*/
static void tcp_disable_fack(struct tcp_sock *tp)
{
+ /* RFC3517 uses different metric in lost marker => reset on change */
+ if (tcp_is_fack(tp))
+ tp->lost_skb_hint = NULL;
tp->rx_opt.sack_ok &= ~2;
}
}
if (dst_metric(dst, RTAX_RTTVAR) > tp->mdev) {
tp->mdev = dst_metric(dst, RTAX_RTTVAR);
- tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN);
+ tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
}
tcp_set_rto(sk);
tcp_bound_rto(sk);
*
* 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.
+ * highest SACK block). 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 received_upto)
+static int tcp_mark_lost_retrans(struct sock *sk)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int flag = 0;
int cnt = 0;
u32 new_low_seq = tp->snd_nxt;
+ u32 received_upto = TCP_SKB_CB(tp->highest_sack)->end_seq;
+
+ if (!tcp_is_fack(tp) || !tp->retrans_out ||
+ !after(received_upto, tp->lost_retrans_low) ||
+ icsk->icsk_ca_state != TCP_CA_Recovery)
+ return flag;
tcp_for_write_queue(skb, sk) {
u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;
return in_sack;
}
+static int tcp_sacktag_one(struct sk_buff *skb, struct tcp_sock *tp,
+ int *reord, int dup_sack, int fack_count)
+{
+ u8 sacked = TCP_SKB_CB(skb)->sacked;
+ int flag = 0;
+
+ /* Account D-SACK for retransmitted packet. */
+ if (dup_sack && (sacked & TCPCB_RETRANS)) {
+ if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
+ tp->undo_retrans--;
+ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una) &&
+ (sacked & TCPCB_SACKED_ACKED))
+ *reord = min(fack_count, *reord);
+ }
+
+ /* Nothing to do; acked frame is about to be dropped (was ACKed). */
+ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
+ return flag;
+
+ if (!(sacked & TCPCB_SACKED_ACKED)) {
+ if (sacked & TCPCB_SACKED_RETRANS) {
+ /* If the segment is not tagged as lost,
+ * we do not clear RETRANS, believing
+ * that retransmission is still in flight.
+ */
+ if (sacked & TCPCB_LOST) {
+ TCP_SKB_CB(skb)->sacked &=
+ ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
+ tp->lost_out -= tcp_skb_pcount(skb);
+ tp->retrans_out -= tcp_skb_pcount(skb);
+
+ /* clear lost hint */
+ tp->retransmit_skb_hint = NULL;
+ }
+ } else {
+ if (!(sacked & TCPCB_RETRANS)) {
+ /* New sack for not retransmitted frame,
+ * which was in hole. It is reordering.
+ */
+ if (before(TCP_SKB_CB(skb)->seq,
+ tcp_highest_sack_seq(tp)))
+ *reord = min(fack_count, *reord);
+
+ /* SACK enhanced F-RTO (RFC4138; Appendix B) */
+ if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark))
+ flag |= FLAG_ONLY_ORIG_SACKED;
+ }
+
+ if (sacked & TCPCB_LOST) {
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
+ tp->lost_out -= tcp_skb_pcount(skb);
+
+ /* clear lost hint */
+ tp->retransmit_skb_hint = NULL;
+ }
+ }
+
+ TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
+ flag |= FLAG_DATA_SACKED;
+ tp->sacked_out += tcp_skb_pcount(skb);
+
+ fack_count += tcp_skb_pcount(skb);
+
+ /* Lost marker hint past SACKed? Tweak RFC3517 cnt */
+ if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->lost_skb_hint)->seq))
+ tp->lost_cnt_hint += tcp_skb_pcount(skb);
+
+ if (fack_count > tp->fackets_out)
+ tp->fackets_out = fack_count;
+
+ 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);
+ }
+
+ /* D-SACK. We can detect redundant retransmission in S|R and plain R
+ * frames and clear it. undo_retrans is decreased above, L|R frames
+ * are accounted above as well.
