summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_frontend.c6
-rw-r--r--net/ipv4/fou.c6
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_gre.c37
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ip_vti.c18
-rw-r--r--net/ipv4/netfilter/arptable_filter.c6
-rw-r--r--net/ipv4/route.c19
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/ipv4/tcp_output.c22
-rw-r--r--net/ipv4/udp.c9
-rw-r--r--net/ipv4/udp_offload.c8
12 files changed, 115 insertions, 26 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8a9246deccfe..63566ec54794 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -904,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
if (ifa->ifa_flags & IFA_F_SECONDARY) {
prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
if (!prim) {
- pr_warn("%s: bug: prim == NULL\n", __func__);
+ /* if the device has been deleted, we don't perform
+ * address promotion
+ */
+ if (!in_dev->dead)
+ pr_warn("%s: bug: prim == NULL\n", __func__);
return;
}
if (iprim && iprim != prim) {
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index a39068b4a4d9..a6962ccad98a 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -228,8 +228,6 @@ static int fou_gro_complete(struct sk_buff *skb, int nhoff,
int err = -ENOSYS;
const struct net_offload **offloads;
- udp_tunnel_gro_complete(skb, nhoff);
-
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
@@ -238,6 +236,8 @@ static int fou_gro_complete(struct sk_buff *skb, int nhoff,
err = ops->callbacks.gro_complete(skb, nhoff);
+ skb_set_inner_mac_header(skb, nhoff);
+
out_unlock:
rcu_read_unlock();
@@ -414,6 +414,8 @@ static int gue_gro_complete(struct sk_buff *skb, int nhoff,
err = ops->callbacks.gro_complete(skb, nhoff + guehlen);
+ skb_set_inner_mac_header(skb, nhoff + guehlen);
+
out_unlock:
rcu_read_unlock();
return err;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index bc68eced0105..0d9e9d7bb029 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -470,6 +470,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
const struct sock *sk2,
bool match_wildcard))
{
+ struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
struct sock *sk2;
struct hlist_nulls_node *node;
kuid_t uid = sock_i_uid(sk);
@@ -479,6 +480,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
sk2->sk_family == sk->sk_family &&
ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
sk2->sk_bound_dev_if == sk->sk_bound_dev_if &&
+ inet_csk(sk2)->icsk_bind_hash == tb &&
sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
saddr_same(sk, sk2, false))
return reuseport_add_sock(sk, sk2);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index af5d1f38217f..4cc84212cce1 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -179,6 +179,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags)
return flags;
}
+/* Fills in tpi and returns header length to be pulled. */
static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
bool *csum_err)
{
@@ -238,7 +239,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
return -EINVAL;
}
}
- return iptunnel_pull_header(skb, hdr_len, tpi->proto, false);
+ return hdr_len;
}
static void ipgre_err(struct sk_buff *skb, u32 info,
@@ -341,7 +342,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
struct tnl_ptk_info tpi;
bool csum_err = false;
- if (parse_gre_header(skb, &tpi, &csum_err)) {
+ if (parse_gre_header(skb, &tpi, &csum_err) < 0) {
if (!csum_err) /* ignore csum errors. */
return;
}
@@ -397,7 +398,10 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
iph->saddr, iph->daddr, tpi->key);
if (tunnel) {
- skb_pop_mac_header(skb);
+ if (tunnel->dev->type != ARPHRD_NONE)
+ skb_pop_mac_header(skb);
+ else
+ skb_reset_mac_header(skb);
if (tunnel->collect_md) {
__be16 flags;
__be64 tun_id;
@@ -419,6 +423,7 @@ static int gre_rcv(struct sk_buff *skb)
{
struct tnl_ptk_info tpi;
bool csum_err = false;
+ int hdr_len;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
@@ -428,7 +433,10 @@ static int gre_rcv(struct sk_buff *skb)
}
#endif
- if (parse_gre_header(skb, &tpi, &csum_err) < 0)
+ hdr_len = parse_gre_header(skb, &tpi, &csum_err);
+ if (hdr_len < 0)
+ goto drop;
+ if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false) < 0)
goto drop;
if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
@@ -523,7 +531,8 @@ static struct rtable *gre_get_rt(struct sk_buff *skb,
return ip_route_output_key(net, fl);
}
-static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
+static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
+ __be16 proto)
{
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
@@ -575,7 +584,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
}
flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY);
- build_header(skb, tunnel_hlen, flags, htons(ETH_P_TEB),
+ build_header(skb, tunnel_hlen, flags, proto,
tunnel_id_to_key(tun_info->key.tun_id), 0);
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
@@ -616,7 +625,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
const struct iphdr *tnl_params;
if (tunnel->collect_md) {
- gre_fb_xmit(skb, dev);
+ gre_fb_xmit(skb, dev, skb->protocol);
return NETDEV_TX_OK;
}
@@ -660,7 +669,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
struct ip_tunnel *tunnel = netdev_priv(dev);
if (tunnel->collect_md) {
- gre_fb_xmit(skb, dev);
+ gre_fb_xmit(skb, dev, htons(ETH_P_TEB));
return NETDEV_TX_OK;
}
@@ -893,7 +902,7 @@ static int ipgre_tunnel_init(struct net_device *dev)
netif_keep_dst(dev);
dev->addr_len = 4;
- if (iph->daddr) {
+ if (iph->daddr && !tunnel->collect_md) {
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
if (!iph->saddr)
@@ -902,8 +911,9 @@ static int ipgre_tunnel_init(struct net_device *dev)
dev->header_ops = &ipgre_header_ops;
}
#endif
- } else
+ } else if (!tunnel->collect_md) {
dev->header_ops = &ipgre_header_ops;
+ }
return ip_tunnel_init(dev);
}
@@ -946,6 +956,11 @@ static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
if (flags & (GRE_VERSION|GRE_ROUTING))
return -EINVAL;
+ if (data[IFLA_GRE_COLLECT_METADATA] &&
+ data[IFLA_GRE_ENCAP_TYPE] &&
+ nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE)
+ return -EINVAL;
+
return 0;
}
@@ -1019,6 +1034,8 @@ static void ipgre_netlink_parms(struct net_device *dev,
