summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c19
-rw-r--r--net/ipv6/af_inet6.c5
-rw-r--r--net/ipv6/anycast.c84
-rw-r--r--net/ipv6/datagram.c10
-rw-r--r--net/ipv6/fou6.c74
-rw-r--r--net/ipv6/icmp.c4
-rw-r--r--net/ipv6/inet6_hashtables.c14
-rw-r--r--net/ipv6/ip6_fib.c4
-rw-r--r--net/ipv6/ip6_gre.c18
-rw-r--r--net/ipv6/ip6_input.c63
-rw-r--r--net/ipv6/ip6_offload.c13
-rw-r--r--net/ipv6/ip6_output.c3
-rw-r--r--net/ipv6/ip6_udp_tunnel.c16
-rw-r--r--net/ipv6/ipv6_sockglue.c2
-rw-r--r--net/ipv6/netfilter.c3
-rw-r--r--net/ipv6/netfilter/ip6t_MASQUERADE.c8
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c13
-rw-r--r--net/ipv6/netfilter/nf_nat_masquerade_ipv6.c49
-rw-r--r--net/ipv6/netfilter/nft_masq_ipv6.c4
-rw-r--r--net/ipv6/raw.c5
-rw-r--r--net/ipv6/route.c19
-rw-r--r--net/ipv6/tcp_ipv6.c13
-rw-r--r--net/ipv6/tunnel6.c12
-rw-r--r--net/ipv6/udp.c241
-rw-r--r--net/ipv6/udp_impl.h4
-rw-r--r--net/ipv6/udp_offload.c6
-rw-r--r--net/ipv6/udplite.c5
-rw-r--r--net/ipv6/xfrm6_protocol.c18
28 files changed, 558 insertions, 171 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 63a808d5af15..045597b9a7c0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -179,7 +179,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp);
static void addrconf_dad_work(struct work_struct *w);
static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
bool send_na);
-static void addrconf_dad_run(struct inet6_dev *idev);
+static void addrconf_dad_run(struct inet6_dev *idev, bool restart);
static void addrconf_rs_timer(struct timer_list *t);
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -3439,6 +3439,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_change_info *change_info;
struct netdev_notifier_changeupper_info *info;
struct inet6_dev *idev = __in6_dev_get(dev);
struct net *net = dev_net(dev);
@@ -3513,7 +3514,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
break;
}
- if (idev) {
+ if (!IS_ERR_OR_NULL(idev)) {
if (idev->if_flags & IF_READY) {
/* device is already configured -
* but resend MLD reports, we might
@@ -3521,6 +3522,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
* multicast snooping switches
*/
ipv6_mc_up(idev);
+ change_info = ptr;
+ if (change_info->flags_changed & IFF_NOARP)
+ addrconf_dad_run(idev, true);
rt6_sync_up(dev, RTNH_F_LINKDOWN);
break;
}
@@ -3555,7 +3559,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
if (!IS_ERR_OR_NULL(idev)) {
if (run_pending)
- addrconf_dad_run(idev);
+ addrconf_dad_run(idev, false);
/* Device has an address by now */
rt6_sync_up(dev, RTNH_F_DEAD);
@@ -4173,16 +4177,19 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
addrconf_verify_rtnl();
}
-static void addrconf_dad_run(struct inet6_dev *idev)
+static void addrconf_dad_run(struct inet6_dev *idev, bool restart)
{
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
list_for_each_entry(ifp, &idev->addr_list, if_list) {
spin_lock(&ifp->lock);
- if (ifp->flags & IFA_F_TENTATIVE &&
- ifp->state == INET6_IFADDR_STATE_DAD)
+ if ((ifp->flags & IFA_F_TENTATIVE &&
+ ifp->state == INET6_IFADDR_STATE_DAD) || restart) {
+ if (restart)
+ ifp->state = INET6_IFADDR_STATE_PREDAD;
addrconf_dad_kick(ifp);
+ }
spin_unlock(&ifp->lock);
}
read_unlock_bh(&idev->lock);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3f4d61017a69..f0cd291034f0 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1001,6 +1001,9 @@ static int __init inet6_init(void)
err = ip6_flowlabel_init();
if (err)
goto ip6_flowlabel_fail;
+ err = ipv6_anycast_init();
+ if (err)
+ goto ipv6_anycast_fail;
err = addrconf_init();
if (err)
goto addrconf_fail;
@@ -1091,6 +1094,8 @@ ipv6_frag_fail:
ipv6_exthdrs_fail:
addrconf_cleanup();
addrconf_fail:
+ ipv6_anycast_cleanup();
+ipv6_anycast_fail:
ip6_flowlabel_cleanup();
ip6_flowlabel_fail:
ndisc_late_cleanup();
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 4e0ff7031edd..cca3b3603c42 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -44,8 +44,22 @@
#include <net/checksum.h>
+#define IN6_ADDR_HSIZE_SHIFT 8
+#define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT)
+/* anycast address hash table
+ */
+static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE];
+static DEFINE_SPINLOCK(acaddr_hash_lock);
+
