summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf_core.c11
-rw-r--r--net/ipv6/ip6_fib.c39
-rw-r--r--net/ipv6/ip6_gre.c9
-rw-r--r--net/ipv6/ip6_output.c43
-rw-r--r--net/ipv6/ip6_vti.c27
-rw-r--r--net/ipv6/netfilter/ip6_tables.c6
-rw-r--r--net/ipv6/route.c19
-rw-r--r--net/ipv6/tcp_ipv6.c5
-rw-r--r--net/ipv6/udp.c10
9 files changed, 131 insertions, 38 deletions
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index d873ceea86e6..ca09bf49ac68 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -133,6 +133,14 @@ static void snmp6_free_dev(struct inet6_dev *idev)
free_percpu(idev->stats.ipv6);
}
+static void in6_dev_finish_destroy_rcu(struct rcu_head *head)
+{
+ struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu);
+
+ snmp6_free_dev(idev);
+ kfree(idev);
+}
+
/* Nobody refers to this device, we may destroy it. */
void in6_dev_finish_destroy(struct inet6_dev *idev)
@@ -151,7 +159,6 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
pr_warn("Freeing alive inet6 device %p\n", idev);
return;
}
- snmp6_free_dev(idev);
- kfree_rcu(idev, rcu);
+ call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu);
}
EXPORT_SYMBOL(in6_dev_finish_destroy);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 96dbffff5a24..bde57b113009 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -693,6 +693,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
+ struct rt6_info **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
@@ -716,8 +717,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
(info->nlh->nlmsg_flags & NLM_F_EXCL))
return -EEXIST;
if (replace) {
- found++;
- break;
+ if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+ found++;
+ break;
+ }
+ if (rt_can_ecmp)
+ fallback_ins = fallback_ins ?: ins;
+ goto next_iter;
}
if (iter->dst.dev == rt->dst.dev &&
@@ -753,9 +759,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
if (iter->rt6i_metric > rt->rt6i_metric)
break;
+next_iter:
ins = &iter->dst.rt6_next;
}
+ if (fallback_ins && !found) {
+ /* No ECMP-able route found, replace first non-ECMP one */
+ ins = fallback_ins;
+ iter = *ins;
+ found++;
+ }
+
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
@@ -815,6 +829,8 @@ add:
}
} else {
+ int nsiblings;
+
if (!found) {
if (add)
goto add;
@@ -835,8 +851,27 @@ add:
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
+ nsiblings = iter->rt6i_nsiblings;
fib6_purge_rt(iter, fn, info->nl_net);
rt6_release(iter);
+
+ if (nsiblings) {
+ /* Replacing an ECMP route, remove all siblings */
+ ins = &rt->dst.rt6_next;
+ iter = *ins;
+ while (iter) {
+ if (rt6_qualify_for_ecmp(iter)) {
+ *ins = iter->dst.rt6_next;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ rt6_release(iter);
+ nsiblings--;
+ } else {
+ ins = &iter->dst.rt6_next;
+ }
+ iter = *ins;
+ }
+ WARN_ON(nsiblings != 0);
+ }
}
return 0;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b5e6cc1d4a73..a38d3ac0f18f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1246,7 +1246,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
static int ip6gre_tunnel_init(struct net_device *dev)
{
struct ip6_tnl *tunnel;
- int i;
tunnel = netdev_priv(dev);
@@ -1260,16 +1259,10 @@ static int ip6gre_tunnel_init(struct net_device *dev)
if (ipv6_addr_any(&tunnel->parms.raddr))
dev->header_ops = &ip6gre_header_ops;
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ip6gre_tunnel_stats;
- ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ip6gre_tunnel_stats->syncp);
- }
-
return 0;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7fde1f265c90..bc09cb97b840 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -886,22 +886,45 @@ static int ip6_dst_lookup_tail(struct sock *sk,
#endif
int err;
- if (!*dst)
- *dst = ip6_route_output(net, sk, fl6);
-
- err = (*dst)->error;
- if (err)
- goto out_err_release;
+ /* 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
+ * ip6_route_output call _before_ ip6_route_get_saddr.
+ *
+ * In source specific routing (no src=any default route),
+ * ip6_route_output will fail given src=any saddr, though, so
+ * that's why we try it again later.
+ */
+ if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
+ struct rt6_info *rt;
+ bool had_dst = *dst != NULL;
- if (ipv6_addr_any(&fl6->saddr)) {
- struct rt6_info *rt = (struct rt6_info *) *dst;
+ if (!had_dst)
+ *dst = ip6_route_output(net, sk, fl6);
+ rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
+
+ /* If we had an erroneous initial result, pretend it
+ * never existed and let the SA-enabled version take
+ * over.
