summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/Kconfig30
-rw-r--r--net/ipv6/Makefile1
-rw-r--r--net/ipv6/addrconf.c369
-rw-r--r--net/ipv6/addrconf_core.c11
-rw-r--r--net/ipv6/af_inet6.c12
-rw-r--r--net/ipv6/ah6.c4
-rw-r--r--net/ipv6/datagram.c10
-rw-r--r--net/ipv6/exthdrs.c2
-rw-r--r--net/ipv6/exthdrs_offload.c2
-rw-r--r--net/ipv6/icmp.c6
-rw-r--r--net/ipv6/ila.c229
-rw-r--r--net/ipv6/inet6_hashtables.c9
-rw-r--r--net/ipv6/ip6_fib.c1
-rw-r--r--net/ipv6/ip6_gre.c5
-rw-r--r--net/ipv6/ip6_input.c5
-rw-r--r--net/ipv6/ip6_output.c18
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6_udp_tunnel.c9
-rw-r--r--net/ipv6/ndisc.c42
-rw-r--r--net/ipv6/netfilter/Kconfig12
-rw-r--r--net/ipv6/netfilter/Makefile3
-rw-r--r--net/ipv6/netfilter/ip6_tables.c29
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c9
-rw-r--r--net/ipv6/netfilter/ip6t_SYNPROXY.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c5
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c1
-rw-r--r--net/ipv6/netfilter/nf_defrag_ipv6_hooks.c23
-rw-r--r--net/ipv6/netfilter/nf_dup_ipv6.c97
-rw-r--r--net/ipv6/netfilter/nf_nat_l3proto_ipv6.c4
-rw-r--r--net/ipv6/netfilter/nf_nat_proto_icmpv6.c2
-rw-r--r--net/ipv6/netfilter/nft_dup_ipv6.c108
-rw-r--r--net/ipv6/raw.c3
-rw-r--r--net/ipv6/route.c143
-rw-r--r--net/ipv6/sit.c2
-rw-r--r--net/ipv6/sysctl_net_ipv6.c15
-rw-r--r--net/ipv6/tcp_ipv6.c7
-rw-r--r--net/ipv6/udp.c3
-rw-r--r--net/ipv6/xfrm6_mode_tunnel.c3
-rw-r--r--net/ipv6/xfrm6_policy.c14
40 files changed, 1000 insertions, 254 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 438a73aa777c..983bb999738c 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -5,16 +5,15 @@
# IPv6 as module will cause a CRASH if you try to unload it
menuconfig IPV6
tristate "The IPv6 protocol"
- default m
+ default y
---help---
- This is complemental support for the IP version 6.
- You will still be able to do traditional IPv4 networking as well.
+ Support for IP version 6 (IPv6).
For general information about IPv6, see
<https://en.wikipedia.org/wiki/IPv6>.
- For Linux IPv6 development information, see <http://www.linux-ipv6.org>.
- For specific information about IPv6 under Linux, read the HOWTO at
- <http://www.bieringer.de/linux/IPv6/>.
+ For specific information about IPv6 under Linux, see
+ Documentation/networking/ipv6.txt and read the HOWTO at
+ <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/>
To compile this protocol support as a module, choose M here: the
module will be called ipv6.
@@ -93,6 +92,25 @@ config IPV6_MIP6
If unsure, say N.
+config IPV6_ILA
+ tristate "IPv6: Identifier Locator Addressing (ILA)"
+ select LWTUNNEL
+ ---help---
+ Support for IPv6 Identifier Locator Addressing (ILA).
+
+ ILA is a mechanism to do network virtualization without
+ encapsulation. The basic concept of ILA is that we split an
+ IPv6 address into a 64 bit locator and 64 bit identifier. The
+ identifier is the identity of an entity in communication
+ ("who") and the locator expresses the location of the
+ entity ("where").
+
+ ILA can be configured using the "encap ila" option with
+ "ip -6 route" command. ILA is described in
+ https://tools.ietf.org/html/draft-herbert-nvo3-ila-00.
+
+ If unsure, say N.
+
config INET6_XFRM_TUNNEL
tristate
select INET6_TUNNEL
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 0f3f1999719a..2c900c7b7eb1 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o
obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
obj-$(CONFIG_IPV6_MIP6) += mip6.o
+obj-$(CONFIG_IPV6_ILA) += ila.o
obj-$(CONFIG_NETFILTER) += netfilter/
obj-$(CONFIG_IPV6_VTI) += ip6_vti.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 21c2c818df3b..99c0f2b843f0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.max_addresses = IPV6_MAX_ADDRESSES,
.accept_ra_defrtr = 1,
.accept_ra_from_local = 0,
+ .accept_ra_min_hop_limit= 1,
.accept_ra_pinfo = 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
.accept_ra_rtr_pref = 1,
@@ -211,7 +212,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.accept_ra_mtu = 1,
.stable_secret = {
.initialized = false,
- }
+ },
+ .use_oif_addrs_only = 0,
+ .ignore_routes_with_linkdown = 0,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -236,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.max_addresses = IPV6_MAX_ADDRESSES,
.accept_ra_defrtr = 1,
.accept_ra_from_local = 0,
+ .accept_ra_min_hop_limit= 1,
.accept_ra_pinfo = 1,
#ifdef CONFIG_IPV6_ROUTER_PREF
.accept_ra_rtr_pref = 1,
@@ -253,6 +257,8 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.stable_secret = {
.initialized = false,
},
+ .use_oif_addrs_only = 0,
+ .ignore_routes_with_linkdown = 0,
};
/* Check if a valid qdisc is available */
@@ -468,6 +474,9 @@ static int inet6_netconf_msgsize_devconf(int type)
if (type == -1 || type == NETCONFA_PROXY_NEIGH)
size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
+ size += nla_total_size(4);
+
return size;
}
@@ -504,6 +513,11 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
+ nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ devconf->ignore_routes_with_linkdown) < 0)
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return 0;
@@ -540,6 +554,7 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
[NETCONFA_IFINDEX] = { .len = sizeof(int) },
[NETCONFA_FORWARDING] = { .len = sizeof(int) },
[NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) },
+ [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) },
};
static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
@@ -762,6 +777,63 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
rt6_purge_dflt_routers(net);
return 1;
}
+
+static void addrconf_linkdown_change(struct net *net, __s32 newf)
+{
+ struct net_device *dev;
+ struct inet6_dev *idev;
+
+ for_each_netdev(net, dev) {
+ idev = __in6_dev_get(dev);
+ if (idev) {
+ int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf);
+
+ idev->cnf.ignore_routes_with_linkdown = newf;
+ if (changed)
+ inet6_netconf_notify_devconf(dev_net(dev),
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ dev->ifindex,
+ &idev->cnf);
+ }
+ }
+}
+
+static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf)
+{
+ struct net *net;
+ int old;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ net = (struct net *)table->extra2;
+ old = *p;
+ *p = newf;
+
+ if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) {
+ if ((!newf) ^ (!old))
+ inet6_netconf_notify_devconf(net,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv6.devconf_dflt);
+ rtnl_unlock();
+ return 0;
+ }
+
+ if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) {
+ net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf;
+ addrconf_linkdown_change(net, newf);
+ if ((!newf) ^ (!old))
+ inet6_netconf_notify_devconf(net,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
+ }
+ rtnl_unlock();
+
+ return 1;
+}
+
#endif
/* Nobody refers to this ifaddr, destroy it */
@@ -1358,15 +1430,96 @@ out:
return ret;
}
+static int __ipv6_dev_get_saddr(struct net *net,
+ struct ipv6_saddr_dst *dst,
+ struct inet6_dev *idev,
+ struct ipv6_saddr_score *scores,
+ int hiscore_idx)
+{
+ struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx];
+
+ read_lock_bh(&idev->lock);
+ list_for_each_entry(score->ifa, &idev->addr_list, if_list) {
+ int i;
+
+ /*
+ * - Tentative Address (RFC2462 section 5.4)
+ * - A tentative address is not considered
+ * "assigned to an interface" in the traditional
+ * sense, unless it is also flagged as optimistic.
