tcp: TCP Fast Open Server - support TFO listeners
This patch builds on top of the previous patch to add the support
for TFO listeners. This includes -
1. allocating, properly initializing, and managing the per listener
fastopen_queue structure when TFO is enabled
2. changes to the inet_csk_accept code to support TFO. E.g., the
request_sock can no longer be freed upon accept(), not until 3WHS
finishes
3. allowing a TCP_SYN_RECV socket to properly poll() and sendmsg()
if it's a TFO socket
4. properly closing a TFO listener, and a TFO socket before 3WHS
finishes
5. supporting TCP_FASTOPEN socket option
6. modifying tcp_check_req() to use to check a TFO socket as well
as request_sock
7. supporting TCP's TFO cookie option
8. adding a new SYN-ACK retransmit handler to use the timer directly
off the TFO socket rather than the listener socket. Note that TFO
server side will not retransmit anything other than SYN-ACK until
the 3WHS is completed.
The patch also contains an important function
"reqsk_fastopen_remove()" to manage the somewhat complex relation
between a listener, its request_sock, and the corresponding child
socket. See the comment above the function for the detail.
Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7f75f21..8464b79 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -283,7 +283,9 @@
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
{
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct request_sock_queue *queue = &icsk->icsk_accept_queue;
struct sock *newsk;
+ struct request_sock *req;
int error;
lock_sock(sk);
@@ -296,7 +298,7 @@
goto out_err;
/* Find already established connection */
- if (reqsk_queue_empty(&icsk->icsk_accept_queue)) {
+ if (reqsk_queue_empty(queue)) {
long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
/* If this is a non blocking socket don't sleep */
@@ -308,14 +310,32 @@
if (error)
goto out_err;
}
+ req = reqsk_queue_remove(queue);
+ newsk = req->sk;
- newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk);
- WARN_ON(newsk->sk_state == TCP_SYN_RECV);
+ sk_acceptq_removed(sk);
+ if (sk->sk_type == SOCK_STREAM && queue->fastopenq != NULL) {
+ spin_lock_bh(&queue->fastopenq->lock);
+ if (tcp_rsk(req)->listener) {
+ /* We are still waiting for the final ACK from 3WHS
+ * so can't free req now. Instead, we set req->sk to
+ * NULL to signify that the child socket is taken
+ * so reqsk_fastopen_remove() will free the req
+ * when 3WHS finishes (or is aborted).
+ */
+ req->sk = NULL;
+ req = NULL;
+ }
+ spin_unlock_bh(&queue->fastopenq->lock);
+ }
out:
release_sock(sk);
+ if (req)
+ __reqsk_free(req);
return newsk;
out_err:
newsk = NULL;
+ req = NULL;
*err = error;
goto out;
}
@@ -720,13 +740,14 @@
void inet_csk_listen_stop(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct request_sock_queue *queue = &icsk->icsk_accept_queue;
struct request_sock *acc_req;
struct request_sock *req;
inet_csk_delete_keepalive_timer(sk);
/* make all the listen_opt local to us */
- acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue);
+ acc_req = reqsk_queue_yank_acceptq(queue);
/* Following specs, it would be better either to send FIN
* (and enter FIN-WAIT-1, it is normal close)
@@ -736,7 +757,7 @@
* To be honest, we are not able to make either
* of the variants now. --ANK
*/
- reqsk_queue_destroy(&icsk->icsk_accept_queue);
+ reqsk_queue_destroy(queue);
while ((req = acc_req) != NULL) {
struct sock *child = req->sk;
@@ -754,6 +775,19 @@
percpu_counter_inc(sk->sk_prot->orphan_count);
+ if (sk->sk_type == SOCK_STREAM && tcp_rsk(req)->listener) {
+ BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+ BUG_ON(sk != tcp_rsk(req)->listener);
+
+ /* Paranoid, to prevent race condition if
+ * an inbound pkt destined for child is
+ * blocked by sock lock in tcp_v4_rcv().
+ * Also to satisfy an assertion in
+ * tcp_v4_destroy_sock().
+ */
+ tcp_sk(child)->fastopen_rsk = NULL;
+ sock_put(sk);
+ }
inet_csk_destroy_sock(child);
bh_unlock_sock(child);
@@ -763,6 +797,17 @@
sk_acceptq_removed(sk);
__reqsk_free(req);
}
+ if (queue->fastopenq != NULL) {
+ /* Free all the reqs queued in rskq_rst_head. */
+ spin_lock_bh(&queue->fastopenq->lock);
+ acc_req = queue->fastopenq->rskq_rst_head;
+ queue->fastopenq->rskq_rst_head = NULL;
+ spin_unlock_bh(&queue->fastopenq->lock);
+ while ((req = acc_req) != NULL) {
+ acc_req = req->dl_next;
+ __reqsk_free(req);
+ }
+ }
WARN_ON(sk->sk_ack_backlog);
}
EXPORT_SYMBOL_GPL(inet_csk_listen_stop);