summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c276
-rw-r--r--net/ipv6/af_inet6.c6
-rw-r--r--net/ipv6/fib6_rules.c6
-rw-r--r--net/ipv6/icmp.c80
-rw-r--r--net/ipv6/ila/ila.h3
-rw-r--r--net/ipv6/ila/ila_common.c16
-rw-r--r--net/ipv6/ila/ila_lwt.c4
-rw-r--r--net/ipv6/ila/ila_xlat.c8
-rw-r--r--net/ipv6/ip6_checksum.c7
-rw-r--r--net/ipv6/ip6_fib.c1
-rw-r--r--net/ipv6/ip6_gre.c5
-rw-r--r--net/ipv6/ip6_icmp.c2
-rw-r--r--net/ipv6/ip6_input.c1
-rw-r--r--net/ipv6/ip6_output.c25
-rw-r--r--net/ipv6/ip6mr.c27
-rw-r--r--net/ipv6/ndisc.c123
-rw-r--r--net/ipv6/netfilter/ip6_tables.c61
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c4
-rw-r--r--net/ipv6/netfilter/nf_dup_ipv6.c1
-rw-r--r--net/ipv6/ping.c4
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/route.c34
-rw-r--r--net/ipv6/sit.c144
-rw-r--r--net/ipv6/tcp_ipv6.c37
-rw-r--r--net/ipv6/udp.c91
-rw-r--r--net/ipv6/xfrm6_policy.c4
26 files changed, 586 insertions, 392 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 47f837a58e0a..6287a8b9f428 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -547,7 +547,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
struct sk_buff *skb;
int err = -ENOBUFS;
- skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_ATOMIC);
+ skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_KERNEL);
if (!skb)
goto errout;
@@ -559,7 +559,7 @@ void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_ATOMIC);
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_KERNEL);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err);
@@ -1524,6 +1524,28 @@ out:
return hiscore_idx;
}
+static int ipv6_get_saddr_master(struct net *net,
+ const struct net_device *dst_dev,
+ const struct net_device *master,
+ struct ipv6_saddr_dst *dst,
+ struct ipv6_saddr_score *scores,
+ int hiscore_idx)
+{
+ struct inet6_dev *idev;
+
+ idev = __in6_dev_get(dst_dev);
+ if (idev)
+ hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+ scores, hiscore_idx);
+
+ idev = __in6_dev_get(master);
+ if (idev)
+ hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+ scores, hiscore_idx);
+
+ 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)
@@ -1577,13 +1599,39 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
if (idev)
hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
} else {
+ const struct net_device *master;
+ int master_idx = 0;
+
+ /* if dst_dev exists and is enslaved to an L3 device, then
+ * prefer addresses from dst_dev and then the master over
+ * any other enslaved devices in the L3 domain.
+ */
+ master = l3mdev_master_dev_rcu(dst_dev);
+ if (master) {
+ master_idx = master->ifindex;
+
+ hiscore_idx = ipv6_get_saddr_master(net, dst_dev,
+ master, &dst,
+ scores, hiscore_idx);
+
+ if (scores[hiscore_idx].ifa)
+ goto out;
+ }
+
for_each_netdev_rcu(net, dev) {
+ /* only consider addresses on devices in the
+ * same L3 domain
+ */
+ if (l3mdev_master_ifindex_rcu(dev) != master_idx)
+ continue;
idev = __in6_dev_get(dev);
if (!idev)
continue;
hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
}
}
+
+out:
rcu_read_unlock();
hiscore = &scores[hiscore_idx];
@@ -2254,7 +2302,7 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
return ERR_PTR(-EACCES);
/* Add default multicast route */
- if (!(dev->flags & IFF_LOOPBACK))
+ if (!(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev))
addrconf_add_mroute(dev);
return idev;
@@ -2333,12 +2381,109 @@ static bool is_addr_mode_generate_stable(struct inet6_dev *idev)
idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
}
+int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
+ const struct prefix_info *pinfo,
+ struct inet6_dev *in6_dev,
+ const struct in6_addr *addr, int addr_type,
+ u32 addr_flags, bool sllao, bool tokenized,
+ __u32 valid_lft, u32 prefered_lft)
+{
+ struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1);
+ int create = 0, update_lft = 0;
+
+ if (!ifp && valid_lft) {
+ int max_addresses = in6_dev->cnf.max_addresses;
+
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+ if (in6_dev->cnf.optimistic_dad &&
+ !net->ipv6.devconf_all->forwarding && sllao)
+ addr_flags |= IFA_F_OPTIMISTIC;
+#endif
+
+ /* Do not allow to create too much of autoconfigured
+ * addresses; this would be too easy way to crash kernel.
+ */
+ if (!max_addresses ||
+ ipv6_count_addresses(in6_dev) < max_addresses)
+ ifp = ipv6_add_addr(in6_dev, addr, NULL,
+ pinfo->prefix_len,
+ addr_type&IPV6_ADDR_SCOPE_MASK,
+ addr_flags, valid_lft,
+ prefered_lft);
+
+ if (IS_ERR_OR_NULL(ifp))
+ return -1;
+
+ update_lft = 0;
+ create = 1;
+ spin_lock_bh(&ifp->lock);
+ ifp->flags |= IFA_F_MANAGETEMPADDR;
+ ifp->cstamp = jiffies;
+ ifp->tokenized = tokenized;
+ spin_unlock_bh(&ifp->lock);
+ addrconf_dad_start(ifp);
+ }
+
+ if (ifp) {
+ u32 flags;
+ unsigned long now;
+ u32 stored_lft;
+
+ /* update lifetime (RFC2462 5.5.3 e) */
+ spin_lock_bh(&ifp->lock);
+ now = jiffies;
+ if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
+ stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
+ else
+ stored_lft = 0;
+ if (!update_lft && !create && stored_lft) {
+ const u32 minimum_lft = min_t(u32,
+ stored_lft, MIN_VALID_LIFETIME);
+ valid_lft = max(valid_lft, minimum_lft);
+
+ /* RFC4862 Section 5.5.3e:
+ * "Note that the preferred lifetime of the
+ * corresponding address is always reset to
+ * the Preferred Lifetime in the received
+ * Prefix Information option, regardless of
+ * whether the valid lifetime is also reset or
+ * ignored."
+ *
+ * So we should always update prefered_lft here.