static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);
+static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr)
+{
+ u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+
+ return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
+}
+
/*
* socket join an anycast group
*/
@@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk)
rtnl_unlock();
}
+static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca)
+{
+ unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr);
+
+ spin_lock(&acaddr_hash_lock);
+ hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]);
+ spin_unlock(&acaddr_hash_lock);
+}
+
+static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca)
+{
+ spin_lock(&acaddr_hash_lock);
+ hlist_del_init_rcu(&aca->aca_addr_lst);
+ spin_unlock(&acaddr_hash_lock);
+}
+
static void aca_get(struct ifacaddr6 *aca)
{
refcount_inc(&aca->aca_refcnt);
}
+static void aca_free_rcu(struct rcu_head *h)
+{
+ struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu);
+
+ fib6_info_release(aca->aca_rt);
+ kfree(aca);
+}
+
static void aca_put(struct ifacaddr6 *ac)
{
if (refcount_dec_and_test(&ac->aca_refcnt)) {
- fib6_info_release(ac->aca_rt);
- kfree(ac);
+ call_rcu(&ac->rcu, aca_free_rcu);
}
}
@@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i,
aca->aca_addr = *addr;
fib6_info_hold(f6i);
aca->aca_rt = f6i;
+ INIT_HLIST_NODE(&aca->aca_addr_lst);
aca->aca_users = 1;
/* aca_tstamp should be updated upon changes */
aca->aca_cstamp = aca->aca_tstamp = jiffies;
@@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
aca_get(aca);
write_unlock_bh(&idev->lock);
+ ipv6_add_acaddr_hash(net, aca);
+
ip6_ins_rt(net, f6i);
addrconf_join_solict(idev->dev, &aca->aca_addr);
@@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
else
idev->ac_list = aca->aca_next;
write_unlock_bh(&idev->lock);
+ ipv6_del_acaddr_hash(aca);
addrconf_leave_solict(idev, &aca->aca_addr);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
@@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev)
idev->ac_list = aca->aca_next;
write_unlock_bh(&idev->lock);
+ ipv6_del_acaddr_hash(aca);
+
addrconf_leave_solict(idev, &aca->aca_addr);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
@@ -390,17 +433,27 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad
bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
const struct in6_addr *addr)
{
+ struct net_device *nh_dev;
+ struct ifacaddr6 *aca;
bool found = false;
rcu_read_lock();
if (dev)
found = ipv6_chk_acast_dev(dev, addr);
- else
- for_each_netdev_rcu(net, dev)
- if (ipv6_chk_acast_dev(dev, addr)) {
+ else {
+ unsigned int hash = inet6_acaddr_hash(net, addr);
+
+ hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash],
+ aca_addr_lst) {
+ nh_dev = fib6_info_nh_dev(aca->aca_rt);
+ if (!nh_dev || !net_eq(dev_net(nh_dev), net))
+ continue;
+ if (ipv6_addr_equal(&aca->aca_addr, addr)) {
found = true;
break;
}
+ }
+ }
rcu_read_unlock();
return found;
}
@@ -540,3 +593,24 @@ void ac6_proc_exit(struct net *net)
remove_proc_entry("anycast6", net->proc_net);
}
#endif
+
+/* Init / cleanup code
+ */
+int __init ipv6_anycast_init(void)
+{
+ int i;
+
+ for (i = 0; i < IN6_ADDR_HSIZE; i++)
+ INIT_HLIST_HEAD(&inet6_acaddr_lst[i]);
+ return 0;
+}
+
+void ipv6_anycast_cleanup(void)
+{
+ int i;
+
+ spin_lock(&acaddr_hash_lock);
+ for (i = 0; i < IN6_ADDR_HSIZE; i++)
+ WARN_ON(!hlist_empty(&inet6_acaddr_lst[i]));
+ spin_unlock(&acaddr_hash_lock);
+}
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..bde08aa549f3 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -772,6 +772,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
case IPV6_2292PKTINFO:
{
struct net_device *dev = NULL;
+ int src_idx;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
err = -EINVAL;
@@ -779,12 +780,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
}
src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+ src_idx = src_info->ipi6_ifindex;
- if (src_info->ipi6_ifindex) {
+ if (src_idx) {
if (fl6->flowi6_oif &&
- src_info->ipi6_ifindex != fl6->flowi6_oif)
+ src_idx != fl6->flowi6_oif &&
+ (sk->sk_bound_dev_if != fl6->flowi6_oif ||
+ !sk_dev_equal_l3scope(sk, src_idx)))
return -EINVAL;
- fl6->flowi6_oif = src_info->ipi6_ifindex;
