summaryrefslogtreecommitdiff
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/fib_semantics.c2
-rw-r--r--net/ipv4/fou.c28
-rw-r--r--net/ipv4/gre_offload.c8
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_gre.c50
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ip_tunnel_core.c4
-rw-r--r--net/ipv4/ip_vti.c18
-rw-r--r--net/ipv4/netfilter/arp_tables.c43
-rw-r--r--net/ipv4/netfilter/arptable_filter.c6
-rw-r--r--net/ipv4/netfilter/ip_tables.c48
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c54
-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
18 files changed, 235 insertions, 100 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/fib_semantics.c b/net/ipv4/fib_semantics.c
index d97268e8ff10..2b68418c7198 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -975,6 +975,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
val = 65535 - 40;
if (type == RTAX_MTU && val > 65535 - 15)
val = 65535 - 15;
+ if (type == RTAX_HOPLIMIT && val > 255)
+ val = 255;
if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
return -EINVAL;
fi->fib_metrics[type - 1] = val;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index a0586b4a197d..a6962ccad98a 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -195,6 +195,17 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head,
u8 proto = NAPI_GRO_CB(skb)->proto;
const struct net_offload **offloads;
+ /* We can clear the encap_mark for FOU as we are essentially doing
+ * one of two possible things. We are either adding an L4 tunnel
+ * header to the outer L3 tunnel header, or we are are simply
+ * treating the GRE tunnel header as though it is a UDP protocol
+ * specific header such as VXLAN or GENEVE.
+ */
+ NAPI_GRO_CB(skb)->encap_mark = 0;
+
+ /* Flag this frame as already having an outer encap header */
+ NAPI_GRO_CB(skb)->is_fou = 1;
+
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[proto]);
@@ -217,8 +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]);
@@ -227,6 +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();
@@ -352,6 +363,17 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
}
}
+ /* We can clear the encap_mark for GUE as we are essentially doing
+ * one of two possible things. We are either adding an L4 tunnel
+ * header to the outer L3 tunnel header, or we are are simply
+ * treating the GRE tunnel header as though it is a UDP protocol
+ * specific header such as VXLAN or GENEVE.
+ */
+ NAPI_GRO_CB(skb)->encap_mark = 0;
+
+ /* Flag this frame as already having an outer encap header */
+ NAPI_GRO_CB(skb)->is_fou = 1;
+
rcu_read_lock();
offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
ops = rcu_dereference(offloads[guehdr->proto_ctype]);
@@ -392,6 +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/gre_offload.c b/net/ipv4/gre_offload.c
index c47539d04b88..6a5bd4317866 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -150,6 +150,14 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
goto out;
+ /* We can only support GRE_CSUM if we can track the location of
+ * the GRE header. In the case of FOU/GUE we cannot because the
+ * outer UDP header displaces the GRE header leaving us in a state
+ * of limbo.
+ */
+ if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou)
+ goto out;
+
type = greh->protocol;
rcu_read_lock();
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 31936d387cfd..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;
}
@@ -862,9 +871,16 @@ static void __gre_tunnel_init(struct net_device *dev)
dev->hw_features |= GRE_FEATURES;
if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
- /* TCP offload with GRE SEQ is not supported. */
- dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ /* TCP offload with GRE SEQ is not supported, nor
+ * can we support 2 levels of outer headers requiring
+ * an update.
+ */
+ if (!(tunnel->parms.o_flags & TUNNEL_CSUM) ||
+ (tunnel->encap.type == TUNNEL_ENCAP_NONE)) {
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ }
+
/* Can use a lockless transmit, unless we generate
* output sequences
*/
@@ -886,7 +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)
@@ -895,8 +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);
}
@@ -939,6 +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;
}
@@ -1012,6 +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_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 02dd990af542..6165f30c4d72 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -372,8 +372,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb,
if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
- nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) ||
- nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) ||
+ nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
+ nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags))
return -ENOMEM;
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/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index bf081927e06b..4133b0f513af 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -359,11 +359,12 @@ unsigned int arpt_do_table(struct sk_buff *skb,
}
/* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
{
static const struct arpt_arp uncond;
- return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct arpt_entry) &&
+ memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
}
/* Figures out from what hook each rule can be called: returns 0 if
@@ -402,11 +403,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct arpt_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 && unconditional(&e->arp)) ||
- visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -474,14 +474,12 @@ next:
return 1;
}
-static inline int check_entry(const struct arpt_entry *e, const char *name)
+static inline int check_entry(const struct arpt_entry *e)
{
const struct xt_entry_target *t;
- if (!arp_checkentry(&e->arp)) {
- duprintf("arp_tables: arp check failed %p %s.\n", e, name);