+ */
+ if (dup_sack && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)) {
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+ tp->retrans_out -= tcp_skb_pcount(skb);
+ tp->retransmit_skb_hint = NULL;
+ }
+
+ return flag;
+}
+
+static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
+ struct tcp_sack_block *next_dup,
+ u32 start_seq, u32 end_seq,
+ int dup_sack_in, int *fack_count,
+ int *reord, int *flag)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ tcp_for_write_queue_from(skb, sk) {
+ int in_sack = 0;
+ int dup_sack = dup_sack_in;
+
+ if (skb == tcp_send_head(sk))
+ break;
+
+ /* queue is in-order => we can short-circuit the walk early */
+ if (!before(TCP_SKB_CB(skb)->seq, end_seq))
+ break;
+
+ if ((next_dup != NULL) &&
+ before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) {
+ in_sack = tcp_match_skb_to_sack(sk, skb,
+ next_dup->start_seq,
+ next_dup->end_seq);
+ if (in_sack > 0)
+ dup_sack = 1;
+ }
+
+ if (in_sack <= 0)
+ in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
+ if (unlikely(in_sack < 0))
+ break;
+
+ if (in_sack)
+ *flag |= tcp_sacktag_one(skb, tp, reord, dup_sack, *fack_count);
+
+ *fack_count += tcp_skb_pcount(skb);
+ }
+ return skb;
+}
+
+/* Avoid all extra work that is being done by sacktag while walking in
+ * a normal way
+ */
+static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
+ u32 skip_to_seq)
+{
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+
+ if (!before(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
+ break;
+ }
+ return skb;
+}
+
+static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
+ struct sock *sk,
+ struct tcp_sack_block *next_dup,
+ u32 skip_to_seq,
+ int *fack_count, int *reord,
+ int *flag)
+{
+ if (next_dup == NULL)
+ return skb;
+
+ if (before(next_dup->start_seq, skip_to_seq)) {
+ skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq);
+ tcp_sacktag_walk(skb, sk, NULL,
+ next_dup->start_seq, next_dup->end_seq,
+ 1, fack_count, reord, flag);
+ }
+
+ return skb;
+}
+
+static int tcp_sack_cache_ok(struct tcp_sock *tp, struct tcp_sack_block *cache)
+{
+ return cache < tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache);
+}
+
static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_una)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned char *ptr = (skb_transport_header(ack_skb) +
TCP_SKB_CB(ack_skb)->sacked);
- struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
- struct sk_buff *cached_skb;
+ struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2);
+ struct tcp_sack_block sp[4];
+ struct tcp_sack_block *cache;
+ struct sk_buff *skb;
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
+ int used_sacks;
int reord = tp->packets_out;
- int prior_fackets;
- u32 highest_sack_end_seq = tp->lost_retrans_low;
int flag = 0;
int found_dup_sack = 0;
- int cached_fack_count;
- int i;
+ int fack_count;
+ int i, j;
int first_sack_index;
- int force_one_sack;
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;
- found_dup_sack = tcp_check_dsack(tp, ack_skb, sp,
+ found_dup_sack = tcp_check_dsack(tp, ack_skb, sp_wire,
num_sacks, prior_snd_una);
if (found_dup_sack)
flag |= FLAG_DSACKING_ACK;
if (!tp->packets_out)
goto out;
- /* SACK fastpath:
- * 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 */
- 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)
- force_one_sack = 0;
- } else {
- if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
- (tp->recv_sack_cache[i].end_seq != end_seq))
- force_one_sack = 0;
- }
- tp->recv_sack_cache[i].start_seq = start_seq;
- tp->recv_sack_cache[i].end_seq = end_seq;
- }
- /* Clear the rest of the cache sack blocks so they won't match mistakenly. */
- for (; i < ARRAY_SIZE(tp->recv_sack_cache); i++) {
- tp->recv_sack_cache[i].start_seq = 0;
- tp->recv_sack_cache[i].end_seq = 0;
- }
-
+ used_sacks = 0;
first_sack_index = 0;
- if (force_one_sack)
- num_sacks = 1;
- else {
- int j;
- tp->fastpath_skb_hint = NULL;
-
- /* order SACK blocks to allow in order walk of the retrans queue */
- for (i = num_sacks-1; i > 0; i--) {
- for (j = 0; j < i; j++){
- if (after(ntohl(sp[j].start_seq),
- ntohl(sp[j+1].start_seq))){
- struct tcp_sack_block_wire tmp;
-
- tmp = sp[j];
- sp[j] = sp[j+1];
- sp[j+1] = tmp;
-
- /* Track where the first SACK block goes to */
- if (j == first_sack_index)
- first_sack_index = j+1;
- }
-
- }
- }
- }
-
- /* Use SACK fastpath hint if valid */
- cached_skb = tp->fastpath_skb_hint;