+ fl6->flowi6_oif = src_idx;
}
addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index 6de3c04b0f30..bd675c61deb1 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -4,6 +4,7 @@
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/udp.h>
+#include <linux/icmpv6.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <net/fou.h>
@@ -69,14 +70,87 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
return 0;
}
+static int gue6_err_proto_handler(int proto, struct sk_buff *skb,
+ struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, u32 info)
+{
+ const struct inet6_protocol *ipprot;
+
+ ipprot = rcu_dereference(inet6_protos[proto]);
+ if (ipprot && ipprot->err_handler) {
+ if (!ipprot->err_handler(skb, opt, type, code, offset, info))
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ int transport_offset = skb_transport_offset(skb);
+ struct guehdr *guehdr;
+ size_t optlen;
+ int ret;
+
+ if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr))
+ return -EINVAL;
+
+ guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+ switch (guehdr->version) {
+ case 0: /* Full GUE header present */
+ break;
+ case 1: {
+ /* Direct encasulation of IPv4 or IPv6 */
+ skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr));
+
+ switch (((struct iphdr *)guehdr)->version) {
+ case 4:
+ ret = gue6_err_proto_handler(IPPROTO_IPIP, skb, opt,
+ type, code, offset, info);
+ goto out;
+ case 6:
+ ret = gue6_err_proto_handler(IPPROTO_IPV6, skb, opt,
+ type, code, offset, info);
+ goto out;
+ default:
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+ }
+ default: /* Undefined version */
+ return -EOPNOTSUPP;
+ }
+
+ if (guehdr->control)
+ return -ENOENT;
+
+ optlen = guehdr->hlen << 2;
+
+ if (validate_gue_flags(guehdr, optlen))
+ return -EINVAL;
+
+ skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr));
+ ret = gue6_err_proto_handler(guehdr->proto_ctype, skb,
+ opt, type, code, offset, info);
+
+out:
+ skb_set_transport_header(skb, transport_offset);
+ return ret;
+}
+
+
static const struct ip6_tnl_encap_ops fou_ip6tun_ops = {
.encap_hlen = fou_encap_hlen,
.build_header = fou6_build_header,
+ .err_handler = gue6_err,
};
static const struct ip6_tnl_encap_ops gue_ip6tun_ops = {
.encap_hlen = gue_encap_hlen,
.build_header = gue6_build_header,
+ .err_handler = gue6_err,
};
static int ip6_tnl_encap_add_fou_ops(void)
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index c9c53ade55c3..5d7aa2c2770c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -84,7 +84,7 @@ static inline struct sock *icmpv6_sk(struct net *net)
return net->ipv6.icmp_sk[smp_processor_id()];
}
-static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
@@ -100,6 +100,8 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
ping_err(skb, offset, ntohl(info));
+
+ return 0;
}
static int icmpv6_rcv(struct sk_buff *skb);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3d7c7460a0c5..5eeeba7181a1 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -99,6 +99,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
const int dif, const int sdif, bool exact_dif)
{
int score = -1;
+ bool dev_match;
if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
sk->sk_family == PF_INET6) {
@@ -109,15 +110,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1b8bc008b53b..ae3786132c23 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
/* fib entries are never clones */
if (arg.filter.flags & RTM_F_CLONED)
- return skb->len;
+ goto out;
w = (void *)cb->args[2];
if (!w) {
@@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
tb = fib6_get_table(net, arg.filter.table_id);
if (!tb) {
if (arg.filter.dump_all_families)
- return skb->len;
+ goto out;
NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
return -ENOENT;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 515adbdba1d2..81b69bcee714 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -423,7 +423,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
}
-static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int 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);
@@ -433,13 +433,13 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6),
offset) < 0)
- return;
+ return -EINVAL;
ipv6h = (const struct ipv6hdr *)skb->data;
