summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c48
-rw-r--r--net/ipv6/addrlabel.c25
-rw-r--r--net/ipv6/ila/ila_xlat.c4
-rw-r--r--net/ipv6/inet6_hashtables.c77
-rw-r--r--net/ipv6/ip6_fib.c30
-rw-r--r--net/ipv6/ip6_gre.c653
-rw-r--r--net/ipv6/ip6_output.c4
-rw-r--r--net/ipv6/ip6_tunnel.c5
-rw-r--r--net/ipv6/ip6_vti.c20
-rw-r--r--net/ipv6/ip6mr.c9
-rw-r--r--net/ipv6/route.c75
-rw-r--r--net/ipv6/seg6.c4
-rw-r--r--net/ipv6/tcp_ipv6.c2
-rw-r--r--net/ipv6/udp.c54
-rw-r--r--net/ipv6/xfrm6_mode_tunnel.c2
-rw-r--r--net/ipv6/xfrm6_policy.c2
16 files changed, 814 insertions, 200 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f49bd7897e95..ed06b1190f05 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6595,27 +6595,45 @@ int __init addrconf_init(void)
rtnl_af_register(&inet6_ops);
- err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo,
- 0);
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETLINK,
+ NULL, inet6_dump_ifinfo, 0);
if (err < 0)
goto errout;
- /* Only the first call to __rtnl_register can fail */
- __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0);
- __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0);
- __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr,
- inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED);
- __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL,
- inet6_dump_ifmcaddr, 0);
- __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL,
- inet6_dump_ifacaddr, 0);
- __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf,
- inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED);
-
- ipv6_addr_label_rtnl_register();
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDR,
+ inet6_rtm_newaddr, NULL, 0);
+ if (err < 0)
+ goto errout;
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDR,
+ inet6_rtm_deladdr, NULL, 0);
+ if (err < 0)
+ goto errout;
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR,
+ inet6_rtm_getaddr, inet6_dump_ifaddr,
+ RTNL_FLAG_DOIT_UNLOCKED);
+ if (err < 0)
+ goto errout;
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST,
+ NULL, inet6_dump_ifmcaddr, 0);
+ if (err < 0)
+ goto errout;
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST,
+ NULL, inet6_dump_ifacaddr, 0);
+ if (err < 0)
+ goto errout;
+ err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF,
+ inet6_netconf_get_devconf,
+ inet6_netconf_dump_devconf,
+ RTNL_FLAG_DOIT_UNLOCKED);
+ if (err < 0)
+ goto errout;
+ err = ipv6_addr_label_rtnl_register();
+ if (err < 0)
+ goto errout;
return 0;
errout:
+ rtnl_unregister_all(PF_INET6);
rtnl_af_unregister(&inet6_ops);
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 00e1f8ee08f8..1d6ced37ad71 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -547,13 +547,22 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
return err;
}
-void __init ipv6_addr_label_rtnl_register(void)
+int __init ipv6_addr_label_rtnl_register(void)
{
- __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel,
- NULL, RTNL_FLAG_DOIT_UNLOCKED);
- __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel,
- NULL, RTNL_FLAG_DOIT_UNLOCKED);
- __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get,
- ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED);
-}
+ int ret;
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDRLABEL,
+ ip6addrlbl_newdel,
+ NULL, RTNL_FLAG_DOIT_UNLOCKED);
+ if (ret < 0)
+ return ret;
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDRLABEL,
+ ip6addrlbl_newdel,
+ NULL, RTNL_FLAG_DOIT_UNLOCKED);
+ if (ret < 0)
+ return ret;
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDRLABEL,
+ ip6addrlbl_get,
+ ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED);
+ return ret;
+}
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 6eb5e68f112a..44c39c5f0638 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -512,9 +512,7 @@ static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct ila_map *ila;
int ret;
- ret = rhashtable_walk_start(rhiter);
- if (ret && ret != -EAGAIN)
- goto done;
+ rhashtable_walk_start(rhiter);
for (;;) {
ila = rhashtable_walk_next(rhiter);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b01858f5deb1..2febe26de6a1 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -125,6 +125,40 @@ static inline int compute_score(struct sock *sk, struct net *net,
}
/* called with rcu_read_lock() */
+static struct sock *inet6_lhash2_lookup(struct net *net,
+ struct inet_listen_hashbucket *ilb2,
+ struct sk_buff *skb, int doff,
+ const struct in6_addr *saddr,
+ const __be16 sport, const struct in6_addr *daddr,
+ const unsigned short hnum, const int dif, const int sdif)
+{
+ bool exact_dif = inet6_exact_dif_match(net, skb);
+ struct inet_connection_sock *icsk;
+ struct sock *sk, *result = NULL;
+ int score, hiscore = 0;
+ u32 phash = 0;
+
+ inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
+ sk = (struct sock *)icsk;
+ score = compute_score(sk, net, hnum, daddr, dif, sdif,
+ exact_dif);
+ if (score > hiscore) {
+ if (sk->sk_reuseport) {
+ phash = inet6_ehashfn(net, daddr, hnum,
+ saddr, sport);
+ result = reuseport_select_sock(sk, phash,
+ skb, doff);
+ if (result)
+ return result;
+ }
+ result = sk;
+ hiscore = score;
+ }
+ }
+
+ return result;
+}
+
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
@@ -134,31 +168,56 @@ struct sock *inet6_lookup_listener(struct net *net,
{
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
- int score, hiscore = 0, matches = 0, reuseport = 0;
bool exact_dif = inet6_exact_dif_match(net, skb);
+ struct inet_listen_hashbucket *ilb2;
struct sock *sk, *result = NULL;
+ int score, hiscore = 0;
+ unsigned int hash2;
u32 phash = 0;
+ if (ilb->count <= 10 || !hashinfo->lhash2)
+ goto port_lookup;
+
+ /* Too many sk in the ilb bucket (which is hashed by port alone).
+ * Try lhash2 (which is hashed by port and addr) instead.
