aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c131
-rw-r--r--net/ipv6/af_inet6.c17
-rw-r--r--net/ipv6/ip6_fib.c5
-rw-r--r--net/ipv6/ip6_gre.c27
-rw-r--r--net/ipv6/ip6_input.c3
-rw-r--r--net/ipv6/ip6_offload.c1
-rw-r--r--net/ipv6/ip6_output.c8
-rw-r--r--net/ipv6/ip6_tunnel.c23
-rw-r--r--net/ipv6/ip6_vti.c2
-rw-r--r--net/ipv6/ipv6_sockglue.c11
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c3
-rw-r--r--net/ipv6/reassembly.c14
-rw-r--r--net/ipv6/route.c86
-rw-r--r--net/ipv6/sit.c6
-rw-r--r--net/ipv6/udp.c65
16 files changed, 242 insertions, 162 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d51a8c0b3372..a9a317322388 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -997,6 +997,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
if (addr_type == IPV6_ADDR_ANY ||
addr_type & IPV6_ADDR_MULTICAST ||
(!(idev->dev->flags & IFF_LOOPBACK) &&
+ !netif_is_l3_master(idev->dev) &&
addr_type & IPV6_ADDR_LOOPBACK))
return ERR_PTR(-EADDRNOTAVAIL);
@@ -4201,7 +4202,6 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
p++;
continue;
}
- state->offset++;
return ifa;
}
@@ -4225,13 +4225,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
return ifa;
}
+ state->offset = 0;
while (++state->bucket < IN6_ADDR_HSIZE) {
- state->offset = 0;
hlist_for_each_entry_rcu(ifa,
&inet6_addr_lst[state->bucket], addr_lst) {
if (!net_eq(dev_net(ifa->idev->dev), net))
continue;
- state->offset++;
return ifa;
}
}
@@ -4491,6 +4490,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = {
[IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
[IFA_FLAGS] = { .len = sizeof(u32) },
[IFA_RT_PRIORITY] = { .len = sizeof(u32) },
+ [IFA_TARGET_NETNSID] = { .type = NLA_S32 },
};
static int
@@ -4793,19 +4793,32 @@ static inline int inet6_ifaddr_msgsize(void)
+ nla_total_size(4) /* IFA_RT_PRIORITY */;
}
+struct inet6_fill_args {
+ u32 portid;
+ u32 seq;
+ int event;
+ unsigned int flags;
+ int netnsid;
+};
+
static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
- u32 portid, u32 seq, int event, unsigned int flags)
+ struct inet6_fill_args *args)
{
struct nlmsghdr *nlh;
u32 preferred, valid;
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
+ nlh = nlmsg_put(skb, args->portid, args->seq, args->event,
+ sizeof(struct ifaddrmsg), args->flags);
if (!nlh)
return -EMSGSIZE;
put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope),
ifa->idev->dev->ifindex);
+ if (args->netnsid >= 0 &&
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ goto error;
+
if (!((ifa->flags&IFA_F_PERMANENT) &&
(ifa->prefered_lft == INFINITY_LIFE_TIME))) {
preferred = ifa->prefered_lft;
@@ -4855,7 +4868,7 @@ error:
}
static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
- u32 portid, u32 seq, int event, u16 flags)
+ struct inet6_fill_args *args)
{
struct nlmsghdr *nlh;
u8 scope = RT_SCOPE_UNIVERSE;
@@ -4864,10 +4877,15 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE)
scope = RT_SCOPE_SITE;
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
+ nlh = nlmsg_put(skb, args->portid, args->seq, args->event,
+ sizeof(struct ifaddrmsg), args->flags);
if (!nlh)
return -EMSGSIZE;
+ if (args->netnsid >= 0 &&
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ return -EMSGSIZE;
+
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 ||
put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp,
@@ -4881,7 +4899,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
}
static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
- u32 portid, u32 seq, int event, unsigned int flags)
+ struct inet6_fill_args *args)
{
struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt);
