Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-2.6.26
diff --git a/include/linux/in6.h b/include/linux/in6.h
index 2a61c82..f674000 100644
--- a/include/linux/in6.h
+++ b/include/linux/in6.h
@@ -249,4 +249,15 @@
* IP6T_SO_GET_REVISION_TARGET 69
*/
+/* RFC5014: Source address selection */
+#define IPV6_ADDR_PREFERENCES 72
+
+#define IPV6_PREFER_SRC_TMP 0x0001
+#define IPV6_PREFER_SRC_PUBLIC 0x0002
+#define IPV6_PREFER_SRC_PUBTMP_DEFAULT 0x0100
+#define IPV6_PREFER_SRC_COA 0x0004
+#define IPV6_PREFER_SRC_HOME 0x0400
+#define IPV6_PREFER_SRC_CGA 0x0008
+#define IPV6_PREFER_SRC_NONCGA 0x0800
+
#endif
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 4aaefc3..c9ba0da 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -274,8 +274,29 @@
__be32 flow_label;
__u32 frag_size;
- __s16 hop_limit;
- __s16 mcast_hops;
+
+ /*
+ * Packed in 16bits.
+ * Omit one shift by by putting the signed field at MSB.
+ */
+#if defined(__BIG_ENDIAN_BITFIELD)
+ __s16 hop_limit:9;
+ __u16 __unused_1:7;
+#else
+ __u16 __unused_1:7;
+ __s16 hop_limit:9;
+#endif
+
+#if defined(__BIG_ENDIAN_BITFIELD)
+ /* Packed in 16bits. */
+ __s16 mcast_hops:9;
+ __u16 __unused_2:6,
+ mc_loop:1;
+#else
+ __u16 mc_loop:1,
+ __unused_2:6;
+ __s16 mcast_hops:9;
+#endif
int mcast_oif;
/* pktoption flags */
@@ -298,11 +319,14 @@
} rxopt;
/* sockopt flags */
- __u8 mc_loop:1,
- recverr:1,
+ __u8 recverr:1,
sndflow:1,
pmtudisc:2,
- ipv6only:1;
+ ipv6only:1,
+ srcprefs:3; /* 001: prefer temporary address
+ * 010: prefer public address
+ * 100: prefer care-of address
+ */
__u8 tclass;
__u32 dst_cookie;
@@ -315,9 +339,8 @@
struct sk_buff *pktoptions;
struct {
struct ipv6_txoptions *opt;
- struct rt6_info *rt;
- int hop_limit;
- int tclass;
+ u8 hop_limit;
+ u8 tclass;
} cork;
};
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 232da20..c9276c7 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -78,6 +78,7 @@
extern int ipv6_dev_get_saddr(struct net_device *dev,
struct in6_addr *daddr,
+ unsigned int srcprefs,
struct in6_addr *saddr);
extern int ipv6_get_lladdr(struct net_device *dev,
struct in6_addr *addr,
@@ -123,8 +124,6 @@
extern void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len);
-extern int ipv6_get_hoplimit(struct net_device *dev);
-
/*
* anycast prototypes (anycast.c)
*/
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index b6db16d..a42cd63 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -136,7 +136,7 @@
unsigned int flags;
unsigned int fragsize;
struct ip_options *opt;
- struct rtable *rt;
+ struct dst_entry *dst;
int length; /* Total length of all frames */
__be32 addr;
struct flowi fl;
diff --git a/include/net/ip.h b/include/net/ip.h
index 9f50d4f..6d7bcd5 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -347,10 +347,11 @@
extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag);
extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
extern void ip_options_fragment(struct sk_buff *skb);
-extern int ip_options_compile(struct ip_options *opt, struct sk_buff *skb);
-extern int ip_options_get(struct ip_options **optp,
+extern int ip_options_compile(struct net *net,
+ struct ip_options *opt, struct sk_buff *skb);
+extern int ip_options_get(struct net *net, struct ip_options **optp,
unsigned char *data, int optlen);
-extern int ip_options_get_from_user(struct ip_options **optp,
+extern int ip_options_get_from_user(struct net *net, struct ip_options **optp,
unsigned char __user *data, int optlen);
extern void ip_options_undo(struct ip_options * opt);
extern void ip_forward_options(struct sk_buff *skb);
@@ -361,7 +362,8 @@
*/
extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
-extern int ip_cmsg_send(struct msghdr *msg, struct ipcm_cookie *ipc);
+extern int ip_cmsg_send(struct net *net,
+ struct msghdr *msg, struct ipcm_cookie *ipc);
extern int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen);
extern int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen);
extern int compat_ip_setsockopt(struct sock *sk, int level,
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 0e2895c..3ae6799 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -30,9 +30,12 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
-#define RT6_LOOKUP_F_IFACE 0x1
-#define RT6_LOOKUP_F_REACHABLE 0x2
-#define RT6_LOOKUP_F_HAS_SADDR 0x4
+#define RT6_LOOKUP_F_IFACE 0x00000001
+#define RT6_LOOKUP_F_REACHABLE 0x00000002
+#define RT6_LOOKUP_F_HAS_SADDR 0x00000004
+#define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008
+#define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010
+#define RT6_LOOKUP_F_SRCPREF_COA 0x00000020
extern struct rt6_info *ip6_null_entry;
@@ -88,6 +91,8 @@
const struct in6_addr *addr,
int anycast);
+extern int ip6_dst_hoplimit(struct dst_entry *dst);
+
/*
* support functions for ND
*
diff --git a/include/net/protocol.h b/include/net/protocol.h
index ad8c584..8d024d7 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -39,7 +39,8 @@
int (*gso_send_check)(struct sk_buff *skb);
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
int features);
- int no_policy;
+ unsigned int no_policy:1,
+ netns_ok:1;
};
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c435620..bed7d43 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1045,6 +1045,23 @@
return NULL;
}
+static __inline__
+void xfrm_flowi_addr_get(struct flowi *fl,
+ xfrm_address_t *saddr, xfrm_address_t *daddr,
+ unsigned short family)
+{
+ switch(family) {
+ case AF_INET:
+ memcpy(&saddr->a4, &fl->fl4_src, sizeof(saddr->a4));
+ memcpy(&daddr->a4, &fl->fl4_dst, sizeof(daddr->a4));
+ break;
+ case AF_INET6:
+ ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->fl6_src);
+ ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->fl6_dst);
+ break;
+ }
+}
+
static __inline__ int
__xfrm4_state_addr_check(struct xfrm_state *x,
xfrm_address_t *daddr, xfrm_address_t *saddr)
diff --git a/net/core/dev.c b/net/core/dev.c
index f973e38..aebd086 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2615,7 +2615,7 @@
if (v == SEQ_START_TOKEN)
seq_puts(seq, "Type Device Function\n");
- else {
+ else if (pt->dev == NULL || pt->dev->nd_net == seq_file_net(seq)) {
if (pt->type == htons(ETH_P_ALL))
seq_puts(seq, "ALL ");
else
@@ -2639,7 +2639,8 @@
static int ptype_seq_open(struct inode *inode, struct file *file)
{
- return seq_open(file, &ptype_seq_ops);
+ return seq_open_net(inode, file, &ptype_seq_ops,
+ sizeof(struct seq_net_private));
}
static const struct file_operations ptype_seq_fops = {
@@ -2647,7 +2648,7 @@
.open = ptype_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = seq_release_net,
};
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 44f5ce1..06cfb0b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -243,6 +243,23 @@
}
EXPORT_SYMBOL(build_ehash_secret);
+static inline int inet_netns_ok(struct net *net, int protocol)
+{
+ int hash;
+ struct net_protocol *ipprot;
+
+ if (net == &init_net)
+ return 1;
+
+ hash = protocol & (MAX_INET_PROTOS - 1);
+ ipprot = rcu_dereference(inet_protos[hash]);
+
+ if (ipprot == NULL)
+ /* raw IP is OK */
+ return 1;
+ return ipprot->netns_ok;
+}
+
/*
* Create an inet socket.