t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
tpi.key, tpi.proto);
if (!t)
- return;
+ return -ENOENT;
switch (type) {
struct ipv6_tlv_tnl_enc_lim *tel;
@@ -449,14 +449,14 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
t->parms.name);
if (code != ICMPV6_PORT_UNREACH)
break;
- return;
+ return 0;
case ICMPV6_TIME_EXCEED:
if (code == ICMPV6_EXC_HOPLIMIT) {
net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
t->parms.name);
break;
}
- return;
+ return 0;
case ICMPV6_PARAMPROB:
teli = 0;
if (code == ICMPV6_HDR_FIELD)
@@ -472,14 +472,14 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
t->parms.name);
}
- return;
+ return 0;
case ICMPV6_PKT_TOOBIG:
ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
- return;
+ return 0;
case NDISC_REDIRECT:
ip6_redirect(skb, net, skb->dev->ifindex, 0,
sock_net_uid(net, NULL));
- return;
+ return 0;
}
if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
@@ -487,6 +487,8 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
else
t->err_count = 1;
t->err_time = jiffies;
+
+ return 0;
}
static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 96577e742afd..3c06cc9e9b79 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -319,28 +319,26 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
/*
* Deliver the packet to the host
*/
-
-
-static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr,
+ bool have_final)
{
const struct inet6_protocol *ipprot;
struct inet6_dev *idev;
unsigned int nhoff;
- int nexthdr;
bool raw;
- bool have_final = false;
/*
* Parse extension headers
*/
- rcu_read_lock();
resubmit:
idev = ip6_dst_idev(skb_dst(skb));
- if (!pskb_pull(skb, skb_transport_offset(skb)))
- goto discard;
nhoff = IP6CB(skb)->nhoff;
- nexthdr = skb_network_header(skb)[nhoff];
+ if (!have_final) {
+ if (!pskb_pull(skb, skb_transport_offset(skb)))
+ goto discard;
+ nexthdr = skb_network_header(skb)[nhoff];
+ }
resubmit_final:
raw = raw6_local_deliver(skb, nexthdr);
@@ -359,6 +357,8 @@ resubmit_final:
}
} else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
+ int sdif = inet6_sdif(skb);
+ struct net_device *dev;
/* Only do this once for first final protocol */
have_final = true;
@@ -371,9 +371,19 @@ resubmit_final:
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
+
+ /* skb->dev passed may be master dev for vrfs. */
+ if (sdif) {
+ dev = dev_get_by_index_rcu(net, sdif);
+ if (!dev)
+ goto discard;
+ } else {
+ dev = skb->dev;
+ }
+
if (ipv6_addr_is_multicast(&hdr->daddr) &&
- !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
- &hdr->saddr) &&
+ !ipv6_chk_mcast_addr(dev, &hdr->daddr,
+ &hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
goto discard;
}
@@ -411,13 +421,19 @@ resubmit_final:
consume_skb(skb);
}
}
- rcu_read_unlock();
- return 0;
+ return;
discard:
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
- rcu_read_unlock();
kfree_skb(skb);
+}
+
+static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ rcu_read_lock();
+ ip6_protocol_deliver_rcu(net, skb, 0, false);
+ rcu_read_unlock();
+
return 0;
}
@@ -432,15 +448,32 @@ EXPORT_SYMBOL_GPL(ip6_input);
int ip6_mc_input(struct sk_buff *skb)
{
+ int sdif = inet6_sdif(skb);
const struct ipv6hdr *hdr;
+ struct net_device *dev;
bool deliver;
__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
skb->len);
+ /* skb->dev passed may be master dev for vrfs. */
+ if (sdif) {
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
+ if (!dev) {
+ rcu_read_unlock();
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ } else {
+ dev = skb->dev;
+ }
+
hdr = ipv6_hdr(skb);
- deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
+ deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
+ if (sdif)
+ rcu_read_unlock();
#ifdef CONFIG_IPV6_MROUTE
/*
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index c7e495f12011..70f525c33cb6 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -229,14 +229,21 @@ static struct sk_buff *ipv6_gro_receive(struct list_head *head,
* XXX skbs on the gro_list have all been parsed and pulled
* already so we don't need to compare nlen
* (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
- * memcmp() alone below is suffcient, right?
+ * memcmp() alone below is sufficient, right?
