summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c3
-rw-r--r--net/ipv4/gre_demux.c1
-rw-r--r--net/ipv4/gre_offload.c3
-rw-r--r--net/ipv4/icmp.c2
-rw-r--r--net/ipv4/igmp.c10
-rw-r--r--net/ipv4/ip_options.c4
-rw-r--r--net/ipv4/ip_tunnel.c26
-rw-r--r--net/ipv4/route.c47
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_fastopen.c2
-rw-r--r--net/ipv4/tcp_input.c10
-rw-r--r--net/ipv4/tcp_offload.c2
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/udp.c5
14 files changed, 84 insertions, 40 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d5e6836cf77..d156b3c5f36 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1429,6 +1429,9 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff)
int proto = iph->protocol;
int err = -ENOSYS;
+ if (skb->encapsulation)
+ skb_set_inner_network_header(skb, nhoff);
+
csum_replace2(&iph->check, iph->tot_len, newlen);
iph->tot_len = newlen;
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 4e9619bca73..0485bf7f8f0 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -68,6 +68,7 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
skb_push(skb, hdr_len);
+ skb_reset_transport_header(skb);
greh = (struct gre_base_hdr *)skb->data;
greh->flags = tnl_flags_to_gre_flags(tpi->flags);
greh->protocol = tpi->proto;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index eb92deb1266..f0bdd47bbbc 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -263,6 +263,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
int err = -ENOENT;
__be16 type;
+ skb->encapsulation = 1;
+ skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
+
type = greh->protocol;
if (greh->flags & GRE_KEY)
grehlen += GRE_HEADER_SECTION;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 79c3d947a48..42b7bcf8045 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -739,8 +739,6 @@ static void icmp_unreach(struct sk_buff *skb)
/* fall through */
case 0:
info = ntohs(icmph->un.frag.mtu);
- if (!info)
- goto out;
}
break;
case ICMP_SR_FAILED:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6748d420f71..db710b059ba 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1944,6 +1944,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
rtnl_lock();
in_dev = ip_mc_find_dev(net, imr);
+ if (!in_dev) {
+ ret = -ENODEV;
+ goto out;
+ }
ifindex = imr->imr_ifindex;
for (imlp = &inet->mc_list;
(iml = rtnl_dereference(*imlp)) != NULL;
@@ -1961,16 +1965,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
*imlp = iml->next_rcu;
- if (in_dev)
- ip_mc_dec_group(in_dev, group);
+ ip_mc_dec_group(in_dev, group);
rtnl_unlock();
/* decrease mem now to avoid the memleak warning */
atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
kfree_rcu(iml, rcu);
return 0;
}
- if (!in_dev)
- ret = -ENODEV;
+out:
rtnl_unlock();
return ret;
}
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 5e7aecea05c..ad382499bac 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -288,6 +288,10 @@ int ip_options_compile(struct net *net,
optptr++;
continue;
}
+ if (unlikely(l < 2)) {
+ pp_ptr = optptr;
+ goto error;
+ }
optlen = optptr[1];
if (optlen < 2 || optlen > l) {
pp_ptr = optptr;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 097b3e7c1e8..6f9de61dce5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -73,12 +73,7 @@ static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
{
struct dst_entry *old_dst;
- if (dst) {
- if (dst->flags & DST_NOCACHE)
- dst = NULL;
- else
- dst_clone(dst);
- }
+ dst_clone(dst);
old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
dst_release(old_dst);
}
@@ -108,13 +103,14 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
rcu_read_lock();
dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
+ if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+ dst = NULL;
if (dst) {
if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
- rcu_read_unlock();
tunnel_dst_reset(t);
- return NULL;
+ dst_release(dst);
+ dst = NULL;
}
- dst_hold(dst);
}
rcu_read_unlock();
return (struct rtable *)dst;
@@ -173,6 +169,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
hlist_for_each_entry_rcu(t, head, hash_node) {
if (remote != t->parms.iph.daddr ||
+ t->parms.iph.saddr != 0 ||
!(t->dev->flags & IFF_UP))
continue;
@@ -189,10 +186,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
head = &itn->tunnels[hash];
hlist_for_each_entry_rcu(t, head, hash_node) {
- if ((local != t->parms.iph.saddr &&
- (local != t->parms.iph.daddr ||
- !ipv4_is_multicast(local))) ||
- !(t->dev->flags & IFF_UP))
+ if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+ (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+ continue;
+
+ if (!(t->dev->flags & IFF_UP))
continue;
if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -209,6 +207,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
hlist_for_each_entry_rcu(t, head, hash_node) {
if (t->parms.i_key != key ||
+ t->parms.iph.saddr != 0 ||
+ t->parms.iph.daddr != 0 ||
!(t->dev->flags & IFF_UP))
continue;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 082239ffe34..190199851c9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -457,8 +457,31 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
return neigh_create(&arp_tbl, pkey, dev);
}
-atomic_t *ip_idents __read_mostly;
-EXPORT_SYMBOL(ip_idents);
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+ atomic_t id;