int ifindex = dev ? dev->ifindex : 1;
@@ -4891,10 +4909,15 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE)
scope = RT_SCOPE_SITE;
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags);
+ nlh = nlmsg_put(skb, args->portid, args->seq, args->event,
+ sizeof(struct ifaddrmsg), args->flags);
if (!nlh)
return -EMSGSIZE;
+ if (args->netnsid >= 0 &&
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ return -EMSGSIZE;
+
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 ||
put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp,
@@ -4916,8 +4939,14 @@ enum addr_type_t {
/* called with rcu_read_lock() */
static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
struct netlink_callback *cb, enum addr_type_t type,
- int s_ip_idx, int *p_ip_idx)
+ int s_ip_idx, int *p_ip_idx, int netnsid)
{
+ struct inet6_fill_args fillargs = {
+ .portid = NETLINK_CB(cb->skb).portid,
+ .seq = cb->nlh->nlmsg_seq,
+ .flags = NLM_F_MULTI,
+ .netnsid = netnsid,
+ };
struct ifmcaddr6 *ifmca;
struct ifacaddr6 *ifaca;
int err = 1;
@@ -4927,16 +4956,13 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
switch (type) {
case UNICAST_ADDR: {
struct inet6_ifaddr *ifa;
+ fillargs.event = RTM_NEWADDR;
/* unicast address incl. temp addr */
list_for_each_entry(ifa, &idev->addr_list, if_list) {
if (++ip_idx < s_ip_idx)
continue;
- err = inet6_fill_ifaddr(skb, ifa,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- RTM_NEWADDR,
- NLM_F_MULTI);
+ err = inet6_fill_ifaddr(skb, ifa, &fillargs);
if (err < 0)
break;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -4944,31 +4970,26 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
break;
}
case MULTICAST_ADDR:
+ fillargs.event = RTM_GETMULTICAST;
+
/* multicast address */
for (ifmca = idev->mc_list; ifmca;
ifmca = ifmca->next, ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
- err = inet6_fill_ifmcaddr(skb, ifmca,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- RTM_GETMULTICAST,
- NLM_F_MULTI);
+ err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs);
if (err < 0)
break;
}
break;
case ANYCAST_ADDR:
+ fillargs.event = RTM_GETANYCAST;
/* anycast address */
for (ifaca = idev->ac_list; ifaca;
ifaca = ifaca->aca_next, ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
- err = inet6_fill_ifacaddr(skb, ifaca,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- RTM_GETANYCAST,
- NLM_F_MULTI);
+ err = inet6_fill_ifacaddr(skb, ifaca, &fillargs);
if (err < 0)
break;
}
@@ -4985,6 +5006,9 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
enum addr_type_t type)
{
struct net *net = sock_net(skb->sk);
+ struct nlattr *tb[IFA_MAX+1];
+ struct net *tgt_net = net;
+ int netnsid = -1;
int h, s_h;
int idx, ip_idx;
int s_idx, s_ip_idx;
@@ -4996,11 +5020,22 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
s_idx = idx = cb->args[1];
s_ip_idx = ip_idx = cb->args[2];
+ if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX,
+ ifa_ipv6_policy, NULL) >= 0) {
+ if (tb[IFA_TARGET_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
+
+ tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
+ if (IS_ERR(tgt_net))
+ return PTR_ERR(tgt_net);
+ }
+ }
+
rcu_read_lock();
- cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq;
+ cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq;
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
- head = &net->dev_index_head[h];
+ head = &tgt_net->dev_index_head[h];
hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
@@ -5012,7 +5047,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
goto cont;