- cached_fack_count = tp->fastpath_cnt_hint;
- if (!cached_skb) {
- cached_skb = tcp_write_queue_head(sk);
- cached_fack_count = 0;
- }
-
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));
+ int dup_sack = !i && found_dup_sack;
- sp++;
+ sp[used_sacks].start_seq = ntohl(get_unaligned(&sp_wire[i].start_seq));
+ sp[used_sacks].end_seq = ntohl(get_unaligned(&sp_wire[i].end_seq));
- if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) {
+ if (!tcp_is_sackblock_valid(tp, dup_sack,
+ sp[used_sacks].start_seq,
+ sp[used_sacks].end_seq)) {
if (dup_sack) {
if (!tp->undo_marker)
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDNOUNDO);
} else {
/* Don't count olds caused by ACK reordering */
if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) &&
- !after(end_seq, tp->snd_una))
+ !after(sp[used_sacks].end_seq, tp->snd_una))
continue;
NET_INC_STATS_BH(LINUX_MIB_TCPSACKDISCARD);
}
+ if (i == 0)
+ first_sack_index = -1;
continue;
}
- skb = cached_skb;
- fack_count = cached_fack_count;
-
- /* Event "B" in the comment above. */
- if (after(end_seq, tp->high_seq))
- flag |= FLAG_DATA_LOST;
-
- tcp_for_write_queue_from(skb, sk) {
- int in_sack = 0;
- u8 sacked;
-
- if (skb == tcp_send_head(sk))
- break;
-
- cached_skb = skb;
- cached_fack_count = fack_count;
- if (i == first_sack_index) {
- tp->fastpath_skb_hint = skb;
- tp->fastpath_cnt_hint = fack_count;
- }
+ /* Ignore very old stuff early */
+ if (!after(sp[used_sacks].end_seq, prior_snd_una))
+ continue;
- /* The retransmission queue is always in order, so
- * we can short-circuit the walk early.
- */
- if (!before(TCP_SKB_CB(skb)->seq, end_seq))
- break;
+ used_sacks++;
+ }
- dup_sack = (found_dup_sack && (i == first_sack_index));
+ /* order SACK blocks to allow in order walk of the retrans queue */
+ for (i = used_sacks - 1; i > 0; i--) {
+ for (j = 0; j < i; j++){
+ if (after(sp[j].start_seq, sp[j+1].start_seq)) {
+ struct tcp_sack_block tmp;
- /* 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);
+ tmp = sp[j];
+ sp[j] = sp[j+1];
+ sp[j+1] = tmp;
- 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;
- }
+ /* Track where the first SACK block goes to */
+ if (j == first_sack_index)
+ first_sack_index = j+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 (unlikely(in_sack < 0))
- break;
+ skb = tcp_write_queue_head(sk);
+ fack_count = 0;
+ i = 0;
- sacked = TCP_SKB_CB(skb)->sacked;
+ if (!tp->sacked_out) {
+ /* It's already past, so skip checking against it */
+ cache = tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache);
+ } else {
+ cache = tp->recv_sack_cache;
+ /* Skip empty blocks in at head of the cache */
+ while (tcp_sack_cache_ok(tp, cache) && !cache->start_seq &&
+ !cache->end_seq)
+ cache++;
+ }
- /* Account D-SACK for retransmitted packet. */
- if ((dup_sack && in_sack) &&
- (sacked & TCPCB_RETRANS) &&
- after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
- tp->undo_retrans--;
+ while (i < used_sacks) {
+ u32 start_seq = sp[i].start_seq;
+ u32 end_seq = sp[i].end_seq;
+ int dup_sack = (found_dup_sack && (i == first_sack_index));
+ struct tcp_sack_block *next_dup = NULL;
- /* The frame is ACKed. */
- if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) {
- if (sacked&TCPCB_RETRANS) {
- if ((dup_sack && in_sack) &&
- (sacked&TCPCB_SACKED_ACKED))
- reord = min(fack_count, reord);
- }
+ if (found_dup_sack && ((i + 1) == first_sack_index))
+ next_dup = &sp[i + 1];
- /* Nothing to do; acked frame is about to be dropped. */
- fack_count += tcp_skb_pcount(skb);
- continue;
- }
+ /* Event "B" in the comment above. */
+ if (after(end_seq, tp->high_seq))
+ flag |= FLAG_DATA_LOST;
- if (!in_sack) {
- fack_count += tcp_skb_pcount(skb);
- continue;
+ /* Skip too early cached blocks */
+ while (tcp_sack_cache_ok(tp, cache) &&
+ !before(start_seq, cache->end_seq))
+ cache++;
+
+ /* Can skip some work by looking recv_sack_cache? */
+ if (tcp_sack_cache_ok(tp, cache) && !dup_sack &&
+ after(end_seq, cache->start_seq)) {
+
+ /* Head todo? */
+ if (before(start_seq, cache->start_seq)) {
+ skb = tcp_sacktag_skip(skb, sk, start_seq);
+ skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq,
+ cache->start_seq, dup_sack,
+ &fack_count, &reord, &flag);
}
- if (!(sacked&TCPCB_SACKED_ACKED)) {
- if (sacked & TCPCB_SACKED_RETRANS) {
- /* If the segment is not tagged as lost,
- * we do not clear RETRANS, believing
- * that retransmission is still in flight.