+ if (!arp_checkentry(&e->arp))
return -EINVAL;
- }
if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
return -EINVAL;
@@ -522,10 +520,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
struct xt_target *target;
int ret;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
e->counters.pcnt = xt_percpu_counter_alloc();
if (IS_ERR_VALUE(e->counters.pcnt))
return -ENOMEM;
@@ -557,7 +551,7 @@ static bool check_underflow(const struct arpt_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->arp))
+ if (!unconditional(e))
return false;
t = arpt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -576,9 +570,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct arpt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -590,6 +586,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
return -EINVAL;
}
+ err = check_entry(e);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -598,9 +598,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -969,6 +969,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
sizeof(struct arpt_get_entries) + get.size);
return -EINVAL;
}
+ get.name[sizeof(get.name) - 1] = '\0';
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
if (!IS_ERR_OR_NULL(t)) {
@@ -1233,7 +1234,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1246,7 +1248,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
}
/* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct arpt_entry *)e, name);
+ ret = check_entry((struct arpt_entry *)e);
if (ret)
return ret;
@@ -1662,6 +1664,7 @@ static int compat_get_entries(struct net *net,
*len, sizeof(get) + get.size);
return -EINVAL;
}
+ get.name[sizeof(get.name) - 1] = '\0';
xt_compat_lock(NFPROTO_ARP);
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
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/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index e53f8d6f326d..631c100a1338 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
/* All zeroes == unconditional rule. */
/* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
{
static const struct ipt_ip uncond;
- return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct ipt_entry) &&
+ memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
#undef FWINV
}
@@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
} else if (s == e) {
(*rulenum)++;
- if (s->target_offset == sizeof(struct ipt_entry) &&
+ if (unconditional(s) &&
strcmp(t->target.u.kernel.target->name,
XT_STANDARD_TARGET) == 0 &&
- t->verdict < 0 &&
- unconditional(&s->ip)) {
+ t->verdict < 0) {
/* Tail of chains: STANDARD target (return/policy) */
*comment = *chainname == hookname
? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -476,11 +476,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct ipt_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 && unconditional(&e->ip)) ||
- visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -569,14 +568,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
}
static int
-check_entry(const struct ipt_entry *e, const char *name)
+check_entry(const struct ipt_entry *e)
{
const struct xt_entry_target *t;
- if (!ip_checkentry(&e->ip)) {
- duprintf("ip check failed %p %s.\n", e, name);
+ if (!ip_checkentry(&e->ip))
return -EINVAL;
- }
if (e->target_offset + sizeof(struct xt_entry_target) >
e->next_offset)
@@ -666,10 +663,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
e->counters.pcnt = xt_percpu_counter_alloc();
if (IS_ERR_VALUE(e->counters.pcnt))
return -ENOMEM;
@@ -721,7 +714,7 @@ static bool check_underflow(const struct ipt_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->ip))
+ if (!unconditional(e))
return false;
t = ipt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -741,9 +734,11 @@ check_entry_size_and_hooks(struct ipt_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct ipt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -755,6 +750,10 @@ check_entry_size_and_hooks(struct ipt_entry *e,
return -EINVAL;
}
+ err = check_entry(e);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_INET_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -763,9 +762,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -1157,6 +1156,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
*len, sizeof(get) + get.size);
return -EINVAL;
}
+ get.name[sizeof(get.name) - 1] = '\0';
t = xt_find_table_lock(net, AF_INET, get.name);
if (!IS_ERR_OR_NULL(t)) {
@@ -1493,7 +1493,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1506,7 +1507,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
}
/* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct ipt_entry *)e, name);
+ ret = check_entry((struct ipt_entry *)e);
if (ret)
return ret;
@@ -1935,6 +1936,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
*len, sizeof(get) + get.size);
return -EINVAL;
}
+ get.name[sizeof(get.name) - 1] = '\0';
xt_compat_lock(AF_INET);
t = xt_find_table_lock(net, AF_INET, get.name);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 7b8fbb352877..db5b87509446 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -18,10 +18,10 @@
#include <net/netfilter/nf_conntrack_synproxy.h>
static struct iphdr *
-synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr)
+synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr,
+ __be32 daddr)
{
struct iphdr *iph;
- struct net *net = sock_net(skb->sk);
skb_reset_network_header(skb);
iph = (struct iphdr *)skb_put(skb, sizeof(*iph));
@@ -40,14 +40,12 @@ synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr)
}
static void
-synproxy_send_tcp(const struct synproxy_net *snet,
+synproxy_send_tcp(struct net *net,
const struct sk_buff *skb, struct sk_buff *nskb,
struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo,
struct iphdr *niph, struct tcphdr *nth,
unsigned int tcp_hdr_size)
{
- struct net *net = nf_ct_net(snet->tmpl);
-
nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)nth - nskb->head;
@@ -72,7 +70,7 @@ free_nskb:
}
static void