if (in6_dump_addrs(idev, skb, cb, type,
- s_ip_idx, &ip_idx) < 0)
+ s_ip_idx, &ip_idx, netnsid) < 0)
goto done;
cont:
idx++;
@@ -5023,6 +5058,8 @@ done:
cb->args[0] = h;
cb->args[1] = idx;
cb->args[2] = ip_idx;
+ if (netnsid >= 0)
+ put_net(tgt_net);
return skb->len;
}
@@ -5053,6 +5090,14 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(in_skb->sk);
+ struct inet6_fill_args fillargs = {
+ .portid = NETLINK_CB(in_skb).portid,
+ .seq = nlh->nlmsg_seq,
+ .event = RTM_NEWADDR,
+ .flags = 0,
+ .netnsid = -1,
+ };
+ struct net *tgt_net = net;
struct ifaddrmsg *ifm;
struct nlattr *tb[IFA_MAX+1];
struct in6_addr *addr = NULL, *peer;
@@ -5066,15 +5111,24 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ if (tb[IFA_TARGET_NETNSID]) {
+ fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
+
+ tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(in_skb).sk,
+ fillargs.netnsid);
+ if (IS_ERR(tgt_net))
+ return PTR_ERR(tgt_net);
+ }
+
addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
if (!addr)
return -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifa_index)
- dev = dev_get_by_index(net, ifm->ifa_index);
+ dev = dev_get_by_index(tgt_net, ifm->ifa_index);
- ifa = ipv6_get_ifaddr(net, addr, dev, 1);
+ ifa = ipv6_get_ifaddr(tgt_net, addr, dev, 1);
if (!ifa) {
err = -EADDRNOTAVAIL;
goto errout;
@@ -5086,20 +5140,22 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout_ifa;
}
- err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, RTM_NEWADDR, 0);
+ err = inet6_fill_ifaddr(skb, ifa, &fillargs);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout_ifa;
}
- err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
+ err = rtnl_unicast(skb, tgt_net, NETLINK_CB(in_skb).portid);
errout_ifa:
in6_ifa_put(ifa);
errout:
if (dev)
dev_put(dev);
+ if (fillargs.netnsid >= 0)
+ put_net(tgt_net);
+
return err;
}
@@ -5107,13 +5163,20 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
{
struct sk_buff *skb;
struct net *net = dev_net(ifa->idev->dev);
+ struct inet6_fill_args fillargs = {
+ .portid = 0,
+ .seq = 0,
+ .event = event,
+ .flags = 0,
+ .netnsid = -1,
+ };
int err = -ENOBUFS;
skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
if (!skb)
goto errout;
- err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0);
+ err = inet6_fill_ifaddr(skb, ifa, &fillargs);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */
WARN_ON(err == -EMSGSIZE);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 673bba31eb18..e9c8cfdf4b4c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -209,6 +209,7 @@ lookup_protocol:
np->hop_limit = -1;
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
+ np->mc_all = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
np->repflow = net->ipv6.sysctl.flowlabel_reflect;
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
@@ -467,12 +468,10 @@ void inet6_destroy_sock(struct sock *sk)
/* Release rx options */
skb = xchg(&np->pktoptions, NULL);
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
skb = xchg(&np->rxpmtu, NULL);
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
/* Free flowlabels */
fl6_free_socklist(sk);
@@ -938,14 +937,14 @@ static int __init inet6_init(void)
err = proto_register(&pingv6_prot, 1);
if (err)
- goto out_unregister_ping_proto;
+ goto out_unregister_raw_proto;
/* We MUST register RAW sockets before we create the ICMP6,
* IGMP6, or NDISC control sockets.
*/
err = rawv6_init();
if (err)
- goto out_unregister_raw_proto;
+ goto out_unregister_ping_proto;
/* Register the family here so that the init calls below will
* be able to create sockets. (?? is this dangerous ??)
