devref=false, it should be protected by RCU, or RTNL
+ */
+struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
+{
+ unsigned int hash = inet_addr_hash(net, addr);
+ struct net_device *result = NULL;
+ struct in_ifaddr *ifa;
+ struct hlist_node *node;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) {
+ struct net_device *dev = ifa->ifa_dev->dev;
+
+ if (!net_eq(dev_net(dev), net))
+ continue;
+ if (ifa->ifa_local == addr) {
+ result = dev;
+ break;
+ }
+ }
+ if (result && devref)
+ dev_hold(result);
+ rcu_read_unlock();
+ return result;
+}
+EXPORT_SYMBOL(__ip_dev_find);
+
static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
@@ -265,6 +331,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
}
if (!do_promote) {
+ inet_hash_remove(ifa);
*ifap1 = ifa->ifa_next;
rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid);
@@ -281,6 +348,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
/* 2. Unlink it */
*ifap = ifa1->ifa_next;
+ inet_hash_remove(ifa1);
/* 3. Announce address deletion */
@@ -368,6 +436,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
ifa->ifa_next = *ifap;
*ifap = ifa;
+ inet_hash_insert(dev_net(in_dev->dev), ifa);
+
/* Send message first, then call notifier.
Notifier will trigger FIB update, so that
listeners of netlink will know about new ifaddr */
@@ -521,6 +591,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
if (tb[IFA_ADDRESS] == NULL)
tb[IFA_ADDRESS] = tb[IFA_LOCAL];
+ INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_prefixlen = ifm->ifa_prefixlen;
ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
ifa->ifa_flags = ifm->ifa_flags;
@@ -670,7 +741,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
ifap = &ifa->ifa_next) {
if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
sin_orig.sin_addr.s_addr ==
- ifa->ifa_address) {
+ ifa->ifa_local) {
break; /* found */
}
}
@@ -728,6 +799,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
if (!ifa) {
ret = -ENOBUFS;
ifa = inet_alloc_ifa();
+ INIT_HLIST_NODE(&ifa->hash);
if (!ifa)
break;
if (colon)
@@ -1030,6 +1102,21 @@ static inline bool inetdev_valid_mtu(unsigned mtu)
return mtu >= 68;
}
+static void inetdev_send_gratuitous_arp(struct net_device *dev,
+ struct in_device *in_dev)
+
+{
+ struct in_ifaddr *ifa = in_dev->ifa_list;
+
+ if (!ifa)
+ return;
+
+ arp_send(ARPOP_REQUEST, ETH_P_ARP,
+ ifa->ifa_local, dev,
+ ifa->ifa_local, NULL,
+ dev->dev_addr, NULL);
+}
+
/* Called only under RTNL semaphore */
static int inetdev_event(struct notifier_block *this, unsigned long event,
@@ -1069,6 +1156,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
struct in_ifaddr *ifa = inet_alloc_ifa();
if (ifa) {
+ INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_local =
ifa->ifa_address = htonl(INADDR_LOOPBACK);
ifa->ifa_prefixlen = 8;
@@ -1082,18 +1170,13 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
}
ip_mc_up(in_dev);
/* fall through */
- case NETDEV_NOTIFY_PEERS:
case NETDEV_CHANGEADDR:
+ if (!IN_DEV_ARP_NOTIFY(in_dev))
+ break;
+ /* fall through */
+ case NETDEV_NOTIFY_PEERS:
/* Send gratuitous ARP to notify of link change */
- if (IN_DEV_ARP_NOTIFY(in_dev)) {
- struct in_ifaddr *ifa = in_dev->ifa_list;
-
- if (ifa)
- arp_send(ARPOP_REQUEST, ETH_P_ARP,
- ifa->ifa_address, dev,
- ifa->ifa_address, NULL,
- dev->dev_addr, NULL);
- }
+ inetdev_send_gratuitous_arp(dev, in_dev);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);
@@ -1710,6 +1793,11 @@ static struct rtnl_af_ops inet_af_ops = {
void __init devinet_init(void)
{
+ int i;
+
+ for (i = 0; i < IN4_ADDR_HSIZE; i++)
+ INIT_HLIST_HEAD(&inet_addr_lst[i]);
+
register_pernet_subsys(&devinet_ops);
register_gifconf(PF_INET, inet_gifconf);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index e42a905180f..03f994bcf7d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -33,11 +33,14 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
*
* TODO: Use spare space in skb for this where possible.