+ */
+ update_lft = 1;
+ }
+
+ if (update_lft) {
+ ifp->valid_lft = valid_lft;
+ ifp->prefered_lft = prefered_lft;
+ ifp->tstamp = now;
+ flags = ifp->flags;
+ ifp->flags &= ~IFA_F_DEPRECATED;
+ spin_unlock_bh(&ifp->lock);
+
+ if (!(flags&IFA_F_TENTATIVE))
+ ipv6_ifa_notify(0, ifp);
+ } else
+ spin_unlock_bh(&ifp->lock);
+
+ manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
+ create, now);
+
+ in6_ifa_put(ifp);
+ addrconf_verify();
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr);
+
void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
{
struct prefix_info *pinfo;
__u32 valid_lft;
__u32 prefered_lft;
- int addr_type;
+ int addr_type, err;
u32 addr_flags = 0;
struct inet6_dev *in6_dev;
struct net *net = dev_net(dev);
@@ -2432,10 +2577,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
/* Try to figure out our local address for this prefix */
if (pinfo->autoconf && in6_dev->cnf.autoconf) {
- struct inet6_ifaddr *ifp;
struct in6_addr addr;
- int create = 0, update_lft = 0;
- bool tokenized = false;
+ bool tokenized = false, dev_addr_generated = false;
if (pinfo->prefix_len == 64) {
memcpy(&addr, &pinfo->prefix, 8);
@@ -2453,106 +2596,36 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
goto ok;
} else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) &&
ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) {
- in6_dev_put(in6_dev);
- return;
+ goto put;
+ } else {
+ dev_addr_generated = true;
}
goto ok;
}
net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n",
pinfo->prefix_len);
- in6_dev_put(in6_dev);
- return;
+ goto put;
ok:
+ err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+ &addr, addr_type,
+ addr_flags, sllao,
+ tokenized, valid_lft,
+ prefered_lft);
+ if (err)
+ goto put;
- ifp = ipv6_get_ifaddr(net, &addr, dev, 1);
-
- if (!ifp && valid_lft) {
- int max_addresses = in6_dev->cnf.max_addresses;
-
-#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- if (in6_dev->cnf.optimistic_dad &&
- !net->ipv6.devconf_all->forwarding && sllao)
- addr_flags |= IFA_F_OPTIMISTIC;
-#endif
-
- /* Do not allow to create too much of autoconfigured
- * addresses; this would be too easy way to crash kernel.
- */
- if (!max_addresses ||
- ipv6_count_addresses(in6_dev) < max_addresses)
- ifp = ipv6_add_addr(in6_dev, &addr, NULL,
- pinfo->prefix_len,
- addr_type&IPV6_ADDR_SCOPE_MASK,
- addr_flags, valid_lft,
- prefered_lft);
-
- if (IS_ERR_OR_NULL(ifp)) {
- in6_dev_put(in6_dev);
- return;
- }
-
- update_lft = 0;
- create = 1;
- spin_lock_bh(&ifp->lock);
- ifp->flags |= IFA_F_MANAGETEMPADDR;
- ifp->cstamp = jiffies;
- ifp->tokenized = tokenized;
- spin_unlock_bh(&ifp->lock);
- addrconf_dad_start(ifp);
- }
-
- if (ifp) {
- u32 flags;
- unsigned long now;
- u32 stored_lft;
-
- /* update lifetime (RFC2462 5.5.3 e) */
- spin_lock_bh(&ifp->lock);
- now = jiffies;
- if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
- stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
- else
- stored_lft = 0;
- if (!update_lft && !create && stored_lft) {
- const u32 minimum_lft = min_t(u32,
- stored_lft, MIN_VALID_LIFETIME);
- valid_lft = max(valid_lft, minimum_lft);
-
- /* RFC4862 Section 5.5.3e:
- * "Note that the preferred lifetime of the
- * corresponding address is always reset to
- * the Preferred Lifetime in the received
- * Prefix Information option, regardless of
- * whether the valid lifetime is also reset or
- * ignored."
- *
- * So we should always update prefered_lft here.
- */
- update_lft = 1;
- }
-
- if (update_lft) {
- ifp->valid_lft = valid_lft;
- ifp->prefered_lft = prefered_lft;
- ifp->tstamp = now;
- flags = ifp->flags;
- ifp->flags &= ~IFA_F_DEPRECATED;
- spin_unlock_bh(&ifp->lock);
-
- if (!(flags&IFA_F_TENTATIVE))
- ipv6_ifa_notify(0, ifp);
- } else
- spin_unlock_bh(&ifp->lock);
-
- manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
- create, now);
-
- in6_ifa_put(ifp);
- addrconf_verify();
- }
+ /* Ignore error case here because previous prefix add addr was
+ * successful which will be notified.
+ */
+ ndisc_ops_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr,
+ addr_type, addr_flags, sllao,
+ tokenized, valid_lft,
+ prefered_lft,
+ dev_addr_generated);
}
inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
+put:
in6_dev_put(in6_dev);
}
@@ -2947,8 +3020,8 @@ static void init_loopback(struct net_device *dev)
}
}
-static void addrconf_add_linklocal(struct inet6_dev *idev,
- const struct in6_addr *addr, u32 flags)
+void addrconf_add_linklocal(struct inet6_dev *idev,
+ const struct in6_addr *addr, u32 flags)
{
struct inet6_ifaddr *ifp;
u32 addr_flags = flags | IFA_F_PERMANENT;
@@ -2967,6 +3040,7 @@ static void addrconf_add_linklocal(struct inet6_dev *idev,
in6_ifa_put(ifp);
}
}
+EXPORT_SYMBOL_GPL(addrconf_add_linklocal);
static bool ipv6_reserved_interfaceid(struct in6_addr address)
{
@@ -3562,6 +3636,10 @@ restart:
if (state != INET6_IFADDR_STATE_DEAD) {
__ipv6_ifa_notify(RTM_DELADDR, ifa);
inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
+ } else {
+ if (idev->cnf.forwarding)
+ addrconf_leave_anycast(ifa);
+ addrconf_leave_solict(ifa->idev, &ifa->addr);
}
write_lock_bh(&idev->lock);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index b0994a49dfca..b454055ba625 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -93,6 +93,12 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces");
module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
+bool ipv6_mod_enabled(void)
+{
+ return disable_ipv6_mod == 0;
+}
+EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
+
static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
{
const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index ed33abf57abd..5857c1fc8b67 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -67,6 +67,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
struct net *net = rule->fr_net;
pol_lookup_t lookup = arg->lookup_ptr;
int err = 0;
+ u32 tb_id;
switch (rule->action) {
case FR_ACT_TO_TBL:
@@ -86,7 +87,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
goto discard_pkt;
}
- table = fib6_get_table(net, rule->table);
+ tb_id = fib_rule_get_table(rule, arg);
+ table = fib6_get_table(net, tb_id);
if (!table) {
err = -EAGAIN;
goto out;
@@ -199,7 +201,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct net *net = sock_net(skb->sk);
struct fib6_rule *rule6 = (struct fib6_rule *) rule;
- if (rule->action == FR_ACT_TO_TBL) {
+ if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
if (rule->table == RT6_TABLE_UNSPEC)
goto errout;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4527285fcaa2..bd59c343d35f 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -98,7 +98,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
- ping_err(skb, offset, info);
+ ping_err(skb, offset, ntohl(info));
}