*/
@@ -259,9 +276,6 @@
int try_loading_module = 0;
int err;
- if (net != &init_net)
- return -EAFNOSUPPORT;
-
if (sock->type != SOCK_RAW &&
sock->type != SOCK_DGRAM &&
!inet_ehash_secret)
@@ -320,6 +334,10 @@
if (answer->capability > 0 && !capable(answer->capability))
goto out_rcu_unlock;
+ err = -EAFNOSUPPORT;
+ if (!inet_netns_ok(net, protocol))
+ goto out_rcu_unlock;
+
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_no_check = answer->no_check;
@@ -446,7 +464,7 @@
if (addr_len < sizeof(struct sockaddr_in))
goto out;
- chk_addr_ret = inet_addr_type(&init_net, addr->sin_addr.s_addr);
+ chk_addr_ret = inet_addr_type(sk->sk_net, addr->sin_addr.s_addr);
/* Not specified by any standard per-se, however it breaks too
* many applications when removed. It is unfortunate since
@@ -1114,7 +1132,7 @@
};
security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&init_net, &rt, &fl, sk, 0);
+ err = ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 0);
}
if (!err)
sk_setup_caps(sk, &rt->u.dst);
@@ -1284,17 +1302,20 @@
.gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp_tso_segment,
.no_policy = 1,
+ .netns_ok = 1,
};
static struct net_protocol udp_protocol = {
.handler = udp_rcv,
.err_handler = udp_err,
.no_policy = 1,
+ .netns_ok = 1,
};
static struct net_protocol icmp_protocol = {
.handler = icmp_rcv,
.no_policy = 1,
+ .netns_ok = 1,
};
static int __init init_ipv4_mibs(void)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index efe01df..832473e 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -242,7 +242,7 @@
return -EINVAL;
}
- neigh->type = inet_addr_type(&init_net, addr);
+ neigh->type = inet_addr_type(dev->nd_net, addr);
parms = in_dev->arp_parms;
__neigh_parms_put(neigh->parms);
@@ -341,14 +341,14 @@
switch (IN_DEV_ARP_ANNOUNCE(in_dev)) {
default:
case 0: /* By default announce any local IP */
- if (skb && inet_addr_type(&init_net, ip_hdr(skb)->saddr) == RTN_LOCAL)
+ if (skb && inet_addr_type(dev->nd_net, ip_hdr(skb)->saddr) == RTN_LOCAL)
saddr = ip_hdr(skb)->saddr;
break;
case 1: /* Restrict announcements of saddr in same subnet */
if (!skb)
break;
saddr = ip_hdr(skb)->saddr;
- if (inet_addr_type(&init_net, saddr) == RTN_LOCAL) {
+ if (inet_addr_type(dev->nd_net, saddr) == RTN_LOCAL) {
/* saddr should be known to target */
if (inet_addr_onlink(in_dev, target, saddr))
break;
@@ -424,7 +424,7 @@
int flag = 0;
/*unsigned long now; */
- if (ip_route_output_key(&init_net, &rt, &fl) < 0)
+ if (ip_route_output_key(dev->nd_net, &rt, &fl) < 0)
return 1;
if (rt->u.dst.dev != dev) {
NET_INC_STATS_BH(LINUX_MIB_ARPFILTER);
@@ -477,7 +477,7 @@
paddr = skb->rtable->rt_gateway;
- if (arp_set_predefined(inet_addr_type(&init_net, paddr), haddr, paddr, dev))
+ if (arp_set_predefined(inet_addr_type(dev->nd_net, paddr), haddr, paddr, dev))
return 0;
n = __neigh_lookup(&arp_tbl, &paddr, dev, 1);
@@ -709,6 +709,7 @@
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
+ struct net *net = dev->nd_net;
/* arp_rcv below verifies the ARP header and verifies the device
* is ARP'able.
@@ -804,7 +805,7 @@
/* Special case: IPv4 duplicate address detection packet (RFC2131) */
if (sip == 0) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
- inet_addr_type(&init_net, tip) == RTN_LOCAL &&
+ inet_addr_type(net, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
dev->dev_addr, sha);
@@ -834,7 +835,7 @@
goto out;
} else if (IN_DEV_FORWARD(in_dev)) {
if (addr_type == RTN_UNICAST && rt->u.dst.dev != dev &&
- (arp_fwd_proxy(in_dev, rt) || pneigh_lookup(&arp_tbl, &init_net, &tip, dev, 0))) {
+ (arp_fwd_proxy(in_dev, rt) || pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n)
neigh_release(n);
@@ -864,7 +865,7 @@
*/
if (n == NULL &&
arp->ar_op == htons(ARPOP_REPLY) &&
- inet_addr_type(&init_net, sip) == RTN_UNICAST)
+ inet_addr_type(net, sip) == RTN_UNICAST)
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
@@ -911,9 +912,6 @@
{
struct arphdr *arp;
- if (dev->nd_net != &init_net)
- goto freeskb;
-
/* ARP header, plus 2 device addresses, plus 2 IP addresses. */
if (!pskb_may_pull(skb, arp_hdr_len(dev)))
goto freeskb;
@@ -1198,9 +1196,6 @@
{
struct net_device *dev = ptr;
- if (dev->nd_net != &init_net)
- return NOTIFY_DONE;
-
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&arp_tbl, dev);
@@ -1382,13 +1377,29 @@
.release = seq_release_net,
};
-static int __init arp_proc_init(void)
+
+static int __net_init arp_net_init(struct net *net)
{
- if (!proc_net_fops_create(&init_net, "arp", S_IRUGO, &arp_seq_fops))
+ if (!proc_net_fops_create(net, "arp", S_IRUGO, &arp_seq_fops))
return -ENOMEM;
return 0;
}
+static void __net_exit arp_net_exit(struct net *net)
+{
+ proc_net_remove(net, "arp");
+}
+
+static struct pernet_operations arp_net_ops = {
+ .init = arp_net_init,
+ .exit = arp_net_exit,
+};
+
+static int __init arp_proc_init(void)
+{
+ return register_pernet_subsys(&arp_net_ops);
+}
+
#else /* CONFIG_PROC_FS */
static int __init arp_proc_init(void)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f9c5c4d..d13c5f1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -333,7 +333,7 @@
.dport = ireq->rmt_port } } };
security_req_classify_flow(req, &fl);
- if (ip_route_output_flow(&init_net, &rt, &fl, sk, 0)) {
+ if (ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 0)) {
IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 3b2e5ad..8b448c4 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -204,8 +204,11 @@
if ((qp->q.last_in&FIRST_IN) && qp->q.fragments != NULL) {
struct sk_buff *head = qp->q.fragments;
+ struct net *net;
+
+ net = container_of(qp->q.net, struct net, ipv4.frags);
/* Send an ICMP "Fragment Reassembly Timeout" message. */
- if ((head->dev = dev_get_by_index(&init_net, qp->iif)) != NULL) {
+ if ((head->dev = dev_get_by_index(net, qp->iif)) != NULL) {
icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
dev_put(head->dev);
}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index e3a0c78..2aeea5d 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -160,6 +160,7 @@
struct ip_ra_chain *ra;
u8 protocol = ip_hdr(skb)->protocol;
struct sock *last = NULL;
+ struct net_device *dev = skb->dev;
read_lock(&ip_ra_lock);
for (ra = ip_ra_chain; ra; ra = ra->next) {
@@ -170,7 +171,8 @@
*/
if (sk && inet_sk(sk)->num == protocol &&
(!sk->sk_bound_dev_if ||
- sk->sk_bound_dev_if == skb->dev->ifindex)) {
+ sk->sk_bound_dev_if == dev->ifindex) &&
+ sk->sk_net == dev->nd_net) {
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) {
read_unlock(&ip_ra_lock);
@@ -197,6 +199,8 @@
static int ip_local_deliver_finish(struct sk_buff *skb)
{
+ struct net *net = skb->dev->nd_net;
+
__skb_pull(skb, ip_hdrlen(skb));
/* Point into the IP datagram, just past the header. */
@@ -212,7 +216,8 @@
raw = raw_local_deliver(skb, protocol);
hash = protocol & (MAX_INET_PROTOS - 1);
- if ((ipprot = rcu_dereference(inet_protos[hash])) != NULL) {
+ ipprot = rcu_dereference(inet_protos[hash]);
+ if (ipprot != NULL && (net == &init_net || ipprot->netns_ok)) {
int ret;
if (!ipprot->no_policy) {
@@ -286,7 +291,7 @@
opt = &(IPCB(skb)->opt);
opt->optlen = iph->ihl*4 - sizeof(struct iphdr);
- if (ip_options_compile(opt, skb)) {
+ if (ip_options_compile(dev->nd_net, opt, skb)) {
IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
goto drop;
}
@@ -373,9 +378,6 @@
struct iphdr *iph;
u32 len;
- if (dev->nd_net != &init_net)
- goto drop;
-
/* When the interface is in promisc. mode, drop all the crap
* that it receives, do not try to analyse it.