+ u32 stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
+ */
+u32 ip_idents_reserve(u32 hash, int segs)
+{
+ struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+ u32 old = ACCESS_ONCE(bucket->stamp32);
+ u32 now = (u32)jiffies;
+ u32 delta = 0;
+
+ if (old != now && cmpxchg(&bucket->stamp32, old, now) == old)
+ delta = prandom_u32_max(now - old);
+
+ return atomic_add_return(segs + delta, &bucket->id) - segs;
+}
+EXPORT_SYMBOL(ip_idents_reserve);
void __ip_select_ident(struct iphdr *iph, int segs)
{
@@ -467,7 +490,10 @@ void __ip_select_ident(struct iphdr *iph, int segs)
net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
- hash = jhash_1word((__force u32)iph->daddr, ip_idents_hashrnd);
+ hash = jhash_3words((__force u32)iph->daddr,
+ (__force u32)iph->saddr,
+ iph->protocol,
+ ip_idents_hashrnd);
id = ip_idents_reserve(hash, segs);
iph->id = htons(id);
}
@@ -1010,7 +1036,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
- struct dst_entry *dst;
+ struct dst_entry *odst = NULL;
bool new = false;
bh_lock_sock(sk);
@@ -1018,16 +1044,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
if (!ip_sk_accept_pmtu(sk))
goto out;
- rt = (struct rtable *) __sk_dst_get(sk);
+ odst = sk_dst_get(sk);
- if (sock_owned_by_user(sk) || !rt) {
+ if (sock_owned_by_user(sk) || !odst) {
__ipv4_sk_update_pmtu(skb, sk, mtu);
goto out;
}
__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
- if (!__sk_dst_check(sk, 0)) {
+ rt = (struct rtable *)odst;
+ if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt))
goto out;
@@ -1037,8 +1064,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
- dst = dst_check(&rt->dst, 0);
- if (!dst) {
+ if (!dst_check(&rt->dst, 0)) {
if (new)
dst_release(&rt->dst);
@@ -1050,10 +1076,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
}
if (new)
- __sk_dst_set(sk, &rt->dst);
+ sk_dst_set(sk, &rt->dst);
out:
bh_unlock_sock(sk);
+ dst_release(odst);
}
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eb1dde37e67..9d2118e5fbc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1108,7 +1108,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (unlikely(tp->repair)) {
if (tp->repair_queue == TCP_RECV_QUEUE) {
copied = tcp_send_rcvq(sk, msg, size);
- goto out;
+ goto out_nopush;
}
err = -EINVAL;
@@ -1282,6 +1282,7 @@ wait_for_memory:
out:
if (copied)
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+out_nopush:
release_sock(sk);
return copied + copied_syn;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 62e48cf84e6..9771563ab56 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -131,7 +131,7 @@ static bool tcp_fastopen_create_child(struct sock *sk,
struct dst_entry *dst,
struct request_sock *req)
{
- struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_sock *tp;
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 40661fc1e23..40639c288dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1106,7 +1106,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
}
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+ if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
tp->undo_retrans--;
@@ -1162,7 +1162,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
unsigned int new_len = (pkt_len / mss) * mss;
if (!in_sack && new_len < pkt_len) {
new_len += mss;
- if (new_len > skb->len)
+ if (new_len >= skb->len)
return 0;
}
pkt_len = new_len;
@@ -1187,7 +1187,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
- if (tp->undo_marker && tp->undo_retrans &&
+ if (tp->undo_marker && tp->undo_retrans > 0 &&
after(end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
@@ -1893,7 +1893,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp)
tp->lost_out = 0;
tp->undo_marker = 0;
- tp->undo_retrans = 0;
+ tp->undo_retrans = -1;
}
void tcp_clear_retrans(struct tcp_sock *tp)
@@ -2665,7 +2665,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
tp->prior_ssthresh = 0;
tp->undo_marker = tp->snd_una;
- tp->undo_retrans = tp->retrans_out;
+ tp->undo_retrans = tp->retrans_out ? : -1;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
if (!ece_ack)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 4e86c59ec7f..55046ecd083 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -309,7 +309,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr,
iph->daddr, 0);
- skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
return tcp_gro_complete(skb);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d92bce0ea24..179b51e6bda 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2525,8 +2525,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
- tp->undo_retrans += tcp_skb_pcount(skb);
-
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
*/
@@ -2534,6 +2532,10 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
} else if (err != -EBUSY) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
}
+
+ if (tp->undo_retrans < 0)
+ tp->undo_retrans = 0;
+ tp->undo_retrans += tcp_skb_pcount(skb);
return err;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d92f94b7e40..7d5a8661df7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1588,8 +1588,11 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
goto csum_error;
- if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf))
+ if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+ is_udplite);
goto drop;
+ }
rc = 0;