+ * - Candidate Source Address (section 4)
+ * - In any case, anycast addresses, multicast
+ * addresses, and the unspecified address MUST
+ * NOT be included in a candidate set.
+ */
+ if ((score->ifa->flags & IFA_F_TENTATIVE) &&
+ (!(score->ifa->flags & IFA_F_OPTIMISTIC)))
+ continue;
+
+ score->addr_type = __ipv6_addr_type(&score->ifa->addr);
+
+ if (unlikely(score->addr_type == IPV6_ADDR_ANY ||
+ score->addr_type & IPV6_ADDR_MULTICAST)) {
+ net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s",
+ idev->dev->name);
+ continue;
+ }
+
+ score->rule = -1;
+ bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX);
+
+ for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) {
+ int minihiscore, miniscore;
+
+ minihiscore = ipv6_get_saddr_eval(net, hiscore, dst, i);
+ miniscore = ipv6_get_saddr_eval(net, score, dst, i);
+
+ 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 out;
+ }
+ break;
+ } else if (minihiscore < miniscore) {
+ if (hiscore->ifa)
+ in6_ifa_put(hiscore->ifa);
+
+ in6_ifa_hold(score->ifa);
+
+ swap(hiscore, score);
+ hiscore_idx = 1 - hiscore_idx;
+
+ /* restore our iterator */
+ score->ifa = hiscore->ifa;
+
+ break;
+ }
+ }
+ }
+out:
+ read_unlock_bh(&idev->lock);
+ return hiscore_idx;
+}
+
int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
const struct in6_addr *daddr, unsigned int prefs,
struct in6_addr *saddr)
{
- struct ipv6_saddr_score scores[2],
- *score = &scores[0], *hiscore = &scores[1];
+ struct ipv6_saddr_score scores[2], *hiscore;
struct ipv6_saddr_dst dst;
+ struct inet6_dev *idev;
struct net_device *dev;
int dst_type;
+ bool use_oif_addr = false;
+ int hiscore_idx = 0;
dst_type = __ipv6_addr_type(daddr);
dst.addr = daddr;
@@ -1375,105 +1528,50 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex);
dst.prefs = prefs;
- hiscore->rule = -1;
- hiscore->ifa = NULL;
+ scores[hiscore_idx].rule = -1;
+ scores[hiscore_idx].ifa = NULL;
rcu_read_lock();
- for_each_netdev_rcu(net, dev) {
- struct inet6_dev *idev;
-
- /* Candidate Source Address (section 4)
- * - multicast and link-local destination address,
- * the set of candidate source address MUST only
- * include addresses assigned to interfaces
- * belonging to the same link as the outgoing
- * interface.
- * (- For site-local destination addresses, the
- * set of candidate source addresses MUST only
- * include addresses assigned to interfaces
- * belonging to the same site as the outgoing
- * interface.)
- */
- if (((dst_type & IPV6_ADDR_MULTICAST) ||
- dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) &&
- dst.ifindex && dev->ifindex != dst.ifindex)
- continue;
-
- idev = __in6_dev_get(dev);
- if (!idev)
- continue;
-
- read_lock_bh(&idev->lock);
- list_for_each_entry(score->ifa, &idev->addr_list, if_list) {
- int i;
-
- /*
- * - Tentative Address (RFC2462 section 5.4)
- * - A tentative address is not considered
- * "assigned to an interface" in the traditional
- * sense, unless it is also flagged as optimistic.
- * - Candidate Source Address (section 4)
- * - In any case, anycast addresses, multicast
- * addresses, and the unspecified address MUST
- * NOT be included in a candidate set.
- */
- if ((score->ifa->flags & IFA_F_TENTATIVE) &&
- (!(score->ifa->flags & IFA_F_OPTIMISTIC)))
- continue;
-
- score->addr_type = __ipv6_addr_type(&score->ifa->addr);
+ /* Candidate Source Address (section 4)
+ * - multicast and link-local destination address,
+ * the set of candidate source address MUST only
+ * include addresses assigned to interfaces
+ * belonging to the same link as the outgoing
+ * interface.
+ * (- For site-local destination addresses, the
+ * set of candidate source addresses MUST only
+ * include addresses assigned to interfaces
+ * belonging to the same site as the outgoing
+ * interface.)
+ * - "It is RECOMMENDED that the candidate source addresses
+ * be the set of unicast addresses assigned to the
+ * interface that will be used to send to the destination
+ * (the 'outgoing' interface)." (RFC 6724)
+ */
+ if (dst_dev) {
+ idev = __in6_dev_get(dst_dev);
+ if ((dst_type & IPV6_ADDR_MULTICAST) ||
+ dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL ||
+ (idev && idev->cnf.use_oif_addrs_only)) {
+ use_oif_addr = true;
+ }
+ }
- if (unlikely(score->addr_type == IPV6_ADDR_ANY ||
- score->addr_type & IPV6_ADDR_MULTICAST)) {
- net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s",
- dev->name);
+ if (use_oif_addr) {
+ if (idev)
+ hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
+ } else {
+ for_each_netdev_rcu(net, dev) {
+ idev = __in6_dev_get(dev);
+ if (!idev)
continue;
- }
-
- score->rule = -1;
- bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX);
-
- for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) {
- int minihiscore, miniscore;
-
- minihiscore = ipv6_get_saddr_eval(net, hiscore, &dst, i);
- miniscore = ipv6_get_saddr_eval(net, score, &dst, i);
-
- 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) {
- if (hiscore->ifa)
- in6_ifa_put(hiscore->ifa);
-
- in6_ifa_hold(score->ifa);
-
- swap(hiscore, score);
-
- /* restore our iterator */
- score->ifa = hiscore->ifa;
-
- break;
- }
- }
+ hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
}
-try_nextdev:
- read_unlock_bh(&idev->lock);
}
rcu_read_unlock();
+ hiscore = &scores[hiscore_idx];
if (!hiscore->ifa)
return -EADDRNOTAVAIL;
@@ -3558,7 +3656,7 @@ static void addrconf_dad_work(struct work_struct *w)
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
- ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
+ ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL);
out:
in6_ifa_put(ifp);
rtnl_unlock();
@@ -4560,6 +4658,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor;
array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
+ array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit;
array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
#ifdef CONFIG_IPV6_ROUTER_PREF
array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
@@ -4585,7 +4684,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
+ array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown;
/* we omit DEVCONF_STABLE_SECRET for now */
+ array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only;
}
static inline size_t inet6_ifla6_size(void)
@@ -4605,6 +4706,7 @@ static inline size_t inet6_if_nlmsg_size(void)
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+ nla_total_size(4) /* IFLA_MTU */
+ nla_total_size(4) /* IFLA_LINK */
+ + nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */
}
@@ -4624,18 +4726,24 @@ static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib,
}
static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib,
- int items, int bytes, size_t syncpoff)
+ int bytes, size_t syncpoff)
{
- int i;
- int pad = bytes - sizeof(u64) * items;
+ int i, c;
+ u64 buff[IPSTATS_MIB_MAX];
+ int pad = bytes - sizeof(u64) * IPSTATS_MIB_MAX;
+
BUG_ON(pad < 0);
- /* Use put_unaligned() because stats may not be aligned for u64. */
- put_unaligned(items, &stats[0]);
- for (i = 1; i < items; i++)
- put_unaligned(snmp_fold_field64(mib, i, syncpoff), &stats[i]);
+ memset(buff, 0, sizeof(buff));
+ buff[0] = IPSTATS_MIB_MAX;
- memset(&stats[items], 0, pad);
+ for_each_possible_cpu(c) {
+ for (i = 1; i < IPSTATS_MIB_MAX; i++)
+ buff[i] += snmp_get_cpu_field64(mib, c, i, syncpoff);
+ }
+
+ memcpy(stats, buff, IPSTATS_MIB_MAX * sizeof(u64));
+ memset(&stats[IPSTATS_MIB_MAX], 0, pad);
}
static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
@@ -4643,8 +4751,8 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
{
switch (attrtype) {
case IFLA_INET6_STATS:
- __snmp6_fill_stats64(stats, idev->stats.ipv6,
- IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp));
+ __snmp6_fill_stats64(stats, idev->stats.ipv6, bytes,
+ offsetof(struct ipstats_mib, syncp));
break;
case IFLA_INET6_ICMP6STATS:
__snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, ICMP6_MIB_MAX, bytes);
@@ -4861,7 +4969,9 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
(dev->ifindex != dev_get_iflink(dev) &&
- nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
+ nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
+ nla_put_u8(skb, IFLA_OPERSTATE,
+ netif_running(dev) ? dev->operstate : IF_OPER_DOWN))
goto nla_put_failure;
protoinfo = nla_nest_start(skb, IFLA_PROTINFO);
if (!protoinfo)
@@ -5306,6 +5416,34 @@ out:
return err;
}
+static
+int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl,
+ int write,
+ void __user *buffer,
+ size_t *lenp,
+ loff_t *ppos)
+{
+ int *valp = ctl->data;
+ int val = *valp;
+ loff_t pos = *ppos;
+ struct ctl_table lctl;
+ int ret;
+
+ /* ctl->data points to idev->cnf.ignore_routes_when_linkdown
+ * we should not modify it until we get the rtnl lock.