*/
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index aeed4e58..87cc122 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -145,7 +145,7 @@
__be32 addr;
memcpy(&addr, sptr+soffset-1, 4);
- if (inet_addr_type(&init_net, addr) != RTN_LOCAL) {
+ if (inet_addr_type(skb->dst->dev->nd_net, addr) != RTN_LOCAL) {
dopt->ts_needtime = 1;
soffset += 8;
}
@@ -248,7 +248,8 @@
* If opt == NULL, then skb->data should point to IP header.
*/
-int ip_options_compile(struct ip_options * opt, struct sk_buff * skb)
+int ip_options_compile(struct net *net,
+ struct ip_options * opt, struct sk_buff * skb)
{
int l;
unsigned char * iph;
@@ -389,7 +390,7 @@
{
__be32 addr;
memcpy(&addr, &optptr[optptr[2]-1], 4);
- if (inet_addr_type(&init_net, addr) == RTN_UNICAST)
+ if (inet_addr_type(net, addr) == RTN_UNICAST)
break;
if (skb)
timeptr = (__be32*)&optptr[optptr[2]+3];
@@ -506,13 +507,13 @@
GFP_KERNEL);
}
-static int ip_options_get_finish(struct ip_options **optp,
+static int ip_options_get_finish(struct net *net, struct ip_options **optp,
struct ip_options *opt, int optlen)
{
while (optlen & 3)
opt->__data[optlen++] = IPOPT_END;
opt->optlen = optlen;
- if (optlen && ip_options_compile(opt, NULL)) {
+ if (optlen && ip_options_compile(net, opt, NULL)) {
kfree(opt);
return -EINVAL;
}
@@ -521,7 +522,8 @@
return 0;
}
-int ip_options_get_from_user(struct ip_options **optp, unsigned char __user *data, int optlen)
+int ip_options_get_from_user(struct net *net, struct ip_options **optp,
+ unsigned char __user *data, int optlen)
{
struct ip_options *opt = ip_options_get_alloc(optlen);
@@ -531,10 +533,11 @@
kfree(opt);
return -EFAULT;
}
- return ip_options_get_finish(optp, opt, optlen);
+ return ip_options_get_finish(net, optp, opt, optlen);
}
-int ip_options_get(struct ip_options **optp, unsigned char *data, int optlen)
+int ip_options_get(struct net *net, struct ip_options **optp,
+ unsigned char *data, int optlen)
{
struct ip_options *opt = ip_options_get_alloc(optlen);
@@ -542,7 +545,7 @@
return -ENOMEM;
if (optlen)
memcpy(opt->__data, data, optlen);
- return ip_options_get_finish(optp, opt, optlen);
+ return ip_options_get_finish(net, optp, opt, optlen);
}
void ip_forward_options(struct sk_buff *skb)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index dc494ea..913266c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -351,7 +351,7 @@
* itself out.
*/
security_sk_classify_flow(sk, &fl);
- if (ip_route_output_flow(&init_net, &rt, &fl, sk, 0))
+ if (ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 0))
goto no_route;
}
sk_setup_caps(sk, &rt->u.dst);
@@ -825,7 +825,7 @@
inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ?
rt->u.dst.dev->mtu :
dst_mtu(rt->u.dst.path);
- inet->cork.rt = rt;
+ inet->cork.dst = &rt->u.dst;
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
@@ -834,7 +834,7 @@
transhdrlen += exthdrlen;
}
} else {
- rt = inet->cork.rt;
+ rt = (struct rtable *)inet->cork.dst;
if (inet->cork.flags & IPCORK_OPT)
opt = inet->cork.opt;
@@ -1083,7 +1083,7 @@
if (skb_queue_empty(&sk->sk_write_queue))
return -EINVAL;
- rt = inet->cork.rt;
+ rt = (struct rtable *)inet->cork.dst;
if (inet->cork.flags & IPCORK_OPT)
opt = inet->cork.opt;
@@ -1208,10 +1208,8 @@
inet->cork.flags &= ~IPCORK_OPT;
kfree(inet->cork.opt);
inet->cork.opt = NULL;
- if (inet->cork.rt) {
- ip_rt_put(inet->cork.rt);
- inet->cork.rt = NULL;
- }
+ dst_release(inet->cork.dst);
+ inet->cork.dst = NULL;
}
/*
@@ -1224,7 +1222,7 @@
struct sk_buff **tail_skb;
struct inet_sock *inet = inet_sk(sk);
struct ip_options *opt = NULL;
- struct rtable *rt = inet->cork.rt;
+ struct rtable *rt = (struct rtable *)inet->cork.dst;
struct iphdr *iph;
__be16 df = 0;
__u8 ttl;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index bb3cbe5..b854431 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -163,7 +163,7 @@
ip_cmsg_recv_security(msg, skb);
}
-int ip_cmsg_send(struct msghdr *msg, struct ipcm_cookie *ipc)
+int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
{
int err;
struct cmsghdr *cmsg;
@@ -176,7 +176,7 @@
switch (cmsg->cmsg_type) {
case IP_RETOPTS:
err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
- err = ip_options_get(&ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40);
+ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40);
if (err)
return err;
break;
@@ -449,7 +449,8 @@
struct ip_options * opt = NULL;
if (optlen > 40 || optlen < 0)
goto e_inval;
- err = ip_options_get_from_user(&opt, optval, optlen);
+ err = ip_options_get_from_user(sk->sk_net, &opt,
+ optval, optlen);
if (err)
break;
if (inet->is_icsk) {
@@ -589,13 +590,13 @@
err = 0;
break;
}
- dev = ip_dev_find(&init_net, mreq.imr_address.s_addr);
+ dev = ip_dev_find(sk->sk_net, mreq.imr_address.s_addr);
if (dev) {
mreq.imr_ifindex = dev->ifindex;
dev_put(dev);
}
} else
- dev = __dev_get_by_index(&init_net, mreq.imr_ifindex);
+ dev = __dev_get_by_index(sk->sk_net, mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b433b48..3f68a93 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -499,7 +499,7 @@
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
- err = ip_cmsg_send(msg, &ipc);
+ err = ip_cmsg_send(sk->sk_net, msg, &ipc);
if (err)
goto out;
if (ipc.opt)
@@ -553,7 +553,7 @@
}
security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1);
+ err = ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 1);
}
if (err)
goto done;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1a47719..649d00a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2425,14 +2425,29 @@
.seq_fops = &tcp4_seq_fops,
};
+static int tcp4_proc_init_net(struct net *net)
+{
+ return tcp_proc_register(net, &tcp4_seq_afinfo);
+}
+
+static void tcp4_proc_exit_net(struct net *net)
+{
+ tcp_proc_unregister(net, &tcp4_seq_afinfo);
+}
+
+static struct pernet_operations tcp4_net_ops = {
+ .init = tcp4_proc_init_net,
+ .exit = tcp4_proc_exit_net,
+};
+
int __init tcp4_proc_init(void)
{
- return tcp_proc_register(&init_net, &tcp4_seq_afinfo);
+ return register_pernet_subsys(&tcp4_net_ops);
}
void tcp4_proc_exit(void)
{
- tcp_proc_unregister(&init_net, &tcp4_seq_afinfo);
+ unregister_pernet_subsys(&tcp4_net_ops);
}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8c1f5ea..b37581d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -607,7 +607,7 @@
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
- err = ip_cmsg_send(msg, &ipc);
+ err = ip_cmsg_send(sk->sk_net, msg, &ipc);
if (err)
return err;
if (ipc.opt)
@@ -656,7 +656,7 @@
{ .sport = inet->sport,
.dport = dport } } };
security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1);
+ err = ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 1);
if (err) {
if (err == -ENETUNREACH)
IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
@@ -1701,14 +1701,29 @@
.seq_fops = &udp4_seq_fops,
};
+static int udp4_proc_init_net(struct net *net)
+{
+ return udp_proc_register(net, &udp4_seq_afinfo);
+}
+
+static void udp4_proc_exit_net(struct net *net)
+{
+ udp_proc_unregister(net, &udp4_seq_afinfo);
+}
+
+static struct pernet_operations udp4_net_ops = {
+ .init = udp4_proc_init_net,
+ .exit = udp4_proc_exit_net,
+};
+
int __init udp4_proc_init(void)
{
- return udp_proc_register(&init_net, &udp4_seq_afinfo);