+ */
+ if (!had_dst && (*dst)->error) {
+ dst_release(*dst);
+ *dst = NULL;
+ }
}
+ if (!*dst)
+ *dst = ip6_route_output(net, sk, fl6);
+
+ err = (*dst)->error;
+ if (err)
+ goto out_err_release;
+
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
@@ -1277,8 +1300,10 @@ emsgsize:
/* If this is the first and only packet and device
* supports checksum offloading, let's use it.
+ * Use transhdrlen, same as IPv4, because partial
+ * sums only work when transhdrlen is set.
*/
- if (!skb && sk->sk_protocol == IPPROTO_UDP &&
+ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
length + fragheaderlen < mtu &&
rt->dst.dev->features & NETIF_F_V6_CSUM &&
!exthdrlen)
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ed9d681207fa..0224c032dca5 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -322,7 +322,6 @@ static int vti6_rcv(struct sk_buff *skb)
}
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
- skb->mark = be32_to_cpu(t->parms.i_key);
rcu_read_unlock();
@@ -342,6 +341,8 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!t)
return 1;
@@ -358,7 +359,11 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(t->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
@@ -430,6 +435,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
struct net_device *tdev;
struct xfrm_state *x;
int err = -1;
+ int mtu;
if (!dst)
goto tx_err_link_failure;
@@ -463,6 +469,19 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
+ mtu = dst_mtu(dst);
+ if (!skb->ignore_df && skb->len > mtu) {
+ skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IPV6))
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ else
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+
+ return -EMSGSIZE;
+ }
+
err = dst_output(skb);
if (net_xmit_eval(err) == 0) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
@@ -495,7 +514,6 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
int ret;
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(t->parms.o_key);
switch (skb->protocol) {
case htons(ETH_P_IPV6):
@@ -516,6 +534,9 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_err;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(t->parms.o_key);
+
ret = vti6_xmit(skb, dev, &fl);
if (ret < 0)
goto tx_err;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 1a732a1d3c8e..62f5b0d0bc9b 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1275,6 +1275,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
/* overflow check */
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
@@ -1822,6 +1825,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
return -ENOMEM;
if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters))
return -ENOMEM;
+ if (tmp.num_counters == 0)
+ return -EINVAL;
+
tmp.name[sizeof(tmp.name)-1] = 0;
newinfo = xt_alloc_table_info(tmp.size);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5c48293ff062..c73ae5039e46 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2245,9 +2245,10 @@ int ip6_route_get_saddr(struct net *net,
unsigned int prefs,
struct in6_addr *saddr)
{
- struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt);
+ struct inet6_dev *idev =
+ rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
int err = 0;
- if (rt->rt6i_prefsrc.plen)
+ if (rt && rt->rt6i_prefsrc.plen)
*saddr = rt->rt6i_prefsrc.addr;
else
err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
@@ -2503,9 +2504,9 @@ static int ip6_route_multipath(struct fib6_config *cfg, int add)
int attrlen;
int err = 0, last_err = 0;
+ remaining = cfg->fc_mp_len;
beginning:
rtnh = (struct rtnexthop *)cfg->fc_mp;
- remaining = cfg->fc_mp_len;
/* Parse a Multipath Entry */
while (rtnh_ok(rtnh, remaining)) {
@@ -2535,15 +2536,19 @@ beginning:
* next hops that have been already added.
*/
add = 0;
+ remaining = cfg->fc_mp_len - remaining;
goto beginning;
}
}
/* Because each route is added like a single route we remove
- * this flag after the first nexthop (if there is a collision,
- * we have already fail to add the first nexthop:
- * fib6_add_rt2node() has reject it).
+ * these flags after the first nexthop: if there is a collision,
+ * we have already failed to add the first nexthop:
+ * fib6_add_rt2node() has rejected it; when replacing, old
+ * nexthops have been replaced by first new, the rest should
+ * be added to it.
*/
- cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL;
+ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
+ NLM_F_REPLACE);
rtnh = rtnh_next(rtnh, &remaining);
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ad51df85aa00..3adffb300238 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -914,7 +914,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
- tw->tw_tclass, (tw->tw_flowlabel << 12));
+ tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
inet_twsk_put(tw);
}
@@ -946,7 +946,8 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
&ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- reqsk_put(req);
+ if (!nsk)
+ reqsk_put(req);
return nsk;
}
nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3477c919fcc8..e51fc3eee6db 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -525,10 +525,8 @@ csum_copy_err:
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
@@ -731,7 +729,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+ (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+ !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
if (!inet6_mc_check(sk, loc_addr, rmt_addr))
return false;
generated by cgit v1.2.3 (git 2.0.4) at 2024-09-13 02:09:46 +0000