summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c51
1 files changed, 43 insertions, 8 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7352c097ae48..af2338294598 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -980,17 +980,22 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
- tcp_rsk(req)->syn_tos : inet_sk(sk)->tos;
-
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
+ tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :
+ inet_sk(sk)->tos;
+
+ if (!INET_ECN_is_capable(tos) &&
+ tcp_bpf_ca_needs_ecn((struct sock *)req))
+ tos |= INET_ECN_ECT_0;
+
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt),
- tos & ~INET_ECN_MASK);
+ tos);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -1439,9 +1444,15 @@ static void tcp_v4_init_req(struct request_sock *req,
}
static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
+ struct sk_buff *skb,
struct flowi *fl,
- const struct request_sock *req)
+ struct request_sock *req)
{
+ tcp_v4_init_req(req, sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ return NULL;
+
return inet_csk_route_req(sk, &fl->u.ip4, req);
}
@@ -1461,7 +1472,6 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
.req_md5_lookup = tcp_v4_md5_lookup,
.calc_md5_hash = tcp_v4_md5_hash_skb,
#endif
- .init_req = tcp_v4_init_req,
#ifdef CONFIG_SYN_COOKIES
.cookie_init_seq = cookie_v4_init_sequence,
#endif
@@ -1498,6 +1508,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
bool *own_req)
{
struct inet_request_sock *ireq;
+ bool found_dup_sk = false;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
@@ -1575,12 +1586,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+ &found_dup_sk);
if (likely(*own_req)) {
tcp_move_syn(newtp, req);
ireq->ireq_opt = NULL;
} else {
- newinet->inet_opt = NULL;
+ if (!req_unhash && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
+ } else {
+ newinet->inet_opt = NULL;
+ }
}
return newsk;
@@ -2740,6 +2761,20 @@ void tcp4_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
+/* @wake is one when sk_stream_write_space() calls us.
+ * This sends EPOLLOUT only if notsent_bytes is half the limit.
+ * This mimics the strategy used in sock_def_write_space().
+ */
+bool tcp_stream_memory_free(const struct sock *sk, int wake)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u32 notsent_bytes = READ_ONCE(tp->write_seq) -
+ READ_ONCE(tp->snd_nxt);
+
+ return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
+}
+EXPORT_SYMBOL(tcp_stream_memory_free);
+
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,