static int icmpv6_rcv(struct sk_buff *skb);
@@ -388,7 +388,8 @@ relookup_failed:
/*
* Send an ICMP message in response to a packet in error
*/
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+ const struct in6_addr *force_saddr)
{
struct net *net = dev_net(skb->dev);
struct inet6_dev *idev = NULL;
@@ -475,6 +476,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.daddr = hdr->saddr;
+ if (force_saddr)
+ saddr = force_saddr;
if (saddr)
fl6.saddr = *saddr;
fl6.flowi6_mark = mark;
@@ -502,12 +505,14 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
+ ipc6.tclass = np->tclass;
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
goto out;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- ipc6.tclass = np->tclass;
ipc6.dontfrag = np->dontfrag;
ipc6.opt = NULL;
@@ -549,10 +554,75 @@ out:
*/
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
- icmp6_send(skb, ICMPV6_PARAMPROB, code, pos);
+ icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
kfree_skb(skb);
}
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ * @nhs is the size of the tunnel header(s) :
+ * Either an IPv4 header for SIT encap
+ * an IPv4 header + GRE header for GRE encap
+ */
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+ unsigned int data_len)
+{
+ struct in6_addr temp_saddr;
+ struct rt6_info *rt;
+ struct sk_buff *skb2;
+ u32 info = 0;
+
+ if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
+ return 1;
+
+ /* RFC 4884 (partial) support for ICMP extensions */
+ if (data_len < 128 || (data_len & 7) || skb->len < data_len)
+ data_len = 0;
+
+ skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
+
+ if (!skb2)
+ return 1;
+
+ skb_dst_drop(skb2);
+ skb_pull(skb2, nhs);
+ skb_reset_network_header(skb2);
+
+ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+
+ if (rt && rt->dst.dev)
+ skb2->dev = rt->dst.dev;
+
+ ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
+
+ if (data_len) {
+ /* RFC 4884 (partial) support :
+ * insert 0 padding at the end, before the extensions
+ */
+ __skb_push(skb2, nhs);
+ skb_reset_network_header(skb2);
+ memmove(skb2->data, skb2->data + nhs, data_len - nhs);
+ memset(skb2->data + data_len - nhs, 0, nhs);
+ /* RFC 4884 4.5 : Length is measured in 64-bit words,
+ * and stored in reserved[0]
+ */
+ info = (data_len/8) << 24;
+ }
+ if (type == ICMP_TIME_EXCEEDED)
+ icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
+ info, &temp_saddr);
+ else
+ icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
+ info, &temp_saddr);
+ if (rt)
+ ip6_rt_put(rt);
+
+ kfree_skb(skb2);
+
+ return 0;
+}
+EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
+
static void icmpv6_echo_reply(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
@@ -585,7 +655,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.daddr = ipv6_hdr(skb)->saddr;
if (saddr)
fl6.saddr = *saddr;
- fl6.flowi6_oif = l3mdev_fib_oif(skb->dev);
+ fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
index d08fd2d48a78..e0170f62bc39 100644
--- a/net/ipv6/ila/ila.h
+++ b/net/ipv6/ila/ila.h
@@ -109,7 +109,8 @@ static inline bool ila_csum_neutral_set(struct ila_identifier ident)
return !!(ident.csum_neutral);
}
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p);
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+ bool set_csum_neutral);
void ila_init_saved_csum(struct ila_params *p);
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 0e94042d1289..ec9efbcdad35 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -34,12 +34,12 @@ static void ila_csum_do_neutral(struct ila_addr *iaddr,
if (p->locator_match.v64) {
diff = p->csum_diff;
} else {
- diff = compute_csum_diff8((__be32 *)iaddr,
- (__be32 *)&p->locator);
+ diff = compute_csum_diff8((__be32 *)&p->locator,
+ (__be32 *)iaddr);
}
fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ?
- ~CSUM_NEUTRAL_FLAG : CSUM_NEUTRAL_FLAG);
+ CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG);
diff = csum_add(diff, fval);
@@ -103,7 +103,8 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
iaddr->loc = p->locator;
}
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+ bool set_csum_neutral)
{
struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct ila_addr *iaddr = ila_a2i(&ip6h->daddr);
@@ -114,7 +115,8 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
* is a locator being translated to a SIR address.
* Perform (receiver) checksum-neutral translation.
*/
- ila_csum_do_neutral(iaddr, p);
+ if (!set_csum_neutral)
+ ila_csum_do_neutral(iaddr, p);
} else {
switch (p->csum_mode) {
case ILA_CSUM_ADJUST_TRANSPORT:
@@ -138,8 +140,8 @@ void ila_init_saved_csum(struct ila_params *p)
return;
p->csum_diff = compute_csum_diff8(
- (__be32 *)&p->locator_match,
- (__be32 *)&p->locator);
+ (__be32 *)&p->locator,
+ (__be32 *)&p->locator_match);
}
static int __init ila_init(void)
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 1dfb64166d7d..c8314c6b6154 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -26,7 +26,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
- ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+ ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), true);
return dst->lwtstate->orig_output(net, sk, skb);
@@ -42,7 +42,7 @@ static int ila_input(struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
- ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+ ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false);
return dst->lwtstate->orig_input(skb);
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index a90e57229c6c..e6eca5fdf4c9 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -210,14 +210,14 @@ static void ila_free_cb(void *ptr, void *arg)
}
}
-static int ila_xlat_addr(struct sk_buff *skb);
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral);
static unsigned int
ila_nf_input(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- ila_xlat_addr(skb);
+ ila_xlat_addr(skb, false);
return NF_ACCEPT;
}
@@ -597,7 +597,7 @@ static struct pernet_operations ila_net_ops = {
.size = sizeof(struct ila_net),
};
-static int ila_xlat_addr(struct sk_buff *skb)
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral)
{
struct ila_map *ila;
struct ipv6hdr *ip6h = ipv6_hdr(skb);
@@ -616,7 +616,7 @@ static int ila_xlat_addr(struct sk_buff *skb)
ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan);
if (ila)
- ila_update_ipv6_locator(skb, &ila->xp.ip);
+ ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral);
rcu_read_unlock();
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index b2025bf3da4a..c0cbcb259f5a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -78,9 +78,12 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
* we accept a checksum of zero here. When we find the socket
* for the UDP packet we'll check if that socket allows zero checksum
* for IPv6 (set by socket option).