+ */
+ lctl = *ctl;
+ lctl.data = &val;
+
+ ret = proc_dointvec(&lctl, write, buffer, lenp, ppos);
+
+ if (write)
+ ret = addrconf_fixup_linkdown(ctl, valp, val);
+ if (ret)
+ *ppos = pos;
+ return ret;
+}
+
static struct addrconf_sysctl_table
{
struct ctl_table_header *sysctl_header;
@@ -5456,6 +5594,13 @@ static struct addrconf_sysctl_table
.proc_handler = proc_dointvec,
},
{
+ .procname = "accept_ra_min_hop_limit",
+ .data = &ipv6_devconf.accept_ra_min_hop_limit,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "accept_ra_pinfo",
.data = &ipv6_devconf.accept_ra_pinfo,
.maxlen = sizeof(int),
@@ -5585,6 +5730,20 @@ static struct addrconf_sysctl_table
.proc_handler = addrconf_sysctl_stable_secret,
},
{
+ .procname = "use_oif_addrs_only",
+ .data = &ipv6_devconf.use_oif_addrs_only,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "ignore_routes_with_linkdown",
+ .data = &ipv6_devconf.ignore_routes_with_linkdown,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown,
+ },
+ {
/* sentinel */
}
},
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index ca09bf49ac68..bfa941fc1165 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -107,7 +107,16 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v)
}
EXPORT_SYMBOL(inet6addr_notifier_call_chain);
-const struct ipv6_stub *ipv6_stub __read_mostly;
+static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
+ struct dst_entry **u2,
+ struct flowi6 *u3)
+{
+ return -EAFNOSUPPORT;
+}
+
+const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
+ .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+};
EXPORT_SYMBOL_GPL(ipv6_stub);
/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7de52b65173f..44bb66bde0e2 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -197,6 +197,7 @@ lookup_protocol:
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
+ np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk));
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
/* Init the ipv4 part of the socket since we can have sockets
@@ -342,7 +343,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
*/
v4addr = LOOPBACK4_IPV6;
if (!(addr_type & IPV6_ADDR_MULTICAST)) {
- if (!(inet->freebind || inet->transparent) &&
+ if (!net->ipv6.sysctl.ip_nonlocal_bind &&
+ !(inet->freebind || inet->transparent) &&
!ipv6_chk_addr(net, &addr->sin6_addr,
dev, 0)) {
err = -EADDRNOTAVAIL;
@@ -679,8 +681,8 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
const struct ipv6_pinfo *np = inet6_sk(sk);
if (np->rxopt.all) {
- if ((opt->hop && (np->rxopt.bits.hopopts ||
- np->rxopt.bits.ohopopts)) ||
+ if (((opt->flags & IP6SKB_HOPBYHOP) &&
+ (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) ||
(ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) &&
np->rxopt.bits.rxflow) ||
(opt->srcrt && (np->rxopt.bits.srcrt ||
@@ -766,10 +768,10 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.bindv6only = 0;
net->ipv6.sysctl.icmpv6_time = 1*HZ;
net->ipv6.sysctl.flowlabel_consistency = 1;
- net->ipv6.sysctl.auto_flowlabels = 0;
+ net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS;
net->ipv6.sysctl.idgen_retries = 3;
net->ipv6.sysctl.idgen_delay = 1 * HZ;
- net->ipv6.sysctl.flowlabel_state_ranges = 1;
+ net->ipv6.sysctl.flowlabel_state_ranges = 0;
atomic_set(&net->ipv6.fib6_sernum, 1);
err = ipv6_init_mibs(net);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index ed7d4e3f9c10..0630a4d5daaa 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -577,8 +577,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len +
ahp->icv_trunc_len + seqhi_len);
- if (!work_iph)
+ if (!work_iph) {
+ err = -ENOMEM;
goto out;
+ }
auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len);
seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index b10a88986a98..9aadd57808a5 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -199,7 +199,7 @@ ipv4_connected:
NULL);
sk->sk_state = TCP_ESTABLISHED;
- ip6_set_txhash(sk);
+ sk_set_txhash(sk);
out:
fl6_sock_release(flowlabel);
return err;
@@ -568,8 +568,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
}
/* HbH is allowed only once */
- if (np->rxopt.bits.hopopts && opt->hop) {
- u8 *ptr = nh + opt->hop;
+ if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
+ u8 *ptr = nh + sizeof(struct ipv6hdr);
put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
}
@@ -630,8 +630,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
int hlim = ipv6_hdr(skb)->hop_limit;
put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
}
- if (np->rxopt.bits.ohopopts && opt->hop) {
- u8 *ptr = nh + opt->hop;
+ if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
+ u8 *ptr = nh + sizeof(struct ipv6hdr);
put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr);
}
if (np->rxopt.bits.odstopts && opt->dst0) {
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index a7bbbe45570b..ce203b0402be 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -632,7 +632,7 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
return -1;
}
- opt->hop = sizeof(struct ipv6hdr);
+ opt->flags |= IP6SKB_HOPBYHOP;
if (ip6_parse_tlv(tlvprochopopt_lst, skb)) {
skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
opt = IP6CB(skb);
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 447a7fbd1bb6..f5e2ba1c18bf 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
return ret;
out_rt:
- inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+ inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
goto out;
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 713d7434c911..6c2b2132c8d3 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -329,7 +329,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
struct flowi6 fl2;
int err;
- err = ip6_dst_lookup(sk, &dst, fl6);
+ err = ip6_dst_lookup(net, sk, &dst, fl6);
if (err)
return ERR_PTR(err);
@@ -361,7 +361,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- err = ip6_dst_lookup(sk, &dst2, &fl2);
+ err = ip6_dst_lookup(net, sk, &dst2, &fl2);
if (err)
goto relookup_failed;
@@ -591,7 +591,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
- err = ip6_dst_lookup(sk, &dst, &fl6);
+ err = ip6_dst_lookup(net, sk, &dst, &fl6);
if (err)
goto out;
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
diff --git a/net/ipv6/ila.c b/net/ipv6/ila.c
new file mode 100644
index 000000000000..678d2df4b8d9
--- /dev/null
+++ b/net/ipv6/ila.c
@@ -0,0 +1,229 @@
+#include <linux/errno.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ip.h>
+#include <net/ip6_fib.h>
+#include <net/lwtunnel.h>
+#include <net/protocol.h>
+#include <uapi/linux/ila.h>
+
+struct ila_params {
+ __be64 locator;
+ __be64 locator_match;
+ __wsum csum_diff;
+};
+
+static inline struct ila_params *ila_params_lwtunnel(
+ struct lwtunnel_state *lwstate)
+{
+ return (struct ila_params *)lwstate->data;
+}
+
+static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to)
+{
+ __be32 diff[] = {
+ ~from[0], ~from[1], to[0], to[1],
+ };
+
+ return csum_partial(diff, sizeof(diff), 0);
+}
+
+static inline __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p)
+{
+ if (*(__be64 *)&ip6h->daddr == p->locator_match)
+ return p->csum_diff;
+ else
+ return compute_csum_diff8((__be32 *)&ip6h->daddr,
+ (__be32 *)&p->locator);
+}
+
+static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
+{
+ __wsum diff;
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ size_t nhoff = sizeof(struct ipv6hdr);
+
+ /* First update checksum */
+ switch (ip6h->nexthdr) {
+ case NEXTHDR_TCP:
+ if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) {
+ struct tcphdr *th = (struct tcphdr *)