+ return register_pernet_subsys(&udp4_net_ops);
}
void udp4_proc_exit(void)
{
- udp_proc_unregister(&init_net, &udp4_seq_afinfo);
+ unregister_pernet_subsys(&udp4_net_ops);
}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 8d42e34..53f3ed4 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -31,6 +31,7 @@
.handler = udplite_rcv,
.err_handler = udplite_err,
.no_policy = 1,
+ .netns_ok = 1,
};
DEFINE_PROTO_INUSE(udplite)
@@ -82,6 +83,31 @@
.seq_show = udp4_seq_show,
.seq_fops = &udplite4_seq_fops,
};
+
+static int udplite4_proc_init_net(struct net *net)
+{
+ return udp_proc_register(net, &udplite4_seq_afinfo);
+}
+
+static void udplite4_proc_exit_net(struct net *net)
+{
+ udp_proc_unregister(net, &udplite4_seq_afinfo);
+}
+
+static struct pernet_operations udplite4_net_ops = {
+ .init = udplite4_proc_init_net,
+ .exit = udplite4_proc_exit_net,
+};
+
+static __init int udplite4_proc_init(void)
+{
+ return register_pernet_subsys(&udplite4_net_ops);
+}
+#else
+static inline int udplite4_proc_init(void)
+{
+ return 0;
+}
#endif
void __init udplite4_register(void)
@@ -94,10 +120,8 @@
inet_register_protosw(&udplite4_protosw);
-#ifdef CONFIG_PROC_FS
- if (udp_proc_register(&init_net, &udplite4_seq_afinfo))
+ if (udplite4_proc_init())
printk(KERN_ERR "%s: Cannot register /proc!\n", __func__);
-#endif
return;
out_unregister_proto:
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4b86d38..8995488 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -877,20 +877,40 @@
/*
* Choose an appropriate source address (RFC3484)
*/
-struct ipv6_saddr_score {
- int addr_type;
- unsigned int attrs;
- int matchlen;
- int scope;
- unsigned int rule;
+enum {
+ IPV6_SADDR_RULE_INIT = 0,
+ IPV6_SADDR_RULE_LOCAL,
+ IPV6_SADDR_RULE_SCOPE,
+ IPV6_SADDR_RULE_PREFERRED,
+#ifdef CONFIG_IPV6_MIP6
+ IPV6_SADDR_RULE_HOA,
+#endif
+ IPV6_SADDR_RULE_OIF,
+ IPV6_SADDR_RULE_LABEL,
+#ifdef CONFIG_IPV6_PRIVACY
+ IPV6_SADDR_RULE_PRIVACY,
+#endif
+ IPV6_SADDR_RULE_ORCHID,
+ IPV6_SADDR_RULE_PREFIX,
+ IPV6_SADDR_RULE_MAX
};
-#define IPV6_SADDR_SCORE_LOCAL 0x0001
-#define IPV6_SADDR_SCORE_PREFERRED 0x0004
-#define IPV6_SADDR_SCORE_HOA 0x0008
-#define IPV6_SADDR_SCORE_OIF 0x0010
-#define IPV6_SADDR_SCORE_LABEL 0x0020
-#define IPV6_SADDR_SCORE_PRIVACY 0x0040
+struct ipv6_saddr_score {
+ int rule;
+ int addr_type;
+ struct inet6_ifaddr *ifa;
+ DECLARE_BITMAP(scorebits, IPV6_SADDR_RULE_MAX);
+ int scopedist;
+ int matchlen;
+};
+
+struct ipv6_saddr_dst {
+ struct in6_addr *addr;
+ int ifindex;
+ int scope;
+ int label;
+ unsigned int prefs;
+};
static inline int ipv6_saddr_preferred(int type)
{
@@ -900,28 +920,152 @@
return 0;
}
-int ipv6_dev_get_saddr(struct net_device *daddr_dev,
- struct in6_addr *daddr, struct in6_addr *saddr)
+static int ipv6_get_saddr_eval(struct ipv6_saddr_score *score,
+ struct ipv6_saddr_dst *dst,
+ int i)
{
- struct ipv6_saddr_score hiscore;
- struct inet6_ifaddr *ifa_result = NULL;
- struct net *net = daddr_dev->nd_net;
- int daddr_type = __ipv6_addr_type(daddr);
- int daddr_scope = __ipv6_addr_src_scope(daddr_type);
- int daddr_ifindex = daddr_dev ? daddr_dev->ifindex : 0;
- u32 daddr_label = ipv6_addr_label(daddr, daddr_type, daddr_ifindex);
- struct net_device *dev;
+ int ret;
- memset(&hiscore, 0, sizeof(hiscore));
+ if (i <= score->rule) {
+ switch (i) {
+ case IPV6_SADDR_RULE_SCOPE:
+ ret = score->scopedist;
+ break;
+ case IPV6_SADDR_RULE_PREFIX:
+ ret = score->matchlen;
+ break;
+ default:
+ ret = !!test_bit(i, score->scorebits);
+ }
+ goto out;
+ }
+
+ switch (i) {
+ case IPV6_SADDR_RULE_INIT:
+ /* Rule 0: remember if hiscore is not ready yet */
+ ret = !!score->ifa;
+ break;
+ case IPV6_SADDR_RULE_LOCAL:
+ /* Rule 1: Prefer same address */
+ ret = ipv6_addr_equal(&score->ifa->addr, dst->addr);
+ break;
+ case IPV6_SADDR_RULE_SCOPE:
+ /* Rule 2: Prefer appropriate scope
+ *
+ * ret
+ * ^
+ * -1 | d 15
+ * ---+--+-+---> scope
+ * |
+ * | d is scope of the destination.
+ * B-d | \
+ * | \ <- smaller scope is better if
+ * B-15 | \ if scope is enough for destinaion.
+ * | ret = B - scope (-1 <= scope >= d <= 15).
+ * d-C-1 | /
+ * |/ <- greater is better
+ * -C / if scope is not enough for destination.
+ * /| ret = scope - C (-1 <= d < scope <= 15).
+ *
+ * d - C - 1 < B -15 (for all -1 <= d <= 15).
+ * C > d + 14 - B >= 15 + 14 - B = 29 - B.
+ * Assume B = 0 and we get C > 29.
+ */
+ ret = __ipv6_addr_src_scope(score->addr_type);
+ if (ret >= dst->scope)
+ ret = -ret;
+ else
+ ret -= 128; /* 30 is enough */
+ score->scopedist = ret;
+ break;
+ case IPV6_SADDR_RULE_PREFERRED:
+ /* Rule 3: Avoid deprecated and optimistic addresses */
+ ret = ipv6_saddr_preferred(score->addr_type) ||
+ !(score->ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC));
+ break;
+#ifdef CONFIG_IPV6_MIP6
+ case IPV6_SADDR_RULE_HOA:
+ {
+ /* Rule 4: Prefer home address */
+ int prefhome = !(dst->prefs & IPV6_PREFER_SRC_COA);
+ ret = !(score->ifa->flags & IFA_F_HOMEADDRESS) ^ prefhome;
+ break;
+ }
+#endif
+ case IPV6_SADDR_RULE_OIF:
+ /* Rule 5: Prefer outgoing interface */
+ ret = (!dst->ifindex ||
+ dst->ifindex == score->ifa->idev->dev->ifindex);
+ break;
+ case IPV6_SADDR_RULE_LABEL:
+ /* Rule 6: Prefer matching label */
+ ret = ipv6_addr_label(&score->ifa->addr, score->addr_type,
+ score->ifa->idev->dev->ifindex) == dst->label;
+ break;
+#ifdef CONFIG_IPV6_PRIVACY
+ case IPV6_SADDR_RULE_PRIVACY:
+ {
+ /* Rule 7: Prefer public address
+ * Note: prefer temprary address if use_tempaddr >= 2
+ */
+ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ?
+ !!(dst->prefs & IPV6_PREFER_SRC_TMP) :
+ score->ifa->idev->cnf.use_tempaddr >= 2;
+ ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp;
+ break;
+ }
+#endif
+ case IPV6_SADDR_RULE_ORCHID:
+ /* Rule 8-: Prefer ORCHID vs ORCHID or
+ * non-ORCHID vs non-ORCHID
+ */
+ ret = !(ipv6_addr_orchid(&score->ifa->addr) ^
+ ipv6_addr_orchid(dst->addr));
+ break;
+ case IPV6_SADDR_RULE_PREFIX:
+ /* Rule 8: Use longest matching prefix */
+ score->matchlen = ret = ipv6_addr_diff(&score->ifa->addr,
+ dst->addr);
+ break;
+ default:
+ ret = 0;
+ }
+
+ if (ret)
+ __set_bit(i, score->scorebits);
+ score->rule = i;
+out:
+ return ret;
+}
+
+int ipv6_dev_get_saddr(struct net_device *dst_dev,
+ struct in6_addr *daddr, unsigned int prefs,
+ struct in6_addr *saddr)
+{
+ struct ipv6_saddr_score scores[2],
+ *score = &scores[0], *hiscore = &scores[1];
+ struct net *net = dst_dev->nd_net;
+ struct ipv6_saddr_dst dst;
+ struct net_device *dev;
+ int dst_type;
+
+ dst_type = __ipv6_addr_type(daddr);
+ dst.addr = daddr;
+ dst.ifindex = dst_dev ? dst_dev->ifindex : 0;
+ dst.scope = __ipv6_addr_src_scope(dst_type);
+ dst.label = ipv6_addr_label(daddr, dst_type, dst.ifindex);
+ dst.prefs = prefs;
+
+ hiscore->rule = -1;
+ hiscore->ifa = NULL;
read_lock(&dev_base_lock);
rcu_read_lock();
for_each_netdev(net, dev) {
struct inet6_dev *idev;
- struct inet6_ifaddr *ifa;
- /* Rule 0: Candidate Source Address (section 4)
+ /* Candidate Source Address (section 4)
* - multicast and link-local destination address,
* the set of candidate source address MUST only
* include addresses assigned to interfaces
@@ -933,9 +1077,9 @@
* belonging to the same site as the outgoing
* interface.)
