#define FLAG_ECE 0x40 /* ECE in this ACK */
#define FLAG_DATA_LOST 0x80 /* SACK detected data lossage. */
#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_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define IsFack(tp) ((tp)->rx_opt.sack_ok & 2)
#define IsDSack(tp) ((tp)->rx_opt.sack_ok & 4)
+#define IsSackFrto() (sysctl_tcp_frto == 0x2)
+
#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
/* Adapt the MSS value used to make delayed ack decision to the
/* clear lost hint */
tp->retransmit_skb_hint = NULL;
}
+ /* SACK enhanced F-RTO detection.
+ * Set flag if and only if non-rexmitted
+ * segments below frto_highmark are
+ * SACKed (RFC4138; Appendix B).
+ * Clearing correct due to in-order walk
+ */
+ if (after(end_seq, tp->frto_highmark)) {
+ flag &= ~FLAG_ONLY_ORIG_SACKED;
+ } else {
+ if (!(sacked & TCPCB_RETRANS))
+ flag |= FLAG_ONLY_ORIG_SACKED;
+ }
}
TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
tp->left_out = tp->sacked_out + tp->lost_out;
- 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->frto_highmark && after(tp->snd_una, tp->frto_highmark)))
tcp_update_reordering(sk, ((tp->fackets_out + 1) - reord), 0);
#if FASTRETRANS_DEBUG > 0
return flag;
}
-/* RTO occurred, but do not yet enter loss state. Instead, transmit two new
- * segments to see from the next ACKs whether any data was really missing.
- * If the RTO was spurious, new ACKs should arrive.
+/* F-RTO can only be used if these conditions are satisfied:
+ * - there must be some unsent new data
+ * - the advertised window should allow sending it
+ * - TCP has never retransmitted anything other than head (SACK enhanced
+ * variant from Appendix B of RFC4138 is more robust here)
+ */
+int tcp_use_frto(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+
+ if (!sysctl_tcp_frto || !sk->sk_send_head ||
+ after(TCP_SKB_CB(sk->sk_send_head)->end_seq,
+ tp->snd_una + tp->snd_wnd))
+ return 0;
+
+ if (IsSackFrto())
+ return 1;
+
+ /* Avoid expensive walking of rexmit queue if possible */
+ if (tp->retrans_out > 1)
+ return 0;
+
+ skb = skb_peek(&sk->sk_write_queue)->next; /* Skips head */
+ sk_stream_for_retrans_queue_from(skb, sk) {
+ if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
+ return 0;
+ /* Short-circuit when first non-SACKed skb has been checked */
+ if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED))
+ break;
+ }
+ return 1;
+}
+
+/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO
+ * recovery a bit and use heuristics in tcp_process_frto() to detect if
+ * the RTO was spurious. Only clear SACKED_RETRANS of the head here to
+ * keep retrans_out counting accurate (with SACK F-RTO, other than head
+ * may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS
+ * bits are handled if the Loss state is really to be entered (in
+ * tcp_enter_frto_loss).
+ *
+ * Do like tcp_enter_loss() would; when RTO expires the second time it
+ * does:
+ * "Reduce ssthresh if it has not yet been made inside this window."
*/
void tcp_enter_frto(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- tp->frto_counter = 1;
-
- if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
+ if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) ||
tp->snd_una == tp->high_seq ||
- (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
+ ((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) &&
+ !icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
- tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ /* Our state is too optimistic in ssthresh() call because cwnd
+ * is not reduced until tcp_enter_frto_loss() when previous FRTO
+ * recovery has not yet completed. Pattern would be this: RTO,
+ * Cumulative ACK, RTO (2xRTO for the same segment does not end
+ * up here twice).
+ * RFC4138 should be more specific on what to do, even though
+ * RTO is quite unlikely to occur after the first Cumulative ACK
+ * due to back-off and complexity of triggering events ...