+ (skb_network_header(skb) + nhoff);
+
+ diff = get_csum_diff(ip6h, p);
+ inet_proto_csum_replace_by_diff(&th->check, skb,
+ diff, true);
+ }
+ break;
+ case NEXTHDR_UDP:
+ if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) {
+ struct udphdr *uh = (struct udphdr *)
+ (skb_network_header(skb) + nhoff);
+
+ if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ diff = get_csum_diff(ip6h, p);
+ inet_proto_csum_replace_by_diff(&uh->check, skb,
+ diff, true);
+ if (!uh->check)
+ uh->check = CSUM_MANGLED_0;
+ }
+ }
+ break;
+ case NEXTHDR_ICMP:
+ if (likely(pskb_may_pull(skb,
+ nhoff + sizeof(struct icmp6hdr)))) {
+ struct icmp6hdr *ih = (struct icmp6hdr *)
+ (skb_network_header(skb) + nhoff);
+
+ diff = get_csum_diff(ip6h, p);
+ inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb,
+ diff, true);
+ }
+ break;
+ }
+
+ /* Now change destination address */
+ *(__be64 *)&ip6h->daddr = p->locator;
+}
+
+static int ila_output(struct sock *sk, struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ if (skb->protocol != htons(ETH_P_IPV6))
+ goto drop;
+
+ update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+
+ return dst->lwtstate->orig_output(sk, skb);
+
+drop:
+ kfree_skb(skb);
+ return -EINVAL;
+}
+
+static int ila_input(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ if (skb->protocol != htons(ETH_P_IPV6))
+ goto drop;
+
+ update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+
+ return dst->lwtstate->orig_input(skb);
+
+drop:
+ kfree_skb(skb);
+ return -EINVAL;
+}
+
+static struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
+ [ILA_ATTR_LOCATOR] = { .type = NLA_U64, },
+};
+
+static int ila_build_state(struct net_device *dev, struct nlattr *nla,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **ts)
+{
+ struct ila_params *p;
+ struct nlattr *tb[ILA_ATTR_MAX + 1];
+ size_t encap_len = sizeof(*p);
+ struct lwtunnel_state *newts;
+ const struct fib6_config *cfg6 = cfg;
+ int ret;
+
+ if (family != AF_INET6)
+ return -EINVAL;
+
+ ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla,
+ ila_nl_policy);
+ if (ret < 0)
+ return ret;
+
+ if (!tb[ILA_ATTR_LOCATOR])
+ return -EINVAL;
+
+ newts = lwtunnel_state_alloc(encap_len);
+ if (!newts)
+ return -ENOMEM;
+
+ newts->len = encap_len;
+ p = ila_params_lwtunnel(newts);
+
+ p->locator = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]);
+
+ if (cfg6->fc_dst_len > sizeof(__be64)) {
+ /* Precompute checksum difference for translation since we
+ * know both the old locator and the new one.
+ */
+ p->locator_match = *(__be64 *)&cfg6->fc_dst;
+ p->csum_diff = compute_csum_diff8(
+ (__be32 *)&p->locator_match, (__be32 *)&p->locator);
+ }
+
+ newts->type = LWTUNNEL_ENCAP_ILA;
+ newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT |
+ LWTUNNEL_STATE_INPUT_REDIRECT;
+
+ *ts = newts;
+
+ return 0;
+}
+
+static int ila_fill_encap_info(struct sk_buff *skb,
+ struct lwtunnel_state *lwtstate)
+{
+ struct ila_params *p = ila_params_lwtunnel(lwtstate);
+
+ if (nla_put_u64(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int ila_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+ /* No encapsulation overhead */
+ return 0;
+}
+
+static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+ struct ila_params *a_p = ila_params_lwtunnel(a);
+ struct ila_params *b_p = ila_params_lwtunnel(b);
+
+ return (a_p->locator != b_p->locator);
+}
+
+static const struct lwtunnel_encap_ops ila_encap_ops = {
+ .build_state = ila_build_state,
+ .output = ila_output,
+ .input = ila_input,
+ .fill_encap = ila_fill_encap_info,
+ .get_encap_size = ila_encap_nlsize,
+ .cmp_encap = ila_encap_cmp,
+};
+
+static int __init ila_init(void)
+{
+ return lwtunnel_encap_add_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA);
+}
+
+static void __exit ila_fini(void)
+{
+ lwtunnel_encap_del_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA);
+}
+
+module_init(ila_init);
+module_exit(ila_fini);
+MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>");
+MODULE_LICENSE("GPL");
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b4fd96de97e6..6ac8dad0138a 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -207,7 +207,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk2;
const struct hlist_nulls_node *node;
struct inet_timewait_sock *tw = NULL;
- int twrefcnt = 0;
spin_lock(lock);
@@ -234,21 +233,17 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
WARN_ON(!sk_unhashed(sk));
__sk_nulls_add_node_rcu(sk, &head->chain);
if (tw) {
- twrefcnt = inet_twsk_unhash(tw);
+ sk_nulls_del_node_init_rcu((struct sock *)tw);
NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
}
spin_unlock(lock);
- if (twrefcnt)
- inet_twsk_put(tw);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
if (twp) {
*twp = tw;
} else if (tw) {
/* Silly. Should hash-dance instead... */
- inet_twsk_deschedule(tw);
-
- inet_twsk_put(tw);
+ inet_twsk_deschedule_put(tw);
}
return 0;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 548c6237b1e7..418d9823692b 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -32,6 +32,7 @@
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
+#include <net/lwtunnel.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 69f4f689f06a..4038c694ec03 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -729,7 +729,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
*/
ipv6h = ipv6_hdr(skb);
ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield),
- ip6_make_flowlabel(net, skb, fl6->flowlabel, false));
+ ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6));
ipv6h->hop_limit = tunnel->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6h->saddr = fl6->saddr;
@@ -1183,7 +1183,8 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
ip6_flow_hdr(ipv6h, 0,
ip6_make_flowlabel(dev_net(dev), skb,
- t->fl.u.ip6.flowlabel, false));
+ t->fl.u.ip6.flowlabel, true,
+ &t->fl.u.ip6));
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = NEXTHDR_GRE;
ipv6h->saddr = t->parms.laddr;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 57990c929cd8..adba03ac7ce9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -45,6 +45,7 @@
#include <net/addrconf.h>
#include <net/xfrm.h>
#include <net/inet_ecn.h>
+#include <net/dst_metadata.h>
int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb)
{
@@ -55,7 +56,7 @@ int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb)
if (ipprot && ipprot->early_demux)
ipprot->early_demux(skb);
}
- if (!skb_dst(skb))
+ if (!skb_valid_dst(skb))
ip6_route_input(skb);
return dst_input(skb);
@@ -98,7 +99,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
* arrived via the sending interface (ethX), because of the
* nature of scoping architecture. --yoshfuji
*/
- IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
+ IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex;
if (unlikely(!pskb_may_pull(skb, sizeof(*hdr))))
goto err;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d5f7716662db..26ea47930740 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -207,7 +207,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel));
+ np->autoflowlabel, fl6));
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
@@ -881,10 +881,9 @@ out:
return dst;
}
-static int ip6_dst_lookup_tail(struct sock *sk,
+static int ip6_dst_lookup_tail(struct net *net, struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
- struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
struct rt6_info *rt;
@@ -994,10 +993,11 @@ out_err_release:
*
* It returns zero on success, or a standard errno code on error.