@@ -1113,11 +1112,11 @@ netfilter_fail:
igmp_fail:
ndisc_cleanup();
ndisc_fail:
- ip6_mr_cleanup();
+ icmpv6_cleanup();
icmp_fail:
- unregister_pernet_subsys(&inet6_net_ops);
+ ip6_mr_cleanup();
ipmr_fail:
- icmpv6_cleanup();
+ unregister_pernet_subsys(&inet6_net_ops);
register_pernet_fail:
sock_unregister(PF_INET6);
rtnl_unregister_all(PF_INET6);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index c861a6d4671d..5516f55e214b 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -989,7 +989,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
fib6_clean_expires(iter);
else
fib6_set_expires(iter, rt->expires);
- fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
+
+ if (rt->fib6_pmtu)
+ fib6_metric_set(iter, RTAX_MTU,
+ rt->fib6_pmtu);
return -EEXIST;
}
/* If we have the same destination and the same metric,
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 18a3794b0f52..515adbdba1d2 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -427,35 +427,17 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct net *net = dev_net(skb->dev);
- const struct gre_base_hdr *greh;
const struct ipv6hdr *ipv6h;
- int grehlen = sizeof(*greh);
+ struct tnl_ptk_info tpi;
struct ip6_tnl *t;
- int key_off = 0;
- __be16 flags;
- __be32 key;
- if (!pskb_may_pull(skb, offset + grehlen))
- return;
- greh = (const struct gre_base_hdr *)(skb->data + offset);
- flags = greh->flags;
- if (flags & (GRE_VERSION | GRE_ROUTING))
+ if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6),
+ offset) < 0)
return;
- if (flags & GRE_CSUM)
- grehlen += 4;
- if (flags & GRE_KEY) {
- key_off = grehlen + offset;
- grehlen += 4;
- }
- if (!pskb_may_pull(skb, offset + grehlen))
- return;
ipv6h = (const struct ipv6hdr *)skb->data;
- greh = (const struct gre_base_hdr *)(skb->data + offset);
- key = key_off ? *(__be32 *)(skb->data + key_off) : 0;
-
t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
- key, greh->protocol);
+ tpi.key, tpi.proto);
if (!t)
return;
@@ -1778,6 +1760,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
if (data[IFLA_GRE_COLLECT_METADATA])
parms->collect_md = true;
+ parms->erspan_ver = 1;
if (data[IFLA_GRE_ERSPAN_VER])
parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 6242682be876..96577e742afd 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -178,7 +178,8 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
*/
if ((ipv6_addr_loopback(&hdr->saddr) ||
ipv6_addr_loopback(&hdr->daddr)) &&
- !(dev->flags & IFF_LOOPBACK))
+ !(dev->flags & IFF_LOOPBACK) &&
+ !netif_is_l3_master(dev))
goto err;
/* RFC4291 Errata ID: 3480
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 37ff4805b20c..c7e495f12011 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
payload_len = skb->len - nhoff - sizeof(*ipv6h);
ipv6h->payload_len = htons(payload_len);
skb->network_header = (u8 *)ipv6h - skb->head;
+ skb_reset_mac_len(skb);
if (udpfrag) {
int err = ip6_find_1stfragopt(skb, &prevhdr);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 16f200f06500..89e0d5118afe 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
kfree_skb(skb);
return -ENOBUFS;
}
+ if (skb->sk)
+ skb_set_owner_w(skb2, skb->sk);
consume_skb(skb);
skb = skb2;
- /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
- * it is safe to call in our context (socket lock not held)
- */
- skb_set_owner_w(skb, (struct sock *)sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
@@ -727,7 +725,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
skb = frag;
frag = skb->next;
- skb->next = NULL;
+ skb_mark_not_on_list(skb);
}
kfree(tmp_hdr);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5df2a58d945c..a0b6932c3afd 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1188,7 +1188,15 @@ route_lookup:
init_tel_txopt(&opt, encap_limit);
ipv6_push_frag_opts(skb, &opt.ops, &proto);
}
- hop_limit = hop_limit ? : ip6_dst_hoplimit(dst);
+
+ if (hop_limit == 0) {
+ if (skb->protocol == htons(ETH_P_IP))
+ hop_limit = ip_hdr(skb)->ttl;
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ hop_limit = ipv6_hdr(skb)->hop_limit;
+ else
+ hop_limit = ip6_dst_hoplimit(dst);
+ }
/* Calculate max headroom for all the headers and adjust
* needed_headroom if necessary.