*/
- if ((daddr_type & IPV6_ADDR_MULTICAST ||
- daddr_scope <= IPV6_ADDR_SCOPE_LINKLOCAL) &&
- daddr_dev && dev != daddr_dev)
+ if (((dst_type & IPV6_ADDR_MULTICAST) ||
+ dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) &&
+ dst.ifindex && dev->ifindex != dst.ifindex)
continue;
idev = __in6_dev_get(dev);
@@ -943,12 +1087,10 @@
continue;
read_lock_bh(&idev->lock);
- for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) {
- struct ipv6_saddr_score score;
+ for (score->ifa = idev->addr_list; score->ifa; score->ifa = score->ifa->if_next) {
+ int i;
- score.addr_type = __ipv6_addr_type(&ifa->addr);
-
- /* Rule 0:
+ /*
* - Tentative Address (RFC2462 section 5.4)
* - A tentative address is not considered
* "assigned to an interface" in the traditional
@@ -958,11 +1100,14 @@
* addresses, and the unspecified address MUST
* NOT be included in a candidate set.
*/
- if ((ifa->flags & IFA_F_TENTATIVE) &&
- (!(ifa->flags & IFA_F_OPTIMISTIC)))
+ if ((score->ifa->flags & IFA_F_TENTATIVE) &&
+ (!(score->ifa->flags & IFA_F_OPTIMISTIC)))
continue;
- if (unlikely(score.addr_type == IPV6_ADDR_ANY ||
- score.addr_type & IPV6_ADDR_MULTICAST)) {
+
+ score->addr_type = __ipv6_addr_type(&score->ifa->addr);
+
+ if (unlikely(score->addr_type == IPV6_ADDR_ANY ||
+ score->addr_type & IPV6_ADDR_MULTICAST)) {
LIMIT_NETDEBUG(KERN_DEBUG
"ADDRCONF: unspecified / multicast address "
"assigned as unicast address on %s",
@@ -970,201 +1115,59 @@
continue;
}
- score.attrs = 0;
- score.matchlen = 0;
- score.scope = 0;
- score.rule = 0;
+ score->rule = -1;
+ bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX);
- if (ifa_result == NULL) {
- /* record it if the first available entry */
- goto record_it;
- }
+ for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) {
+ int minihiscore, miniscore;
- /* Rule 1: Prefer same address */
- if (hiscore.rule < 1) {
- if (ipv6_addr_equal(&ifa_result->addr, daddr))
- hiscore.attrs |= IPV6_SADDR_SCORE_LOCAL;
- hiscore.rule++;
- }
- if (ipv6_addr_equal(&ifa->addr, daddr)) {
- score.attrs |= IPV6_SADDR_SCORE_LOCAL;
- if (!(hiscore.attrs & IPV6_SADDR_SCORE_LOCAL)) {
- score.rule = 1;
- goto record_it;
- }
- } else {
- if (hiscore.attrs & IPV6_SADDR_SCORE_LOCAL)
- continue;
- }
+ minihiscore = ipv6_get_saddr_eval(hiscore, &dst, i);
+ miniscore = ipv6_get_saddr_eval(score, &dst, i);
- /* Rule 2: Prefer appropriate scope */
- if (hiscore.rule < 2) {
- hiscore.scope = __ipv6_addr_src_scope(hiscore.addr_type);
- hiscore.rule++;
- }
- score.scope = __ipv6_addr_src_scope(score.addr_type);
- if (hiscore.scope < score.scope) {
- if (hiscore.scope < daddr_scope) {
- score.rule = 2;
- goto record_it;
- } else
- continue;
- } else if (score.scope < hiscore.scope) {
- if (score.scope < daddr_scope)
- break; /* addresses sorted by scope */
- else {
- score.rule = 2;
- goto record_it;
+ if (minihiscore > miniscore) {
+ if (i == IPV6_SADDR_RULE_SCOPE &&
+ score->scopedist > 0) {
+ /*
+ * special case:
+ * each remaining entry
+ * has too small (not enough)
+ * scope, because ifa entries
+ * are sorted by their scope
+ * values.
+ */
+ goto try_nextdev;
+ }
+ break;
+ } else if (minihiscore < miniscore) {
+ struct ipv6_saddr_score *tmp;
+
+ if (hiscore->ifa)
+ in6_ifa_put(hiscore->ifa);
+
+ in6_ifa_hold(score->ifa);
+
+ tmp = hiscore;
+ hiscore = score;
+ score = tmp;
+
+ /* restore our iterator */
+ score->ifa = hiscore->ifa;
+
+ break;
}
}
-
- /* Rule 3: Avoid deprecated and optimistic addresses */
- if (hiscore.rule < 3) {
- if (ipv6_saddr_preferred(hiscore.addr_type) ||
- (((ifa_result->flags &
- (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0)))
- hiscore.attrs |= IPV6_SADDR_SCORE_PREFERRED;
- hiscore.rule++;
- }
- if (ipv6_saddr_preferred(score.addr_type) ||
- (((ifa->flags &
- (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) {
- score.attrs |= IPV6_SADDR_SCORE_PREFERRED;
- if (!(hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)) {
- score.rule = 3;
- goto record_it;
- }
- } else {
- if (hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)
- continue;
- }
-
- /* Rule 4: Prefer home address */
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
- if (hiscore.rule < 4) {
- if (ifa_result->flags & IFA_F_HOMEADDRESS)
- hiscore.attrs |= IPV6_SADDR_SCORE_HOA;
- hiscore.rule++;
- }
- if (ifa->flags & IFA_F_HOMEADDRESS) {
- score.attrs |= IPV6_SADDR_SCORE_HOA;
- if (!(ifa_result->flags & IFA_F_HOMEADDRESS)) {
- score.rule = 4;
- goto record_it;
- }
- } else {
- if (hiscore.attrs & IPV6_SADDR_SCORE_HOA)
- continue;
- }
-#else
- if (hiscore.rule < 4)
- hiscore.rule++;
-#endif
-
- /* Rule 5: Prefer outgoing interface */
- if (hiscore.rule < 5) {
- if (daddr_dev == NULL ||
- daddr_dev == ifa_result->idev->dev)
- hiscore.attrs |= IPV6_SADDR_SCORE_OIF;
- hiscore.rule++;
- }
- if (daddr_dev == NULL ||
- daddr_dev == ifa->idev->dev) {
- score.attrs |= IPV6_SADDR_SCORE_OIF;
- if (!(hiscore.attrs & IPV6_SADDR_SCORE_OIF)) {
- score.rule = 5;
- goto record_it;
- }
- } else {
- if (hiscore.attrs & IPV6_SADDR_SCORE_OIF)
- continue;
- }
-
- /* Rule 6: Prefer matching label */
- if (hiscore.rule < 6) {
- if (ipv6_addr_label(&ifa_result->addr,
- hiscore.addr_type,
- ifa_result->idev->dev->ifindex) == daddr_label)
- hiscore.attrs |= IPV6_SADDR_SCORE_LABEL;
- hiscore.rule++;
- }
- if (ipv6_addr_label(&ifa->addr,
- score.addr_type,
- ifa->idev->dev->ifindex) == daddr_label) {
- score.attrs |= IPV6_SADDR_SCORE_LABEL;
- if (!(hiscore.attrs & IPV6_SADDR_SCORE_LABEL)) {
- score.rule = 6;
- goto record_it;
- }
- } else {
- if (hiscore.attrs & IPV6_SADDR_SCORE_LABEL)
- continue;
- }
-
-#ifdef CONFIG_IPV6_PRIVACY
- /* Rule 7: Prefer public address
- * Note: prefer temprary address if use_tempaddr >= 2
- */
- if (hiscore.rule < 7) {
- if ((!(ifa_result->flags & IFA_F_TEMPORARY)) ^
- (ifa_result->idev->cnf.use_tempaddr >= 2))
- hiscore.attrs |= IPV6_SADDR_SCORE_PRIVACY;
- hiscore.rule++;
- }
- if ((!(ifa->flags & IFA_F_TEMPORARY)) ^
- (ifa->idev->cnf.use_tempaddr >= 2)) {
- score.attrs |= IPV6_SADDR_SCORE_PRIVACY;
- if (!(hiscore.attrs & IPV6_SADDR_SCORE_PRIVACY)) {
- score.rule = 7;
- goto record_it;
- }
- } else {
- if (hiscore.attrs & IPV6_SADDR_SCORE_PRIVACY)
- continue;
- }
-#else
- if (hiscore.rule < 7)
- hiscore.rule++;
-#endif
-
- /* Skip rule 8 for orchid -> non-orchid address pairs. */
- if (ipv6_addr_orchid(&ifa->addr) && !ipv6_addr_orchid(daddr))
- continue;
-
- /* Rule 8: Use longest matching prefix */
- if (hiscore.rule < 8) {
- hiscore.matchlen = ipv6_addr_diff(&ifa_result->addr, daddr);
- hiscore.rule++;
- }
- score.matchlen = ipv6_addr_diff(&ifa->addr, daddr);
