summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c61
-rw-r--r--net/ipv6/calipso.c29
-rw-r--r--net/ipv6/esp6.c49
-rw-r--r--net/ipv6/fib6_rules.c4
-rw-r--r--net/ipv6/ila/ila_common.c6
-rw-r--r--net/ipv6/ila/ila_lwt.c4
-rw-r--r--net/ipv6/ip6_fib.c24
-rw-r--r--net/ipv6/ip6_offload.c4
-rw-r--r--net/ipv6/ip6_output.c3
-rw-r--r--net/ipv6/ip6mr.c3
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/netfilter.c12
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c23
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c13
-rw-r--r--net/ipv6/route.c103
-rw-r--r--net/ipv6/rpl_iptunnel.c8
-rw-r--r--net/ipv6/seg6_local.c6
17 files changed, 215 insertions, 139 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f52527c86e71..69915bb8b96d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3162,16 +3162,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
- int scope, plen, offset = 0;
+ int scope, plen;
u32 pflags = 0;
ASSERT_RTNL();
memset(&addr, 0, sizeof(struct in6_addr));
- /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
- if (idev->dev->addr_len == sizeof(struct in6_addr))
- offset = sizeof(struct in6_addr) - 4;
- memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+ memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
scope = IPV6_ADDR_COMPATv4;
@@ -3475,21 +3472,22 @@ static void addrconf_gre_config(struct net_device *dev)
ASSERT_RTNL();
- idev = ipv6_find_idev(dev);
- if (IS_ERR(idev)) {
- pr_debug("%s: add_dev failed\n", __func__);
+ idev = addrconf_add_dev(dev);
+ if (IS_ERR(idev))
return;
- }
- if (dev->type == ARPHRD_ETHER) {
+ /* Generate the IPv6 link-local address using addrconf_addr_gen(),
+ * unless we have an IPv4 GRE device not bound to an IP address and
+ * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+ * case). Such devices fall back to add_v4_addrs() instead.
+ */
+ if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
addrconf_addr_gen(idev, true);
return;
}
add_v4_addrs(idev);
-
- if (dev->flags & IFF_POINTOPOINT)
- addrconf_add_mroute(dev);
}
#endif
@@ -5718,6 +5716,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
}
}
+static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb,
+ struct inet6_dev *idev)
+{
+ struct nlattr *nla;
+
+ nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
+ if (!nla)
+ goto nla_put_failure;
+ snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
+
+ nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
+ if (!nla)
+ goto nla_put_failure;
+ snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
u32 ext_filter_mask)
{
@@ -5739,18 +5758,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
/* XXX - MC not implemented */
- if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
- return 0;
-
- nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
- if (!nla)
- goto nla_put_failure;
- snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
-
- nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
- if (!nla)
- goto nla_put_failure;
- snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+ if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) {
+ if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0)
+ goto nla_put_failure;
+ }
nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
if (!nla)
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 1578ed9e97d8..24666291c54a 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1075,8 +1075,13 @@ static int calipso_sock_getattr(struct sock *sk,
struct ipv6_opt_hdr *hop;
int opt_len, len, ret_val = -ENOMSG, offset;
unsigned char *opt;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+
+ if (!pinfo)
+ return -EAFNOSUPPORT;
+ txopts = txopt_get(pinfo);
if (!txopts || !txopts->hopopt)
goto done;
@@ -1128,8 +1133,13 @@ static int calipso_sock_setattr(struct sock *sk,
{
int ret_val;
struct ipv6_opt_hdr *old, *new;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+ if (!pinfo)
+ return -EAFNOSUPPORT;
+
+ txopts = txopt_get(pinfo);
old = NULL;
if (txopts)
old = txopts->hopopt;
@@ -1156,8 +1166,13 @@ static int calipso_sock_setattr(struct sock *sk,
static void calipso_sock_delattr(struct sock *sk)
{
struct ipv6_opt_hdr *new_hop;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+ if (!pinfo)
+ return;
+
+ txopts = txopt_get(pinfo);
if (!txopts || !txopts->hopopt)
goto done;
@@ -1195,6 +1210,10 @@ static int calipso_req_setattr(struct request_sock *req,