struct ip_tunnel *t = netdev_priv(dev);
t->collect_md = true;
+ if (dev->type == ARPHRD_IPGRE)
+ dev->type = ARPHRD_NONE;
}
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6aad0192443d..a69ed94bda1b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -326,12 +326,12 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
- dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst,
- fl4.saddr);
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
dev->flags |= IFF_POINTOPOINT;
+
+ dst_cache_reset(&tunnel->dst_cache);
}
if (!tdev && tunnel->parms.link)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5cf10b777b7e..a917903d5e97 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -156,6 +156,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev; /* Device to other host */
int err;
+ int mtu;
if (!dst) {
dev->stats.tx_carrier_errors++;
@@ -192,6 +193,23 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
tunnel->err_count = 0;
}
+ mtu = dst_mtu(dst);
+ if (skb->len > mtu) {
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+ if (skb->protocol == htons(ETH_P_IP)) {
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+ } else {
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ }
+
+ dst_release(dst);
+ goto tx_error;
+ }
+
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index dd8c80dc32a2..8f8713b4388f 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -81,6 +81,12 @@ static int __init arptable_filter_init(void)
return ret;
}
+ ret = arptable_filter_table_init(&init_net);
+ if (ret) {
+ unregister_pernet_subsys(&arptable_filter_net_ops);
+ kfree(arpfilter_ops);
+ }
+
return ret;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02c62299d717..60398a9370e7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1438,9 +1438,9 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
#endif
}
-static struct rtable *rt_dst_alloc(struct net_device *dev,
- unsigned int flags, u16 type,
- bool nopolicy, bool noxfrm, bool will_cache)
+struct rtable *rt_dst_alloc(struct net_device *dev,
+ unsigned int flags, u16 type,
+ bool nopolicy, bool noxfrm, bool will_cache)
{
struct rtable *rt;
@@ -1468,6 +1468,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev,
return rt;
}
+EXPORT_SYMBOL(rt_dst_alloc);
/* called in rcu_read_lock() section */
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
@@ -2045,6 +2046,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
*/
if (fi && res->prefixlen < 4)
fi = NULL;
+ } else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+ (orig_oif != dev_out->ifindex)) {
+ /* For local routes that require a particular output interface
+ * we do not want to cache the result. Caching the result
+ * causes incorrect behaviour when there are multiple source
+ * addresses on the interface, the end result being that if the
+ * intended recipient is waiting on that interface for the
+ * packet he won't receive it because it will be delivered on
+ * the loopback interface and the IP_PKTINFO ipi_ifindex will
+ * be set to the loopback interface as well.
+ */
+ fi = NULL;
}
fnhe = NULL;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e6e65f79ade8..c124c3c12f7c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1309,6 +1309,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
+ tcp_skb_collapse_tstamp(prev, skb);
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
@@ -3098,7 +3099,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
shinfo = skb_shinfo(skb);
if ((shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
- between(shinfo->tskey, prior_snd_una, tcp_sk(sk)->snd_una - 1))
+ !before(shinfo->tskey, prior_snd_una) &&
+ before(shinfo->tskey, tcp_sk(sk)->snd_una))
__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7d2dc015cd19..79a03b87a771 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2441,6 +2441,20 @@ u32 __tcp_select_window(struct sock *sk)
return window;
}
+void tcp_skb_collapse_tstamp(struct sk_buff *skb,
+ const struct sk_buff *next_skb)
+{
+ const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb);
+ u8 tsflags = next_shinfo->tx_flags & SKBTX_ANY_TSTAMP;
+
+ if (unlikely(tsflags)) {
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+ shinfo->tx_flags |= tsflags;
+ shinfo->tskey = next_shinfo->tskey;
+ }
+}
+
/* Collapses two adjacent SKB's during retransmission. */
static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
{
@@ -2484,6 +2498,8 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));
+ tcp_skb_collapse_tstamp(skb, next_skb);
+
sk_wmem_free_skb(sk, next_skb);
}
@@ -2624,8 +2640,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
*/
if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
skb_headroom(skb) >= 0xFFFF)) {
- struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
- GFP_ATOMIC);
+ struct sk_buff *nskb;
+
+ skb_mstamp_get(&skb->skb_mstamp);
+ nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-ENOBUFS;
} else {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 08eed5e16df0..a2e7f55a1f61 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -339,8 +339,13 @@ found:
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
spin_lock(&hslot2->lock);
- hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
- &hslot2->head);
+ if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+ sk->sk_family == AF_INET6)
+ hlist_nulls_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
+ &hslot2->head);
+ else
+ hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+ &hslot2->head);
hslot2->count++;
spin_unlock(&hslot2->lock);
}
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0ed2dafb7cc4..e330c0e56b11 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -399,6 +399,11 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
uh->len = newlen;
+ /* Set encapsulation before calling into inner gro_complete() functions
+ * to make them set up the inner offsets.
+ */
+ skb->encapsulation = 1;
+
rcu_read_lock();
uo_priv = rcu_dereference(udp_offload_base);
@@ -421,9 +426,6 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
if (skb->remcsum_offload)
skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
- skb->encapsulation = 1;
- skb_set_inner_mac_header(skb, nhoff + sizeof(struct udphdr));
-
return err;
}
OpenPOWER on IntegriCloud