*/
if ((first_word & htonl(0xF00FFFFF)) ||
- memcmp(&iph->nexthdr, &iph2->nexthdr,
- nlen - offsetof(struct ipv6hdr, nexthdr))) {
+ !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
+ !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
+ *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
+not_same_flow:
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
+ if (unlikely(nlen > sizeof(struct ipv6hdr))) {
+ if (memcmp(iph + 1, iph2 + 1,
+ nlen - sizeof(struct ipv6hdr)))
+ goto not_same_flow;
+ }
/* flush if Traffic Class fields are different */
NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
NAPI_GRO_CB(p)->flush |= flush;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 89e0d5118afe..827a3f5ff3bb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1354,7 +1354,7 @@ emsgsize:
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
- unsigned int pagedlen = 0;
+ unsigned int pagedlen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
@@ -1378,6 +1378,7 @@ alloc_new_skb:
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
+ pagedlen = 0;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index b283f293ee4a..3965d5396b0a 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -31,6 +31,22 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
if (err < 0)
goto error;
}
+ if (cfg->bind_ifindex) {
+ struct net_device *dev;
+
+ dev = dev_get_by_index(net, cfg->bind_ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto error;
+ }
+
+ err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
+ dev->name, strlen(dev->name) + 1);
+ dev_put(dev);
+
+ if (err < 0)
+ goto error;
+ }
udp6_addr.sin6_family = AF_INET6;
memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 381ce38940ae..973e215c3114 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -486,7 +486,7 @@ sticky_done:
retv = -EFAULT;
break;
}
- if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
+ if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex))
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 5ae8e1c51079..8b075f0bc351 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
unsigned int hh_len;
struct dst_entry *dst;
struct flowi6 fl6 = {
- .flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
+ .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
+ rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
.flowi6_mark = skb->mark,
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 491f808e356a..29c7f1915a96 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void)
int err;
err = xt_register_target(&masquerade_tg6_reg);
- if (err == 0)
- nf_nat_masquerade_ipv6_register_notifier();
+ if (err)
+ return err;
+
+ err = nf_nat_masquerade_ipv6_register_notifier();
+ if (err)
+ xt_unregister_target(&masquerade_tg6_reg);
return err;
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b8ac369f98ad..d219979c3e52 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -587,11 +587,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
*/
ret = -EINPROGRESS;
if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- fq->q.meat == fq->q.len &&
- nf_ct_frag6_reasm(fq, skb, dev))
- ret = 0;
- else
+ fq->q.meat == fq->q.len) {
+ unsigned long orefdst = skb->_skb_refdst;
+
+ skb->_skb_refdst = 0UL;
+ if (nf_ct_frag6_reasm(fq, skb, dev))
+ ret = 0;
+ skb->_skb_refdst = orefdst;
+ } else {
skb_dst_drop(skb);
+ }
out_unlock:
spin_unlock_bh(&fq->q.lock);
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 3e4bf2286abe..0ad0da5a2600 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work)
* of ipv6 addresses being deleted), we also need to add an upper
* limit to the number of queued work items.
*/
-static int masq_inet_event(struct notifier_block *this,
- unsigned long event, void *ptr)
+static int masq_inet6_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
{
struct inet6_ifaddr *ifa = ptr;
const struct net_device *dev;
@@ -171,30 +171,53 @@ static int masq_inet_event(struct notifier_block *this,
return NOTIFY_DONE;
}
-static struct notifier_block masq_inet_notifier = {
- .notifier_call = masq_inet_event,
+static struct notifier_block masq_inet6_notifier = {
+ .notifier_call = masq_inet6_event,
};
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
-void nf_nat_masquerade_ipv6_register_notifier(void)
+int nf_nat_masquerade_ipv6_register_notifier(void)
{
+ int ret = 0;
+
+ mutex_lock(&masq_mutex);
/* check if the notifier is already set */
- if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
- return;
+ if (++masq_refcnt > 1)
+ goto out_unlock;
+
+ ret = register_netdevice_notifier(&masq_dev_notifier);
+ if (ret)
+ goto err_dec;
+
+ ret = register_inet6addr_notifier(&masq_inet6_notifier);
+ if (ret)
+ goto err_unregister;
- register_netdevice_notifier(&masq_dev_notifier);
- register_inet6addr_notifier(&masq_inet_notifier);
+ mutex_unlock(&masq_mutex);
+ return ret;
+
+err_unregister:
+ unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+ masq_refcnt--;
+out_unlock:
+ mutex_unlock(&masq_mutex);
+ return ret;
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
void nf_nat_masquerade_ipv6_unregister_notifier(void)
{
+ mutex_lock(&masq_mutex);
/* check if the notifier still has clients */
- if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
- return;
+ if (--masq_refcnt > 0)
+ goto out_unlock;
- unregister_inet6addr_notifier(&masq_inet_notifier);
+ unregister_inet6addr_notifier(&masq_inet6_notifier);
unregister_netdevice_notifier(&masq_dev_notifier);
+out_unlock:
+ mutex_unlock(&masq_mutex);
}
EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index dd0122f3cffe..e06c82e9dfcd 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void)
if (ret < 0)
return ret;
- nf_nat_masquerade_ipv6_register_notifier();
+ ret = nf_nat_masquerade_ipv6_register_notifier();
+ if (ret)
+ nft_unregister_expr(&nft_masq_ipv6_type);
return ret;