struct ipv6_opt_hdr *old, *new;
struct sock *sk = sk_to_full_sk(req_to_sk(req));
+ /* sk is NULL for SYN+ACK w/ SYN Cookie */
+ if (!sk)
+ return -ENOMEM;
+
if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt)
old = req_inet->ipv6_opt->hopopt;
else
@@ -1235,6 +1254,10 @@ static void calipso_req_delattr(struct request_sock *req)
struct ipv6_txoptions *txopts;
struct sock *sk = sk_to_full_sk(req_to_sk(req));
+ /* sk is NULL for SYN+ACK w/ SYN Cookie */
+ if (!sk)
+ return;
+
if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt)
return;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index a021c88d3d9b..085a83b807af 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -135,47 +135,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
}
#ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -188,20 +157,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -224,6 +179,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -427,6 +384,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 6eeab21512ba..e0f0c5f8cccd 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -350,9 +350,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
+ struct fib6_rule *rule6 = (struct fib6_rule *)rule;
+ struct net *net = rule->fr_net;
int err = -EINVAL;
- struct net *net = sock_net(skb->sk);
- struct fib6_rule *rule6 = (struct fib6_rule *) rule;
if (!inet_validate_dscp(frh->tos)) {
NL_SET_ERR_MSG(extack,
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 95e9146918cc..b8d43ed4689d 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -86,7 +86,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
diff = get_csum_diff(ip6h, p);
inet_proto_csum_replace_by_diff(&th->check, skb,
- diff, true);
+ diff, true, true);
}
break;
case NEXTHDR_UDP:
@@ -97,7 +97,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
diff = get_csum_diff(ip6h, p);
inet_proto_csum_replace_by_diff(&uh->check, skb,
- diff, true);
+ diff, true, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
@@ -111,7 +111,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb,
diff = get_csum_diff(ip6h, p);
inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb,
- diff, true);
+ diff, true, true);
}
break;
}
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 9d37f7164e73..7397f764c66c 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -88,13 +88,15 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
- if (ilwt->connected) {
+ /* cache only if we don't create a dst reference loop */
+ if (ilwt->connected && orig_dst->lwtstate != dst->lwtstate) {
local_bh_disable();
dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
local_bh_enable();
}
}
+ skb_dst_drop(skb);
skb_dst_set(skb, dst);
return dst_output(net, sk, skb);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b6a7cbd6bee0..bb51a911a6ce 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -438,15 +438,17 @@ struct fib6_dump_arg {
static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
{
enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE;
+ unsigned int nsiblings;
int err;
if (!rt || rt == arg->net->ipv6.fib6_null_entry)
return 0;
- if (rt->fib6_nsiblings)
+ nsiblings = READ_ONCE(rt->fib6_nsiblings);
+ if (nsiblings)
err = call_fib6_multipath_entry_notifier(arg->nb, fib_event,
rt,
- rt->fib6_nsiblings,
+ nsiblings,
arg->extack);
else
err = call_fib6_entry_notifier(arg->nb, fib_event, rt,
@@ -1119,7 +1121,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
if (rt6_duplicate_nexthop(iter, rt)) {
if (rt->fib6_nsiblings)
- rt->fib6_nsiblings = 0;
+ WRITE_ONCE(rt->fib6_nsiblings, 0);
if (!(iter->fib6_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->fib6_flags & RTF_EXPIRES))
@@ -1145,7 +1147,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
*/
if (rt_can_ecmp &&
rt6_qualify_for_ecmp(iter))
- rt->fib6_nsiblings++;
+ WRITE_ONCE(rt->fib6_nsiblings,
+ rt->fib6_nsiblings + 1);
}
if (iter->fib6_metric > rt->fib6_metric)
@@ -1195,7 +1198,8 @@ next_iter:
fib6_nsiblings = 0;
list_for_each_entry_safe(sibling, temp_sibling,
&rt->fib6_siblings, fib6_siblings) {
- sibling->fib6_nsiblings++;
+ WRITE_ONCE(sibling->fib6_nsiblings,
+ sibling->fib6_nsiblings + 1);
BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
fib6_nsiblings++;
}
@@ -1240,8 +1244,9 @@ add:
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings,