+ */
+
+ hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+ ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+ if (ilb2->count > ilb->count)
+ goto port_lookup;
+
+ result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+ saddr, sport, daddr, hnum,
+ dif, sdif);
+ if (result)
+ return result;
+
+ /* Lookup lhash2 with in6addr_any */
+
+ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
+ ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+ if (ilb2->count > ilb->count)
+ goto port_lookup;
+
+ return inet6_lhash2_lookup(net, ilb2, skb, doff,
+ saddr, sport, daddr, hnum,
+ dif, sdif);
+
+port_lookup:
sk_for_each(sk, &ilb->head) {
score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif);
if (score > hiscore) {
- reuseport = sk->sk_reuseport;
- if (reuseport) {
+ if (sk->sk_reuseport) {
phash = inet6_ehashfn(net, daddr, hnum,
saddr, sport);
result = reuseport_select_sock(sk, phash,
skb, doff);
if (result)
return result;
- matches = 1;
}
result = sk;
hiscore = score;
- } else if (score == hiscore && reuseport) {
- matches++;
- if (reciprocal_scale(phash, matches) == 0)
- result = sk;
- phash = next_pseudo_random32(phash);
}
}
return result;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f5285f4e1d08..a64d559fa513 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -893,7 +893,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
ins = &fn->leaf;
for (iter = leaf; iter;
- iter = rcu_dereference_protected(iter->dst.rt6_next,
+ iter = rcu_dereference_protected(iter->rt6_next,
lockdep_is_held(&rt->rt6i_table->tb6_lock))) {
/*
* Search for duplicates
@@ -950,7 +950,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
break;
next_iter:
- ins = &iter->dst.rt6_next;
+ ins = &iter->rt6_next;
}
if (fallback_ins && !found) {
@@ -979,7 +979,7 @@ next_iter:
&sibling->rt6i_siblings);
break;
}
- sibling = rcu_dereference_protected(sibling->dst.rt6_next,
+ sibling = rcu_dereference_protected(sibling->rt6_next,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
}
/* For each sibling in the list, increment the counter of
@@ -1009,7 +1009,7 @@ add:
if (err)
return err;
- rcu_assign_pointer(rt->dst.rt6_next, iter);
+ rcu_assign_pointer(rt->rt6_next, iter);
atomic_inc(&rt->rt6i_ref);
rcu_assign_pointer(rt->rt6i_node, fn);
rcu_assign_pointer(*ins, rt);
@@ -1040,7 +1040,7 @@ add:
atomic_inc(&rt->rt6i_ref);
rcu_assign_pointer(rt->rt6i_node, fn);
- rt->dst.rt6_next = iter->dst.rt6_next;
+ rt->rt6_next = iter->rt6_next;
rcu_assign_pointer(*ins, rt);
call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE,
rt, extack);
@@ -1059,14 +1059,14 @@ add:
if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
- ins = &rt->dst.rt6_next;
+ ins = &rt->rt6_next;
iter = rcu_dereference_protected(*ins,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
while (iter) {
if (iter->rt6i_metric > rt->rt6i_metric)
break;
if (rt6_qualify_for_ecmp(iter)) {
- *ins = iter->dst.rt6_next;
+ *ins = iter->rt6_next;
iter->rt6i_node = NULL;
fib6_purge_rt(iter, fn, info->nl_net);
if (rcu_access_pointer(fn->rr_ptr) == iter)
@@ -1075,7 +1075,7 @@ add:
nsiblings--;
info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
} else {
- ins = &iter->dst.rt6_next;
+ ins = &iter->rt6_next;
}
iter = rcu_dereference_protected(*ins,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
@@ -1644,7 +1644,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
/* Unlink it */
- *rtp = rt->dst.rt6_next;
+ *rtp = rt->rt6_next;
rt->rt6i_node = NULL;
net->ipv6.rt6_stats->fib_rt_entries--;
net->ipv6.rt6_stats->fib_discarded_routes++;
@@ -1672,7 +1672,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
FOR_WALKERS(net, w) {
if (w->state == FWS_C && w->leaf == rt) {
RT6_TRACE("walker %p adjusted by delroute\n", w);
- w->leaf = rcu_dereference_protected(rt->dst.rt6_next,
+ w->leaf = rcu_dereference_protected(rt->rt6_next,
lockdep_is_held(&table->tb6_lock));
if (!w->leaf)
w->state = FWS_U;
@@ -1731,7 +1731,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
fib6_del_route(table, fn, rtp, info);
return 0;
}
- rtp_next = &cur->dst.rt6_next;
+ rtp_next = &cur->rt6_next;
}
return -ENOENT;
}
@@ -2142,8 +2142,8 @@ int __init fib6_init(void)
if (ret)
goto out_kmem_cache_create;
- ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib,
- 0);
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL,
+ inet6_dump_fib, 0);
if (ret)
goto out_unregister_subsys;
@@ -2208,7 +2208,7 @@ static int ipv6_route_yield(struct fib6_walker *w)
do {
iter->w.leaf = rcu_dereference_protected(
- iter->w.leaf->dst.rt6_next,
+ iter->w.leaf->rt6_next,
lockdep_is_held(&iter->tbl->tb6_lock));
iter->skip--;
if (!iter->skip && iter->w.leaf)
@@ -2274,7 +2274,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
if (!v)
goto iter_table;
- n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next);
+ n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next);
if (n) {
++*pos;
return n;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 416c8913f132..97f148f15429 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -55,6 +55,8 @@
#include <net/ip6_route.h>
#include <net/ip6_tunnel.h>
#include <net/gre.h>
+#include <net/erspan.h>
+#include <net/dst_metadata.h>
static bool log_ecn_error = true;
@@ -68,11 +70,13 @@ static unsigned int ip6gre_net_id __read_mostly;
struct ip6gre_net {
struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
+ struct ip6_tnl __rcu *collect_md_tun;
struct net_device *fb_tunnel_dev;
};
static struct rtnl_link_ops ip6gre_link_ops __read_mostly;
static struct rtnl_link_ops ip6gre_tap_ops __read_mostly;
+static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly;
static int ip6gre_tunnel_init(struct net_device *dev);
static void ip6gre_tunnel_setup(struct net_device *dev);
static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
@@ -121,7 +125,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
unsigned int h1 = HASH_KEY(key);
struct ip6_tnl *t, *cand = NULL;
struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
- int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
+ int dev_type = (gre_proto == htons(ETH_P_TEB) ||
+ gre_proto == htons(ETH_P_ERSPAN)) ?