@@ -1226,7 +1234,7 @@ static inline int
ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- const struct iphdr *iph = ip_hdr(skb);
+ const struct iphdr *iph;
int encap_limit = -1;
struct flowi6 fl6;
__u8 dsfield;
@@ -1234,6 +1242,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
u8 tproto;
int err;
+ /* ensure we can access the full inner ip header */
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ return -1;
+
+ iph = ip_hdr(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
tproto = READ_ONCE(t->parms.proto);
@@ -1298,7 +1311,7 @@ static inline int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct ipv6hdr *ipv6h;
int encap_limit = -1;
__u16 offset;
struct flowi6 fl6;
@@ -1307,6 +1320,10 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
u8 tproto;
int err;
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
+ return -1;
+
+ ipv6h = ipv6_hdr(skb);
tproto = READ_ONCE(t->parms.proto);
if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
ip6_tnl_addr_conflict(t, ipv6h))
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 5095367c7204..eeaf7455d51e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -481,7 +481,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
}
mtu = dst_mtu(dst);
- if (!skb->ignore_df && skb->len > mtu) {
+ if (skb->len > mtu) {
skb_dst_update_pmtu(skb, mtu);
if (skb->protocol == htons(ETH_P_IPV6)) {
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index c0cac9cc3a28..381ce38940ae 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -674,6 +674,13 @@ done:
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
+ case IPV6_MULTICAST_ALL:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ np->mc_all = valbool;
+ retv = 0;
+ break;
+
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
@@ -1266,6 +1273,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val = np->mcast_oif;
break;
+ case IPV6_MULTICAST_ALL:
+ val = np->mc_all;
+ break;
+
case IPV6_UNICAST_IF:
val = (__force int)htonl((__u32) np->ucast_oif);
break;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 4ae54aaca373..6895e1dc0b03 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -636,7 +636,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
}
if (!mc) {
rcu_read_unlock();
- return true;
+ return np->mc_all;
}
read_lock(&mc->sflock);
psl = mc->sflist;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 2a14d8b65924..b8ac369f98ad 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -445,11 +445,12 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
+ fp->sk = NULL;
}
sub_frag_mem_limit(fq->q.net, head->truesize);
head->ignore_df = 1;
- head->next = NULL;
+ skb_mark_not_on_list(head);
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 5c5b4f79296e..5c3c92713096 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -145,7 +145,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
*/
if (end < fq->q.len ||
((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
- goto err;
+ goto discard_fq;
fq->q.flags |= INET_FRAG_LAST_IN;
fq->q.len = end;
} else {
@@ -162,20 +162,20 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
if (end > fq->q.len) {
/* Some bits beyond end -> corruption. */
if (fq->q.flags & INET_FRAG_LAST_IN)
- goto err;
+ goto discard_fq;
fq->q.len = end;
}
}
if (end == offset)
- goto err;
+ goto discard_fq;
/* Point into the IP datagram 'data' part. */
if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
- goto err;
+ goto discard_fq;
if (pskb_trim_rcsum(skb, end - offset))
- goto err;
+ goto discard_fq;
/* Find out which fragments are in front and at the back of us
* in the chain of fragments so far. We must know where to put
@@ -388,7 +388,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
}
sub_frag_mem_limit(fq->q.net, sum_truesize);
- head->next = NULL;
+ skb_mark_not_on_list(head);
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
@@ -418,6 +418,7 @@ out_fail:
rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
+ inet_frag_kill(&fq->q);
return -1;
}
@@ -553,7 +554,6 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
table[0].data = &net->ipv6.frags.high_thresh;
table[0].extra1 = &net->ipv6.frags.low_thresh;
- table[0].extra2 = &init_net.ipv6.frags.high_thresh;
table[1].data = &net->ipv6.frags.low_thresh;
table[1].extra2 = &net->ipv6.frags.high_thresh;
table[2].data = &net->ipv6.frags.timeout;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c4ea13e8360b..d28f83e01593 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -364,11 +364,14 @@ EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
+ struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
struct rt6_info *rt = (struct rt6_info *)dst;
struct fib6_info *from;
struct inet6_dev *idev;
- dst_destroy_metrics_generic(dst);
+ if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
+ kfree(p);
+
rt6_uncached_list_del(rt);
idev = rt->rt6i_idev;
@@ -946,8 +949,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
{
- rt->dst.flags |= fib6_info_dst_flags(ort);
-
if (ort->fib6_flags & RTF_REJECT) {
ip6_rt_init_dst_reject(rt, ort);
return;
@@ -978,6 +979,10 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
rt->rt6i_flags &= ~RTF_EXPIRES;
rcu_assign_pointer(rt->from, from);
dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
+ if (from->fib6_metrics != &dst_default_metrics) {
+ rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+ refcount_inc(&from->fib6_metrics->refcnt);
+ }
}
/* Caller must already hold reference to @ort */
@@ -995,8 +1000,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
#ifdef CONFIG_IPV6_SUBTREES
rt->rt6i_src = ort->fib6_src;
#endif
- rt->rt6i_prefsrc = ort->fib6_prefsrc;
- rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
}
static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
@@ -1450,11 +1453,6 @@ static int rt6_insert_exception(struct rt6_info *nrt,
if (ort->fib6_src.plen)
src_key = &nrt->rt6i_src.addr;
#endif
-
- /* Update rt6i_prefsrc as it could be changed
- * in rt6_remove_prefsrc()
- */
- nrt->rt6i_prefsrc = ort->fib6_prefsrc;
/* rt6_mtu_change() might lower mtu on ort.