*/
-int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6)
+int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
+ struct flowi6 *fl6)
{
*dst = NULL;
- return ip6_dst_lookup_tail(sk, dst, fl6);
+ return ip6_dst_lookup_tail(net, sk, dst, fl6);
}
EXPORT_SYMBOL_GPL(ip6_dst_lookup);
@@ -1018,11 +1018,13 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
struct dst_entry *dst = NULL;
int err;
- err = ip6_dst_lookup_tail(sk, &dst, fl6);
+ err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
if (err)
return ERR_PTR(err);
if (final_dst)
fl6->daddr = *final_dst;
+ if (!fl6->flowi6_oif)
+ fl6->flowi6_oif = dst->dev->ifindex;
return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
@@ -1050,7 +1052,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
dst = ip6_sk_dst_check(sk, dst, fl6);
- err = ip6_dst_lookup_tail(sk, &dst, fl6);
+ err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
if (err)
return ERR_PTR(err);
if (final_dst)
@@ -1647,7 +1649,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
ip6_flow_hdr(hdr, v6_cork->tclass,
ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel));
+ np->autoflowlabel, fl6));
hdr->hop_limit = v6_cork->hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2e67b660118b..b0ab420612bc 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1095,7 +1095,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield),
- ip6_make_flowlabel(net, skb, fl6->flowlabel, false));
+ ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6));
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6h->saddr = fl6->saddr;
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index e1a1136bda7c..14dacf1df529 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -23,6 +23,15 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
if (err < 0)
goto error;
+ if (cfg->ipv6_v6only) {
+ int val = 1;
+
+ err = kernel_setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY,
+ (char *) &val, sizeof(val));
+ if (err < 0)
+ goto error;
+ }
+
udp6_addr.sin6_family = AF_INET6;
memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
sizeof(udp6_addr.sin6_addr));
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c53331cfed95..64a71354b069 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -553,7 +553,8 @@ static void ndisc_send_unsol_na(struct net_device *dev)
void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *solicit,
- const struct in6_addr *daddr, const struct in6_addr *saddr)
+ const struct in6_addr *daddr, const struct in6_addr *saddr,
+ struct sk_buff *oskb)
{
struct sk_buff *skb;
struct in6_addr addr_buf;
@@ -589,6 +590,9 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
dev->dev_addr);
+ if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb)
+ skb_dst_copy(skb, oskb);
+
ndisc_send_skb(skb, daddr, saddr);
}
@@ -675,12 +679,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
"%s: trying to ucast probe in NUD_INVALID: %pI6\n",
__func__, target);
}
- ndisc_send_ns(dev, neigh, target, target, saddr);
+ ndisc_send_ns(dev, neigh, target, target, saddr, skb);
} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
neigh_app_ns(neigh);
} else {
addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(dev, NULL, target, &mcaddr, saddr);
+ ndisc_send_ns(dev, NULL, target, &mcaddr, saddr, skb);
}
}
@@ -1074,6 +1078,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
struct ndisc_options ndopts;
int optlen;
unsigned int pref = 0;
+ __u32 old_if_flags;
+ bool send_ifinfo_notify = false;
__u8 *opt = (__u8 *)(ra_msg + 1);
@@ -1144,6 +1150,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
* Remember the managed/otherconf flags from most recently
* received RA message (RFC 2462) -- yoshfuji
*/
+ old_if_flags = in6_dev->if_flags;
in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED |
IF_RA_OTHERCONF)) |
(ra_msg->icmph.icmp6_addrconf_managed ?
@@ -1151,6 +1158,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
(ra_msg->icmph.icmp6_addrconf_other ?
IF_RA_OTHERCONF : 0);
+ if (old_if_flags != in6_dev->if_flags)
+ send_ifinfo_notify = true;
+
if (!in6_dev->cnf.accept_ra_defrtr) {
ND_PRINTK(2, info,
"RA: %s, defrtr is false for dev: %s\n",
@@ -1225,18 +1235,16 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (rt)
rt6_set_expires(rt, jiffies + (HZ * lifetime));
- if (ra_msg->icmph.icmp6_hop_limit) {
- /* Only set hop_limit on the interface if it is higher than
- * the current hop_limit.
- */
- if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+ if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
+ ra_msg->icmph.icmp6_hop_limit) {
+ if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+ if (rt)
+ dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
+ ra_msg->icmph.icmp6_hop_limit);
} else {
- ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+ ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
}
- if (rt)
- dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
- ra_msg->icmph.icmp6_hop_limit);
}
skip_defrtr:
@@ -1254,7 +1262,7 @@ skip_defrtr:
rtime = HZ/10;
NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime);
in6_dev->tstamp = jiffies;
- inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
+ send_ifinfo_notify = true;
}
rtime = ntohl(ra_msg->reachable_time);
@@ -1271,11 +1279,17 @@ skip_defrtr:
GC_STALETIME, 3 * rtime);
in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime);
in6_dev->tstamp = jiffies;
- inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
+ send_ifinfo_notify = true;
}
}
}
+ /*
+ * Send a notify if RA changed managed/otherconf flags or timer settings
+ */
+ if (send_ifinfo_notify)
+ inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
+
skip_linkparms:
/*
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index b552cf0d6198..96833e4b3193 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -47,9 +47,21 @@ config NFT_REJECT_IPV6
default NFT_REJECT
tristate
+config NFT_DUP_IPV6
+ tristate "IPv6 nf_tables packet duplication support"
+ select NF_DUP_IPV6
+ help
+ This module enables IPv6 packet duplication support for nf_tables.
+
endif # NF_TABLES_IPV6
endif # NF_TABLES
+config NF_DUP_IPV6
+ tristate "Netfilter IPv6 packet duplication to alternate destination"
+ help
+ This option enables the nf_dup_ipv6 core, which duplicates an IPv6
+ packet to be rerouted to another destination.
+
config NF_REJECT_IPV6
tristate "IPv6 packet rejection"
default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index c36e0a5490de..b4f7d0b4e2af 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -30,6 +30,8 @@ obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
# reject
obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
+obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
+
# nf_tables
obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
@@ -37,6 +39,7 @@ obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o
+obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 3c35ced39b42..0771991ed812 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -305,7 +305,7 @@ static void trace_packet(const struct sk_buff *skb,
}
#endif
-static inline __pure struct ip6t_entry *
+static inline struct ip6t_entry *
ip6t_next_entry(const struct ip6t_entry *entry)
{
return (void *)entry + entry->next_offset;
@@ -324,12 +324,13 @@ ip6t_do_table(struct sk_buff *skb,
const char *indev, *outdev;
const void *table_base;
struct ip6t_entry *e, **jumpstack;
- unsigned int *stackptr, origptr, cpu;
+ unsigned int stackidx, cpu;
const struct xt_table_info *private;
struct xt_action_param acpar;
unsigned int addend;
/* Initialization */
+ stackidx = 0;
indev = state->in ? state->in->name : nulldevname;
outdev = state->out ? state->out->name : nulldevname;
/* We handle fragments by dealing with the first fragment as
@@ -357,8 +358,16 @@ ip6t_do_table(struct sk_buff *skb,
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct ip6t_entry **)private->jumpstack[cpu];
- stackptr = per_cpu_ptr(private->stackptr, cpu);
- origptr = *stackptr;
+
+ /* Switch to alternate jumpstack if we're being invoked via TEE.