+ *
+ * Note, we are only interested in != 0 or == 0, thus the
+ * force to int.
*/
- return skb_checksum_init_zero_check(skb, proto, uh->check,
- ip6_compute_pseudo);
+ return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+ ip6_compute_pseudo);
}
EXPORT_SYMBOL(udp6_csum_init);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1bcef2369d64..771be1fa4176 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -177,6 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
}
}
+ free_percpu(non_pcpu_rt->rt6i_pcpu);
non_pcpu_rt->rt6i_pcpu = NULL;
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f4ac2842d4d9..776d145113e1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -468,7 +468,7 @@ static int gre_rcv(struct sk_buff *skb)
bool csum_err = false;
int hdr_len;
- hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6));
+ hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6), 0);
if (hdr_len < 0)
goto drop;
@@ -1256,6 +1256,8 @@ static int ip6gre_tap_init(struct net_device *dev)
if (ret)
return ret;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
tunnel = netdev_priv(dev);
ip6gre_tnl_link_config(tunnel, 1);
@@ -1289,6 +1291,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
}
static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 14dacc544c3e..713676f14a0e 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -39,7 +39,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
if (!send)
goto out;
- send(skb, type, code, info);
+ send(skb, type, code, info, NULL);
out:
rcu_read_unlock();
}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 94611e450ec9..aacfb4bce153 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -323,6 +323,7 @@ int ip6_input(struct sk_buff *skb)
dev_net(skb->dev), NULL, skb, skb->dev, NULL,
ip6_input_finish);
}
+EXPORT_SYMBOL_GPL(ip6_input);
int ip6_mc_input(struct sk_buff *skb)
{
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index cbf127ae7c67..1dfc402d9ad1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -368,7 +368,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
if (skb->ignore_df)
return false;
- if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
return false;
return true;
@@ -910,6 +910,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
int err;
int flags = 0;
+ if (ipv6_addr_any(&fl6->saddr) && fl6->flowi6_oif &&
+ (!*dst || !(*dst)->error)) {
+ err = l3mdev_get_saddr6(net, sk, fl6);
+ if (err)
+ goto out_err;
+ }
+
/* The correct way to handle this would be to do
* ip6_route_get_saddr, and then ip6_route_output; however,
* the route-specific preferred source forces the
@@ -999,10 +1006,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
return 0;
out_err_release:
- if (err == -ENETUNREACH)
- IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
+out_err:
+ if (err == -ENETUNREACH)
+ IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
return err;
}
@@ -1071,17 +1079,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst)
{
struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
- int err;
dst = ip6_sk_dst_check(sk, dst, fl6);
+ if (!dst)
+ dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
- err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
- if (err)
- return ERR_PTR(err);
- if (final_dst)
- fl6->daddr = *final_dst;
-
- return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+ return dst;
}
EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f2e2013f8346..6122f9c5cc49 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -921,6 +921,7 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
cache->mfc_un.res.maxvif = vifi + 1;
}
}
+ cache->mfc_un.res.lastuse = jiffies;
}
static int mif6_add(struct net *net, struct mr6_table *mrt,
@@ -1074,6 +1075,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (!c)
return NULL;
+ c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXMIFS;
return c;
}
@@ -1591,14 +1593,15 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
if (likely(mrt->mroute6_sk == NULL)) {
mrt->mroute6_sk = sk;
net->ipv6.devconf_all->mc_forwarding++;
- inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
- NETCONFA_IFINDEX_ALL,
- net->ipv6.devconf_all);
- }
- else
+ } else {
err = -EADDRINUSE;
+ }
write_unlock_bh(&mrt_lock);
+ if (!err)
+ inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
rtnl_unlock();
return err;
@@ -1616,11 +1619,11 @@ int ip6mr_sk_done(struct sock *sk)
write_lock_bh(&mrt_lock);
mrt->mroute6_sk = NULL;
net->ipv6.devconf_all->mc_forwarding--;
+ write_unlock_bh(&mrt_lock);
inet6_netconf_notify_devconf(net,
NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
- write_unlock_bh(&mrt_lock);
mroute_clean_tables(mrt, false);
err = 0;
@@ -2090,6 +2093,7 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
vif = cache->mf6c_parent;
cache->mfc_un.res.pkt++;
cache->mfc_un.res.bytes += skb->len;
+ cache->mfc_un.res.lastuse = jiffies;
if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) {
struct mfc6_cache *cache_proxy;
@@ -2232,10 +2236,10 @@ int ip6_mr_input(struct sk_buff *skb)
static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
struct mfc6_cache *c, struct rtmsg *rtm)
{
- int ct;
- struct rtnexthop *nhp;
- struct nlattr *mp_attr;
struct rta_mfc_stats mfcs;
+ struct nlattr *mp_attr;
+ struct rtnexthop *nhp;
+ int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mf6c_parent >= MAXMIFS)
@@ -2268,7 +2272,10 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
- if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) < 0)
+ if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
+ nla_put_u64_64bit(skb, RTA_EXPIRES,
+ jiffies_to_clock_t(c->mfc_un.res.lastuse),
+ RTA_PAD))
return -EMSGSIZE;
rtm->rtm_type = RTN_MULTICAST;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c245895a3d41..fe65cdc28a45 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -73,15 +73,6 @@
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
-/* Set to 3 to get tracing... */
-#define ND_DEBUG 1
-
-#define ND_PRINTK(val, level, fmt, ...) \
-do { \
- if (val <= ND_DEBUG) \
- net_##level##_ratelimited(fmt, ##__VA_ARGS__); \
-} while (0)
-
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
@@ -150,11 +141,10 @@ struct neigh_table nd_tbl = {
};
EXPORT_SYMBOL_GPL(nd_tbl);
-static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+ int data_len, int pad)
{
- int pad = ndisc_addr_option_pad(skb->dev->type);
- int data_len = skb->dev->addr_len;
- int space = ndisc_opt_addr_space(skb->dev);
+ int space = __ndisc_opt_addr_space(data_len, pad);
u8 *opt = skb_put(skb, space);
opt[0] = type;
@@ -171,6 +161,23 @@ static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
if (space > 0)
memset(opt, 0, space);
}
+EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
+
+static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
+ void *data, u8 icmp6_type)
+{
+ __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
+ ndisc_addr_option_pad(skb->dev->type));
+ ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type);
+}
+
+static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb,
+ void *ha,
+ const u8 *ops_data)
+{
+ ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT);
+ ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data);
+}
static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
@@ -185,24 +192,28 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}
-static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
