/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".
* Event "C". 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
+ * SACK blocks by the caller). Also calculate the lowest snd_nxt among the
+ * remaining retransmitted skbs to avoid some costly processing per ACKs.
*/
-static int tcp_mark_lost_retrans(struct sock *sk, u32 lost_retrans)
+static int tcp_mark_lost_retrans(struct sock *sk, u32 received_upto)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int flag = 0;
+ int cnt = 0;
+ u32 new_low_seq = 0;
tcp_for_write_queue(skb, sk) {
u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;
if (skb == tcp_send_head(sk))
break;
- if (after(TCP_SKB_CB(skb)->seq, lost_retrans))
+ 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) &&
- after(lost_retrans, ack_seq) &&
+ if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS))
+ continue;
+
+ if (after(received_upto, ack_seq) &&
(tcp_is_fack(tp) ||
- !before(lost_retrans,
+ !before(received_upto,
ack_seq + tp->reordering * tp->mss_cache))) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
flag |= FLAG_DATA_SACKED;
NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT);
}
+ } else {
+ if (!new_low_seq || 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;
+
return flag;
}
return dup_sack;
}
+/* Check if skb is fully within the SACK block. In presence of GSO skbs,
+ * the incoming SACK may not exactly match but we can find smaller MSS
+ * aligned portion of it that matches. Therefore we might need to fragment
+ * which may fail and creates some hassle (caller must handle error case
+ * returns).
+ */
+int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
+ u32 start_seq, u32 end_seq)
+{
+ int in_sack, err;
+ unsigned int pkt_len;
+
+ in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
+ !before(end_seq, TCP_SKB_CB(skb)->end_seq);
+
+ if (tcp_skb_pcount(skb) > 1 && !in_sack &&
+ after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
+
+ in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);
+
+ if (!in_sack)
+ pkt_len = start_seq - TCP_SKB_CB(skb)->seq;
+ else
+ pkt_len = end_seq - TCP_SKB_CB(skb)->seq;
+ err = tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size);
+ if (err < 0)
+ return err;
+ }
+
+ return in_sack;
+}
+
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int reord = tp->packets_out;
int prior_fackets;
- u32 lost_retrans = 0;
+ u32 highest_sack_end_seq = 0;
int flag = 0;
int found_dup_sack = 0;
int cached_fack_count;
flag |= FLAG_DATA_LOST;
tcp_for_write_queue_from(skb, sk) {
- int in_sack, pcount;
+ int in_sack;
u8 sacked;
if (skb == tcp_send_head(sk))
if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
- in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
- !before(end_seq, TCP_SKB_CB(skb)->end_seq);
-
- pcount = tcp_skb_pcount(skb);
-
- if (pcount > 1 && !in_sack &&
- after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
- unsigned int pkt_len;
-
- in_sack = !after(start_seq,
- TCP_SKB_CB(skb)->seq);
-
- if (!in_sack)
- pkt_len = (start_seq -
- TCP_SKB_CB(skb)->seq);
- else
- pkt_len = (end_seq -
- TCP_SKB_CB(skb)->seq);
- if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
- break;
- pcount = tcp_skb_pcount(skb);
- }
+ in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
+ if (in_sack < 0)
+ break;
- fack_count += pcount;
+ fack_count += tcp_skb_pcount(skb);
sacked = TCP_SKB_CB(skb)->sacked;
continue;
}
- if ((sacked&TCPCB_SACKED_RETRANS) &&
- after(end_seq, TCP_SKB_CB(skb)->ack_seq) &&
- (!lost_retrans || after(end_seq, lost_retrans)))
- lost_retrans = end_seq;
-
if (!in_sack)
continue;
if (fack_count > tp->fackets_out)
tp->fackets_out = fack_count;
- if (after(TCP_SKB_CB(skb)->seq,
- tp->highest_sack))
+ 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;
+ }
} else {
if (dup_sack && (sacked&TCPCB_RETRANS))
reord = min(fack_count, reord);
}
}
- if (lost_retrans && icsk->icsk_ca_state == TCP_CA_Recovery)
- flag |= tcp_mark_lost_retrans(sk, lost_retrans);
+ if (tp->retrans_out &&
+ after(highest_sack_end_seq, tp->lost_retrans_low) &&
+ icsk->icsk_ca_state == TCP_CA_Recovery)
+ flag |= tcp_mark_lost_retrans(sk, highest_sack_end_seq);
tcp_verify_left_out(tp);
tcp_clear_retrans_hints_partial(tp);
}
-void tcp_clear_retrans(struct tcp_sock *tp)
+static void tcp_clear_retrans_partial(struct tcp_sock *tp)
{
tp->retrans_out = 0;
-
- tp->fackets_out = 0;
- tp->sacked_out = 0;
tp->lost_out = 0;
tp->undo_marker = 0;
tp->undo_retrans = 0;
}
+void tcp_clear_retrans(struct tcp_sock *tp)
+{
+ tcp_clear_retrans_partial(tp);
+
+ tp->fackets_out = 0;
+ tp->sacked_out = 0;
+}
+
/* Enter Loss state. If "how" is not zero, forget all SACK information
* and reset tags completely, otherwise preserve SACKs. If receiver
* dropped its ofo queue, we will know this due to reneging detection.
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int cnt = 0;
/* Reduce ssthresh if it has not yet been made inside this window. */
if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->bytes_acked = 0;
- tcp_clear_retrans(tp);
+ tcp_clear_retrans_partial(tp);
+
+ if (tcp_is_reno(tp))
+ tcp_reset_reno_sack(tp);
if (!how) {
/* Push undo marker, if it was plain RTO and nothing
tp->undo_marker = tp->snd_una;
tcp_clear_retrans_hints_partial(tp);
} else {
+ tp->sacked_out = 0;
+ tp->fackets_out = 0;
tcp_clear_all_retrans_hints(tp);
}
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
break;
- cnt += tcp_skb_pcount(skb);
+
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
tp->undo_marker = 0;
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
- } else {
- tp->sacked_out += tcp_skb_pcount(skb);
- tp->fackets_out = cnt;
}
}
tcp_verify_left_out(tp);
}
/* Mark head of queue up as lost. */
-static void tcp_mark_head_lost(struct sock *sk,
- int packets, u32 high_seq)
+static void tcp_mark_head_lost(struct sock *sk, int packets)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
tp->lost_skb_hint = skb;
tp->lost_cnt_hint = cnt;
cnt += tcp_skb_pcount(skb);
- if (cnt > packets || after(TCP_SKB_CB(skb)->end_seq, high_seq))
+ if (cnt > packets || after(TCP_SKB_CB(skb)->end_seq, tp->high_seq))
break;
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
+ if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_SACKED_ACKED|TCPCB_LOST))) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
tcp_verify_retransmit_hint(tp, skb);
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, lost, tp->high_seq);
+ tcp_mark_head_lost(sk, lost);
} else {
- tcp_mark_head_lost(sk, 1, tp->high_seq);
+ tcp_mark_head_lost(sk, 1);
}
/* New heuristics: it is possible only after we switched
before(tp->snd_una, tp->high_seq) &&
icsk->icsk_ca_state != TCP_CA_Open &&
tp->fackets_out > tp->reordering) {
- tcp_mark_head_lost(sk, tp->fackets_out-tp->reordering, tp->high_seq);
+ tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}