Commit ec3c0982 authored by Patrick McManus's avatar Patrick McManus Committed by David S. Miller
Browse files

[TCP]: TCP_DEFER_ACCEPT updates - process as established 



Change TCP_DEFER_ACCEPT implementation so that it transitions a
connection to ESTABLISHED after handshake is complete instead of
leaving it in SYN-RECV until some data arrvies. Place connection in
accept queue when first data packet arrives from slow path.

Benefits:
  - established connection is now reset if it never makes it
   to the accept queue

 - diagnostic state of established matches with the packet traces
   showing completed handshake

 - TCP_DEFER_ACCEPT timeouts are expressed in seconds and can now be
   enforced with reasonable accuracy instead of rounding up to next
   exponential back-off of syn-ack retry.

Signed-off-by: default avatarPatrick McManus <mcmanus@ducksong.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent e4c78840

include/linux/tcp.h

+7 −0
Original line number Diff line number Diff line
@@ -239,6 +239,11 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) 
	return (struct tcp_request_sock *)req;

}



struct tcp_deferred_accept_info {

	struct sock *listen_sk;

	struct request_sock *request;

};



struct tcp_sock {

	/* inet_connection_sock has to be the first member of tcp_sock */

	struct inet_connection_sock	inet_conn;
@@ -374,6 +379,8 @@ struct tcp_sock { 
	unsigned int		keepalive_intvl;  /* time interval between keep alive probes */

	int			linger2;



	struct tcp_deferred_accept_info defer_tcp_accept;



	unsigned long last_synq_overflow; 



	u32	tso_deferred;

include/net/request_sock.h

+2 −2
Original line number Diff line number Diff line
@@ -115,8 +115,8 @@ struct request_sock_queue { 
	struct request_sock	*rskq_accept_head;

	struct request_sock	*rskq_accept_tail;

	rwlock_t		syn_wait_lock;

	u8			rskq_defer_accept;

	/* 3 bytes hole, try to pack */

	u16			rskq_defer_accept;

	/* 2 bytes hole, try to pack */

	struct listen_sock	*listen_opt;

};

include/net/tcp.h

+1 −0
Original line number Diff line number Diff line
@@ -139,6 +139,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); 
#define MAX_TCP_KEEPINTVL	32767

#define MAX_TCP_KEEPCNT		127

#define MAX_TCP_SYNCNT		127

#define MAX_TCP_ACCEPT_DEFERRED 65535



#define TCP_SYNQ_INTERVAL	(HZ/5)	/* Period of SYNACK timer */

net/ipv4/inet_connection_sock.c

+3 −8
Original line number Diff line number Diff line
@@ -414,8 +414,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, 
	struct inet_connection_sock *icsk = inet_csk(parent);

	struct request_sock_queue *queue = &icsk->icsk_accept_queue;

	struct listen_sock *lopt = queue->listen_opt;

	int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;

	int thresh = max_retries;

	int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;

	unsigned long now = jiffies;

	struct request_sock **reqp, *req;

	int i, budget;
@@ -451,9 +450,6 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, 
		}

	}



	if (queue->rskq_defer_accept)

		max_retries = queue->rskq_defer_accept;



	budget = 2 * (lopt->nr_table_entries / (timeout / interval));

	i = lopt->clock_hand;
@@ -461,9 +457,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, 
		reqp=&lopt->syn_table[i];

		while ((req = *reqp) != NULL) {

			if (time_after_eq(now, req->expires)) {

				if ((req->retrans < (inet_rsk(req)->acked ? max_retries : thresh)) &&

				    (inet_rsk(req)->acked ||

				     !req->rsk_ops->rtx_syn_ack(parent, req))) {

				if (req->retrans < thresh &&

				    !req->rsk_ops->rtx_syn_ack(parent, req)) {

					unsigned long timeo;



					if (req->retrans++ == 0)

net/ipv4/tcp.c

+7 −11
Original line number Diff line number Diff line
@@ -2105,15 +2105,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, 
		break;



	case TCP_DEFER_ACCEPT:

		icsk->icsk_accept_queue.rskq_defer_accept = 0;

		if (val > 0) {

			/* Translate value in seconds to number of

			 * retransmits */

			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&

			       val > ((TCP_TIMEOUT_INIT / HZ) <<

				       icsk->icsk_accept_queue.rskq_defer_accept))

				icsk->icsk_accept_queue.rskq_defer_accept++;

			icsk->icsk_accept_queue.rskq_defer_accept++;

		if (val < 0) {

			err = -EINVAL;

		} else {

			if (val > MAX_TCP_ACCEPT_DEFERRED)

				val = MAX_TCP_ACCEPT_DEFERRED;

			icsk->icsk_accept_queue.rskq_defer_accept = val;

		}

		break;
@@ -2295,8 +2292,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, 
			val = (val ? : sysctl_tcp_fin_timeout) / HZ;

		break;

	case TCP_DEFER_ACCEPT:

		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :

			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));

		val = icsk->icsk_accept_queue.rskq_defer_accept;

		break;

	case TCP_WINDOW_CLAMP:

		val = tp->window_clamp;

CRA Git | Maintained and supported by SUSTech CRA and CCSE