- */
- if (sacked & TCPCB_LOST) {
- TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
- tp->lost_out -= tcp_skb_pcount(skb);
- tp->retrans_out -= tcp_skb_pcount(skb);
-
- /* clear lost hint */
- tp->retransmit_skb_hint = NULL;
- }
- } else {
- if (!(sacked & TCPCB_RETRANS)) {
- /* New sack for not retransmitted frame,
- * which was in hole. It is reordering.
- */
- if (fack_count < prior_fackets)
- reord = min(fack_count, reord);
+ /* Rest of the block already fully processed? */
+ if (!after(end_seq, cache->end_seq))
+ goto advance_sp;
- /* SACK enhanced F-RTO (RFC4138; Appendix B) */
- if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark))
- flag |= FLAG_ONLY_ORIG_SACKED;
- }
-
- if (sacked & TCPCB_LOST) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
- tp->lost_out -= tcp_skb_pcount(skb);
-
- /* clear lost hint */
- tp->retransmit_skb_hint = NULL;
- }
- }
+ skb = tcp_maybe_skipping_dsack(skb, sk, next_dup, cache->end_seq,
+ &fack_count, &reord, &flag);
- TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
- flag |= FLAG_DATA_SACKED;
- tp->sacked_out += tcp_skb_pcount(skb);
-
- fack_count += tcp_skb_pcount(skb);
- 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;
- }
- } else {
- if (dup_sack && (sacked&TCPCB_RETRANS))
- reord = min(fack_count, reord);
-
- fack_count += tcp_skb_pcount(skb);
+ /* ...tail remains todo... */
+ if (TCP_SKB_CB(tp->highest_sack)->end_seq == cache->end_seq) {
+ /* ...but better entrypoint exists! */
+ skb = tcp_write_queue_next(sk, tp->highest_sack);
+ fack_count = tp->fackets_out;
+ cache++;
+ goto walk;
}
- /* D-SACK. We can detect redundant retransmission
- * in S|R and plain R frames and clear it.
- * undo_retrans is decreased above, L|R frames
- * are accounted above as well.
- */
- if (dup_sack &&
- (TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS)) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
- tp->retrans_out -= tcp_skb_pcount(skb);
- tp->retransmit_skb_hint = NULL;
- }
+ skb = tcp_sacktag_skip(skb, sk, cache->end_seq);
+ /* Check overlap against next cached too (past this one already) */
+ cache++;
+ continue;
+ }
+
+ if (tp->sacked_out && !before(start_seq, tcp_highest_sack_seq(tp))) {
+ skb = tcp_write_queue_next(sk, tp->highest_sack);
+ fack_count = tp->fackets_out;
}
+ skb = tcp_sacktag_skip(skb, sk, start_seq);
+walk:
+ skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, end_seq,
+ dup_sack, &fack_count, &reord, &flag);
+
+advance_sp:
/* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct
* due to in-order walk
*/
if (after(end_seq, tp->frto_highmark))
flag &= ~FLAG_ONLY_ORIG_SACKED;
+
+ i++;
}
- 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);
+ /* Clear the head of the cache sack blocks so we can skip it next time */
+ for (i = 0; i < ARRAY_SIZE(tp->recv_sack_cache) - used_sacks; i++) {
+ tp->recv_sack_cache[i].start_seq = 0;
+ tp->recv_sack_cache[i].end_seq = 0;
+ }
+ for (j = 0; j < used_sacks; j++)
+ tp->recv_sack_cache[i++] = sp[j];
+
+ flag |= tcp_mark_lost_retrans(sk);
tcp_verify_left_out(tp);
- if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss &&
+ if ((reord < tp->fackets_out) &&
+ ((icsk->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker) &&
(!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
tcp_update_reordering(sk, tp->fackets_out - reord, 0);
return tcp_is_reno(tp) ? tp->sacked_out+1 : tp->fackets_out;
}
+/* Heurestics to calculate number of duplicate ACKs. There's no dupACKs
+ * counter when SACK is enabled (without SACK, sacked_out is used for
+ * that purpose).