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5e0efd3954e9..aed7eb5c2123 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -86,9 +86,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
- if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif)
+ if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif))
continue;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2a7423c39456..194bc162866d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2232,8 +2232,7 @@ static void ip6_link_failure(struct sk_buff *skb)
if (rt) {
rcu_read_lock();
if (rt->rt6i_flags & RTF_CACHE) {
- if (dst_hold_safe(&rt->dst))
- rt6_remove_exception_rt(rt);
+ rt6_remove_exception_rt(rt);
} else {
struct fib6_info *from;
struct fib6_node *fn;
@@ -2360,10 +2359,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
+ int oif = sk->sk_bound_dev_if;
struct dst_entry *dst;
- ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
+ if (!oif && skb->dev)
+ oif = l3mdev_master_ifindex(skb->dev);
+
+ ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -2975,7 +2977,8 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (!rt)
goto out;
- rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len);
+ rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
+ extack);
if (IS_ERR(rt->fib6_metrics)) {
err = PTR_ERR(rt->fib6_metrics);
/* Do not leave garbage there. */
@@ -3214,8 +3217,8 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
if (cfg->fc_flags & RTF_GATEWAY &&
!ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
goto out;
- if (dst_hold_safe(&rt->dst))
- rc = rt6_remove_exception_rt(rt);
+
+ rc = rt6_remove_exception_rt(rt);
out:
return rc;
}
@@ -3708,7 +3711,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
if (!f6i)
return ERR_PTR(-ENOMEM);
- f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0);
+ f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0, NULL);
f6i->dst_nocount = true;
f6i->dst_host = true;
f6i->fib6_protocol = RTPROT_KERNEL;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 03e6b7a2bc53..a3f559162521 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -349,7 +349,7 @@ static void tcp_v6_mtu_reduced(struct sock *sk)
}
}
-static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -371,17 +371,19 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
- return;
+ return -ENOENT;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
- return;
+ return 0;
}
seq = ntohl(th->seq);
fatal = icmpv6_err_convert(type, code, &err);
- if (sk->sk_state == TCP_NEW_SYN_RECV)
- return tcp_req_err(sk, seq, fatal);
+ if (sk->sk_state == TCP_NEW_SYN_RECV) {
+ tcp_req_err(sk, seq, fatal);
+ return 0;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -467,6 +469,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index dae25cad05cd..1991dede7367 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -134,24 +134,28 @@ drop:
return 0;
}
-static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_tunnel *handler;
for_each_tunnel_rcu(tunnel6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
-static void tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_tunnel *handler;
for_each_tunnel_rcu(tunnel46_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static const struct inet6_protocol tunnel6_protocol = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d2d97d07ef27..09cba4cfe31f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -45,6 +45,7 @@
#include <net/raw.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
+#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
@@ -117,6 +118,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -144,15 +146,10 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
+ dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
@@ -329,6 +326,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int err;
int is_udplite = IS_UDPLITE(sk);
bool checksum_valid = false;
+ struct udp_mib *mib;
int is_udp4;
if (flags & MSG_ERRQUEUE)
@@ -352,6 +350,7 @@ try_again:
msg->msg_flags |= MSG_TRUNC;
is_udp4 = (skb->protocol == htons(ETH_P_IP));
+ mib = __UDPX_MIB(sk, is_udp4);
/*
* If checksum is needed at all, try to do it while copying the
@@ -380,24 +379,13 @@ try_again:
if (unlikely(err)) {
if (!peeked) {
atomic_inc(&sk->sk_drops);
- if (is_udp4)
- UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
- is_udplite);
- else
- UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
- is_udplite);
+ SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
return err;
}
- if (!peeked) {
- if (is_udp4)
- UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
- is_udplite);
- else
- UDP6_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
- is_udplite);
- }
+ if (!peeked)
+ SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
sock_recv_ts_and_drops(msg, sk, skb);
@@ -421,6 +409,9 @@ try_again:
*addr_len = sizeof(*sin6);
}
+ if (udp_sk(sk)->gro_enabled)
+ udp_cmsg_recv(msg, sk, skb);
+
if (np->rxopt.all)
ip6_datagram_recv_common_ctl(sk, msg, skb);
@@ -443,17 +434,8 @@ try_again:
csum_copy_err:
if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
udp_skb_destructor)) {
- if (is_udp4) {
- UDP_INC_STATS(sock_net(sk),
- UDP_MIB_CSUMERRORS, is_udplite);
- UDP_INC_STATS(sock_net(sk),
- UDP_MIB_INERRORS, is_udplite);
- } else {
- UDP6_INC_STATS(sock_net(sk),
- UDP_MIB_CSUMERRORS, is_udplite);
- UDP6_INC_STATS(sock_net(sk),
- UDP_MIB_INERRORS, is_udplite);
- }
+ SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
+ SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
@@ -463,15 +445,106 @@ csum_copy_err:
goto try_again;
}
-void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info,
- struct udp_table *udptable)
+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+void udpv6_encap_enable(void)
+{
+ static_branch_inc(&udpv6_encap_needed_key);
+}
+EXPORT_SYMBOL(udpv6_encap_enable);
+
+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
+ * through error handlers in encapsulations looking for a match.