- if (score.matchlen > hiscore.matchlen) {
- score.rule = 8;
- goto record_it;
- }
-#if 0
- else if (score.matchlen < hiscore.matchlen)
- continue;
-#endif
-
- /* Final Rule: choose first available one */
- continue;
-record_it:
- if (ifa_result)
- in6_ifa_put(ifa_result);
- in6_ifa_hold(ifa);
- ifa_result = ifa;
- hiscore = score;
}
+try_nextdev:
read_unlock_bh(&idev->lock);
}
rcu_read_unlock();
read_unlock(&dev_base_lock);
- if (!ifa_result)
+ if (!hiscore->ifa)
return -EADDRNOTAVAIL;
- ipv6_addr_copy(saddr, &ifa_result->addr);
- in6_ifa_put(ifa_result);
+ ipv6_addr_copy(saddr, &hiscore->ifa->addr);
+ in6_ifa_put(hiscore->ifa);
return 0;
}
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 5513740..e7a7fe2 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -84,8 +84,18 @@
if ((rule->flags & FIB_RULE_FIND_SADDR) &&
r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
struct in6_addr saddr;
+ unsigned int srcprefs = 0;
+
+ if (flags & RT6_LOOKUP_F_SRCPREF_TMP)
+ srcprefs |= IPV6_PREFER_SRC_TMP;
+ if (flags & RT6_LOOKUP_F_SRCPREF_PUBLIC)
+ srcprefs |= IPV6_PREFER_SRC_PUBLIC;
+ if (flags & RT6_LOOKUP_F_SRCPREF_COA)
+ srcprefs |= IPV6_PREFER_SRC_COA;
+
if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev,
- &flp->fl6_dst, &saddr))
+ &flp->fl6_dst, srcprefs,
+ &saddr))
goto again;
if (!ipv6_prefix_equal(&saddr, &r->src.addr,
r->src.plen))
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 6b5391a..8633241 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -464,9 +464,7 @@
else
hlimit = np->hop_limit;
if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
+ hlimit = ip6_dst_hoplimit(dst);
tclass = np->tclass;
if (tclass < 0)
@@ -560,9 +558,7 @@
else
hlimit = np->hop_limit;
if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
+ hlimit = ip6_dst_hoplimit(dst);
tclass = np->tclass;
if (tclass < 0)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 98762fd..d34aa61 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -237,9 +237,7 @@
if (np)
hlimit = np->hop_limit;
if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
+ hlimit = ip6_dst_hoplimit(dst);
tclass = -1;
if (np)
@@ -922,7 +920,9 @@
if (ipv6_addr_any(&fl->fl6_src)) {
err = ipv6_dev_get_saddr(ip6_dst_idev(*dst)->dev,
- &fl->fl6_dst, &fl->fl6_src);
+ &fl->fl6_dst,
+ sk ? inet6_sk(sk)->srcprefs : 0,
+ &fl->fl6_src);
if (err)
goto out_err_release;
}
@@ -1115,7 +1115,7 @@
/* need source address above miyazawa*/
}
dst_hold(&rt->u.dst);
- np->cork.rt = rt;
+ inet->cork.dst = &rt->u.dst;
inet->cork.fl = *fl;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
@@ -1136,7 +1136,7 @@
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
- rt = np->cork.rt;
+ rt = (struct rt6_info *)inet->cork.dst;
fl = &inet->cork.fl;
if (inet->cork.flags & IPCORK_OPT)
opt = np->cork.opt;
@@ -1381,9 +1381,9 @@
inet->cork.flags &= ~IPCORK_OPT;
kfree(np->cork.opt);
np->cork.opt = NULL;
- if (np->cork.rt) {
- dst_release(&np->cork.rt->u.dst);
- np->cork.rt = NULL;
+ if (inet->cork.dst) {
+ dst_release(inet->cork.dst);
+ inet->cork.dst = NULL;
inet->cork.flags &= ~IPCORK_ALLFRAG;
}
memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
@@ -1398,7 +1398,7 @@
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6hdr *hdr;
struct ipv6_txoptions *opt = np->cork.opt;
- struct rt6_info *rt = np->cork.rt;
+ struct rt6_info *rt = (struct rt6_info *)inet->cork.dst;
struct flowi *fl = &inet->cork.fl;
unsigned char proto = fl->proto;
int err = 0;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index c11c76c..dc6695c 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -617,7 +617,67 @@
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
+ case IPV6_ADDR_PREFERENCES:
+ {
+ unsigned int pref = 0;
+ unsigned int prefmask = ~0;
+
+ retv = -EINVAL;
+
+ /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
+ switch (val & (IPV6_PREFER_SRC_PUBLIC|
+ IPV6_PREFER_SRC_TMP|
+ IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
+ case IPV6_PREFER_SRC_PUBLIC:
+ pref |= IPV6_PREFER_SRC_PUBLIC;
+ break;
+ case IPV6_PREFER_SRC_TMP:
+ pref |= IPV6_PREFER_SRC_TMP;
+ break;
+ case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
+ break;
+ case 0:
+ goto pref_skip_pubtmp;
+ default:
+ goto e_inval;
+ }
+
+ prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
+ IPV6_PREFER_SRC_TMP);
+pref_skip_pubtmp:
+
+ /* check HOME/COA conflicts */
+ switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
+ case IPV6_PREFER_SRC_HOME:
+ break;
+ case IPV6_PREFER_SRC_COA:
+ pref |= IPV6_PREFER_SRC_COA;
+ case 0:
+ goto pref_skip_coa;
+ default:
+ goto e_inval;
+ }
+
+ prefmask &= ~IPV6_PREFER_SRC_COA;
+pref_skip_coa:
+
+ /* check CGA/NONCGA conflicts */
+ switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
+ case IPV6_PREFER_SRC_CGA:
+ case IPV6_PREFER_SRC_NONCGA:
+ case 0:
+ break;
+ default:
+ goto e_inval;
+ }
+
+ np->srcprefs = (np->srcprefs & prefmask) | pref;
+ retv = 0;
+
+ break;
+ }
}
+
release_sock(sk);
return retv;
@@ -904,9 +964,7 @@
dst = sk_dst_get(sk);
if (dst) {
if (val < 0)
- val = dst_metric(dst, RTAX_HOPLIMIT);
- if (val < 0)
- val = ipv6_get_hoplimit(dst->dev);
+ val = ip6_dst_hoplimit(dst);
dst_release(dst);
}
if (val < 0)
@@ -934,6 +992,24 @@
val = np->sndflow;
break;
+ case IPV6_ADDR_PREFERENCES:
+ val = 0;
+
+ if (np->srcprefs & IPV6_PREFER_SRC_TMP)
+ val |= IPV6_PREFER_SRC_TMP;
+ else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC)
+ val |= IPV6_PREFER_SRC_PUBLIC;
+ else {
+ /* XXX: should we return system default? */
+ val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT;
+ }
+
+ if (np->srcprefs & IPV6_PREFER_SRC_COA)
+ val |= IPV6_PREFER_SRC_COA;
+ else
+ val |= IPV6_PREFER_SRC_HOME;
+ break;
+
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e7d8e74..3f68a6e 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -546,7 +546,9 @@
override = 0;
in6_ifa_put(ifp);
} else {
- if (ipv6_dev_get_saddr(dev, daddr, &tmpaddr))
+ if (ipv6_dev_get_saddr(dev, daddr,
+ inet6_sk(dev->nd_net->ipv6.ndisc_sk)->srcprefs,
+ &tmpaddr))
return;
src_addr = &tmpaddr;
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a9e4235..548d076 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -885,9 +885,7 @@
else
hlimit = np->hop_limit;
if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
+ hlimit = ip6_dst_hoplimit(dst);
}
if (tclass < 0) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a4b5aee..06faa46 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -782,6 +782,15 @@
if (!ipv6_addr_any(&fl->fl6_src))
flags |= RT6_LOOKUP_F_HAS_SADDR;
+ else if (sk) {
+ unsigned int prefs = inet6_sk(sk)->srcprefs;