-synproxy_send_client_synack(const struct synproxy_net *snet,
+synproxy_send_client_synack(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts)
{
@@ -91,7 +89,7 @@ synproxy_send_client_synack(const struct synproxy_net *snet,
return;
skb_reserve(nskb, MAX_TCP_HEADER);
- niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr);
+ niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr);
skb_reset_transport_header(nskb);
nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size);
@@ -109,15 +107,16 @@ synproxy_send_client_synack(const struct synproxy_net *snet,
synproxy_build_options(nth, opts);
- synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
+ synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
niph, nth, tcp_hdr_size);
}
static void
-synproxy_send_server_syn(const struct synproxy_net *snet,
+synproxy_send_server_syn(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts, u32 recv_seq)
{
+ struct synproxy_net *snet = synproxy_pernet(net);
struct sk_buff *nskb;
struct iphdr *iph, *niph;
struct tcphdr *nth;
@@ -132,7 +131,7 @@ synproxy_send_server_syn(const struct synproxy_net *snet,
return;
skb_reserve(nskb, MAX_TCP_HEADER);
- niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr);
+ niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr);
skb_reset_transport_header(nskb);
nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size);
@@ -153,12 +152,12 @@ synproxy_send_server_syn(const struct synproxy_net *snet,
synproxy_build_options(nth, opts);
- synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW,
+ synproxy_send_tcp(net, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW,
niph, nth, tcp_hdr_size);
}
static void
-synproxy_send_server_ack(const struct synproxy_net *snet,
+synproxy_send_server_ack(struct net *net,
const struct ip_ct_tcp *state,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts)
@@ -177,7 +176,7 @@ synproxy_send_server_ack(const struct synproxy_net *snet,
return;
skb_reserve(nskb, MAX_TCP_HEADER);
- niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr);
+ niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr);
skb_reset_transport_header(nskb);
nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size);
@@ -193,11 +192,11 @@ synproxy_send_server_ack(const struct synproxy_net *snet,
synproxy_build_options(nth, opts);
- synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
+ synproxy_send_tcp(net, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
}
static void
-synproxy_send_client_ack(const struct synproxy_net *snet,
+synproxy_send_client_ack(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
const struct synproxy_options *opts)
{
@@ -215,7 +214,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet,
return;
skb_reserve(nskb, MAX_TCP_HEADER);
- niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr);
+ niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr);
skb_reset_transport_header(nskb);
nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size);
@@ -231,15 +230,16 @@ synproxy_send_client_ack(const struct synproxy_net *snet,
synproxy_build_options(nth, opts);
- synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
+ synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
niph, nth, tcp_hdr_size);
}
static bool
-synproxy_recv_client_ack(const struct synproxy_net *snet,
+synproxy_recv_client_ack(struct net *net,
const struct sk_buff *skb, const struct tcphdr *th,
struct synproxy_options *opts, u32 recv_seq)
{
+ struct synproxy_net *snet = synproxy_pernet(net);
int mss;
mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1);
@@ -255,7 +255,7 @@ synproxy_recv_client_ack(const struct synproxy_net *snet,
if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_check_timestamp_cookie(opts);
- synproxy_send_server_syn(snet, skb, th, opts, recv_seq);
+ synproxy_send_server_syn(net, skb, th, opts, recv_seq);
return true;
}
@@ -263,7 +263,8 @@ static unsigned int
synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_synproxy_info *info = par->targinfo;
- struct synproxy_net *snet = synproxy_pernet(par->net);
+ struct net *net = par->net;
+ struct synproxy_net *snet = synproxy_pernet(net);
struct synproxy_options opts = {};
struct tcphdr *th, _th;
@@ -292,12 +293,12 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
XT_SYNPROXY_OPT_SACK_PERM |
XT_SYNPROXY_OPT_ECN);
- synproxy_send_client_synack(snet, skb, th, &opts);
+ synproxy_send_client_synack(net, skb, th, &opts);
return NF_DROP;
} else if (th->ack && !(th->fin || th->rst || th->syn)) {
/* ACK from client */
- synproxy_recv_client_ack(snet, skb, th, &opts, ntohl(th->seq));
+ synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq));
return NF_DROP;
}
@@ -308,7 +309,8 @@ static unsigned int ipv4_synproxy_hook(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *nhs)
{
- struct synproxy_net *snet = synproxy_pernet(nhs->net);
+ struct net *net = nhs->net;
+ struct synproxy_net *snet = synproxy_pernet(net);
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
struct nf_conn_synproxy *synproxy;
@@ -365,7 +367,7 @@ static unsigned int ipv4_synproxy_hook(void *priv,
* therefore we need to add 1 to make the SYN sequence
* number match the one of first SYN.
*/
- if (synproxy_recv_client_ack(snet, skb, th, &opts,
+ if (synproxy_recv_client_ack(net, skb, th, &opts,
ntohl(th->seq) + 1))
this_cpu_inc(snet->stats->cookie_retrans);
@@ -391,12 +393,12 @@ static unsigned int ipv4_synproxy_hook(void *priv,
XT_SYNPROXY_OPT_SACK_PERM);
swap(opts.tsval, opts.tsecr);
- synproxy_send_server_ack(snet, state, skb, th, &opts);
+ synproxy_send_server_ack(net, state, skb, th, &opts);
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq));
swap(opts.tsval, opts.tsecr);
- synproxy_send_client_ack(snet, skb, th, &opts);
+ synproxy_send_client_ack(net, skb, th, &opts);
consume_skb(skb);
return NF_STOLEN;
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;
}
generated by cgit (git 2.34.1) at 2025-04-04 07:34:53 +0000