*/
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
{
unsigned int len;
- len = crypto_aead_ivsize(aead);
+ len = seqhilen;
+
+ len += crypto_aead_ivsize(aead);
+
if (len) {
len += crypto_aead_alignmask(aead) &
~(crypto_tfm_ctx_alignment() - 1);
@@ -52,10 +55,15 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags)
return kmalloc(len, GFP_ATOMIC);
}
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp)
+static inline __be32 *esp_tmp_seqhi(void *tmp)
+{
+ return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+}
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
{
return crypto_aead_ivsize(aead) ?
- PTR_ALIGN((u8 *)tmp, crypto_aead_alignmask(aead) + 1) : tmp;
+ PTR_ALIGN((u8 *)tmp + seqhilen,
+ crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
}
static inline struct aead_givcrypt_request *esp_tmp_givreq(
@@ -122,6 +130,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
int plen;
int tfclen;
int nfrags;
+ int assoclen;
+ int sglists;
+ int seqhilen;
+ __be32 *seqhi;
/* skb is pure payload to encrypt */
@@ -151,14 +163,25 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
goto error;
nfrags = err;
- tmp = esp_alloc_tmp(aead, nfrags + 1);
+ assoclen = sizeof(*esph);
+ sglists = 1;
+ seqhilen = 0;
+
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists += 2;
+ seqhilen += sizeof(__be32);
+ assoclen += seqhilen;
+ }
+
+ tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
if (!tmp)
goto error;
- iv = esp_tmp_iv(aead, tmp);
+ seqhi = esp_tmp_seqhi(tmp);
+ iv = esp_tmp_iv(aead, tmp, seqhilen);
req = esp_tmp_givreq(aead, iv);
asg = esp_givreq_sg(aead, req);
- sg = asg + 1;
+ sg = asg + sglists;
/* Fill padding... */
tail = skb_tail_pointer(trailer);
@@ -215,19 +238,27 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
}
esph->spi = x->id.spi;
- esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output);
+ esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
sg_init_table(sg, nfrags);
skb_to_sgvec(skb, sg,
esph->enc_data + crypto_aead_ivsize(aead) - skb->data,
clen + alen);
- sg_init_one(asg, esph, sizeof(*esph));
+
+ if ((x->props.flags & XFRM_STATE_ESN)) {
+ sg_init_table(asg, 3);
+ sg_set_buf(asg, &esph->spi, sizeof(__be32));
+ *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+ sg_set_buf(asg + 1, seqhi, seqhilen);
+ sg_set_buf(asg + 2, &esph->seq_no, sizeof(__be32));
+ } else
+ sg_init_one(asg, esph, sizeof(*esph));
aead_givcrypt_set_callback(req, 0, esp_output_done, skb);
aead_givcrypt_set_crypt(req, sg, sg, clen, iv);
- aead_givcrypt_set_assoc(req, asg, sizeof(*esph));
+ aead_givcrypt_set_assoc(req, asg, assoclen);
aead_givcrypt_set_giv(req, esph->enc_data,
- XFRM_SKB_CB(skb)->seq.output);
+ XFRM_SKB_CB(skb)->seq.output.low);
ESP_SKB_CB(skb)->tmp = tmp;
err = crypto_aead_givencrypt(req);
@@ -346,6 +377,10 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
struct sk_buff *trailer;
int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
int nfrags;
+ int assoclen;
+ int sglists;
+ int seqhilen;
+ __be32 *seqhi;
void *tmp;
u8 *iv;
struct scatterlist *sg;
@@ -362,16 +397,27 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
goto out;
nfrags = err;
+ assoclen = sizeof(*esph);
+ sglists = 1;
+ seqhilen = 0;
+
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists += 2;
+ seqhilen += sizeof(__be32);
+ assoclen += seqhilen;
+ }
+
err = -ENOMEM;
- tmp = esp_alloc_tmp(aead, nfrags + 1);
+ tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
if (!tmp)
goto out;