+static inline int ndisc_is_useropt(const struct net_device *dev,
+ struct nd_opt_hdr *opt)
{
return opt->nd_opt_type == ND_OPT_RDNSS ||
- opt->nd_opt_type == ND_OPT_DNSSL;
+ opt->nd_opt_type == ND_OPT_DNSSL ||
+ ndisc_ops_is_useropt(dev, opt->nd_opt_type);
}
-static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
+static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
+ struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
{
if (!cur || !end || cur >= end)
return NULL;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
- } while (cur < end && !ndisc_is_useropt(cur));
- return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
+ } while (cur < end && !ndisc_is_useropt(dev, cur));
+ return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL;
}
-struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+ u8 *opt, int opt_len,
struct ndisc_options *ndopts)
{
struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
@@ -217,6 +228,8 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
l = nd_opt->nd_opt_len << 3;
if (opt_len < l || l == 0)
return NULL;
+ if (ndisc_ops_parse_options(dev, nd_opt, ndopts))
+ goto next_opt;
switch (nd_opt->nd_opt_type) {
case ND_OPT_SOURCE_LL_ADDR:
case ND_OPT_TARGET_LL_ADDR:
@@ -243,7 +256,7 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
break;
#endif
default:
- if (ndisc_is_useropt(nd_opt)) {
+ if (ndisc_is_useropt(dev, nd_opt)) {
ndopts->nd_useropts_end = nd_opt;
if (!ndopts->nd_useropts)
ndopts->nd_useropts = nd_opt;
@@ -260,6 +273,7 @@ struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
nd_opt->nd_opt_len);
}
}
+next_opt:
opt_len -= l;
nd_opt = ((void *)nd_opt) + l;
}
@@ -509,7 +523,8 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
if (!dev->addr_len)
inc_opt = 0;
if (inc_opt)
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_opt_addr_space(dev,
+ NDISC_NEIGHBOUR_ADVERTISEMENT);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -528,8 +543,8 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
if (inc_opt)
ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
- dev->dev_addr);
-
+ dev->dev_addr,
+ NDISC_NEIGHBOUR_ADVERTISEMENT);
ndisc_send_skb(skb, daddr, src_addr);
}
@@ -574,7 +589,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
if (ipv6_addr_any(saddr))
inc_opt = false;
if (inc_opt)
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_opt_addr_space(dev,
+ NDISC_NEIGHBOUR_SOLICITATION);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -590,7 +606,8 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
if (inc_opt)
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
- dev->dev_addr);
+ dev->dev_addr,
+ NDISC_NEIGHBOUR_SOLICITATION);
ndisc_send_skb(skb, daddr, saddr);
}
@@ -626,7 +643,7 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
}
#endif
if (send_sllao)
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
@@ -641,7 +658,8 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
if (send_sllao)
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
- dev->dev_addr);
+ dev->dev_addr,
+ NDISC_ROUTER_SOLICITATION);
ndisc_send_skb(skb, daddr, saddr);
}
@@ -702,6 +720,15 @@ static int pndisc_is_router(const void *pkey,
return ret;
}
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+ const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+ struct ndisc_options *ndopts)
+{
+ neigh_update(neigh, lladdr, new, flags);
+ /* report ndisc ops about neighbour update */
+ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
+}
+
static void ndisc_recv_ns(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
@@ -738,7 +765,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
return;
}
- if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+ if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, warn, "NS: invalid ND options\n");
return;
}
@@ -856,9 +883,10 @@ have_ifp:
neigh = __neigh_lookup(&nd_tbl, saddr, dev,
!inc || lladdr || !dev->addr_len);
if (neigh)
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
- NEIGH_UPDATE_F_OVERRIDE);
+ NEIGH_UPDATE_F_OVERRIDE,
+ NDISC_NEIGHBOUR_SOLICITATION, &ndopts);
if (neigh || !dev->header_ops) {
ndisc_send_na(dev, saddr, &msg->target, !!is_router,
true, (ifp != NULL && inc), inc);
@@ -911,7 +939,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
idev->cnf.drop_unsolicited_na)
return;
- if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+ if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, warn, "NS: invalid ND option\n");
return;
}
@@ -967,12 +995,13 @@ static void ndisc_recv_na(struct sk_buff *skb)
goto out;
}
- neigh_update(neigh, lladdr,
+ ndisc_update(dev, neigh, lladdr,
msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
(msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
- (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0));
+ (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0),
+ NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts);
if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
/*
@@ -1017,7 +1046,7 @@ static void ndisc_recv_rs(struct sk_buff *skb)
goto out;
/* Parse ND options */
- if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) {
+ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
goto out;
}
@@ -1031,10 +1060,11 @@ static void ndisc_recv_rs(struct sk_buff *skb)
neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
if (neigh) {
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
- NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
+ NEIGH_UPDATE_F_OVERRIDE_ISROUTER,
+ NDISC_ROUTER_SOLICITATION, &ndopts);
neigh_release(neigh);
}
out:
@@ -1135,7 +1165,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
return;
}
- if (!ndisc_parse_options(opt, optlen, &ndopts)) {
+ if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) {
ND_PRINTK(2, warn, "RA: invalid ND options\n");
return;
}
@@ -1329,11 +1359,12 @@ skip_linkparms:
goto out;
}
}
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
- NEIGH_UPDATE_F_ISROUTER);
+ NEIGH_UPDATE_F_ISROUTER,
+ NDISC_ROUTER_ADVERTISEMENT, &ndopts);
}
if (!ipv6_accept_ra(in6_dev)) {
@@ -1421,7 +1452,8 @@ skip_routeinfo:
struct nd_opt_hdr *p;
for (p = ndopts.nd_useropts;
p;
- p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) {
+ p = ndisc_next_useropt(skb->dev, p,
+ ndopts.nd_useropts_end)) {
ndisc_ra_useropt(skb, p);
}
}
@@ -1459,7 +1491,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
return;
}
- if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts))
+ if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts))
return;
if (!ndopts.nd_opts_rh) {
@@ -1504,7 +1536,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
struct dst_entry *dst;
struct flowi6 fl6;
int rd_len;
- u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
+ u8 ha_buf[MAX_ADDR_LEN], *ha = NULL,
+ ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
int oif = l3mdev_fib_oif(dev);
bool ret;
@@ -1563,7 +1596,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
memcpy(ha_buf, neigh->ha, dev->addr_len);
read_unlock_bh(&neigh->lock);
ha = ha_buf;
- optlen += ndisc_opt_addr_space(dev);
+ optlen += ndisc_redirect_opt_addr_space(dev, neigh,
+ ops_data_buf,
+ &ops_data);
} else
read_unlock_bh(&neigh->lock);
@@ -1594,7 +1629,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
*/
if (ha)
- ndisc_fill_addr_option(buff, ND_OPT_TARGET_LL_ADDR, ha);
+ ndisc_fill_redirect_addr_option(buff, ha, ops_data);
/*
* build redirect option and copy skb over to the new packet.