+ */
+ if (tp->frto_counter) {
+ u32 stored_cwnd;
+ stored_cwnd = tp->snd_cwnd;
+ tp->snd_cwnd = 2;
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ tp->snd_cwnd = stored_cwnd;
+ } else {
+ tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
+ }
+ /* ... in theory, cong.control module could do "any tricks" in
+ * ssthresh(), which means that ca_state, lost bits and lost_out
+ * counter would have to be faked before the call occurs. We
+ * consider that too expensive, unlikely and hacky, so modules
+ * using these in ssthresh() must deal these incompatibility
+ * issues if they receives CA_EVENT_FRTO and frto_counter != 0
+ */
tcp_ca_event(sk, CA_EVENT_FRTO);
}
- /* Have to clear retransmission markers here to keep the bookkeeping
- * in shape, even though we are not yet in Loss state.
- * If something was really lost, it is eventually caught up
- * in tcp_enter_frto_loss.
- */
- tp->retrans_out = 0;
tp->undo_marker = tp->snd_una;
tp->undo_retrans = 0;
- sk_stream_for_retrans_queue(skb, sk) {
+ skb = skb_peek(&sk->sk_write_queue);
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+ tp->retrans_out -= tcp_skb_pcount(skb);
}
tcp_sync_left_out(tp);
- tcp_set_ca_state(sk, TCP_CA_Open);
- tp->frto_highmark = tp->snd_nxt;
+ /* Earlier loss recovery underway (see RFC4138; Appendix B).
+ * The last condition is necessary at least in tp->frto_counter case.
+ */
+ if (IsSackFrto() && (tp->frto_counter ||
+ ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
+ after(tp->high_seq, tp->snd_una)) {
+ tp->frto_highmark = tp->high_seq;
+ } else {
+ tp->frto_highmark = tp->snd_nxt;
+ }
+ tcp_set_ca_state(sk, TCP_CA_Disorder);
+ tp->high_seq = tp->snd_nxt;
+ tp->frto_counter = 1;
}
/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO,
* which indicates that we should follow the traditional RTO recovery,
* i.e. mark everything lost and do go-back-N retransmission.
*/
-static void tcp_enter_frto_loss(struct sock *sk)
+static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
tp->sacked_out = 0;
tp->lost_out = 0;
tp->fackets_out = 0;
+ tp->retrans_out = 0;
sk_stream_for_retrans_queue(skb, sk) {
cnt += tcp_skb_pcount(skb);
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
+ /*
+ * Count the retransmission made on RTO correctly (only when
+ * waiting for the first ACK and did not get it)...
+ */
+ if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) {
+ tp->retrans_out += tcp_skb_pcount(skb);
+ /* ...enter this if branch just for the first segment */
+ flag |= FLAG_DATA_ACKED;
+ } else {
+ TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
+ }
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
/* Do not mark those segments lost that were
}
tcp_sync_left_out(tp);
- tp->snd_cwnd = tp->frto_counter + tcp_packets_in_flight(tp)+1;
+ tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->undo_marker = 0;
{
__u32 packets_out;
+ /* Do not perform any recovery during FRTO algorithm */
+ if (tp->frto_counter)
+ return 0;
+
/* Trick#1: The loss is proven. */
if (tp->lost_out)
return 1;
/* E. Check state exit conditions. State can be terminated
* when high_seq is ACKed. */
if (icsk->icsk_ca_state == TCP_CA_Open) {
- if (!sysctl_tcp_frto)
- BUG_TRAP(tp->retrans_out == 0);
+ BUG_TRAP(tp->retrans_out == 0);
tp->retrans_stamp = 0;
} else if (!before(tp->snd_una, tp->high_seq)) {
switch (icsk->icsk_ca_state) {
return flag;
}
-static void tcp_process_frto(struct sock *sk, u32 prior_snd_una)
+/* A very conservative spurious RTO response algorithm: reduce cwnd and
+ * continue in congestion avoidance.