+ *
+ * Instead, with FACK TCP uses fackets_out that includes both SACKed
+ * segments up to the highest received SACK block so far and holes in
+ * between them.
+ *
+ * With reordering, holes may still be in flight, so RFC3517 recovery
+ * uses pure sacked_out (total number of SACKed segments) even though
+ * it violates the RFC that uses duplicate ACKs, often these are equal
+ * but when e.g. out-of-window ACKs or packet duplication occurs,
+ * they differ. Since neither occurs due to loss, TCP should really
+ * ignore them.
+ */
+static inline int tcp_dupack_heurestics(struct tcp_sock *tp)
+{
+ return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
+}
+
static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb)
{
return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
return 1;
/* Not-A-Trick#2 : Classic rule... */
- if (tcp_fackets_out(tp) > tp->reordering)
+ if (tcp_dupack_heurestics(tp) > tp->reordering)
return 1;
/* Trick#3 : when we use RFC2988 timer restart, fast
* retransmit can be triggered by timeout of queue head.
*/
- if (tcp_head_timedout(sk))
+ if (tcp_is_fack(tp) && tcp_head_timedout(sk))
return 1;
/* Trick#4: It is still not OK... But will it be useful to delay
tp->retransmit_skb_hint = NULL;
}
-/* Mark head of queue up as lost. */
-static void tcp_mark_head_lost(struct sock *sk, int packets)
+/* Mark head of queue up as lost. With RFC3517 SACK, the packets is
+ * is against sacked "cnt", otherwise it's against facked "cnt"
+ */
+static void tcp_mark_head_lost(struct sock *sk, int packets, int fast_rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
/* this is not the most efficient way to do this... */
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, tp->high_seq))
+
+ if (tcp_is_fack(tp) ||
+ (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
+ cnt += tcp_skb_pcount(skb);
+
+ if (((!fast_rexmit || (tp->lost_out > 0)) && (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;
/* Account newly detected lost packet(s) */
-static void tcp_update_scoreboard(struct sock *sk)
+static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_fack(tp)) {
+ if (tcp_is_reno(tp)) {
+ tcp_mark_head_lost(sk, 1, fast_rexmit);
+ } else if (tcp_is_fack(tp)) {
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, lost);
+ tcp_mark_head_lost(sk, lost, fast_rexmit);
} else {
- tcp_mark_head_lost(sk, 1);
+ int sacked_upto = tp->sacked_out - tp->reordering;
+ if (sacked_upto < 0)
+ sacked_upto = 0;
+ tcp_mark_head_lost(sk, sacked_upto, fast_rexmit);
}
/* New heuristics: it is possible only after we switched
* Hence, we can detect timed out packets during fast
* retransmit without falling to slow start.