+ if (prefs & IPV6_PREFER_SRC_TMP)
+ flags |= RT6_LOOKUP_F_SRCPREF_TMP;
+ if (prefs & IPV6_PREFER_SRC_PUBLIC)
+ flags |= RT6_LOOKUP_F_SRCPREF_PUBLIC;
+ if (prefs & IPV6_PREFER_SRC_COA)
+ flags |= RT6_LOOKUP_F_SRCPREF_COA;
+ }
return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
}
@@ -1034,15 +1043,17 @@
return mtu;
}
-int ipv6_get_hoplimit(struct net_device *dev)
+int ip6_dst_hoplimit(struct dst_entry *dst)
{
- int hoplimit = ipv6_devconf.hop_limit;
- struct inet6_dev *idev;
-
- idev = in6_dev_get(dev);
- if (idev) {
- hoplimit = idev->cnf.hop_limit;
- in6_dev_put(idev);
+ int hoplimit = dst_metric(dst, RTAX_HOPLIMIT);
+ if (hoplimit < 0) {
+ struct net_device *dev = dst->dev;
+ struct inet6_dev *idev = in6_dev_get(dev);
+ if (idev) {
+ hoplimit = idev->cnf.hop_limit;
+ in6_dev_put(idev);
+ } else
+ hoplimit = ipv6_devconf.hop_limit;
}
return hoplimit;
}
@@ -2160,7 +2171,7 @@
else if (dst) {
struct in6_addr saddr_buf;
if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev,
- dst, &saddr_buf) == 0)
+ dst, 0, &saddr_buf) == 0)
NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 5f5d121..593d3ef 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -792,9 +792,7 @@
else
hlimit = np->hop_limit;
if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
+ hlimit = ip6_dst_hoplimit(dst);
}
if (tclass < 0) {
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 93e52e0..706c5c3 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -109,13 +109,28 @@
.seq_fops = &udplite6_seq_fops,
};
+static int udplite6_proc_init_net(struct net *net)
+{
+ return udp_proc_register(net, &udplite6_seq_afinfo);
+}
+
+static void udplite6_proc_exit_net(struct net *net)
+{
+ udp_proc_unregister(net, &udplite6_seq_afinfo);
+}
+
+static struct pernet_operations udplite6_net_ops = {
+ .init = udplite6_proc_init_net,
+ .exit = udplite6_proc_exit_net,
+};
+
int __init udplite6_proc_init(void)
{
- return udp_proc_register(&init_net, &udplite6_seq_afinfo);
+ return register_pernet_subsys(&udplite6_net_ops);
}
void udplite6_proc_exit(void)
{
- udp_proc_unregister(&init_net, &udplite6_seq_afinfo);
+ unregister_pernet_subsys(&udplite6_net_ops);
}
#endif
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index a4714d7..a71c7dd 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -59,9 +59,6 @@
xfrm_address_t *saddr, u8 proto)
{
struct xfrm_state *x = NULL;
- int wildcard = 0;
- xfrm_address_t *xany;
- int nh = 0;
int i = 0;
/* Allocate new secpath or COW existing one. */
@@ -83,10 +80,9 @@
goto drop;
}
- xany = (xfrm_address_t *)&in6addr_any;
-
for (i = 0; i < 3; i++) {
xfrm_address_t *dst, *src;
+
switch (i) {
case 0:
dst = daddr;
@@ -94,16 +90,13 @@
break;
case 1:
/* lookup state with wild-card source address */
- wildcard = 1;
dst = daddr;
- src = xany;
+ src = (xfrm_address_t *)&in6addr_any;
break;
- case 2:
default:
/* lookup state with wild-card addresses */
- wildcard = 1; /* XXX */
- dst = xany;
- src = xany;
+ dst = (xfrm_address_t *)&in6addr_any;
+ src = (xfrm_address_t *)&in6addr_any;
break;
}
@@ -113,39 +106,19 @@
spin_lock(&x->lock);
- if (wildcard) {
- if ((x->props.flags & XFRM_STATE_WILDRECV) == 0) {
- spin_unlock(&x->lock);
- xfrm_state_put(x);
- x = NULL;
- continue;
+ if ((!i || (x->props.flags & XFRM_STATE_WILDRECV)) &&
+ likely(x->km.state == XFRM_STATE_VALID) &&
+ !xfrm_state_check_expire(x)) {
+ spin_unlock(&x->lock);
+ if (x->type->input(x, skb) > 0) {
+ /* found a valid state */
+ break;
}
- }
-
- if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+ } else
spin_unlock(&x->lock);
- xfrm_state_put(x);
- x = NULL;
- continue;
- }
- if (xfrm_state_check_expire(x)) {
- spin_unlock(&x->lock);
- xfrm_state_put(x);
- x = NULL;
- continue;
- }
- spin_unlock(&x->lock);
-
- nh = x->type->input(x, skb);
- if (nh <= 0) {
- xfrm_state_put(x);
- x = NULL;
- continue;
- }
-
- /* Found a state */
- break;
+ xfrm_state_put(x);
+ x = NULL;
}
if (!x) {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index e96dafd..d92d1fc 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -58,7 +58,7 @@
return -EHOSTUNREACH;
ipv6_dev_get_saddr(ip6_dst_idev(dst)->dev,
- (struct in6_addr *)&daddr->a6,
+ (struct in6_addr *)&daddr->a6, 0,
(struct in6_addr *)&saddr->a6);
dst_release(dst);
return 0;
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index dc817e0..5a46bb9 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -49,125 +49,102 @@
x->props.family = AF_INET6;
}
+/* distribution counting sort function for xfrm_state and xfrm_tmpl */
+static int
+__xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass)
+{
+ int i;
+ int class[XFRM_MAX_DEPTH];
+ int count[maxclass];
+
+ memset(count, 0, sizeof(count));
+
+ for (i = 0; i < n; i++) {
+ int c;
+ class[i] = c = cmp(src[i]);
+ count[c]++;
+ }
+
+ for (i = 2; i < maxclass; i++)
+ count[i] += count[i - 1];
+
+ for (i = 0; i < n; i++) {
+ dst[count[class[i] - 1]++] = src[i];
+ src[i] = 0;
+ }
+
+ return 0;
+}
+
+/*
+ * Rule for xfrm_state:
+ *
+ * rule 1: select IPsec transport except AH
+ * rule 2: select MIPv6 RO or inbound trigger
+ * rule 3: select IPsec transport AH
+ * rule 4: select IPsec tunnel
+ * rule 5: others
+ */
+static int __xfrm6_state_sort_cmp(void *p)
+{
+ struct xfrm_state *v = p;
+
+ switch (v->props.mode) {
+ case XFRM_MODE_TRANSPORT:
+ if (v->id.proto != IPPROTO_AH)
+ return 1;
+ else
+ return 3;
+#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+ case XFRM_MODE_ROUTEOPTIMIZATION:
+ case XFRM_MODE_IN_TRIGGER:
+ return 2;
+#endif
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ return 4;
+ }
+ return 5;
+}
+
static int
__xfrm6_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n)
{
- int i;
- int j = 0;
+ return __xfrm6_sort((void **)dst, (void **)src, n,
+ __xfrm6_state_sort_cmp, 6);
+}
- /* Rule 1: select IPsec transport except AH */
- for (i = 0; i < n; i++) {
- if (src[i]->props.mode == XFRM_MODE_TRANSPORT &&
- src[i]->id.proto != IPPROTO_AH) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
- if (j == n)
- goto end;
-
- /* Rule 2: select MIPv6 RO or inbound trigger */
+/*
+ * Rule for xfrm_tmpl:
+ *
+ * rule 1: select IPsec transport
+ * rule 2: select MIPv6 RO or inbound trigger
+ * rule 3: select IPsec tunnel
+ * rule 4: others
+ */
+static int __xfrm6_tmpl_sort_cmp(void *p)
+{
+ struct xfrm_tmpl *v = p;
+ switch (v->mode) {
+ case XFRM_MODE_TRANSPORT:
+ return 1;
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
- for (i = 0; i < n; i++) {
- if (src[i] &&
- (src[i]->props.mode == XFRM_MODE_ROUTEOPTIMIZATION ||