fib6_siblings)
- sibling->fib6_nsiblings--;
- rt->fib6_nsiblings = 0;
+ WRITE_ONCE(sibling->fib6_nsiblings,
+ sibling->fib6_nsiblings - 1);
+ WRITE_ONCE(rt->fib6_nsiblings, 0);
list_del_rcu(&rt->fib6_siblings);
rt6_multipath_rebalance(next_sibling);
return err;
@@ -1953,8 +1958,9 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
notify_del = true;
list_for_each_entry_safe(sibling, next_sibling,
&rt->fib6_siblings, fib6_siblings)
- sibling->fib6_nsiblings--;
- rt->fib6_nsiblings = 0;
+ WRITE_ONCE(sibling->fib6_nsiblings,
+ sibling->fib6_nsiblings - 1);
+ WRITE_ONCE(rt->fib6_nsiblings, 0);
list_del_rcu(&rt->fib6_siblings);
rt6_multipath_rebalance(next_sibling);
}
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 3ee345672849..171a5c1afefe 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -134,7 +134,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
- skb_reset_transport_header(skb);
+ if (!skb_reset_transport_header_careful(skb))
+ goto out;
+
segs = ops->callbacks.gso_segment(skb, features);
if (!segs)
skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d7f7a714bd23..f7a225da8525 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1985,7 +1985,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
u8 icmp6_type;
- if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+ if (sk->sk_socket->type == SOCK_RAW &&
+ !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH))
icmp6_type = fl6->fl6_icmp_type;
else
icmp6_type = icmp6_hdr(skb)->icmp6_type;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 138f6aee70af..06f66531628f 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2045,6 +2045,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
struct sk_buff *skb, int vifi)
{
struct vif_device *vif = &mrt->vif_table[vifi];
+ struct net_device *indev = skb->dev;
struct net_device *vif_dev;
struct ipv6hdr *ipv6h;
struct dst_entry *dst;
@@ -2107,7 +2108,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
IP6CB(skb)->flags |= IP6SKB_FORWARDED;
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
- net, NULL, skb, skb->dev, vif_dev,
+ net, NULL, skb, indev, skb->dev,
ip6mr_forward2_finish);
out_free:
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index a1b3f3e7921f..e9e59a83ba9b 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -803,8 +803,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
} else {
im->mca_crcount = idev->mc_qrv;
}
- in6_dev_put(pmc->idev);
ip6_mc_clear_src(pmc);
+ in6_dev_put(pmc->idev);
kfree_rcu(pmc, rcu);
}
}
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 857713d7a38a..d873658fc821 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -163,20 +163,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct ip6_fraglist_iter iter;
struct sk_buff *frag2;
- if (first_len - hlen > mtu ||
- skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+ if (first_len - hlen > mtu)
goto blackhole;
- if (skb_cloned(skb))
+ if (skb_cloned(skb) ||
+ skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
goto slow_path;
skb_walk_frags(skb, frag2) {
- if (frag2->len > mtu ||
- skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+ if (frag2->len > mtu)
goto blackhole;
/* Partially cloned skb? */
- if (skb_shared(frag2))
+ if (skb_shared(frag2) ||
+ skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
goto slow_path;
}
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index a7690ec62325..9ea5ef56cb27 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -103,6 +103,10 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
struct sk_buff *data_skb = NULL;
int doff = 0;
int thoff = 0, tproto;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn const *ct;
+#endif
tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
@@ -136,6 +140,25 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
return NULL;
}
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ /* Do the lookup with the original socket address in
+ * case this is a reply packet of an established
+ * SNAT-ted connection.
+ */
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct &&
+ ((tproto != IPPROTO_ICMPV6 &&
+ ctinfo == IP_CT_ESTABLISHED_REPLY) ||
+ (tproto == IPPROTO_ICMPV6 &&
+ ctinfo == IP_CT_RELATED_REPLY)) &&
+ (ct->status & IPS_SRC_NAT_DONE)) {
+ daddr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
+ dport = (tproto == IPPROTO_TCP) ?