+ */
+static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
+ struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, u32 info)
+{
+ int i;
+
+ for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
+ int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, u32 info);
+
+ if (!ip6tun_encaps[i])
+ continue;
+ handler = rcu_dereference(ip6tun_encaps[i]->err_handler);
+ if (handler && !handler(skb, opt, type, code, offset, info))
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+/* Try to match ICMP errors to UDP tunnels by looking up a socket without
+ * reversing source and destination port: this will match tunnels that force the
+ * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
+ * lwtunnels might actually break this assumption by being configured with
+ * different destination ports on endpoints, in this case we won't be able to
+ * trace ICMP messages back to them.
+ *
+ * If this doesn't match any socket, probe tunnels with arbitrary destination
+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
+ * we've sent packets to won't necessarily match the local destination port.
+ *
+ * Then ask the tunnel implementation to match the error against a valid
+ * association.
+ *
+ * Return an error if we can't find a match, the socket if we need further
+ * processing, zero otherwise.
+ */
+static struct sock *__udp6_lib_err_encap(struct net *net,
+ const struct ipv6hdr *hdr, int offset,
+ struct udphdr *uh,
+ struct udp_table *udptable,
+ struct sk_buff *skb,
+ struct inet6_skb_parm *opt,
+ u8 type, u8 code, __be32 info)
+{
+ int network_offset, transport_offset;
+ struct sock *sk;
+
+ network_offset = skb_network_offset(skb);
+ transport_offset = skb_transport_offset(skb);
+
+ /* Network header needs to point to the outer IPv6 header inside ICMP */
+ skb_reset_network_header(skb);
+
+ /* Transport header needs to point to the UDP header */
+ skb_set_transport_header(skb, offset);
+
+ sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
+ &hdr->saddr, uh->dest,
+ inet6_iif(skb), 0, udptable, skb);
+ if (sk) {
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
+ struct udp_sock *up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (!lookup || lookup(sk, skb))
+ sk = NULL;
+ }
+
+ if (!sk) {
+ sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
+ offset, info));
+ }
+
+ skb_set_transport_header(skb, transport_offset);
+ skb_set_network_header(skb, network_offset);
+
+ return sk;
+}
+
+int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info,
+ struct udp_table *udptable)
{
struct ipv6_pinfo *np;
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct in6_addr *saddr = &hdr->saddr;
const struct in6_addr *daddr = &hdr->daddr;
struct udphdr *uh = (struct udphdr *)(skb->data+offset);
+ bool tunnel = false;
struct sock *sk;
int harderr;
int err;
@@ -480,9 +553,23 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, skb);
if (!sk) {
- __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
- ICMP6_MIB_INERRORS);
- return;
+ /* No socket for error: try tunnels before discarding */
+ sk = ERR_PTR(-ENOENT);
+ if (static_branch_unlikely(&udpv6_encap_needed_key)) {
+ sk = __udp6_lib_err_encap(net, hdr, offset, uh,
+ udptable, skb,
+ opt, type, code, info);
+ if (!sk)
+ return 0;
+ }
+
+ if (IS_ERR(sk)) {
+ __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
+ ICMP6_MIB_INERRORS);
+ return PTR_ERR(sk);
+ }
+
+ tunnel = true;
}
harderr = icmpv6_err_convert(type, code, &err);
@@ -496,10 +583,19 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
harderr = 1;
}
if (type == NDISC_REDIRECT) {
- ip6_sk_redirect(skb, sk);
+ if (tunnel) {
+ ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
+ sk->sk_mark, sk->sk_uid);
+ } else {
+ ip6_sk_redirect(skb, sk);
+ }
goto out;
}
+ /* Tunnels don't have an application socket: don't pass errors back */
+ if (tunnel)
+ goto out;
+
if (!np->recverr) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
@@ -510,7 +606,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk->sk_err = err;
sk->sk_error_report(sk);
out:
- return;
+ return 0;
}
static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
@@ -541,21 +637,14 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
return 0;
}
-static __inline__ void udpv6_err(struct sk_buff *skb,
- struct inet6_skb_parm *opt, u8 type,
- u8 code, int offset, __be32 info)
+static __inline__ int udpv6_err(struct sk_buff *skb,
+ struct inet6_skb_parm *opt, u8 type,
+ u8 code, int offset, __be32 info)
{
- __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
+ return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
}
-DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