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 63e06c3dd319..552fac2f390a 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -73,22 +73,22 @@ ip6_packet_match(const struct sk_buff *skb,
unsigned long ret;
const struct ipv6hdr *ipv6 = ipv6_hdr(skb);
-#define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg)))
-
- if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk,
- &ip6info->src), IP6T_INV_SRCIP) ||
- FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk,
- &ip6info->dst), IP6T_INV_DSTIP))
+ if (NF_INVF(ip6info, IP6T_INV_SRCIP,
+ ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk,
+ &ip6info->src)) ||
+ NF_INVF(ip6info, IP6T_INV_DSTIP,
+ ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk,
+ &ip6info->dst)))
return false;
ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask);
- if (FWINV(ret != 0, IP6T_INV_VIA_IN))
+ if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0))
return false;
ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask);
- if (FWINV(ret != 0, IP6T_INV_VIA_OUT))
+ if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0))
return false;
/* ... might want to do something with class and flowlabel here ... */
@@ -402,23 +402,12 @@ ip6t_do_table(struct sk_buff *skb,
else return verdict;
}
-static bool find_jump_target(const struct xt_table_info *t,
- const struct ip6t_entry *target)
-{
- struct ip6t_entry *iter;
-
- xt_entry_foreach(iter, t->entries, t->size) {
- if (iter == target)
- return true;
- }
- return false;
-}
-
/* Figures out from what hook each rule can be called: returns 0 if
there are loops. Puts hook bitmask in comefrom. */
static int
mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;
@@ -487,10 +476,11 @@ mark_source_chains(const struct xt_table_info *newinfo,
XT_STANDARD_TARGET) == 0 &&
newpos >= 0) {
/* This a jump; chase it. */
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
e = (struct ip6t_entry *)
(entry0 + newpos);
- if (!find_jump_target(newinfo, e))
- return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
@@ -724,6 +714,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ip6t_replace *repl)
{
struct ip6t_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;
@@ -736,6 +727,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
newinfo->underflow[i] = 0xFFFFFFFF;
}
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;
/* Walk through entries, checking offsets. */
xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -745,15 +739,18 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- return ret;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(ip6t_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}
+ ret = -EINVAL;
if (i != repl->num_entries)
- return -EINVAL;
+ goto out_free;
/* Check hooks all assigned */
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
@@ -761,13 +758,16 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
if (!(repl->valid_hooks & (1 << i)))
continue;
if (newinfo->hook_entry[i] == 0xFFFFFFFF)
- return -EINVAL;
+ goto out_free;
if (newinfo->underflow[i] == 0xFFFFFFFF)
- return -EINVAL;
+ goto out_free;
}
- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
+ }
+ kvfree(offsets);
/* Finally, each sanity check must pass */
i = 0;
@@ -788,6 +788,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index cb2b28883252..2b1a9dcdbcb3 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -83,10 +83,6 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb,
{
if (state->hook == NF_INET_LOCAL_OUT)
return ip6t_mangle_out(skb, state);
- if (state->hook == NF_INET_POST_ROUTING)
- return ip6t_do_table(skb, state,
- state->net->ipv6.ip6table_mangle);
- /* INPUT/FORWARD */
return ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle);
}
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 6989c70ae29f..4a84b5ad9ecb 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -33,6 +33,7 @@ static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb,
fl6.daddr = *gw;
fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
(iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
+ fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 3ee3e444a66b..fed40d1ec29b 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -116,6 +116,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
+ ipc6.tclass = np->tclass;
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr);
if (IS_ERR(dst))
return PTR_ERR(dst);
@@ -140,7 +143,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
pfh.family = AF_INET6;
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- ipc6.tclass = np->tclass;
ipc6.dontfrag = np->dontfrag;
ipc6.opt = NULL;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896350df6423..590dd1f7746f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -878,6 +878,11 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (inet->hdrincl)
fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
+ if (ipc6.tclass < 0)
+ ipc6.tclass = np->tclass;
+
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
@@ -886,9 +891,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
if (ipc6.dontfrag < 0)
ipc6.dontfrag = np->dontfrag;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 969913da494f..49817555449e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1042,8 +1042,8 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
return pcpu_rt;
}
-static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
- struct flowi6 *fl6, int flags)
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int flags)
{
struct fib6_node *fn, *saved_fn;
struct rt6_info *rt;
@@ -1139,6 +1139,7 @@ redo_rt6_select:
}
}
+EXPORT_SYMBOL_GPL(ip6_pol_route);
static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
struct flowi6 *fl6, int flags)
@@ -1782,7 +1783,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
};
struct fib6_table *table;
struct rt6_info *rt;
- int flags = 0;
+ int flags = RT6_LOOKUP_F_IFACE;
table = fib6_get_table(net, cfg->fc_table);
if (!table)
@@ -2200,7 +2201,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
* first-hop router for the specified ICMP Destination Address.
*/
- if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) {
+ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) {
net_dbg_ratelimited("rt6_redirect: invalid ND options\n");
return;
}
@@ -2235,12 +2236,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
* We have finally decided to accept it.