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
+ }
+#endif
+
return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
sport, dport, indev);
}
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c9f1634b3838..a89ce0fbfe4b 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -158,6 +158,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
{
const struct nft_fib *priv = nft_expr_priv(expr);
int noff = skb_network_offset(pkt->skb);
+ const struct net_device *found = NULL;
const struct net_device *oif = NULL;
u32 *dest = &regs->data[priv->dreg];
struct ipv6hdr *iph, _iph;
@@ -202,11 +203,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
goto put_rt_err;
- if (oif && oif != rt->rt6i_idev->dev &&
- l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
- goto put_rt_err;
+ if (!oif) {
+ found = rt->rt6i_idev->dev;
+ } else {
+ if (oif == rt->rt6i_idev->dev ||
+ l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex)
+ found = oif;
+ }
- nft_fib_store_result(dest, priv, rt->rt6i_idev->dev);
+ nft_fib_store_result(dest, priv, found);
put_rt_err:
ip6_rt_put(rt);
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 17918f411386..07e3d59c2405 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -416,12 +416,37 @@ static bool rt6_check_expired(const struct rt6_info *rt)
return false;
}
+static struct fib6_info *
+rt6_multipath_first_sibling_rcu(const struct fib6_info *rt)
+{
+ struct fib6_info *iter;
+ struct fib6_node *fn;
+
+ fn = rcu_dereference(rt->fib6_node);
+ if (!fn)
+ goto out;
+ iter = rcu_dereference(fn->leaf);
+ if (!iter)
+ goto out;
+
+ while (iter) {
+ if (iter->fib6_metric == rt->fib6_metric &&
+ rt6_qualify_for_ecmp(iter))
+ return iter;
+ iter = rcu_dereference(iter->fib6_next);
+ }
+
+out:
+ return NULL;
+}
+
void fib6_select_path(const struct net *net, struct fib6_result *res,
struct flowi6 *fl6, int oif, bool have_oif_match,
const struct sk_buff *skb, int strict)
{
- struct fib6_info *match = res->f6i;
+ struct fib6_info *first, *match = res->f6i;
struct fib6_info *sibling;
+ int hash;
if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
goto out;
@@ -444,16 +469,25 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
return;
}
- if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
+ first = rt6_multipath_first_sibling_rcu(match);
+ if (!first)
goto out;
- list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+ hash = fl6->mp_hash;
+ if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) {
+ if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+ strict) >= 0)
+ match = first;
+ goto out;
+ }
+
+ list_for_each_entry_rcu(sibling, &first->fib6_siblings,
fib6_siblings) {
const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
- if (fl6->mp_hash > nh_upper_bound)
+ if (hash > nh_upper_bound)
continue;
if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
break;
@@ -3637,7 +3671,8 @@ out:
in6_dev_put(idev);
if (err) {
- lwtstate_put(fib6_nh->fib_nh_lws);
+ fib_nh_common_release(&fib6_nh->nh_common);
+ fib6_nh->nh_common.nhc_pcpu_rth_output = NULL;
fib6_nh->fib_nh_lws = NULL;
dev_put(dev);
}
@@ -3797,10 +3832,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (nh) {
if (rt->fib6_src.plen) {
NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ err = -EINVAL;
goto out_free;
}
if (!nexthop_get(nh)) {
NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+ err = -ENOENT;
goto out_free;
}
rt->nh = nh;
@@ -5196,7 +5233,8 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
*/
rcu_read_lock();
- if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
+ if ((nlflags & NLM_F_APPEND) && rt_last &&
+ READ_ONCE(rt_last->fib6_nsiblings)) {
rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
struct fib6_info,
fib6_siblings);
@@ -5543,32 +5581,34 @@ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
static size_t rt6_nlmsg_size(struct fib6_info *f6i)
{
+ struct fib6_info *sibling;
+ struct fib6_nh *nh;
int nexthop_len;
if (f6i->nh) {
nexthop_len = nla_total_size(4); /* RTA_NH_ID */
nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
