#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
-#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained DSACK info */
+#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */
#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
tp->rx_opt.sack_ok &= ~2;
}
-/* Take a notice that peer is sending DSACKs */
+/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
tp->rx_opt.sack_ok |= 4;
*
* With D-SACK the lower bound is extended to cover sequence space below
* SND.UNA down to undo_marker, which is the last point of interest. Yet
- * again, DSACK block must not to go across snd_una (for the same reason as
+ * again, D-SACK block must not to go across snd_una (for the same reason as
* for the normal SACK blocks, explained above). But there all simplicity
* ends, TCP might receive valid D-SACKs below that. As long as they reside
* fully below undo_marker they do not affect behavior in anyway and can
if (!before(start_seq, tp->snd_nxt))
return 0;
- /* In outstanding window? ...This is valid exit for DSACKs too.
+ /* In outstanding window? ...This is valid exit for D-SACKs too.
* start_seq == snd_una is non-sensical (see comments above)
*/
if (after(start_seq, tp->snd_una))
/* 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 = tp->snd_nxt;
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 (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;
}
* 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)
+static 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;
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 = tp->lost_retrans_low;
int flag = 0;
int found_dup_sack = 0;
int cached_fack_count;
int i;
int first_sack_index;
+ int force_one_sack;
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
* if the only SACK change is the increase of the end_seq of
* the first block then only apply that SACK block
* and use retrans queue hinting otherwise slowpath */
- flag = 1;
+ force_one_sack = 1;
for (i = 0; i < num_sacks; i++) {
__be32 start_seq = sp[i].start_seq;
__be32 end_seq = sp[i].end_seq;
if (i == 0) {
if (tp->recv_sack_cache[i].start_seq != start_seq)
- flag = 0;
+ force_one_sack = 0;
} else {
if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
(tp->recv_sack_cache[i].end_seq != end_seq))
- flag = 0;
+ force_one_sack = 0;
}
tp->recv_sack_cache[i].start_seq = start_seq;
tp->recv_sack_cache[i].end_seq = end_seq;
}
first_sack_index = 0;
- if (flag)
+ if (force_one_sack)
num_sacks = 1;
else {
int j;
}
}
- /* clear flag as used for different purpose in following code */
- flag = 0;
-
/* Use SACK fastpath hint if valid */
cached_skb = tp->fastpath_skb_hint;
cached_fack_count = tp->fastpath_cnt_hint;
cached_fack_count = 0;
}
- for (i=0; i<num_sacks; i++, sp++) {
+ for (i = 0; i < num_sacks; i++) {
struct sk_buff *skb;
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
int dup_sack = (found_dup_sack && (i == first_sack_index));
+ int next_dup = (found_dup_sack && (i+1 == first_sack_index));
+
+ sp++;
if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) {
if (dup_sack) {
flag |= FLAG_DATA_LOST;
tcp_for_write_queue_from(skb, sk) {
- int in_sack;
+ int in_sack = 0;
u8 sacked;
if (skb == tcp_send_head(sk))
if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
- in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
+ dup_sack = (found_dup_sack && (i == first_sack_index));
+
+ /* Due to sorting DSACK may reside within this SACK block! */
+ if (next_dup) {
+ u32 dup_start = ntohl(sp->start_seq);
+ u32 dup_end = ntohl(sp->end_seq);
+
+ if (before(TCP_SKB_CB(skb)->seq, dup_end)) {
+ in_sack = tcp_match_skb_to_sack(sk, skb, dup_start, dup_end);
+ if (in_sack > 0)
+ dup_sack = 1;
+ }
+ }
+
+ /* DSACK info lost if out-of-mem, try SACK still */
+ if (in_sack <= 0)
+ in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
if (in_sack < 0)
break;
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);
!icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
/* Our state is too optimistic in ssthresh() call because cwnd
- * is not reduced until tcp_enter_frto_loss() when previous FRTO
+ * is not reduced until tcp_enter_frto_loss() when previous F-RTO
* recovery has not yet completed. Pattern would be this: RTO,
* Cumulative ACK, RTO (2xRTO for the same segment does not end
* up here twice).
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
- /* Abort FRTO algorithm if one is in progress */
+ /* Abort F-RTO algorithm if one is in progress */
tp->frto_counter = 0;
}
struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
- /* Do not perform any recovery during FRTO algorithm */
+ /* Do not perform any recovery during F-RTO algorithm */
if (tp->frto_counter)
return 0;
}
/* 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_SACKED_ACKED|TCPCB_LOST))) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
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
if (!tcp_skb_timedout(sk, skb))
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);
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);
}
}
if (tp->frto_counter == 1) {
- /* Sending of the next skb must be allowed or no FRTO */
+ /* Sending of the next skb must be allowed or no F-RTO */
if (!tcp_send_head(sk) ||
after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
while (before(start, end)) {
struct sk_buff *nskb;
- int header = skb_headroom(skb);
+ unsigned int header = skb_headroom(skb);
int copy = SKB_MAX_ORDER(header, 0);
/* Too big header? This can happen with IPv6. */