*/
- neigh_update(neigh, lladdr, NUD_STALE,
+ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
(on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
- NEIGH_UPDATE_F_ISROUTER))
- );
+ NEIGH_UPDATE_F_ISROUTER)),
+ NDISC_REDIRECT, &ndopts);
nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
if (!nrt)
@@ -2585,23 +2586,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
return rt;
}
-int ip6_route_get_saddr(struct net *net,
- struct rt6_info *rt,
- const struct in6_addr *daddr,
- unsigned int prefs,
- struct in6_addr *saddr)
-{
- struct inet6_dev *idev =
- rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
- int err = 0;
- if (rt && rt->rt6i_prefsrc.plen)
- *saddr = rt->rt6i_prefsrc.addr;
- else
- err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
- daddr, prefs, saddr);
- return err;
-}
-
/* remove deleted ip from prefsrc entries */
struct arg_dev_net_ip {
struct net_device *dev;
@@ -3306,6 +3290,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
err = -EINVAL;
memset(&fl6, 0, sizeof(fl6));
+ rtm = nlmsg_data(nlh);
+ fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
if (tb[RTA_SRC]) {
if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0a5a255277e5..182b6a9be29d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -479,47 +479,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
dev_put(dev);
}
-/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
- * if sufficient data bytes are available
- */
-static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb)
-{
- int ihl = ((const struct iphdr *)skb->data)->ihl*4;
- struct rt6_info *rt;
- struct sk_buff *skb2;
-
- if (!pskb_may_pull(skb, ihl + sizeof(struct ipv6hdr) + 8))
- return 1;
-
- skb2 = skb_clone(skb, GFP_ATOMIC);
-
- if (!skb2)
- return 1;
-
- skb_dst_drop(skb2);
- skb_pull(skb2, ihl);
- skb_reset_network_header(skb2);
-
- rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
-
- if (rt && rt->dst.dev)
- skb2->dev = rt->dst.dev;
-
- icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-
- if (rt)
- ip6_rt_put(rt);
-
- kfree_skb(skb2);
-
- return 0;
-}
-
static int ipip6_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
+ unsigned int data_len = 0;
struct ip_tunnel *t;
int err;
@@ -544,6 +509,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return 0;
+ data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
break;
case ICMP_REDIRECT:
break;
@@ -560,22 +526,22 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, IPPROTO_IPV6, 0);
+ t->parms.link, 0, iph->protocol, 0);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
- IPPROTO_IPV6, 0);
+ iph->protocol, 0);
err = 0;
goto out;
}
- if (t->parms.iph.daddr == 0)
+ err = 0;
+ if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
goto out;
- err = 0;
- if (!ipip6_err_gen_icmpv6_unreach(skb))
+ if (t->parms.iph.daddr == 0)
goto out;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
@@ -722,12 +688,19 @@ out:
return 0;
}
-static const struct tnl_ptk_info tpi = {
+static const struct tnl_ptk_info ipip_tpi = {
/* no tunnel info required for ipip. */
.proto = htons(ETH_P_IP),
};
-static int ipip_rcv(struct sk_buff *skb)
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct tnl_ptk_info mplsip_tpi = {
+ /* no tunnel info required for mplsip. */
+ .proto = htons(ETH_P_MPLS_UC),
+};
+#endif
+
+static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
{
const struct iphdr *iph;
struct ip_tunnel *tunnel;
@@ -736,15 +709,23 @@ static int ipip_rcv(struct sk_buff *skb)
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel) {
- if (tunnel->parms.iph.protocol != IPPROTO_IPIP &&
+ const struct tnl_ptk_info *tpi;
+
+ if (tunnel->parms.iph.protocol != ipproto &&
tunnel->parms.iph.protocol != 0)
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
- if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+#if IS_ENABLED(CONFIG_MPLS)
+ if (ipproto == IPPROTO_MPLS)
+ tpi = &mplsip_tpi;
+ else
+#endif
+ tpi = &ipip_tpi;
+ if (iptunnel_pull_header(skb, 0, tpi->proto, false))
goto drop;
- return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error);
+ return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
}
return 1;
@@ -754,6 +735,18 @@ drop:
return 0;
}
+static int ipip_rcv(struct sk_buff *skb)
+{
+ return sit_tunnel_rcv(skb, IPPROTO_IPIP);
+}
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int mplsip_rcv(struct sk_buff *skb)
+{
+ return sit_tunnel_rcv(skb, IPPROTO_MPLS);
+}
+#endif
+
/*
* If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
* stores the embedded IPv4 address in v4dst and returns true.
@@ -825,9 +818,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
u8 protocol = IPPROTO_IPV6;
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
- if (skb->protocol != htons(ETH_P_IPV6))
- goto tx_error;
-
if (tos == 1)
tos = ipv6_get_dsfield(iph6);
@@ -995,7 +985,8 @@ tx_error:
return NETDEV_TX_OK;
}
-static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
+ struct net_device *dev, u8 ipproto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
@@ -1003,9 +994,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
goto tx_error;
- skb_set_inner_ipproto(skb, IPPROTO_IPIP);
+ skb_set_inner_ipproto(skb, ipproto);
- ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
+ ip_tunnel_xmit(skb, dev, tiph, ipproto);
return NETDEV_TX_OK;
tx_error:
kfree_skb(skb);
@@ -1018,11 +1009,16 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
{
switch (skb->protocol) {
case htons(ETH_P_IP):
- ipip_tunnel_xmit(skb, dev);
+ sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);
break;
case htons(ETH_P_IPV6):
ipip6_tunnel_xmit(skb, dev);
break;
+#if IS_ENABLED(CONFIG_MPLS)
+ case htons(ETH_P_MPLS_UC):
+ sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS);
+ break;
+#endif
default:
goto tx_err;
}
@@ -1130,6 +1126,16 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
}
#endif
+bool ipip6_valid_ip_proto(u8 ipproto)
+{
+ return ipproto == IPPROTO_IPV6 ||
+ ipproto == IPPROTO_IPIP ||
+#if IS_ENABLED(CONFIG_MPLS)
+ ipproto == IPPROTO_MPLS ||
+#endif
+ ipproto == 0;
+}
+
static int
ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
@@ -1189,9 +1195,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
goto done;
err = -EINVAL;
- if (p.iph.protocol != IPPROTO_IPV6 &&
- p.iph.protocol != IPPROTO_IPIP &&
- p.iph.protocol != 0)
+ if (!ipip6_valid_ip_proto(p.iph.protocol))
goto done;
if (p.iph.version != 4 ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
@@ -1416,9 +1420,7 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
- if (proto != IPPROTO_IPV6 &&
- proto != IPPROTO_IPIP &&
- proto != 0)
+ if (!ipip6_valid_ip_proto(proto))
return -EINVAL;
return 0;
@@ -1760,6 +1762,14 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
.priority = 2,
};
+#if IS_ENABLED(CONFIG_MPLS)
+static struct xfrm_tunnel mplsip_handler __read_mostly = {
+ .handler = mplsip_rcv,
+ .err_handler = ipip6_err,
+ .priority = 2,
+};
+#endif
+
static void __net_exit sit_destroy_tunnels(struct net *net,
struct list_head *head)
{
@@ -1855,6 +1865,9 @@ static void __exit sit_cleanup(void)
rtnl_link_unregister(&sit_link_ops);
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+#if IS_ENABLED(CONFIG_MPLS)
+ xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+#endif
unregister_pernet_device(&sit_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
@@ -1864,7 +1877,7 @@ static int __init sit_init(void)
{
int err;
- pr_info("IPv6 over IPv4 tunneling driver\n");
+ pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n");
err = register_pernet_device(&sit_net_ops);
if (err < 0)
@@ -1879,6 +1892,13 @@ static int __init sit_init(void)
pr_info("%s: can't register ip4ip4\n", __func__);
goto xfrm_tunnel4_failed;
}
+#if IS_ENABLED(CONFIG_MPLS)
+ err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS);
+ if (err < 0) {
+ pr_info("%s: can't register mplsip\n", __func__);
+ goto xfrm_tunnel_mpls_failed;
+ }
+#endif
err = rtnl_link_register(&sit_link_ops);
if (err < 0)
goto rtnl_link_failed;
@@ -1887,6 +1907,10 @@ out:
return err;
rtnl_link_failed:
+#if IS_ENABLED(CONFIG_MPLS)
+ xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+xfrm_tunnel_mpls_failed:
+#endif
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_tunnel4_failed:
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 818b3b5cd490..33df8b8575cc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -530,26 +530,33 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval,
AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
-static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr, int nbytes)
+static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr,
+ const struct tcphdr *th, int nbytes)
{
struct tcp6_pseudohdr *bp;
struct scatterlist sg;
+ struct tcphdr *_th;
- bp = &hp->md5_blk.ip6;
+ bp = hp->scratch;
/* 1. TCP pseudo-header (RFC2460) */
bp->saddr = *saddr;
bp->daddr = *daddr;
bp->protocol = cpu_to_be32(IPPROTO_TCP);
bp->len = cpu_to_be32(nbytes);
- sg_init_one(&sg, bp, sizeof(*bp));
- ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+ _th = (struct tcphdr *)(bp + 1);
+ memcpy(_th, th, sizeof(*th));
+ _th->check = 0;
+
+ sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
+ ahash_request_set_crypt(hp->md5_req, &sg, NULL,
+ sizeof(*bp) + sizeof(*th));
return crypto_ahash_update(hp->md5_req);
}
-static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
+static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
const struct in6_addr *daddr, struct in6_addr *saddr,
const struct tcphdr *th)
{
@@ -563,9 +570,7 @@ static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
if (crypto_ahash_init(req))
goto clear_hash;
- if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
- goto clear_hash;
- if (tcp_md5_hash_header(hp, th))
+ if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(hp, key))
goto clear_hash;
@@ -610,9 +615,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
if (crypto_ahash_init(req))
goto clear_hash;
- if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
- goto clear_hash;
- if (tcp_md5_hash_header(hp, th))
+ if (tcp_v6_md5_hash_headers(hp, daddr, saddr, th, skb->len))
goto clear_hash;
if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
goto clear_hash;
@@ -742,7 +745,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr,
int oif, struct tcp_md5sig_key *key, int rst,
- u8 tclass, u32 label)
+ u8 tclass, __be32 label)
{
const struct tcphdr *th = tcp_hdr(skb);
struct tcphdr *t1;
@@ -915,7 +918,7 @@ out:
static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
u32 ack, u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key, u8 tclass,
- u32 label)
+ __be32 label)
{
tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0,
tclass, label);
@@ -1727,7 +1730,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
destp = ntohs(inet->inet_dport);
srcp = ntohs(inet->inet_sport);
- if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+ if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2da1896af934..81e2f98b958d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -115,11 +115,10 @@ static void udp_v6_rehash(struct sock *sk)
udp_lib_rehash(sk, new_hash);
}
-static inline int compute_score(struct sock *sk, struct net *net,
- unsigned short hnum,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, __be16 dport,
- int dif)
+static int compute_score(struct sock *sk, struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, unsigned short hnum,
+ int dif)
{
int score;
struct inet_sock *inet;
@@ -162,54 +161,11 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
-static inline int compute_score2(struct sock *sk, struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr,
- unsigned short hnum, int dif)
-{
- int score;
- struct inet_sock *inet;
-
- if (!net_eq(sock_net(sk), net) ||
- udp_sk(sk)->udp_port_hash != hnum ||
- sk->sk_family != PF_INET6)
- return -1;
-
- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
- return -1;
-
- score = 0;
- inet = inet_sk(sk);
-
- if (inet->inet_dport) {
- if (inet->inet_dport != sport)
- return -1;
- score++;
- }
-
- if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
- return -1;
- score++;
- }
-
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
- score++;
- }
-
- if (sk->sk_incoming_cpu == raw_smp_processor_id())
- score++;
-
- return score;
-}
-
-/* called with read_rcu_lock() */
+/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned int hnum, int dif,
- struct udp_hslot *hslot2, unsigned int slot2,
+ struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
@@ -219,7 +175,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
result = NULL;
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- score = compute_score2(sk, net, saddr, sport,
+ score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
@@ -268,17 +224,22 @@ struct sock *__udp6_lib_lookup(struct net *net,
result = udp6_lib_lookup2(net, saddr, sport,
daddr, hnum, dif,
- hslot2, slot2, skb);
+ hslot2, skb);
if (!result) {
+ unsigned int old_slot2 = slot2;
hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
slot2 = hash2 & udptable->mask;
+ /* avoid searching the same slot again. */
+ if (unlikely(slot2 == old_slot2))
+ return result;
+
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
result = udp6_lib_lookup2(net, saddr, sport,
- &in6addr_any, hnum, dif,
- hslot2, slot2, skb);
+ daddr, hnum, dif,
+ hslot2, skb);
}
return result;
}
@@ -286,7 +247,7 @@ begin:
result = NULL;
badness = -1;
sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
+ score = compute_score(sk, net, saddr, sport, daddr, hnum, dif);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
@@ -653,12 +614,12 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
}
- if (rcu_access_pointer(sk->sk_filter)) {
- if (udp_lib_checksum_complete(skb))
- goto csum_error;
- if (sk_filter(sk, skb))
- goto drop;
- }
+ if (rcu_access_pointer(sk->sk_filter) &&
+ udp_lib_checksum_complete(skb))
+ goto csum_error;
+
+ if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr)))
+ goto drop;
udp_csum_pull_header(skb);
if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
@@ -1246,6 +1207,11 @@ do_udp_sendmsg:
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+ if (ipc6.tclass < 0)
+ ipc6.tclass = np->tclass;
+
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
@@ -1256,9 +1222,6 @@ do_udp_sendmsg:
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c074771a10f7..6cc97003e4a9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -366,12 +366,12 @@ static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
kfree(table);
}
#else /* CONFIG_SYSCTL */
-static int inline xfrm6_net_sysctl_init(struct net *net)
+static inline int xfrm6_net_sysctl_init(struct net *net)
{
return 0;
}
-static void inline xfrm6_net_sysctl_exit(struct net *net)
+static inline void xfrm6_net_sysctl_exit(struct net *net)
{
}
#endif
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-16 11:53:34 +0000