ARPHRD_ETHER : ARPHRD_IP6GRE;
int score, cand_score = 4;
@@ -226,6 +231,10 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
if (cand)
return cand;
+ t = rcu_dereference(ign->collect_md_tun);
+ if (t && t->dev->flags & IFF_UP)
+ return t;
+
dev = ign->fb_tunnel_dev;
if (dev->flags & IFF_UP)
return netdev_priv(dev);
@@ -261,6 +270,9 @@ static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t);
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun, t);
+
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
@@ -270,6 +282,9 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t)
struct ip6_tnl __rcu **tp;
struct ip6_tnl *iter;
+ if (t->parms.collect_md)
+ rcu_assign_pointer(ign->collect_md_tun, NULL);
+
for (tp = ip6gre_bucket(ign, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
@@ -460,7 +475,111 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
&ipv6h->saddr, &ipv6h->daddr, tpi->key,
tpi->proto);
if (tunnel) {
- ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
+ if (tunnel->parms.collect_md) {
+ struct metadata_dst *tun_dst;
+ __be64 tun_id;
+ __be16 flags;
+
+ flags = tpi->flags;
+ tun_id = key32_to_tunnel_id(tpi->key);
+
+ tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, 0);
+ if (!tun_dst)
+ return PACKET_REJECT;
+
+ ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
+ } else {
+ ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
+ }
+
+ return PACKET_RCVD;
+ }
+
+ return PACKET_REJECT;
+}
+
+static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
+ struct tnl_ptk_info *tpi)
+{
+ struct erspan_base_hdr *ershdr;
+ struct erspan_metadata *pkt_md;
+ const struct ipv6hdr *ipv6h;
+ struct ip6_tnl *tunnel;
+ u8 ver;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr))))
+ return PACKET_REJECT;
+
+ ipv6h = ipv6_hdr(skb);
+ ershdr = (struct erspan_base_hdr *)skb->data;
+ ver = (ntohs(ershdr->ver_vlan) & VER_MASK) >> VER_OFFSET;
+ tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK);
+
+ tunnel = ip6gre_tunnel_lookup(skb->dev,
+ &ipv6h->saddr, &ipv6h->daddr, tpi->key,
+ tpi->proto);
+ if (tunnel) {
+ int len = erspan_hdr_len(ver);
+
+ if (unlikely(!pskb_may_pull(skb, len)))
+ return PACKET_REJECT;
+
+ ershdr = (struct erspan_base_hdr *)skb->data;
+ pkt_md = (struct erspan_metadata *)(ershdr + 1);
+
+ if (__iptunnel_pull_header(skb, len,
+ htons(ETH_P_TEB),
+ false, false) < 0)
+ return PACKET_REJECT;
+
+ if (tunnel->parms.collect_md) {
+ struct metadata_dst *tun_dst;
+ struct ip_tunnel_info *info;
+ struct erspan_metadata *md;
+ __be64 tun_id;
+ __be16 flags;
+
+ tpi->flags |= TUNNEL_KEY;
+ flags = tpi->flags;
+ tun_id = key32_to_tunnel_id(tpi->key);
+
+ tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id,
+ sizeof(*md));
+ if (!tun_dst)
+ return PACKET_REJECT;
+
+ info = &tun_dst->u.tun_info;
+ md = ip_tunnel_info_opts(info);
+ if (!md) {
+ dst_release((struct dst_entry *)tun_dst);
+ return PACKET_REJECT;
+ }
+
+ memcpy(md, pkt_md, sizeof(*md));
+ md->version = ver;
+ info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+ info->options_len = sizeof(*md);
+
+ ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
+
+ } else {
+ tunnel->parms.erspan_ver = ver;
+
+ if (ver == 1) {
+ tunnel->parms.index = ntohl(pkt_md->u.index);
+ } else {
+ u16 md2_flags;
+ u16 dir, hwid;
+
+ md2_flags = ntohs(pkt_md->u.md2.flags);
+ dir = (md2_flags & DIR_MASK) >> DIR_OFFSET;
+ hwid = (md2_flags & HWID_MASK) >> HWID_OFFSET;
+ tunnel->parms.dir = dir;
+ tunnel->parms.hwid = hwid;
+ }
+
+ ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
+ }
return PACKET_RCVD;
}
@@ -481,9 +600,17 @@ static int gre_rcv(struct sk_buff *skb)
if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false))
goto drop;
+ if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) ||
+ tpi.proto == htons(ETH_P_ERSPAN2))) {
+ if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD)
+ return 0;
+ goto out;
+ }
+
if (ip6gre_rcv(skb, &tpi) == PACKET_RCVD)
return 0;
+out:
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
drop:
kfree_skb(skb);
@@ -496,6 +623,78 @@ static int gre_handle_offloads(struct sk_buff *skb, bool csum)
csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
}
+static void prepare_ip6gre_xmit_ipv4(struct sk_buff *skb,
+ struct net_device *dev,
+ struct flowi6 *fl6, __u8 *dsfield,
+ int *encap_limit)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ struct ip6_tnl *t = netdev_priv(dev);
+
+ if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+ *encap_limit = t->parms.encap_limit;
+
+ memcpy(fl6, &t->fl.u.ip6, sizeof(*fl6));
+
+ if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+ *dsfield = ipv4_get_dsfield(iph);
+ else
+ *dsfield = ip6_tclass(t->parms.flowinfo);
+
+ if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
+ fl6->flowi6_mark = skb->mark;
+ else
+ fl6->flowi6_mark = t->parms.fwmark;
+
+ fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+}
+
+static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
+ struct net_device *dev,
+ struct flowi6 *fl6, __u8 *dsfield,
+ int *encap_limit)
+{
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct ip6_tnl *t = netdev_priv(dev);
+ __u16 offset;
+
+ offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+ /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+
+ if (offset > 0) {
+ struct ipv6_tlv_tnl_enc_lim *tel;
+
+ tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
+ if (tel->encap_limit == 0) {
+ icmpv6_send(skb, ICMPV6_PARAMPROB,
+ ICMPV6_HDR_FIELD, offset + 2);
+ return -1;
+ }
+ *encap_limit = tel->encap_limit - 1;
+ } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) {
+ *encap_limit = t->parms.encap_limit;
+ }
+
+ memcpy(fl6, &t->fl.u.ip6, sizeof(*fl6));
+
+ if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
+ *dsfield = ipv6_get_dsfield(ipv6h);
+ else
+ *dsfield = ip6_tclass(t->parms.flowinfo);
+
+ if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+ fl6->flowlabel |= ip6_flowlabel(ipv6h);
+
+ if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
+ fl6->flowi6_mark = skb->mark;
+ else
+ fl6->flowi6_mark = t->parms.fwmark;
+
+ fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
+ return 0;
+}
+
static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
struct net_device *dev, __u8 dsfield,
struct flowi6 *fl6, int encap_limit,
@@ -517,8 +716,38 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
/* Push GRE header. */
protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
- gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
- protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));
+
+ if (tunnel->parms.collect_md) {
+ struct ip_tunnel_info *tun_info;
+ const struct ip_tunnel_key *key;
+ __be16 flags;
+
+ tun_info = skb_tunnel_info(skb);
+ if (unlikely(!tun_info ||
+ !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ ip_tunnel_info_af(tun_info) != AF_INET6))
+ return -EINVAL;
+
+ key = &tun_info->key;
+ memset(fl6, 0, sizeof(*fl6));
+ fl6->flowi6_proto = IPPROTO_GRE;
+ fl6->daddr = key->u.ipv6.dst;
+ fl6->flowlabel = key->label;
+ fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
+ dsfield = key->tos;
+ flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY);
+ tunnel->tun_hlen = gre_calc_hlen(flags);
+
+ gre_build_header(skb, tunnel->tun_hlen,
+ flags, protocol,
+ tunnel_id_to_key32(tun_info->key.tun_id), 0);
+
+ } else {
+ gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
+ protocol, tunnel->parms.o_key,
+ htonl(tunnel->o_seqno));
+ }
return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
NEXTHDR_GRE);
@@ -527,30 +756,17 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- const struct iphdr *iph = ip_hdr(skb);
int encap_limit = -1;
struct flowi6 fl6;
- __u8 dsfield;
+ __u8 dsfield = 0;
__u32 mtu;
int err;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- encap_limit = t->parms.encap_limit;
-
- memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-
- if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
- dsfield = ipv4_get_dsfield(iph);
- else
- dsfield = ip6_tclass(t->parms.flowinfo);
- if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
- fl6.flowi6_mark = skb->mark;
- else
- fl6.flowi6_mark = t->parms.fwmark;
-
- fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+ if (!t->parms.collect_md)
+ prepare_ip6gre_xmit_ipv4(skb, dev, &fl6,
+ &dsfield, &encap_limit);
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
@@ -574,46 +790,17 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
struct ip6_tnl *t = netdev_priv(dev);
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
int encap_limit = -1;
- __u16 offset;
struct flowi6 fl6;
- __u8 dsfield;
+ __u8 dsfield = 0;
__u32 mtu;
int err;
if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr))
return -1;
- offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
- /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
- ipv6h = ipv6_hdr(skb);
-
- if (offset > 0) {
- struct ipv6_tlv_tnl_enc_lim *tel;
- tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
- if (tel->encap_limit == 0) {
- icmpv6_send(skb, ICMPV6_PARAMPROB,
- ICMPV6_HDR_FIELD, offset + 2);
- return -1;
- }
- encap_limit = tel->encap_limit - 1;
- } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- encap_limit = t->parms.encap_limit;
-
- memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-
- if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
- dsfield = ipv6_get_dsfield(ipv6h);
- else
- dsfield = ip6_tclass(t->parms.flowinfo);
-
- if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
- fl6.flowlabel |= ip6_flowlabel(ipv6h);
- if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
- fl6.flowi6_mark = skb->mark;
- else
- fl6.flowi6_mark = t->parms.fwmark;
-
- fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+ if (!t->parms.collect_md &&
+ prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit))
+ return -1;
if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)))
return -1;
@@ -660,7 +847,8 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev)
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
- memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+ if (!t->parms.collect_md)
+ memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
@@ -705,6 +893,141 @@ tx_err:
return NETDEV_TX_OK;
}
+static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct ip6_tnl *t = netdev_priv(dev);
+ struct dst_entry *dst = skb_dst(skb);
+ struct net_device_stats *stats;
+ bool truncate = false;
+ int encap_limit = -1;
+ __u8 dsfield = false;
+ struct flowi6 fl6;
+ int err = -EINVAL;
+ __u32 mtu;
+
+ if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
+ goto tx_err;
+
+ if (gre_handle_offloads(skb, false))
+ goto tx_err;
+
+ if (skb->len > dev->mtu + dev->hard_header_len) {
+ pskb_trim(skb, dev->mtu + dev->hard_header_len);
+ truncate = true;
+ }
+
+ t->parms.o_flags &= ~TUNNEL_KEY;
+ IPCB(skb)->flags = 0;
+
+ /* For collect_md mode, derive fl6 from the tunnel key,
+ * for native mode, call prepare_ip6gre_xmit_{ipv4,ipv6}.
+ */
+ if (t->parms.collect_md) {
+ struct ip_tunnel_info *tun_info;
+ const struct ip_tunnel_key *key;
+ struct erspan_metadata *md;
+
+ tun_info = skb_tunnel_info(skb);
+ if (unlikely(!tun_info ||
+ !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
+ ip_tunnel_info_af(tun_info) != AF_INET6))
+ return -EINVAL;
+
+ key = &tun_info->key;
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_proto = IPPROTO_GRE;
+ fl6.daddr = key->u.ipv6.dst;
+ fl6.flowlabel = key->label;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
+ dsfield = key->tos;
+ md = ip_tunnel_info_opts(tun_info);
+ if (!md)
+ goto tx_err;
+
+ if (md->version == 1) {
+ erspan_build_header(skb,
+ tunnel_id_to_key32(key->tun_id),
+ ntohl(md->u.index), truncate,
+ false);
+ } else if (md->version == 2) {
+ u16 md2_flags;
+ u16 dir, hwid;
+
+ md2_flags = ntohs(md->u.md2.flags);
+ dir = (md2_flags & DIR_MASK) >> DIR_OFFSET;
+ hwid = (md2_flags & HWID_MASK) >> HWID_OFFSET;
+
+ erspan_build_header_v2(skb,
+ tunnel_id_to_key32(key->tun_id),
+ dir, hwid, truncate,
+ false);
+ }
+ } else {
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ prepare_ip6gre_xmit_ipv4(skb, dev, &fl6,
+ &dsfield, &encap_limit);
+ break;
+ case htons(ETH_P_IPV6):
+ if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr))
+ goto tx_err;
+ if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6,
+ &dsfield, &encap_limit))
+ goto tx_err;
+ break;
+ default:
+ memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+ break;
+ }
+
+ if (t->parms.erspan_ver == 1)
+ erspan_build_header(skb, t->parms.o_key,
+ t->parms.index,
+ truncate, false);
+ else
+ erspan_build_header_v2(skb, t->parms.o_key,
+ t->parms.dir,
+ t->parms.hwid,
+ truncate, false);
+ fl6.daddr = t->parms.raddr;
+ }
+
+ /* Push GRE header. */
+ gre_build_header(skb, 8, TUNNEL_SEQ,
+ htons(ETH_P_ERSPAN), 0, htonl(t->o_seqno++));
+
+ /* TooBig packet may have updated dst->dev's mtu */
+ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
+ dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+
+ err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
+ NEXTHDR_GRE);
+ if (err != 0) {
+ /* XXX: send ICMP error even if DF is not set. */
+ if (err == -EMSGSIZE) {
+ if (skb->protocol == htons(ETH_P_IP))
+ icmp_send(skb, ICMP_DEST_UNREACH,
+ ICMP_FRAG_NEEDED, htonl(mtu));
+ else
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ }
+
+ goto tx_err;
+ }
+ return NETDEV_TX_OK;
+
+tx_err:
+ stats = &t->dev->stats;
+ stats->tx_errors++;
+ stats->tx_dropped++;
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
{
struct net_device *dev = t->dev;
@@ -1048,6 +1371,11 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
+ if (tunnel->parms.collect_md) {
+ dev->features |= NETIF_F_NETNS_LOCAL;
+ netif_keep_dst(dev);
+ }
+
return 0;
}
@@ -1062,6 +1390,9 @@ static int ip6gre_tunnel_init(struct net_device *dev)
tunnel = netdev_priv(dev);
+ if (tunnel->parms.collect_md)
+ return 0;
+
memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr));
@@ -1084,7 +1415,6 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev)
dev_hold(dev);
}
-
static struct inet6_protocol ip6gre_protocol __read_mostly = {
.handler = gre_rcv,
.err_handler = ip6gre_err,
@@ -1099,7 +1429,8 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
for_each_netdev_safe(net, dev, aux)
if (dev->rtnl_link_ops == &ip6gre_link_ops ||
- dev->rtnl_link_ops == &ip6gre_tap_ops)
+ dev->rtnl_link_ops == &ip6gre_tap_ops ||
+ dev->rtnl_link_ops == &ip6erspan_tap_ops)
unregister_netdevice_queue(dev, head);
for (prio = 0; prio < 4; prio++) {
@@ -1221,6 +1552,70 @@ out:
return ip6gre_tunnel_validate(tb, data, extack);
}
+static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ __be16 flags = 0;
+ int ret, ver = 0;
+
+ if (!data)
+ return 0;
+
+ ret = ip6gre_tap_validate(tb, data, extack);
+ if (ret)
+ return ret;
+
+ /* ERSPAN should only have GRE sequence and key flag */
+ if (data[IFLA_GRE_OFLAGS])
+ flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]);
+ if (data[IFLA_GRE_IFLAGS])
+ flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]);
+ if (!data[IFLA_GRE_COLLECT_METADATA] &&
+ flags != (GRE_SEQ | GRE_KEY))
+ return -EINVAL;
+
+ /* ERSPAN Session ID only has 10-bit. Since we reuse
+ * 32-bit key field as ID, check it's range.
+ */
+ if (data[IFLA_GRE_IKEY] &&
+ (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK))
+ return -EINVAL;
+
+ if (data[IFLA_GRE_OKEY] &&
+ (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK))
+ return -EINVAL;
+
+ if (data[IFLA_GRE_ERSPAN_VER]) {
+ ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
+ if (ver != 1 && ver != 2)
+ return -EINVAL;
+ }
+
+ if (ver == 1) {
+ if (data[IFLA_GRE_ERSPAN_INDEX]) {
+ u32 index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
+
+ if (index & ~INDEX_MASK)
+ return -EINVAL;
+ }
+ } else if (ver == 2) {
+ if (data[IFLA_GRE_ERSPAN_DIR]) {
+ u16 dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
+
+ if (dir & ~(DIR_MASK >> DIR_OFFSET))
+ return -EINVAL;
+ }
+
+ if (data[IFLA_GRE_ERSPAN_HWID]) {
+ u16 hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
+
+ if (hwid & ~(HWID_MASK >> HWID_OFFSET))
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
static void ip6gre_netlink_parms(struct nlattr *data[],
struct __ip6_tnl_parm *parms)
@@ -1267,6 +1662,22 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
if (data[IFLA_GRE_FWMARK])
parms->fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
+
+ if (data[IFLA_GRE_COLLECT_METADATA])
+ parms->collect_md = true;
+
+ if (data[IFLA_GRE_ERSPAN_VER])
+ parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
+
+ if (parms->erspan_ver == 1) {
+ if (data[IFLA_GRE_ERSPAN_INDEX])
+ parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
+ } else if (parms->erspan_ver == 2) {
+ if (data[IFLA_GRE_ERSPAN_DIR])
+ parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
+ if (data[IFLA_GRE_ERSPAN_HWID])
+ parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
+ }
}
static int ip6gre_tap_init(struct net_device *dev)
@@ -1303,6 +1714,59 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
NETIF_F_HIGHDMA | \
NETIF_F_HW_CSUM)
+static int ip6erspan_tap_init(struct net_device *dev)
+{
+ struct ip6_tnl *tunnel;
+ int t_hlen;
+ int ret;
+
+ tunnel = netdev_priv(dev);
+
+ tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
+ strcpy(tunnel->parms.name, dev->name);
+
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
+ if (ret) {
+ free_percpu(dev->tstats);
+ dev->tstats = NULL;
+ return ret;
+ }
+
+ tunnel->tun_hlen = 8;
+ tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
+ erspan_hdr_len(tunnel->parms.erspan_ver);
+ t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
+
+ dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ dev->mtu = ETH_DATA_LEN - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ dev->mtu -= ETH_HLEN;
+ if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+ dev->mtu -= 8;
+
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+ tunnel = netdev_priv(dev);
+ ip6gre_tnl_link_config(tunnel, 1);
+
+ return 0;
+}
+
+static const struct net_device_ops ip6erspan_netdev_ops = {
+ .ndo_init = ip6erspan_tap_init,
+ .ndo_uninit = ip6gre_tunnel_uninit,
+ .ndo_start_xmit = ip6erspan_tunnel_xmit,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = ip6_tnl_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_iflink = ip6_tnl_get_iflink,
+};
+
static void ip6gre_tap_setup(struct net_device *dev)
{
@@ -1373,8 +1837,13 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
ip6gre_netlink_parms(data, &nt->parms);
- if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
- return -EEXIST;
+ if (nt->parms.collect_md) {
+ if (rtnl_dereference(ign->collect_md_tun))
+ return -EEXIST;
+ } else {
+ if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
+ return -EEXIST;
+ }
if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
@@ -1493,8 +1962,12 @@ static size_t ip6gre_get_size(const struct net_device *dev)
nla_total_size(2) +
/* IFLA_GRE_ENCAP_DPORT */
nla_total_size(2) +
+ /* IFLA_GRE_COLLECT_METADATA */
+ nla_total_size(0) +
/* IFLA_GRE_FWMARK */
nla_total_size(4) +
+ /* IFLA_GRE_ERSPAN_INDEX */
+ nla_total_size(4) +
0;
}
@@ -1516,7 +1989,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) ||
- nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark))
+ nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) ||
+ nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -1529,6 +2003,24 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
t->encap.flags))
goto nla_put_failure;
+ if (p->collect_md) {
+ if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA))
+ goto nla_put_failure;
+ }
+
+ if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
+ goto nla_put_failure;
+
+ if (p->erspan_ver == 1) {
+ if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+ goto nla_put_failure;
+ } else if (p->erspan_ver == 2) {
+ if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
+ goto nla_put_failure;
+ if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
+ goto nla_put_failure;
+ }
+
return 0;
nla_put_failure:
@@ -1551,9 +2043,28 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = {
[IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 },
[IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 },
[IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 },
+ [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG },
[IFLA_GRE_FWMARK] = { .type = NLA_U32 },
+ [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 },
+ [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 },
+ [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 },
+ [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 },
};
+static void ip6erspan_tap_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+
+ dev->netdev_ops = &ip6erspan_netdev_ops;
+ dev->needs_free_netdev = true;
+ dev->priv_destructor = ip6gre_dev_free;
+
+ dev->features |= NETIF_F_NETNS_LOCAL;
+ dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+ netif_keep_dst(dev);
+}
+
static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
.kind = "ip6gre",
.maxtype = IFLA_GRE_MAX,
@@ -1583,6 +2094,20 @@ static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
.get_link_net = ip6_tnl_get_link_net,
};
+static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly = {
+ .kind = "ip6erspan",
+ .maxtype = IFLA_GRE_MAX,
+ .policy = ip6gre_policy,
+ .priv_size = sizeof(struct ip6_tnl),
+ .setup = ip6erspan_tap_setup,
+ .validate = ip6erspan_tap_validate,
+ .newlink = ip6gre_newlink,
+ .changelink = ip6gre_changelink,
+ .get_size = ip6gre_get_size,
+ .fill_info = ip6gre_fill_info,
+ .get_link_net = ip6_tnl_get_link_net,
+};
+
/*
* And now the modules code and kernel interface.
*/
@@ -1611,9 +2136,15 @@ static int __init ip6gre_init(void)
if (err < 0)
goto tap_ops_failed;
+ err = rtnl_link_register(&ip6erspan_tap_ops);
+ if (err < 0)
+ goto erspan_link_failed;
+
out:
return err;
+erspan_link_failed:
+ rtnl_link_unregister(&ip6gre_tap_ops);
tap_ops_failed:
rtnl_link_unregister(&ip6gre_link_ops);
rtnl_link_failed:
@@ -1627,6 +2158,7 @@ static void __exit ip6gre_fini(void)
{
rtnl_link_unregister(&ip6gre_tap_ops);
rtnl_link_unregister(&ip6gre_link_ops);
+ rtnl_link_unregister(&ip6erspan_tap_ops);
inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE);
unregister_pernet_device(&ip6gre_net_ops);
}
@@ -1638,4 +2170,5 @@ MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
MODULE_DESCRIPTION("GRE over IPv6 tunneling device");
MODULE_ALIAS_RTNL_LINK("ip6gre");
MODULE_ALIAS_RTNL_LINK("ip6gretap");
+MODULE_ALIAS_RTNL_LINK("ip6erspan");
MODULE_ALIAS_NETDEV("ip6gre0");
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f7dd51c42314..ece2781a31b2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1209,13 +1209,13 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
- rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+ rt->dst.dev->mtu : dst_mtu(xfrm_dst_path(&rt->dst));
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
cork->base.fragsize = mtu;
- if (dst_allfrag(rt->dst.path))
+ if (dst_allfrag(xfrm_dst_path(&rt->dst)))
cork->base.flags |= IPCORK_ALLFRAG;
cork->base.length = 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 931c38f6ff4a..8a4610e84e58 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -861,7 +861,7 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
struct metadata_dst *tun_dst,
bool log_ecn_err)
{
- return __ip6_tnl_rcv(t, skb, tpi, NULL, ip6ip6_dscp_ecn_decapsulate,
+ return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate,
log_ecn_err);
}
EXPORT_SYMBOL(ip6_tnl_rcv);
@@ -979,6 +979,9 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
int ret = 0;
struct net *net = t->net;
+ if (t->parms.collect_md)
+ return 1;
+
if ((p->flags & IP6_TNL_F_CAP_XMIT) ||
((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
(ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) {
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index dbb74f3c57a7..18caa9539e6d 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -626,6 +626,7 @@ static void vti6_link_config(struct ip6_tnl *t)
{
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
+ struct net_device *tdev = NULL;
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -638,6 +639,25 @@ static void vti6_link_config(struct ip6_tnl *t)
dev->flags |= IFF_POINTOPOINT;
else
dev->flags &= ~IFF_POINTOPOINT;
+
+ if (p->flags & IP6_TNL_F_CAP_XMIT) {
+ int strict = (ipv6_addr_type(&p->raddr) &
+ (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
+ struct rt6_info *rt = rt6_lookup(t->net,
+ &p->raddr, &p->laddr,
+ p->link, strict);
+
+ if (rt)
+ tdev = rt->dst.dev;
+ ip6_rt_put(rt);
+ }
+
+ if (!tdev && p->link)
+ tdev = __dev_get_by_index(t->net, p->link);
+
+ if (tdev)
+ dev->mtu = max_t(int, tdev->mtu - dev->hard_header_len,
+ IPV6_MIN_MTU);
}
/**
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a2e1a864eb46..890f9bda06a4 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1425,10 +1425,13 @@ int __init ip6_mr_init(void)
goto add_proto_fail;
}
#endif
- rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL,
- ip6mr_rtm_dumproute, 0);
- return 0;
+ err = rtnl_register_module(THIS_MODULE, RTNL_FAMILY_IP6MR, RTM_GETROUTE,
+ NULL, ip6mr_rtm_dumproute, 0);
+ if (err == 0)
+ return 0;
+
#ifdef CONFIG_IPV6_PIMSM_V2
+ inet6_del_protocol(&pim6_protocol, IPPROTO_PIM);
add_proto_fail:
unregister_netdevice_notifier(&ip6_mr_notifier);
#endif
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0458b761f3c5..2490280b3394 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -186,7 +186,7 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt)
{
- return dst_metrics_write_ptr(rt->dst.from);
+ return dst_metrics_write_ptr(&rt->from->dst);
}
static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
@@ -391,7 +391,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct rt6_exception_bucket *bucket;