* Only insert this exception route if its mtu
* is less than ort's mtu value.
@@ -1636,25 +1634,6 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
rcu_read_unlock();
}
-static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt)
-{
- struct rt6_exception_bucket *bucket;
- struct rt6_exception *rt6_ex;
- int i;
-
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
- lockdep_is_held(&rt6_exception_lock));
-
- if (bucket) {
- for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
- hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
- rt6_ex->rt6i->rt6i_prefsrc.plen = 0;
- }
- bucket++;
- }
- }
-}
-
static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
struct rt6_info *rt, int mtu)
{
@@ -2099,7 +2078,8 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
{
bool any_src;
- if (rt6_need_strict(&fl6->daddr)) {
+ if (ipv6_addr_type(&fl6->daddr) &
+ (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) {
struct dst_entry *dst;
dst = l3mdev_link_scope_lookup(net, fl6);
@@ -3138,8 +3118,6 @@ install_route:
rt->fib6_nh.nh_dev = dev;
rt->fib6_table = table;
- cfg->fc_nlinfo.nl_net = dev_net(dev);
-
if (idev)
in6_dev_put(idev);
@@ -3796,8 +3774,6 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
spin_lock_bh(&rt6_exception_lock);
/* remove prefsrc entry */
rt->fib6_prefsrc.plen = 0;
- /* need to update cache as well */
- rt6_exceptions_remove_prefsrc(rt);
spin_unlock_bh(&rt6_exception_lock);
}
return 0;
@@ -4671,20 +4647,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
int iif, int type, u32 portid, u32 seq,
unsigned int flags)
{
- struct rtmsg *rtm;
+ struct rt6_info *rt6 = (struct rt6_info *)dst;
+ struct rt6key *rt6_dst, *rt6_src;
+ u32 *pmetrics, table, rt6_flags;
struct nlmsghdr *nlh;
+ struct rtmsg *rtm;
long expires = 0;
- u32 *pmetrics;
- u32 table;
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
if (!nlh)
return -EMSGSIZE;
+ if (rt6) {
+ rt6_dst = &rt6->rt6i_dst;
+ rt6_src = &rt6->rt6i_src;
+ rt6_flags = rt6->rt6i_flags;
+ } else {
+ rt6_dst = &rt->fib6_dst;
+ rt6_src = &rt->fib6_src;
+ rt6_flags = rt->fib6_flags;
+ }
+
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET6;
- rtm->rtm_dst_len = rt->fib6_dst.plen;
- rtm->rtm_src_len = rt->fib6_src.plen;
+ rtm->rtm_dst_len = rt6_dst->plen;
+ rtm->rtm_src_len = rt6_src->plen;
rtm->rtm_tos = 0;
if (rt->fib6_table)
table = rt->fib6_table->tb6_id;
@@ -4699,7 +4686,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
rtm->rtm_protocol = rt->fib6_protocol;
- if (rt->fib6_flags & RTF_CACHE)
+ if (rt6_flags & RTF_CACHE)
rtm->rtm_flags |= RTM_F_CLONED;
if (dest) {
@@ -4707,7 +4694,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
goto nla_put_failure;
rtm->rtm_dst_len = 128;
} else if (rtm->rtm_dst_len)
- if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr))
+ if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr))
goto nla_put_failure;
#ifdef CONFIG_IPV6_SUBTREES
if (src) {
@@ -4715,12 +4702,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
goto nla_put_failure;
rtm->rtm_src_len = 128;
} else if (rtm->rtm_src_len &&
- nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr))
+ nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr))
goto nla_put_failure;
#endif
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
- if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) {
+ if (ipv6_addr_is_multicast(&rt6_dst->addr)) {
int err = ip6mr_get_route(net, skb, rtm, portid);
if (err == 0)
@@ -4755,7 +4742,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
/* For multipath routes, walk the siblings list and add
* each as a nexthop within RTA_MULTIPATH.
