Commit af82f4e8 authored by Yuchung Cheng's avatar Yuchung Cheng Committed by David S. Miller
Browse files

tcp: remove tcp_mark_lost_retrans() 



Remove the existing lost retransmit detection because RACK subsumes
it completely. This also stops the overloading the ack_seq field of
the skb control block.

Signed-off-by: default avatarYuchung Cheng <ycheng@google.com>
Signed-off-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent f6722583

include/linux/tcp.h

+0 −2
Original line number Diff line number Diff line
@@ -283,8 +283,6 @@ struct tcp_sock { 
	int     lost_cnt_hint;

	u32     retransmit_high;	/* L-bits may be on up to this seqno */



	u32	lost_retrans_low;	/* Sent seq after any rxmit (lowest) */



	u32	prior_ssthresh; /* ssthresh saved at recovery start	*/

	u32	high_seq;	/* snd_nxt at onset of congestion	*/

net/ipv4/tcp_input.c

+0 −65
Original line number Diff line number Diff line
@@ -1048,70 +1048,6 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, 
	return !before(start_seq, end_seq - tp->max_window);

}



/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".

 * Event "B". Later note: FACK people cheated me again 8), we have to account

 * for reordering! Ugly, but should help.

 *

 * Search retransmitted skbs from write_queue that were sent when snd_nxt was

 * less than what is now known to be received by the other end (derived from

 * highest SACK block). Also calculate the lowest snd_nxt among the remaining

 * retransmitted skbs to avoid some costly processing per ACKs.

 */

static void tcp_mark_lost_retrans(struct sock *sk, int *flag)

{

	const struct inet_connection_sock *icsk = inet_csk(sk);

	struct tcp_sock *tp = tcp_sk(sk);

	struct sk_buff *skb;

	int cnt = 0;

	u32 new_low_seq = tp->snd_nxt;

	u32 received_upto = tcp_highest_sack_seq(tp);



	if (!tcp_is_fack(tp) || !tp->retrans_out ||

	    !after(received_upto, tp->lost_retrans_low) ||

	    icsk->icsk_ca_state != TCP_CA_Recovery)

		return;



	tcp_for_write_queue(skb, sk) {

		u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;



		if (skb == tcp_send_head(sk))

			break;

		if (cnt == tp->retrans_out)

			break;

		if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))

			continue;



		if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS))

			continue;



		/* TODO: We would like to get rid of tcp_is_fack(tp) only

		 * constraint here (see above) but figuring out that at

		 * least tp->reordering SACK blocks reside between ack_seq

		 * and received_upto is not easy task to do cheaply with

		 * the available datastructures.

		 *

		 * Whether FACK should check here for tp->reordering segs

		 * in-between one could argue for either way (it would be

		 * rather simple to implement as we could count fack_count

		 * during the walk and do tp->fackets_out - fack_count).

		 */

		if (after(received_upto, ack_seq)) {

			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;

			tp->retrans_out -= tcp_skb_pcount(skb);

			*flag |= FLAG_LOST_RETRANS;

			tcp_skb_mark_lost_uncond_verify(tp, skb);

			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);

		} else {

			if (before(ack_seq, new_low_seq))

				new_low_seq = ack_seq;

			cnt += tcp_skb_pcount(skb);

		}

	}



	if (tp->retrans_out)

		tp->lost_retrans_low = new_low_seq;

}



static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,

			    struct tcp_sack_block_wire *sp, int num_sacks,

			    u32 prior_snd_una)
@@ -1838,7 +1774,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, 
	    ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))

		tcp_update_reordering(sk, tp->fackets_out - state->reord, 0);



	tcp_mark_lost_retrans(sk, &state->flag);

	tcp_verify_left_out(tp);

out:

net/ipv4/tcp_output.c

+0 −6
Original line number Diff line number Diff line
@@ -2655,8 +2655,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) 
			net_dbg_ratelimited("retrans_out leaked\n");

		}

#endif

		if (!tp->retrans_out)

			tp->lost_retrans_low = tp->snd_nxt;

		TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;

		tp->retrans_out += tcp_skb_pcount(skb);
@@ -2664,10 +2662,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) 
		if (!tp->retrans_stamp)

			tp->retrans_stamp = tcp_skb_timestamp(skb);



		/* snd_nxt is stored to detect loss of retransmitted segment,

		 * see tcp_input.c tcp_sacktag_write_queue().

		 */

		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;

	} else if (err != -EBUSY) {

		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);

	}