[TCP]: Convert highest_sack to sk_buff to allow direct access

It is going to replace the sack fastpath hint quite soon... :-)

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 30 insertions, 17 deletions

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index bac17c59b24..34acee66223 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -332,8 +332,10 @@ struct tcp_sock {
 
 	struct tcp_sack_block_wire recv_sack_cache[4];
 
-	u32	highest_sack;	/* Start seq of globally highest revd SACK
-				 * (validity guaranteed only if sacked_out > 0) */
+	struct sk_buff *highest_sack;   /* highest skb with SACK received
+					 * (validity guaranteed only if
+					 * sacked_out > 0)
+					 */
 
 	/* from STCP, retrans queue hinting */
 	struct sk_buff* lost_skb_hint;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d893b448076..0ede804b16d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1312,6 +1312,16 @@ static inline int tcp_write_queue_empty(struct sock *sk)
 	return skb_queue_empty(&sk->sk_write_queue);
 }
 
+/* Start sequence of the highest skb with SACKed bit, valid only if
+ * sacked > 0 or when the caller has ensured validity by itself.
+ */
+static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
+{
+	if (!tp->sacked_out)
+		return tp->snd_una;
+	return TCP_SKB_CB(tp->highest_sack)->seq;
+}
+
 /* /proc */
 enum tcp_seq_states {
 	TCP_SEQ_STATE_LISTENING,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c0e8f2b1fa7..31294b52ad4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1245,7 +1245,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 	int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
 	int reord = tp->packets_out;
 	int prior_fackets;
-	u32 highest_sack_end_seq = tp->lost_retrans_low;
+	u32 highest_sack_end_seq;
 	int flag = 0;
 	int found_dup_sack = 0;
 	int cached_fack_count;
@@ -1256,7 +1256,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 	if (!tp->sacked_out) {
 		if (WARN_ON(tp->fackets_out))
 			tp->fackets_out = 0;
-		tp->highest_sack = tp->snd_una;
+		tp->highest_sack = tcp_write_queue_head(sk);
 	}
 	prior_fackets = tp->fackets_out;
 
@@ -1483,10 +1483,9 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 				if (fack_count > tp->fackets_out)
 					tp->fackets_out = fack_count;
 
-				if (after(TCP_SKB_CB(skb)->seq, tp->highest_sack)) {
-					tp->highest_sack = TCP_SKB_CB(skb)->seq;
-					highest_sack_end_seq = TCP_SKB_CB(skb)->end_seq;
-				}
+				if (after(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
+					tp->highest_sack = skb;
+
 			} else {
 				if (dup_sack && (sacked&TCPCB_RETRANS))
 					reord = min(fack_count, reord);
@@ -1514,6 +1513,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 			flag &= ~FLAG_ONLY_ORIG_SACKED;
 	}
 
+	highest_sack_end_seq = TCP_SKB_CB(tp->highest_sack)->end_seq;
 	if (tcp_is_fack(tp) && tp->retrans_out &&
 	    after(highest_sack_end_seq, tp->lost_retrans_low) &&
 	    icsk->icsk_ca_state == TCP_CA_Recovery)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f4c1eef89af..ce506af5ce0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -657,13 +657,15 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned
  * tweak SACK fastpath hint too as it would overwrite all changes unless
  * hint is also changed.
  */
-static void tcp_adjust_fackets_out(struct tcp_sock *tp, struct sk_buff *skb,
+static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb,
 				   int decr)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	if (!tp->sacked_out || tcp_is_reno(tp))
 		return;
 
-	if (!before(tp->highest_sack, TCP_SKB_CB(skb)->seq))
+	if (!before(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq))
 		tp->fackets_out -= decr;
 
 	/* cnt_hint is "off-by-one" compared with fackets_out (see sacktag) */
@@ -712,9 +714,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
 	TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
 	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;
 
-	if (tcp_is_sack(tp) && tp->sacked_out &&
-	    (TCP_SKB_CB(skb)->seq == tp->highest_sack))
-		tp->highest_sack = TCP_SKB_CB(buff)->seq;
+	if (tcp_is_sack(tp) && tp->sacked_out && (skb == tp->highest_sack))
+		tp->highest_sack = buff;
 
 	/* PSH and FIN should only be set in the second packet. */
 	flags = TCP_SKB_CB(skb)->flags;
@@ -772,7 +773,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss
 			tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
 			tcp_verify_left_out(tp);
 		}
-		tcp_adjust_fackets_out(tp, skb, diff);
+		tcp_adjust_fackets_out(sk, skb, diff);
 	}
 
 	/* Link BUFF into the send queue. */
@@ -1712,7 +1713,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m
 		       tcp_skb_pcount(next_skb) != 1);
 
 		if (WARN_ON(tcp_is_sack(tp) && tp->sacked_out &&
-		    (TCP_SKB_CB(next_skb)->seq == tp->highest_sack)))
+		    (next_skb == tp->highest_sack)))
 			return;
 
 		/* Ok.	We will be able to collapse the packet. */
@@ -1747,7 +1748,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m
 		if (tcp_is_reno(tp) && tp->sacked_out)
 			tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
 
-		tcp_adjust_fackets_out(tp, next_skb, tcp_skb_pcount(next_skb));
+		tcp_adjust_fackets_out(sk, next_skb, tcp_skb_pcount(next_skb));
 		tp->packets_out -= tcp_skb_pcount(next_skb);
 
 		/* changed transmit queue under us so clear hints */
@@ -2028,7 +2029,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 			break;
 		tp->forward_skb_hint = skb;
 
-		if (after(TCP_SKB_CB(skb)->seq, tp->highest_sack))
+		if (after(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
 			break;
 
 		if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)