- struct dst_entry *from = dst->from;
+ struct rt6_info *from = rt->from;
struct inet6_dev *idev;
dst_destroy_metrics_generic(dst);
@@ -409,8 +409,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
kfree(bucket);
}
- dst->from = NULL;
- dst_release(from);
+ rt->from = NULL;
+ dst_release(&from->dst);
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -443,9 +443,9 @@ static bool rt6_check_expired(const struct rt6_info *rt)
if (rt->rt6i_flags & RTF_EXPIRES) {
if (time_after(jiffies, rt->dst.expires))
return true;
- } else if (rt->dst.from) {
+ } else if (rt->from) {
return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK ||
- rt6_check_expired((struct rt6_info *)rt->dst.from);
+ rt6_check_expired(rt->from);
}
return false;
}
@@ -502,7 +502,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
if (!oif && ipv6_addr_any(saddr))
goto out;
- for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) {
+ for (sprt = rt; sprt; sprt = rcu_dereference(sprt->rt6_next)) {
struct net_device *dev = sprt->dst.dev;
if (oif) {
@@ -721,7 +721,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
match = NULL;
cont = NULL;
- for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) {
+ for (rt = rr_head; rt; rt = rcu_dereference(rt->rt6_next)) {
if (rt->rt6i_metric != metric) {
cont = rt;
break;
@@ -731,7 +731,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
}
for (rt = leaf; rt && rt != rr_head;
- rt = rcu_dereference(rt->dst.rt6_next)) {
+ rt = rcu_dereference(rt->rt6_next)) {
if (rt->rt6i_metric != metric) {
cont = rt;
break;
@@ -743,7 +743,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
if (match || !cont)
return match;
- for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next))
+ for (rt = cont; rt; rt = rcu_dereference(rt->rt6_next))
match = find_match(rt, oif, strict, &mpri, match, do_rr);
return match;
@@ -781,7 +781,7 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
&do_rr);
if (do_rr) {
- struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next);
+ struct rt6_info *next = rcu_dereference(rt0->rt6_next);
/* no entries matched; do round-robin */
if (!next || next->rt6i_metric != rt0->rt6i_metric)
@@ -1054,7 +1054,7 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
*/
if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = (struct rt6_info *)ort->dst.from;
+ ort = ort->from;
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(ort);
@@ -1274,7 +1274,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
/* ort can't be a cache or pcpu route */
if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = (struct rt6_info *)ort->dst.from;
+ ort = ort->from;
WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
spin_lock_bh(&rt6_exception_lock);
@@ -1415,8 +1415,8 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
/* Remove the passed in cached rt from the hash table that contains it */
int rt6_remove_exception_rt(struct rt6_info *rt)
{
- struct rt6_info *from = (struct rt6_info *)rt->dst.from;
struct rt6_exception_bucket *bucket;
+ struct rt6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
int err;
@@ -1460,8 +1460,8 @@ int rt6_remove_exception_rt(struct rt6_info *rt)
*/
static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
{
- struct rt6_info *from = (struct rt6_info *)rt->dst.from;
struct rt6_exception_bucket *bucket;
+ struct rt6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
@@ -1929,9 +1929,9 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
static void rt6_dst_from_metrics_check(struct rt6_info *rt)
{
- if (rt->dst.from &&
- dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(rt->dst.from))
- dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true);
+ if (rt->from &&
+ dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(&rt->from->dst))
+ dst_init_metrics(&rt->dst, dst_metrics_ptr(&rt->from->dst), true);
}
static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
@@ -1951,7 +1951,7 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
{
if (!__rt6_check_expired(rt) &&
rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
- rt6_check((struct rt6_info *)(rt->dst.from), cookie))
+ rt6_check(rt->from, cookie))
return &rt->dst;
else
return NULL;
@@ -1971,7 +1971,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
rt6_dst_from_metrics_check(rt);
if (rt->rt6i_flags & RTF_PCPU ||
- (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from))
+ (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from))
return rt6_dst_from_check(rt, cookie);
else
return rt6_check(rt, cookie);
@@ -3056,11 +3056,11 @@ out:
static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
{
- BUG_ON(from->dst.from);
+ BUG_ON(from->from);
rt->rt6i_flags &= ~RTF_EXPIRES;
dst_hold(&from->dst);
- rt->dst.from = &from->dst;
+ rt->from = from;
dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
}
@@ -4321,9 +4321,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout;
}
- if (fibmatch && rt->dst.from) {
- struct rt6_info *ort = container_of(rt->dst.from,
- struct rt6_info, dst);
+ if (fibmatch && rt->from) {
+ struct rt6_info *ort = rt->from;
dst_hold(&ort->dst);
ip6_rt_put(rt);
@@ -4600,8 +4599,6 @@ static int __net_init ip6_route_net_init(struct net *net)
GFP_KERNEL);
if (!net->ipv6.ip6_null_entry)
goto out_ip6_dst_entries;
- net->ipv6.ip6_null_entry->dst.path =
- (struct dst_entry *)net->ipv6.ip6_null_entry;
net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
ip6_template_metrics, true);
@@ -4613,8 +4610,6 @@ static int __net_init ip6_route_net_init(struct net *net)
GFP_KERNEL);
if (!net->ipv6.ip6_prohibit_entry)
goto out_ip6_null_entry;
- net->ipv6.ip6_prohibit_entry->dst.path =
- (struct dst_entry *)net->ipv6.ip6_prohibit_entry;
net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
ip6_template_metrics, true);
@@ -4624,8 +4619,6 @@ static int __net_init ip6_route_net_init(struct net *net)
GFP_KERNEL);
if (!net->ipv6.ip6_blk_hole_entry)
goto out_ip6_prohibit_entry;
- net->ipv6.ip6_blk_hole_entry->dst.path =
- (struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
ip6_template_metrics, true);
@@ -4782,11 +4775,20 @@ int __init ip6_route_init(void)
if (ret)
goto fib6_rules_init;
- ret = -ENOBUFS;
- if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, 0) ||
- __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, 0) ||
- __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL,
- RTNL_FLAG_DOIT_UNLOCKED))
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWROUTE,
