/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+static inline void tcp_packets_out_inc(struct sock *sk,
+ const struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int orig = tp->packets_out;
+
+ tp->packets_out += tcp_skb_pcount(skb);
+ if (!orig)
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
+}
+
static void update_send_head(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
} else {
- unsigned int factor;
-
- factor = skb->len + (mss_now - 1);
- factor /= mss_now;
- skb_shinfo(skb)->gso_segs = factor;
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
skb_shinfo(skb)->gso_size = mss_now;
skb_shinfo(skb)->gso_type = sk->sk_gso_type;
}
}
+/* When a modification to fackets out becomes necessary, we need to check
+ * skb is counted to fackets_out or not.
+ */
+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(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq))
+ tp->fackets_out -= decr;
+}
+
/* Function to create two new TCP segments. Shrinks the given segment
* to the specified size and appends a new segment with the rest of the
* packet to the list. This won't be called frequently, I hope.
BUG_ON(len > skb->len);
- clear_all_retrans_hints(tp);
+ tcp_clear_retrans_hints_partial(tp);
nsize = skb_headlen(skb) - len;
if (nsize < 0)
nsize = 0;
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 && (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;
TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= diff;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
tp->lost_out -= diff;
- tp->left_out -= diff;
- }
-
- if (diff > 0) {
- /* Adjust Reno SACK estimate. */
- if (!tp->rx_opt.sack_ok) {
- tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
- tcp_sync_left_out(tp);
- }
- tcp_dec_pcount_approx_int(&tp->fackets_out, diff);
- /* SACK fastpath might overwrite it unless dealt with */
- if (tp->fastpath_skb_hint != NULL &&
- after(TCP_SKB_CB(tp->fastpath_skb_hint)->seq,
- TCP_SKB_CB(skb)->seq)) {
- tcp_dec_pcount_approx_int(&tp->fastpath_cnt_hint, diff);
- }
+ /* Adjust Reno SACK estimate. */
+ if (tcp_is_reno(tp) && diff > 0) {
+ tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
+ tcp_verify_left_out(tp);
}
+ tcp_adjust_fackets_out(sk, skb, diff);
}
/* Link BUFF into the send queue. */
return (skb &&
tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
(tcp_skb_is_last(sk, skb) ?
- TCP_NAGLE_PUSH :
- tp->nonagle)));
+ tp->nonagle : TCP_NAGLE_PUSH)));
}
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
struct sk_buff *skb, *nskb, *next;
int len;
int probe_size;
+ int size_needed;
unsigned int pif;
int copy;
int mss_now;
/* Very simple search strategy: just double the MSS. */
mss_now = tcp_current_mss(sk, 0);
probe_size = 2*tp->mss_cache;
+ size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
/* TODO: set timer for probe_converge_event */
return -1;
}
/* Have enough data in the send queue to probe? */
- len = 0;
- if ((skb = tcp_send_head(sk)) == NULL)
- return -1;
- while ((len += skb->len) < probe_size && !tcp_skb_is_last(sk, skb))
- skb = tcp_write_queue_next(sk, skb);
- if (len < probe_size)
+ if (tp->write_seq - tp->snd_nxt < size_needed)
return -1;
- /* Receive window check. */
- if (after(TCP_SKB_CB(skb)->seq + probe_size, tp->snd_una + tp->snd_wnd)) {
- if (tp->snd_wnd < probe_size)
- return -1;
- else
- return 0;
- }
+ if (tp->snd_wnd < size_needed)
+ return -1;
+ if (after(tp->snd_nxt + size_needed, tp->snd_una + tp->snd_wnd))
+ return 0;
/* Do we need to wait to drain cwnd? */
pif = tcp_packets_in_flight(tp);
skb = tcp_send_head(sk);
tcp_insert_write_queue_before(nskb, skb, sk);
- tcp_advance_send_head(sk, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
BUG_ON(tcp_skb_pcount(skb) != 1 ||
tcp_skb_pcount(next_skb) != 1);
- /* changing transmit queue under us so clear hints */
- clear_all_retrans_hints(tp);
+ if (WARN_ON(tcp_is_sack(tp) && tp->sacked_out &&
+ (next_skb == tp->highest_sack)))
+ return;
/* Ok. We will be able to collapse the packet. */
tcp_unlink_write_queue(next_skb, sk);
TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked&(TCPCB_EVER_RETRANS|TCPCB_AT_TAIL);
if (TCP_SKB_CB(next_skb)->sacked&TCPCB_SACKED_RETRANS)
tp->retrans_out -= tcp_skb_pcount(next_skb);
- if (TCP_SKB_CB(next_skb)->sacked&TCPCB_LOST) {
+ if (TCP_SKB_CB(next_skb)->sacked&TCPCB_LOST)
tp->lost_out -= tcp_skb_pcount(next_skb);
- tp->left_out -= tcp_skb_pcount(next_skb);
- }
/* Reno case is special. Sigh... */
- if (!tp->rx_opt.sack_ok && tp->sacked_out) {
+ if (tcp_is_reno(tp) && tp->sacked_out)
tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
- tp->left_out -= tcp_skb_pcount(next_skb);
- }
- /* Not quite right: it can be > snd.fack, but
- * it is better to underestimate fackets.
- */
- tcp_dec_pcount_approx(&tp->fackets_out, next_skb);
- tcp_packets_out_dec(tp, 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 */
+ tcp_clear_retrans_hints_partial(tp);
+
sk_stream_free_skb(sk, next_skb);
}
}
}
}
- clear_all_retrans_hints(tp);
+ tcp_clear_all_retrans_hints(tp);
if (!lost)
return;
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
/* Don't muck with the congestion window here.
* Reason is that we do not increase amount of _data_
printk(KERN_DEBUG "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);
return;
/* No forward retransmissions in Reno are possible. */
- if (!tp->rx_opt.sack_ok)
+ if (tcp_is_reno(tp))
return;
/* Yeah, we have to make difficult choice between forward transmission
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)