-void udpv6_encap_enable(void)
-{
- static_branch_enable(&udpv6_encap_needed_key);
-}
-EXPORT_SYMBOL(udpv6_encap_enable);
-
-static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
@@ -638,10 +727,32 @@ drop:
return -1;
}
+static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct sk_buff *next, *segs;
+ int ret;
+
+ if (likely(!udp_unexpected_gso(sk, skb)))
+ return udpv6_queue_rcv_one_skb(sk, skb);
+
+ __skb_push(skb, -skb_mac_offset(skb));
+ segs = udp_rcv_segment(sk, skb, false);
+ for (skb = segs; skb; skb = next) {
+ next = skb->next;
+ __skb_pull(skb, skb_transport_offset(skb));
+
+ ret = udpv6_queue_rcv_one_skb(sk, skb);
+ if (ret > 0)
+ ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
+ true);
+ }
+ return 0;
+}
+
static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
- int dif, unsigned short hnum)
+ int dif, int sdif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
@@ -653,7 +764,7 @@ 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) ||
+ !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
@@ -687,6 +798,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
unsigned int offset = offsetof(typeof(*sk), sk_node);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
int dif = inet6_iif(skb);
+ int sdif = inet6_sdif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
@@ -701,7 +813,8 @@ start_lookup:
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
- uh->source, saddr, dif, hnum))
+ uh->source, saddr, dif, sdif,
+ hnum))
continue;
/* If zero checksum and no_check is not on for
* the socket then skip it.
@@ -1458,11 +1571,15 @@ void udpv6_destroy_sock(struct sock *sk)
udp_v6_flush_pending_frames(sk);
release_sock(sk);
- if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
- void (*encap_destroy)(struct sock *sk);
- encap_destroy = READ_ONCE(up->encap_destroy);
- if (encap_destroy)
- encap_destroy(sk);
+ if (static_branch_unlikely(&udpv6_encap_needed_key)) {
+ if (up->encap_type) {
+ void (*encap_destroy)(struct sock *sk);
+ encap_destroy = READ_ONCE(up->encap_destroy);
+ if (encap_destroy)
+ encap_destroy(sk);
+ }
+ if (up->encap_enabled)
+ static_branch_dec(&udpv6_encap_needed_key);
}
inet6_destroy_sock(sk);
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 7903e21c178b..5730e6503cb4 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -9,8 +9,8 @@
#include <net/transp_v6.h>
int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int);
-void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
- __be32, struct udp_table *);
+int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
+ __be32, struct udp_table *);
int udp_v6_get_port(struct sock *sk, unsigned short snum);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 1b8e161ac527..828b2457f97b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -147,13 +147,9 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
- if (uh->check) {
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+ if (uh->check)
uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
&ipv6h->daddr, 0);
- } else {
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
- }
return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
}
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 5000ad6878e6..a125aebc29e5 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -20,11 +20,12 @@ static int udplitev6_rcv(struct sk_buff *skb)
return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
}
-static void udplitev6_err(struct sk_buff *skb,
+static int udplitev6_err(struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
- __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table);
+ return __udp6_lib_err(skb, opt, type, code, offset, info,
+ &udplite_table);
}
static const struct inet6_protocol udplitev6_protocol = {
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index b2dc8ce49378..cc979b702c89 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -80,14 +80,16 @@ static int xfrm6_esp_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_protocol *handler;
for_each_protocol_rcu(esp6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static int xfrm6_ah_rcv(struct sk_buff *skb)
@@ -107,14 +109,16 @@ static int xfrm6_ah_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_protocol *handler;
for_each_protocol_rcu(ah6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
@@ -134,14 +138,16 @@ static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_protocol *handler;
for_each_protocol_rcu(ipcomp6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static const struct inet6_protocol esp6_protocol = {
generated by cgit (git 2.34.1) at 2025-05-13 00:06:21 +0000