+ inet6_rtm_newroute, NULL, 0);
+ if (ret < 0)
+ goto out_register_late_subsys;
+
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELROUTE,
+ inet6_rtm_delroute, NULL, 0);
+ if (ret < 0)
+ goto out_register_late_subsys;
+
+ ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE,
+ inet6_rtm_getroute, NULL,
+ RTNL_FLAG_DOIT_UNLOCKED);
+ if (ret < 0)
goto out_register_late_subsys;
ret = register_netdevice_notifier(&ip6_route_dev_notifier);
@@ -4804,6 +4806,7 @@ out:
return ret;
out_register_late_subsys:
+ rtnl_unregister_all(PF_INET6);
unregister_pernet_subsys(&ip6_route_net_late_ops);
fib6_rules_init:
fib6_rules_cleanup();
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index c81407770956..7f5621d09571 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -306,9 +306,7 @@ static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb)
struct seg6_hmac_info *hinfo;
int ret;
- ret = rhashtable_walk_start(iter);
- if (ret && ret != -EAGAIN)
- goto done;
+ rhashtable_walk_start(iter);
for (;;) {
hinfo = rhashtable_walk_next(iter);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7178476b3d2f..aa12a26a96c6 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1795,7 +1795,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
timer_expires = jiffies;
}
- state = sk_state_load(sp);
+ state = inet_sk_state_load(sp);
if (state == TCP_LISTEN)
rx_queue = sp->sk_ack_backlog;
else
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3f30fa313bf2..eecf9f0faf29 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -89,28 +89,12 @@ static u32 udp6_ehashfn(const struct net *net,
udp_ipv6_hash_secret + net_hash_mix(net));
}
-static u32 udp6_portaddr_hash(const struct net *net,
- const struct in6_addr *addr6,
- unsigned int port)
-{
- unsigned int hash, mix = net_hash_mix(net);
-
- if (ipv6_addr_any(addr6))
- hash = jhash_1word(0, mix);
- else if (ipv6_addr_v4mapped(addr6))
- hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix);
- else
- hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix);
-
- return hash ^ port;
-}
-
int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
- udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
+ ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
unsigned int hash2_partial =
- udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
+ ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
@@ -119,7 +103,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
static void udp_v6_rehash(struct sock *sk)
{
- u16 new_hash = udp6_portaddr_hash(sock_net(sk),
+ u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
@@ -184,7 +168,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
struct udp_hslot *hslot2, struct sk_buff *skb)
{
struct sock *sk, *result;
- int score, badness, matches = 0, reuseport = 0;
+ int score, badness;
u32 hash = 0;
result = NULL;
@@ -193,8 +177,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif, exact_dif);
if (score > badness) {
- reuseport = sk->sk_reuseport;
- if (reuseport) {
+ if (sk->sk_reuseport) {
hash = udp6_ehashfn(net, daddr, hnum,
saddr, sport);
@@ -202,15 +185,9 @@ static struct sock *udp6_lib_lookup2(struct net *net,
sizeof(struct udphdr));
if (result)
return result;
- matches = 1;
}
result = sk;
badness = score;
- } else if (score == badness && reuseport) {
- matches++;
- if (reciprocal_scale(hash, matches) == 0)
- result = sk;
- hash = next_pseudo_random32(hash);
}
}
return result;
@@ -228,11 +205,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
bool exact_dif = udp6_lib_exact_dif_match(net, skb);
- int score, badness, matches = 0, reuseport = 0;
+ int score, badness;
u32 hash = 0;
if (hslot->count > 10) {
- hash2 = udp6_portaddr_hash(net, daddr, hnum);
+ hash2 = ipv6_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
@@ -243,7 +220,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
hslot2, skb);
if (!result) {
unsigned int old_slot2 = slot2;
- hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
+ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
slot2 = hash2 & udptable->mask;
/* avoid searching the same slot again. */
if (unlikely(slot2 == old_slot2))
@@ -267,23 +244,16 @@ begin:
score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
sdif, exact_dif);
if (score > badness) {
- reuseport = sk->sk_reuseport;
- if (reuseport) {
+ if (sk->sk_reuseport) {
hash = udp6_ehashfn(net, daddr, hnum,
saddr, sport);
result = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
if (result)
return result;
- matches = 1;
}
result = sk;
badness = score;
- } else if (score == badness && reuseport) {
- matches++;
- if (reciprocal_scale(hash, matches) == 0)
- result = sk;
- hash = next_pseudo_random32(hash);
}
}
return result;
@@ -719,9 +689,9 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct sk_buff *nskb;
if (use_hash2) {
- hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
+ hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) &
udptable->mask;
- hash2 = udp6_portaddr_hash(net, daddr, hnum) & udptable->mask;
+ hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
hslot = &udptable->hash2[hash2];
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
@@ -909,7 +879,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
int dif, int sdif)
{
unsigned short hnum = ntohs(loc_port);
- unsigned int hash2 = udp6_portaddr_hash(net, loc_addr, hnum);
+ unsigned int hash2 = ipv6_portaddr_hash(net, loc_addr, hnum);
unsigned int slot2 = hash2 & udp_table.mask;
struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 02556e356f87..e66b94f46532 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -59,7 +59,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
if (x->props.flags & XFRM_STATE_NOECN)
dsfield &= ~INET_ECN_MASK;
ipv6_change_dsfield(top_iph, 0, dsfield);
- top_iph->hop_limit = ip6_dst_hoplimit(dst->child);
+ top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst));
top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
return 0;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 885ade234a49..09fb44ee3b45 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -265,7 +265,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
in6_dev_put(xdst->u.rt6.rt6i_idev);
xdst->u.rt6.rt6i_idev = loopback_idev;
in6_dev_hold(loopback_idev);
- xdst = (struct xfrm_dst *)xdst->u.dst.child;
+ xdst = (struct xfrm_dst *)xfrm_dst_child(&xdst->u.dst);
} while (xdst->u.dst.xfrm);
__in6_dev_put(loopback_idev);
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-18 23:39:58 +0300