&nexthop_len);
- } else {
- struct fib6_nh *nh = f6i->fib6_nh;
- struct fib6_info *sibling;
-
- nexthop_len = 0;
- if (f6i->fib6_nsiblings) {
- rt6_nh_nlmsg_size(nh, &nexthop_len);
-
- rcu_read_lock();
+ goto common;
+ }
- list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
- fib6_siblings) {
- rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
- }
+ rcu_read_lock();
+retry:
+ nh = f6i->fib6_nh;
+ nexthop_len = 0;
+ if (READ_ONCE(f6i->fib6_nsiblings)) {
+ rt6_nh_nlmsg_size(nh, &nexthop_len);
- rcu_read_unlock();
+ list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+ fib6_siblings) {
+ rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
+ if (!READ_ONCE(f6i->fib6_nsiblings))
+ goto retry;
}
- nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
}
-
+ rcu_read_unlock();
+ nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+common:
return NLMSG_ALIGN(sizeof(struct rtmsg))
+ nla_total_size(16) /* RTA_SRC */
+ nla_total_size(16) /* RTA_DST */
@@ -5727,7 +5767,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
if (dst->lwtstate &&
lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
goto nla_put_failure;
- } else if (rt->fib6_nsiblings) {
+ } else if (READ_ONCE(rt->fib6_nsiblings)) {
struct fib6_info *sibling;
struct nlattr *mp;
@@ -5829,16 +5869,21 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
if (f6i->fib6_nh->fib_nh_dev == dev)
return true;
- if (f6i->fib6_nsiblings) {
- struct fib6_info *sibling, *next_sibling;
+ if (READ_ONCE(f6i->fib6_nsiblings)) {
+ const struct fib6_info *sibling;
- list_for_each_entry_safe(sibling, next_sibling,
- &f6i->fib6_siblings, fib6_siblings) {
- if (sibling->fib6_nh->fib_nh_dev == dev)
+ rcu_read_lock();
+ list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+ fib6_siblings) {
+ if (sibling->fib6_nh->fib_nh_dev == dev) {
+ rcu_read_unlock();
return true;
+ }
+ if (!READ_ONCE(f6i->fib6_nsiblings))
+ break;
}
+ rcu_read_unlock();
}
-
return false;
}
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 862ac1e2e191..952ec785853a 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -129,13 +129,13 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
struct dst_entry *cache_dst)
{
struct ipv6_rpl_sr_hdr *isrh, *csrh;
- const struct ipv6hdr *oldhdr;
+ struct ipv6hdr oldhdr;
struct ipv6hdr *hdr;
unsigned char *buf;
size_t hdrlen;
int err;
- oldhdr = ipv6_hdr(skb);
+ memcpy(&oldhdr, ipv6_hdr(skb), sizeof(oldhdr));
buf = kcalloc(struct_size(srh, segments.addr, srh->segments_left), 2, GFP_ATOMIC);
if (!buf)
@@ -147,7 +147,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
memcpy(isrh, srh, sizeof(*isrh));
memcpy(isrh->rpl_segaddr, &srh->rpl_segaddr[1],
(srh->segments_left - 1) * 16);
- isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr->daddr;
+ isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr.daddr;
ipv6_rpl_srh_compress(csrh, isrh, &srh->rpl_segaddr[0],
isrh->segments_left - 1);
@@ -169,7 +169,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt,
skb_mac_header_rebuild(skb);
hdr = ipv6_hdr(skb);
- memmove(hdr, oldhdr, sizeof(*hdr));
+ memmove(hdr, &oldhdr, sizeof(*hdr));
isrh = (void *)hdr + sizeof(*hdr);
memcpy(isrh, csrh, hdrlen);
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 33cb0381b574..b7d9a68a265d 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -1250,10 +1250,8 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_SRH] = { .type = NLA_BINARY },
[SEG6_LOCAL_TABLE] = { .type = NLA_U32 },
[SEG6_LOCAL_VRFTABLE] = { .type = NLA_U32 },
- [SEG6_LOCAL_NH4] = { .type = NLA_BINARY,
- .len = sizeof(struct in_addr) },
- [SEG6_LOCAL_NH6] = { .type = NLA_BINARY,
- .len = sizeof(struct in6_addr) },
+ [SEG6_LOCAL_NH4] = NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
+ [SEG6_LOCAL_NH6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
[SEG6_LOCAL_IIF] = { .type = NLA_U32 },
[SEG6_LOCAL_OIF] = { .type = NLA_U32 },
[SEG6_LOCAL_BPF] = { .type = NLA_NESTED },
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-24 09:41:34 +0300