It is going to replace the sack fastpath hint quite soon... :-)
Signed-off-by: Ilpo Järvinen <[EMAIL PROTECTED]>
---
include/linux/tcp.h | 6 ++++--
include/net/tcp.h | 13 +++++++++++++
net/ipv4/tcp_input.c | 11 ++++++-----
net/ipv4/tcp_output.c | 19 ++++++++++---------
4 files changed, 33 insertions(+), 16 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index c5b94c1..0ec6bb6 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 92049e6..aead90a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1306,6 +1306,19 @@ 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 sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (WARN_ON(!tp->sacked_out &&
+ tp->highest_sack != tcp_write_queue_head(sk)))
+ 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 9d3d390..39d6a6a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1238,10 +1238,11 @@ int tcp_match_skb_to_sack(struct sock *sk, struct
sk_buff *skb,
return in_sack;
}
-static void tcp_sacktag_one(struct sk_buff *skb, struct tcp_sock *tp,
+static void tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
struct tcp_sacktag_state *state, int in_sack,
int dup_sack, int fack_count, u32 end_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
u8 sacked = TCP_SKB_CB(skb)->sacked;
/* Account D-SACK for retransmitted packet. */
@@ -1321,8 +1322,8 @@ static void tcp_sacktag_one(struct sk_buff *skb, struct
tcp_sock *tp,
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;
+ if (after(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(sk))) {
+ tp->highest_sack = skb;
state->highest_sack_end_seq = TCP_SKB_CB(skb)->end_seq;
}
} else {
@@ -1363,7 +1364,7 @@ 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);
}
found_dup_sack = tcp_check_dsack(tp, ack_skb, sp, num_sacks,
prior_snd_una);
@@ -1497,7 +1498,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff
*ack_skb, u32 prior_snd_
fack_count += tcp_skb_pcount(skb);
- tcp_sacktag_one(skb, tp, &state, in_sack,
+ tcp_sacktag_one(skb, sk, &state, in_sack,
dup_sack, fack_count, end_seq);
}
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 324b420..9603de8 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(sk), 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. */
@@ -1720,7 +1721,7 @@ 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. */
@@ -1755,7 +1756,7 @@ 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 */
@@ -2036,7 +2037,7 @@ 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(sk)))
break;
if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
--
1.5.0.6
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