- src[i]->props.mode == XFRM_MODE_IN_TRIGGER)) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
- if (j == n)
- goto end;
+ case XFRM_MODE_ROUTEOPTIMIZATION:
+ case XFRM_MODE_IN_TRIGGER:
+ return 2;
#endif
-
- /* Rule 3: select IPsec transport AH */
- for (i = 0; i < n; i++) {
- if (src[i] &&
- src[i]->props.mode == XFRM_MODE_TRANSPORT &&
- src[i]->id.proto == IPPROTO_AH) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ return 3;
}
- if (j == n)
- goto end;
-
- /* Rule 4: select IPsec tunnel */
- for (i = 0; i < n; i++) {
- if (src[i] &&
- (src[i]->props.mode == XFRM_MODE_TUNNEL ||
- src[i]->props.mode == XFRM_MODE_BEET)) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
- if (likely(j == n))
- goto end;
-
- /* Final rule */
- for (i = 0; i < n; i++) {
- if (src[i]) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
-
- end:
- return 0;
+ return 4;
}
static int
__xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n)
{
- int i;
- int j = 0;
-
- /* Rule 1: select IPsec transport */
- for (i = 0; i < n; i++) {
- if (src[i]->mode == XFRM_MODE_TRANSPORT) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
- if (j == n)
- goto end;
-
- /* Rule 2: select MIPv6 RO or inbound trigger */
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
- for (i = 0; i < n; i++) {
- if (src[i] &&
- (src[i]->mode == XFRM_MODE_ROUTEOPTIMIZATION ||
- src[i]->mode == XFRM_MODE_IN_TRIGGER)) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
- if (j == n)
- goto end;
-#endif
-
- /* Rule 3: select IPsec tunnel */
- for (i = 0; i < n; i++) {
- if (src[i] &&
- (src[i]->mode == XFRM_MODE_TUNNEL ||
- src[i]->mode == XFRM_MODE_BEET)) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
- if (likely(j == n))
- goto end;
-
- /* Final rule */
- for (i = 0; i < n; i++) {
- if (src[i]) {
- dst[j++] = src[i];
- src[i] = NULL;
- }
- }
-
- end:
- return 0;
+ return __xfrm6_sort((void **)dst, (void **)src, n,
+ __xfrm6_tmpl_sort_cmp, 5);
}
int xfrm6_extract_header(struct sk_buff *skb)
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 639fe8a..c2b2781 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -140,12 +140,26 @@
EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup);
+static int __xfrm6_tunnel_spi_check(u32 spi)
+{
+ struct xfrm6_tunnel_spi *x6spi;
+ int index = xfrm6_tunnel_spi_hash_byspi(spi);
+ struct hlist_node *pos;
+
+ hlist_for_each_entry(x6spi, pos,
+ &xfrm6_tunnel_spi_byspi[index],
+ list_byspi) {
+ if (x6spi->spi == spi)
+ return -1;
+ }
+ return index;
+}
+
static u32 __xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr)
{
u32 spi;
struct xfrm6_tunnel_spi *x6spi;
- struct hlist_node *pos;
- unsigned index;
+ int index;
if (xfrm6_tunnel_spi < XFRM6_TUNNEL_SPI_MIN ||
xfrm6_tunnel_spi >= XFRM6_TUNNEL_SPI_MAX)
@@ -154,32 +168,19 @@
xfrm6_tunnel_spi++;
for (spi = xfrm6_tunnel_spi; spi <= XFRM6_TUNNEL_SPI_MAX; spi++) {
- index = xfrm6_tunnel_spi_hash_byspi(spi);
- hlist_for_each_entry(x6spi, pos,
- &xfrm6_tunnel_spi_byspi[index],
- list_byspi) {
- if (x6spi->spi == spi)
- goto try_next_1;
- }
- xfrm6_tunnel_spi = spi;
- goto alloc_spi;
-try_next_1:;
+ index = __xfrm6_tunnel_spi_check(spi);
+ if (index >= 0)
+ goto alloc_spi;
}
for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tunnel_spi; spi++) {
- index = xfrm6_tunnel_spi_hash_byspi(spi);
- hlist_for_each_entry(x6spi, pos,
- &xfrm6_tunnel_spi_byspi[index],
- list_byspi) {
- if (x6spi->spi == spi)
- goto try_next_2;
- }
- xfrm6_tunnel_spi = spi;
- goto alloc_spi;
-try_next_2:;
+ index = __xfrm6_tunnel_spi_check(spi);
+ if (index >= 0)
+ goto alloc_spi;
}
spi = 0;
goto out;
alloc_spi:
+ xfrm6_tunnel_spi = spi;
x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, GFP_ATOMIC);
if (!x6spi)
goto out;
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index c4065b8..ec05684 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -165,6 +165,14 @@
unsigned int verdict;
int ret = 0;
+#ifdef CONFIG_NET_NS
+ struct net *net;
+
+ net = indev == NULL ? outdev->nd_net : indev->nd_net;
+ if (net != &init_net)
+ return 1;
+#endif
+
/* We may already have this, but read-locks nest anyway */
rcu_read_lock();
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 46c5b3c..dc71d0d 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -316,7 +316,9 @@
if (!asoc) {
ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL,
- &daddr->v6.sin6_addr, &saddr->v6.sin6_addr);
+ &daddr->v6.sin6_addr,
+ inet6_sk(asoc->base.sk)->srcprefs,
+ &saddr->v6.sin6_addr);
SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n",
NIP6(saddr->v6.sin6_addr));
return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index bae94a8..8e588f2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -97,25 +97,52 @@
return 0;
}
-static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos,
- int family)
+static inline struct dst_entry *__xfrm_dst_lookup(int tos,
+ xfrm_address_t *saddr,
+ xfrm_address_t *daddr,
+ int family)
{
- xfrm_address_t *saddr = &x->props.saddr;
- xfrm_address_t *daddr = &x->id.daddr;
struct xfrm_policy_afinfo *afinfo;
struct dst_entry *dst;
- if (x->type->flags & XFRM_TYPE_LOCAL_COADDR)
- saddr = x->coaddr;
- if (x->type->flags & XFRM_TYPE_REMOTE_COADDR)
- daddr = x->coaddr;
-
afinfo = xfrm_policy_get_afinfo(family);
if (unlikely(afinfo == NULL))
return ERR_PTR(-EAFNOSUPPORT);
dst = afinfo->dst_lookup(tos, saddr, daddr);
+
xfrm_policy_put_afinfo(afinfo);
+
+ return dst;
+}
+
+static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos,
+ xfrm_address_t *prev_saddr,
+ xfrm_address_t *prev_daddr,
+ int family)
+{
+ xfrm_address_t *saddr = &x->props.saddr;
+ xfrm_address_t *daddr = &x->id.daddr;
+ struct dst_entry *dst;
+
+ if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) {
+ saddr = x->coaddr;
+ daddr = prev_daddr;
+ }
+ if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) {
+ saddr = prev_saddr;
+ daddr = x->coaddr;
+ }
+
+ dst = __xfrm_dst_lookup(tos, saddr, daddr, family);
+
+ if (!IS_ERR(dst)) {
+ if (prev_saddr != saddr)
+ memcpy(prev_saddr, saddr, sizeof(*prev_saddr));
+ if (prev_daddr != daddr)
+ memcpy(prev_daddr, daddr, sizeof(*prev_daddr));
+ }
+
return dst;
}
@@ -1354,6 +1381,9 @@
int trailer_len = 0;
int tos;
int family = policy->selector.family;
+ xfrm_address_t saddr, daddr;
+
+ xfrm_flowi_addr_get(fl, &saddr, &daddr, family);
tos = xfrm_get_tos(fl, family);
err = tos;
@@ -1384,7 +1414,8 @@
if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
family = xfrm[i]->props.family;
- dst = xfrm_dst_lookup(xfrm[i], tos, family);
+ dst = xfrm_dst_lookup(xfrm[i], tos, &saddr, &daddr,
+ family);
err = PTR_ERR(dst);
if (IS_ERR(dst))
goto put_states;