+ * TEE issues XT_CONTINUE verdict on original skb so we must not
+ * clobber the jumpstack.
+ *
+ * For recursion via REJECT or SYNPROXY the stack will be clobbered
+ * but it is no problem since absolute verdict is issued by these.
+ */
+ if (static_key_false(&xt_tee_enabled))
+ jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated);
e = get_entry(table_base, private->hook_entry[hook]);
@@ -406,20 +415,16 @@ ip6t_do_table(struct sk_buff *skb,
verdict = (unsigned int)(-v) - 1;
break;
}
- if (*stackptr <= origptr)
+ if (stackidx == 0)
e = get_entry(table_base,
private->underflow[hook]);
else
- e = ip6t_next_entry(jumpstack[--*stackptr]);
+ e = ip6t_next_entry(jumpstack[--stackidx]);
continue;
}
if (table_base + v != ip6t_next_entry(e) &&
!(e->ipv6.flags & IP6T_F_GOTO)) {
- if (*stackptr >= private->stacksize) {
- verdict = NF_DROP;
- break;
- }
- jumpstack[(*stackptr)++] = e;
+ jumpstack[stackidx++] = e;
}
e = get_entry(table_base, v);
@@ -437,8 +442,6 @@ ip6t_do_table(struct sk_buff *skb,
break;
} while (!acpar.hotdrop);
- *stackptr = origptr;
-
xt_write_recseq_end(addend);
local_bh_enable();
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 12331efd49cf..0ed841a3fa33 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -35,14 +35,12 @@ MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>");
MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6");
MODULE_LICENSE("GPL");
-
static unsigned int
reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_reject_info *reject = par->targinfo;
struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
- pr_debug("%s: medium point\n", __func__);
switch (reject->with) {
case IP6T_ICMP6_NO_ROUTE:
nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum);
@@ -65,8 +63,11 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
case IP6T_TCP_RESET:
nf_send_reset6(net, skb, par->hooknum);
break;
- default:
- net_info_ratelimited("case %u not handled yet\n", reject->with);
+ case IP6T_ICMP6_POLICY_FAIL:
+ nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, par->hooknum);
+ break;
+ case IP6T_ICMP6_REJECT_ROUTE:
+ nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE, par->hooknum);
break;
}
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index ebbb754c2111..1e4bf99ed16e 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -237,7 +237,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet,
nth->ack_seq = th->ack_seq;
tcp_flag_word(nth) = TCP_FLAG_ACK;
nth->doff = tcp_hdr_size / 4;
- nth->window = ntohs(htons(th->window) >> opts->wscale);
+ nth->window = htons(ntohs(th->window) >> opts->wscale);
nth->check = 0;
nth->urg_ptr = 0;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 4ba0c34c627b..7302900c321a 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -251,7 +251,7 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
if (*len < 0 || (unsigned int) *len < sizeof(sin6))
return -EINVAL;
- h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
+ h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
if (!h) {
pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
&tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 90388d606483..0e6fae103d33 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -150,7 +150,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
struct nf_conntrack_tuple intuple, origtuple;
const struct nf_conntrack_tuple_hash *h;
const struct nf_conntrack_l4proto *inproto;
- u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
+ struct nf_conntrack_zone tmp;
NF_CT_ASSERT(skb->nfct == NULL);
@@ -177,7 +177,8 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
*ctinfo = IP_CT_RELATED;
- h = nf_conntrack_find_get(net, zone, &intuple);
+ h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
+ &intuple);
if (!h) {
pr_debug("icmpv6_error: no match\n");
return -NF_ACCEPT;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6d02498172c1..701cd2bae0a9 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -633,6 +633,7 @@ ret_orig:
kfree_skb(clone);
return skb;
}
+EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
void nf_ct_frag6_consume_orig(struct sk_buff *skb)
{
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index a45db0b4785c..6d9c0b3d5b8c 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -33,23 +33,22 @@
static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
struct sk_buff *skb)
{
- u16 zone = NF_CT_DEFAULT_ZONE;
-
+ u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
- if (skb->nfct)
- zone = nf_ct_zone((struct nf_conn *)skb->nfct);
-#endif
+ if (skb->nfct) {
+ enum ip_conntrack_info ctinfo;
+ const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
- if (skb->nf_bridge &&
- skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
- return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
+ zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
+ }
#endif
+ if (nf_bridge_in_prerouting(skb))
+ return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
+
if (hooknum == NF_INET_PRE_ROUTING)
- return IP6_DEFRAG_CONNTRACK_IN + zone;
+ return IP6_DEFRAG_CONNTRACK_IN + zone_id;
else
- return IP6_DEFRAG_CONNTRACK_OUT + zone;
-
+ return IP6_DEFRAG_CONNTRACK_OUT + zone_id;
}
static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
new file mode 100644
index 000000000000..c8ab626556a0
--- /dev/null
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -0,0 +1,97 @@
+/*
+ * (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag>
+ * (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de>
+ *
+ * Extracted from xt_TEE.c
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 or later, as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/netfilter/ipv6/nf_dup_ipv6.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
+static struct net *pick_net(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+ const struct dst_entry *dst;
+
+ if (skb->dev != NULL)
+ return dev_net(skb->dev);
+ dst = skb_dst(skb);
+ if (dst != NULL && dst->dev != NULL)
+ return dev_net(dst->dev);
+#endif
+ return &init_net;
+}
+
+static bool nf_dup_ipv6_route(struct sk_buff *skb, const struct in6_addr *gw,
+ int oif)
+{
+ const struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct net *net = pick_net(skb);
+ struct dst_entry *dst;
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ if (oif != -1)
+ fl6.flowi6_oif = oif;
+
+ fl6.daddr = *gw;
+ fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
+ (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (dst->error) {
+ dst_release(dst);
+ return false;
+ }
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst);
+ skb->dev = dst->dev;
+ skb->protocol = htons(ETH_P_IPV6);
+
+ return true;
+}
+
+void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum,
+ const struct in6_addr *gw, int oif)
+{
+ if (this_cpu_read(nf_skb_duplicated))
+ return;
+ skb = pskb_copy(skb, GFP_ATOMIC);
+ if (skb == NULL)
+ return;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ nf_conntrack_put(skb->nfct);
+ skb->nfct = &nf_ct_untracked_get()->ct_general;
+ skb->nfctinfo = IP_CT_NEW;
+ nf_conntrack_get(skb->nfct);
+#endif
+ if (hooknum == NF_INET_PRE_ROUTING ||
+ hooknum == NF_INET_LOCAL_IN) {
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ --iph->hop_limit;
+ }
+ if (nf_dup_ipv6_route(skb, gw, oif)) {
+ __this_cpu_write(nf_skb_duplicated, true);
+ ip6_local_out(skb);
+ __this_cpu_write(nf_skb_duplicated, false);
+ } else {
+ kfree_skb(skb);
+ }
+}
+EXPORT_SYMBOL_GPL(nf_dup_ipv6);
+
+MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_DESCRIPTION("nf_dup_ipv6: IPv6 packet duplication");
+MODULE_LICENSE("GPL");
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index e76900e0aa92..70fbaed49edb 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -124,7 +124,7 @@ static void nf_nat_ipv6_csum_update(struct sk_buff *skb,