*/
- if (!tcp_is_reno(tp) && tcp_head_timedout(sk)) {
+ if (tcp_is_fack(tp) && tcp_head_timedout(sk)) {
struct sk_buff *skb;
skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
{
struct tcp_sock *tp = tcp_sk(sk);
/* Partial ACK arrived. Force Hoe's retransmit. */
- int failed = tcp_is_reno(tp) || tp->fackets_out>tp->reordering;
+ int failed = tcp_is_reno(tp) || (tcp_fackets_out(tp) > tp->reordering);
if (tcp_may_undo(tp)) {
/* Plain luck! Hole if filled with delayed
struct tcp_sock *tp = tcp_sk(sk);
int is_dupack = !(flag&(FLAG_SND_UNA_ADVANCED|FLAG_NOT_DUP));
int do_lost = is_dupack || ((flag&FLAG_DATA_SACKED) &&
- (tp->fackets_out > tp->reordering));
+ (tcp_fackets_out(tp) > tp->reordering));
+ int fast_rexmit = 0;
/* Some technical things:
* 1. Reno does not count dupacks (sacked_out) automatically. */
return;
/* C. Process data loss notification, provided it is valid. */
- if ((flag&FLAG_DATA_LOST) &&
+ if (tcp_is_fack(tp) && (flag & FLAG_DATA_LOST) &&
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);
+ tcp_mark_head_lost(sk, tp->fackets_out-tp->reordering, 0);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}
tp->bytes_acked = 0;
tp->snd_cwnd_cnt = 0;
tcp_set_ca_state(sk, TCP_CA_Recovery);
+ fast_rexmit = 1;
}
- if (do_lost || tcp_head_timedout(sk))
- tcp_update_scoreboard(sk);
+ if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk)))
+ tcp_update_scoreboard(sk, fast_rexmit);
tcp_cwnd_down(sk, flag);
tcp_xmit_retransmit_queue(sk);
}
u32 cnt = 0;
u32 reord = tp->packets_out;
s32 seq_rtt = -1;
+ s32 ca_seq_rtt = -1;
ktime_t last_ackt = net_invalid_timestamp();
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
u32 packets_acked;
u8 sacked = scb->sacked;
+ /* Determine how many packets and what bytes were acked, tso and else */
if (after(scb->end_seq, tp->snd_una)) {
if (tcp_skb_pcount(skb) == 1 ||
!after(tp->snd_una, scb->seq))
if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= packets_acked;
flag |= FLAG_RETRANS_DATA_ACKED;
+ ca_seq_rtt = -1;
seq_rtt = -1;
if ((flag & FLAG_DATA_ACKED) ||
(packets_acked > 1))
flag |= FLAG_NONHEAD_RETRANS_ACKED;
} else {
+ ca_seq_rtt = now - scb->when;
+ last_ackt = skb->tstamp;
if (seq_rtt < 0) {
- seq_rtt = now - scb->when;
- if (fully_acked)
- last_ackt = skb->tstamp;
+ seq_rtt = ca_seq_rtt;
}
if (!(sacked & TCPCB_SACKED_ACKED))
reord = min(cnt, reord);
!before(end_seq, tp->snd_up))
tp->urg_mode = 0;
} else {
+ ca_seq_rtt = now - scb->when;
+ last_ackt = skb->tstamp;
if (seq_rtt < 0) {
- seq_rtt = now - scb->when;
- if (fully_acked)
- last_ackt = skb->tstamp;
+ seq_rtt = ca_seq_rtt;
}
reord = min(cnt, reord);
}
}
tp->fackets_out -= min(pkts_acked, tp->fackets_out);
- /* hint's skb might be NULL but we don't need to care */
- tp->fastpath_cnt_hint -= min_t(u32, pkts_acked,
- tp->fastpath_cnt_hint);
+
if (ca_ops->pkts_acked) {
s32 rtt_us = -1;
net_invalid_timestamp()))
rtt_us = ktime_us_delta(ktime_get_real(),
last_ackt);
- else if (seq_rtt > 0)
- rtt_us = jiffies_to_usecs(seq_rtt);
+ else if (ca_seq_rtt > 0)
+ rtt_us = jiffies_to_usecs(ca_seq_rtt);
}
ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
/* Do not send POLL_HUP for half duplex close. */
if (sk->sk_shutdown == SHUTDOWN_MASK ||
sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, 1, POLL_HUP);
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
else
- sk_wake_async(sk, 1, POLL_IN);
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
}
}
if (!sock_flag(sk, SOCK_DEAD)) {
sk->sk_state_change(sk);
- sk_wake_async(sk, 0, POLL_OUT);
+ sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
}
if (sk->sk_write_pending ||
* are not waked up, because sk->sk_sleep ==
* NULL and sk->sk_socket == NULL.
*/
- if (sk->sk_socket) {
- sk_wake_async(sk,0,POLL_OUT);
- }
+ if (sk->sk_socket)
+ sk_wake_async(sk,
+ SOCK_WAKE_IO, POLL_OUT);
tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
tp->snd_wnd = ntohs(th->window) <<
git.openpandora.org / pandora-kernel.git / blobdiff