*/
- if (rt->fib6_nsiblings) {
+ if (rt6) {
+ if (rt6_flags & RTF_GATEWAY &&
+ nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway))
+ goto nla_put_failure;
+
+ if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex))
+ goto nla_put_failure;
+ } else if (rt->fib6_nsiblings) {
struct fib6_info *sibling, *next_sibling;
struct nlattr *mp;
@@ -4778,7 +4772,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
goto nla_put_failure;
}
- if (rt->fib6_flags & RTF_EXPIRES) {
+ if (rt6_flags & RTF_EXPIRES) {
expires = dst ? dst->expires : rt->expires;
expires -= jiffies;
}
@@ -4786,7 +4780,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
goto nla_put_failure;
- if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags)))
+ if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags)))
goto nla_put_failure;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e9400ffa7875..51c9f75f34b9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -534,13 +534,13 @@ 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, iph->protocol, 0);
+ t->parms.link, iph->protocol);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
- iph->protocol, 0);
+ ipv4_redirect(skb, dev_net(skb->dev), t->parms.link,
+ iph->protocol);
err = 0;
goto out;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 83f4c77c79d8..28c4aa5078fc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -752,6 +752,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
}
}
+/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+ * return code conversion for ip layer consumption
+ */
+static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
+ struct udphdr *uh)
+{
+ int ret;
+
+ if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
+ skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+ ip6_compute_pseudo);
+
+ ret = udpv6_queue_rcv_skb(sk, skb);
+
+ /* a return value > 0 means to resubmit the input, but
+ * it wants the return to be -protocol, or 0
+ */
+ if (ret > 0)
+ return -ret;
+ return 0;
+}
+
int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
int proto)
{
@@ -803,13 +825,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (unlikely(sk->sk_rx_dst != dst))
udp6_sk_rx_dst_set(sk, dst);
- ret = udpv6_queue_rcv_skb(sk, skb);
- sock_put(sk);
+ if (!uh->check && !udp_sk(sk)->no_check6_rx) {
+ sock_put(sk);
+ goto report_csum_error;
+ }
- /* a return value > 0 means to resubmit the input */
- if (ret > 0)
- return ret;
- return 0;
+ ret = udp6_unicast_rcv_skb(sk, skb, uh);
+ sock_put(sk);
+ return ret;
}
/*
@@ -822,30 +845,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
/* Unicast */
sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk) {
- int ret;
-
- if (!uh->check && !udp_sk(sk)->no_check6_rx) {
- udp6_csum_zero_error(skb);
- goto csum_error;
- }
-
- if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
- skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
- ip6_compute_pseudo);
-
- ret = udpv6_queue_rcv_skb(sk, skb);
-
- /* a return value > 0 means to resubmit the input */
- if (ret > 0)
- return ret;
-
- return 0;
+ if (!uh->check && !udp_sk(sk)->no_check6_rx)
+ goto report_csum_error;
+ return udp6_unicast_rcv_skb(sk, skb, uh);
}
- if (!uh->check) {
- udp6_csum_zero_error(skb);
- goto csum_error;
- }
+ if (!uh->check)
+ goto report_csum_error;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
@@ -866,6 +872,9 @@ short_packet:
ulen, skb->len,
daddr, ntohs(uh->dest));
goto discard;
+
+report_csum_error:
+ udp6_csum_zero_error(skb);
csum_error:
__UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
discard:
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.