newip = &t->dst.u3.in6;
}
inet_proto_csum_replace16(check, skb, oldip->s6_addr32,
- newip->s6_addr32, 1);
+ newip->s6_addr32, true);
}
static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
@@ -155,7 +155,7 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
}
} else
inet_proto_csum_replace2(check, skb,
- htons(oldlen), htons(datalen), 1);
+ htons(oldlen), htons(datalen), true);
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
index 2205e8eeeacf..57593b00c5b4 100644
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
@@ -73,7 +73,7 @@ icmpv6_manip_pkt(struct sk_buff *skb,
hdr->icmp6_type == ICMPV6_ECHO_REPLY) {
inet_proto_csum_replace2(&hdr->icmp6_cksum, skb,
hdr->icmp6_identifier,
- tuple->src.u.icmp.id, 0);
+ tuple->src.u.icmp.id, false);
hdr->icmp6_identifier = tuple->src.u.icmp.id;
}
return true;
diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c
new file mode 100644
index 000000000000..0eaa4f65fdea
--- /dev/null
+++ b/net/ipv6/netfilter/nft_dup_ipv6.c
@@ -0,0 +1,108 @@
+/*
+ * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/ipv6/nf_dup_ipv6.h>
+
+struct nft_dup_ipv6 {
+ enum nft_registers sreg_addr:8;
+ enum nft_registers sreg_dev:8;
+};
+
+static void nft_dup_ipv6_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
+ struct in6_addr *gw = (struct in6_addr *)&regs->data[priv->sreg_addr];
+ int oif = regs->data[priv->sreg_dev];
+
+ nf_dup_ipv6(pkt->skb, pkt->ops->hooknum, gw, oif);
+}
+
+static int nft_dup_ipv6_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
+ int err;
+
+ if (tb[NFTA_DUP_SREG_ADDR] == NULL)
+ return -EINVAL;
+
+ priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]);
+ err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in6_addr));
+ if (err < 0)
+ return err;
+
+ if (tb[NFTA_DUP_SREG_DEV] != NULL) {
+ priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]);
+ return nft_validate_register_load(priv->sreg_dev, sizeof(int));
+ }
+ return 0;
+}
+
+static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
+
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_type nft_dup_ipv6_type;
+static const struct nft_expr_ops nft_dup_ipv6_ops = {
+ .type = &nft_dup_ipv6_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv6)),
+ .eval = nft_dup_ipv6_eval,
+ .init = nft_dup_ipv6_init,
+ .dump = nft_dup_ipv6_dump,
+};
+
+static const struct nla_policy nft_dup_ipv6_policy[NFTA_DUP_MAX + 1] = {
+ [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 },
+ [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 },
+};
+
+static struct nft_expr_type nft_dup_ipv6_type __read_mostly = {
+ .family = NFPROTO_IPV6,
+ .name = "dup",
+ .ops = &nft_dup_ipv6_ops,
+ .policy = nft_dup_ipv6_policy,
+ .maxattr = NFTA_DUP_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_dup_ipv6_module_init(void)
+{
+ return nft_register_expr(&nft_dup_ipv6_type);
+}
+
+static void __exit nft_dup_ipv6_module_exit(void)
+{
+ nft_unregister_expr(&nft_dup_ipv6_type);
+}
+
+module_init(nft_dup_ipv6_module_init);
+module_exit(nft_dup_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "dup");
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ca4700cb26c4..fdbada1569a3 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -295,7 +295,8 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
* unspecified and mapped address have a v4 equivalent.
*/
v4addr = LOOPBACK4_IPV6;
- if (!(addr_type & IPV6_ADDR_MULTICAST)) {
+ if (!(addr_type & IPV6_ADDR_MULTICAST) &&
+ !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) {
err = -EADDRNOTAVAIL;
if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr,
dev, 0)) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d15586490cec..f45cac6f8356 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -54,10 +54,13 @@
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
+#include <net/dst_metadata.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>
#include <net/nexthop.h>
+#include <net/lwtunnel.h>
+#include <net/ip_tunnels.h>
#include <asm/uaccess.h>
@@ -535,13 +538,14 @@ static void rt6_probe_deferred(struct work_struct *w)
container_of(w, struct __rt6_probe_work, work);
addrconf_addr_solict_mult(&work->target, &mcaddr);
- ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
+ ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
dev_put(work->dev);
kfree(work);
}
static void rt6_probe(struct rt6_info *rt)
{
+ struct __rt6_probe_work *work;
struct neighbour *neigh;
/*
* Okay, this does not seem to be appropriate
@@ -556,34 +560,33 @@ static void rt6_probe(struct rt6_info *rt)
rcu_read_lock_bh();
neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
if (neigh) {
- write_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
goto out;
- }
-
- if (!neigh ||
- time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
- struct __rt6_probe_work *work;
+ work = NULL;
+ write_lock(&neigh->lock);
+ if (!(neigh->nud_state & NUD_VALID) &&
+ time_after(jiffies,
+ neigh->updated +
+ rt->rt6i_idev->cnf.rtr_probe_interval)) {
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work)
+ __neigh_set_probe_once(neigh);
+ }
+ write_unlock(&neigh->lock);
+ } else {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ }
- if (neigh && work)
- __neigh_set_probe_once(neigh);
-
- if (neigh)
- write_unlock(&neigh->lock);
+ if (work) {
+ INIT_WORK(&work->work, rt6_probe_deferred);
+ work->target = rt->rt6i_gateway;
+ dev_hold(rt->dst.dev);
+ work->dev = rt->dst.dev;
+ schedule_work(&work->work);
+ }
- if (work) {
- INIT_WORK(&work->work, rt6_probe_deferred);
- work->target = rt->rt6i_gateway;
- dev_hold(rt->dst.dev);
- work->dev = rt->dst.dev;
- schedule_work(&work->work);
- }
- } else {
out:
- write_unlock(&neigh->lock);
- }
rcu_read_unlock_bh();
}
#else
@@ -662,6 +665,12 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
{
int m;
bool match_do_rr = false;
+ struct inet6_dev *idev = rt->rt6i_idev;
+ struct net_device *dev = rt->dst.dev;
+
+ if (dev && !netif_carrier_ok(dev) &&
+ idev->cnf.ignore_routes_with_linkdown)
+ goto out;
if (rt6_check_expired(rt))
goto out;
@@ -1154,6 +1163,7 @@ void ip6_route_input(struct sk_buff *skb)
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
int flags = RT6_LOOKUP_F_HAS_SADDR;
+ struct ip_tunnel_info *tun_info;
struct flowi6 fl6 = {
.flowi6_iif = skb->dev->ifindex,
.daddr = iph->daddr,
@@ -1163,6 +1173,10 @@ void ip6_route_input(struct sk_buff *skb)
.flowi6_proto = iph->nexthdr,
};
+ tun_info = skb_tunnel_info(skb);
+ if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
+ fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id;
+ skb_dst_drop(skb);
skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
}
@@ -1684,6 +1698,7 @@ out:
static int ip6_convert_metrics(struct mx6_config *mxc,
const struct fib6_config *cfg)
{
+ bool ecn_ca = false;
struct nlattr *nla;
int remaining;
u32 *mp;
@@ -1697,30 +1712,36 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
+ u32 val;
+
+ if (!type)
+ continue;
+ if (unlikely(type > RTAX_MAX))
+ goto err;
- if (type) {
- u32 val;
+ if (type == RTAX_CC_ALGO) {
+ char tmp[TCP_CA_NAME_MAX];
- if (unlikely(type > RTAX_MAX))
+ nla_strlcpy(tmp, nla, sizeof(tmp));
+ val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+ if (val == TCP_CA_UNSPEC)
goto err;
- if (type == RTAX_CC_ALGO) {
- char tmp[TCP_CA_NAME_MAX];
+ } else {
+ val = nla_get_u32(nla);
+ }
+ if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
+ goto err;
- nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(tmp);
- if (val == TCP_CA_UNSPEC)
- goto err;
- } else {
- val = nla_get_u32(nla);
- }
+ mp[type - 1] = val;
+ __set_bit(type - 1, mxc->mx_valid);
+ }
- mp[type - 1] = val;
- __set_bit(type - 1, mxc->mx_valid);
- }
+ if (ecn_ca) {
+ __set_bit(RTAX_FEATURES - 1, mxc->mx_valid);
+ mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
}
mxc->mx = mp;
-
return 0;
err:
kfree(mp);
@@ -1801,6 +1822,25 @@ int ip6_route_add(struct fib6_config *cfg)
rt->dst.output = ip6_output;
+ if (cfg->fc_encap) {
+ struct lwtunnel_state *lwtstate;
+
+ err = lwtunnel_build_state(dev, cfg->fc_encap_type,
+ cfg->fc_encap, AF_INET6, cfg,
+ &lwtstate);
+ if (err)
+ goto out;
+ rt->dst.lwtstate = lwtstate_get(lwtstate);
+ if (lwtunnel_output_redirect(rt->dst.lwtstate)) {
+ rt->dst.lwtstate->orig_output = rt->dst.output;
+ rt->dst.output = lwtunnel_output;
+ }
+ if (lwtunnel_input_redirect(rt->dst.lwtstate)) {
+ rt->dst.lwtstate->orig_input = rt->dst.input;
+ rt->dst.input = lwtunnel_input;
+ }
+ }
+
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
if (rt->rt6i_dst.plen == 128)
@@ -2180,6 +2220,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
#endif
rt->rt6i_prefsrc = ort->rt6i_prefsrc;
rt->rt6i_table = ort->rt6i_table;
+ rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate);
}
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -2628,6 +2669,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_PREF] = { .type = NLA_U8 },
+ [RTA_ENCAP_TYPE] = { .type = NLA_U16 },
+ [RTA_ENCAP] = { .type = NLA_NESTED },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2722,6 +2765,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->fc_flags |= RTF_PREF(pref);
}
+ if (tb[RTA_ENCAP])
+ cfg->fc_encap = tb[RTA_ENCAP];
+
+ if (tb[RTA_ENCAP_TYPE])
+ cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
+
err = 0;
errout:
return err;
@@ -2754,6 +2803,10 @@ beginning:
r_cfg.fc_gateway = nla_get_in6_addr(nla);
r_cfg.fc_flags |= RTF_GATEWAY;
}
+ r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+ if (nla)
+ r_cfg.fc_encap_type = nla_get_u16(nla);
}
err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
if (err) {
@@ -2816,7 +2869,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
return ip6_route_add(&cfg);
}
-static inline size_t rt6_nlmsg_size(void)
+static inline size_t rt6_nlmsg_size(struct rt6_info *rt)
{
return NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(16) /* RTA_SRC */
@@ -2830,7 +2883,8 @@ static inline size_t rt6_nlmsg_size(void)
+ RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
+ nla_total_size(sizeof(struct rta_cacheinfo))
+ nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
- + nla_total_size(1); /* RTA_PREF */
+ + nla_total_size(1) /* RTA_PREF */
+ + lwtunnel_get_encap_size(rt->dst.lwtstate);
}
static int rt6_fill_node(struct net *net,
@@ -2891,6 +2945,11 @@ static int rt6_fill_node(struct net *net,
else
rtm->rtm_type = RTN_UNICAST;
rtm->rtm_flags = 0;
+ if (!netif_carrier_ok(rt->dst.dev)) {
+ rtm->rtm_flags |= RTNH_F_LINKDOWN;
+ if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
+ rtm->rtm_flags |= RTNH_F_DEAD;
+ }
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->rt6i_protocol;
if (rt->rt6i_flags & RTF_DYNAMIC)
@@ -2978,6 +3037,8 @@ static int rt6_fill_node(struct net *net,
if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
goto nla_put_failure;
+ lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+
nlmsg_end(skb, nlh);
return 0;
@@ -3104,7 +3165,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
err = -ENOBUFS;
seq = info->nlh ? info->nlh->nlmsg_seq : 0;
- skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
+ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
if (!skb)
goto errout;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ac35a28599be..94428fd85b2f 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -742,7 +742,7 @@ static int ipip_rcv(struct sk_buff *skb)
goto drop;
if (iptunnel_pull_header(skb, 0, tpi.proto))
goto drop;
- return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+ return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error);
}
return 1;
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 4e705add4f18..45243bbe5253 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -17,6 +17,9 @@
#include <net/inet_frag.h>
static int one = 1;
+static int auto_flowlabels_min;
+static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
+
static struct ctl_table ipv6_table_template[] = {
{
@@ -45,7 +48,9 @@ static struct ctl_table ipv6_table_template[] = {
.data = &init_net.ipv6.sysctl.auto_flowlabels,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &auto_flowlabels_min,
+ .extra2 = &auto_flowlabels_max
},
{
.procname = "fwmark_reflect",
@@ -75,6 +80,13 @@ static struct ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "ip_nonlocal_bind",
+ .data = &init_net.ipv6.sysctl.ip_nonlocal_bind,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{ }
};
@@ -117,6 +129,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries;
ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay;
ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges;
+ ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind;
ipv6_route_table = ipv6_route_sysctl_init(net);
if (!ipv6_route_table)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7a6cea5e4274..97d9314ea361 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (err)
goto late_failure;
- ip6_set_txhash(sk);
+ sk_set_txhash(sk);
if (!tp->write_seq && likely(!tp->repair))
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
@@ -1090,7 +1090,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
newsk->sk_bound_dev_if = ireq->ir_iif;
- ip6_set_txhash(newsk);
+ sk_set_txhash(newsk);
/* Now IPv6 options...
@@ -1481,8 +1481,7 @@ do_time_wait:
ntohs(th->dest), tcp_v6_iif(skb));
if (sk2) {
struct inet_timewait_sock *tw = inet_twsk(sk);
- inet_twsk_deschedule(tw);
- inet_twsk_put(tw);
+ inet_twsk_deschedule_put(tw);
sk = sk2;
tcp_v6_restore_cb(skb);
goto process;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e51fc3eee6db..0aba654f5b91 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1496,7 +1496,8 @@ int __net_init udp6_proc_init(struct net *net)
return udp_proc_register(net, &udp6_seq_afinfo);
}
-void udp6_proc_exit(struct net *net) {
+void udp6_proc_exit(struct net *net)
+{
udp_proc_unregister(net, &udp6_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 901ef6f8addc..f7fbdbabe50e 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -20,10 +20,9 @@
static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
{
- const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
- if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
+ if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
IP6_ECN_set_ce(inner_iph);
}
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index ed0583c1b9fc..30caa289c5db 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -20,13 +20,14 @@
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
+#include <net/vrf.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
-static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
+static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
@@ -35,6 +36,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
int err;
memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
@@ -50,13 +52,13 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
return dst;
}
-static int xfrm6_get_saddr(struct net *net,
+static int xfrm6_get_saddr(struct net *net, int oif,
xfrm_address_t *saddr, xfrm_address_t *daddr)
{
struct dst_entry *dst;
struct net_device *dev;
- dst = xfrm6_dst_lookup(net, 0, NULL, daddr);
+ dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr);
if (IS_ERR(dst))
return -EHOSTUNREACH;
@@ -130,8 +132,10 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
nexthdr = nh[nhoff];
- if (skb_dst(skb))
- oif = skb_dst(skb)->dev->ifindex;
+ if (skb_dst(skb)) {
+ oif = vrf_master_ifindex(skb_dst(skb)->dev) ?
+ : skb_dst(skb)->dev->ifindex;
+ }
memset(fl6, 0, sizeof(struct flowi6));
fl6->flowi6_mark = skb->mark;