+ */
+static void tcp_conservative_spur_to_response(struct tcp_sock *tp)
+{
+ tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
+ tp->snd_cwnd_cnt = 0;
+ tcp_moderate_cwnd(tp);
+}
+
+/* F-RTO spurious RTO detection algorithm (RFC4138)
+ *
+ * F-RTO affects during two new ACKs following RTO (well, almost, see inline
+ * comments). State (ACK number) is kept in frto_counter. When ACK advances
+ * window (but not to or beyond highest sequence sent before RTO):
+ * On First ACK, send two new segments out.
+ * On Second ACK, RTO was likely spurious. Do spurious response (response
+ * algorithm is not part of the F-RTO detection algorithm
+ * given in RFC4138 but can be selected separately).
+ * Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
+ * and TCP falls back to conventional RTO recovery.
+ *
+ * Rationale: if the RTO was spurious, new ACKs should arrive from the
+ * original window even after we transmit two new data segments.
+ *
+ * SACK version:
+ * on first step, wait until first cumulative ACK arrives, then move to
+ * the second step. In second step, the next ACK decides.
+ *
+ * F-RTO is implemented (mainly) in four functions:
+ * - tcp_use_frto() is used to determine if TCP is can use F-RTO
+ * - tcp_enter_frto() prepares TCP state on RTO if F-RTO is used, it is
+ * called when tcp_use_frto() showed green light
+ * - tcp_process_frto() handles incoming ACKs during F-RTO algorithm
+ * - tcp_enter_frto_loss() is called if there is not enough evidence
+ * to prove that the RTO is indeed spurious. It transfers the control
+ * from F-RTO to the conventional RTO recovery
+ */
+static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
tcp_sync_left_out(tp);
- if (tp->snd_una == prior_snd_una ||
- !before(tp->snd_una, tp->frto_highmark)) {
- /* RTO was caused by loss, start retransmitting in
- * go-back-N slow start
- */
- tcp_enter_frto_loss(sk);
- return;
+ /* Duplicate the behavior from Loss state (fastretrans_alert) */
+ if (flag&FLAG_DATA_ACKED)
+ inet_csk(sk)->icsk_retransmits = 0;
+
+ if (!before(tp->snd_una, tp->frto_highmark)) {
+ tcp_enter_frto_loss(sk, tp->frto_counter + 1, flag);
+ return 1;
}
- if (tp->frto_counter == 1) {
- /* First ACK after RTO advances the window: allow two new
- * segments out.
+ if (!IsSackFrto() || IsReno(tp)) {
+ /* RFC4138 shortcoming in step 2; should also have case c):
+ * ACK isn't duplicate nor advances window, e.g., opposite dir
+ * data, winupdate
*/
- tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
+ if ((tp->snd_una == prior_snd_una) && (flag&FLAG_NOT_DUP) &&
+ !(flag&FLAG_FORWARD_PROGRESS))
+ return 1;
+
+ if (!(flag&FLAG_DATA_ACKED)) {
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3),
+ flag);
+ return 1;
+ }
} else {
- /* Also the second ACK after RTO advances the window.
- * The RTO was likely spurious. Reduce cwnd and continue
- * in congestion avoidance
- */
- tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
- tcp_moderate_cwnd(tp);
+ if (!(flag&FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
+ /* Prevent sending of new data. */
+ tp->snd_cwnd = min(tp->snd_cwnd,
+ tcp_packets_in_flight(tp));
+ return 1;
+ }
+
+ if ((tp->frto_counter == 2) &&
+ (!(flag&FLAG_FORWARD_PROGRESS) ||
+ ((flag&FLAG_DATA_SACKED) && !(flag&FLAG_ONLY_ORIG_SACKED)))) {
+ /* RFC4138 shortcoming (see comment above) */
+ if (!(flag&FLAG_FORWARD_PROGRESS) && (flag&FLAG_NOT_DUP))
+ return 1;
+
+ tcp_enter_frto_loss(sk, 3, flag);
+ return 1;
+ }
}
- /* F-RTO affects on two new ACKs following RTO.
- * At latest on third ACK the TCP behavior is back to normal.
- */
- tp->frto_counter = (tp->frto_counter + 1) % 3;
+ if (tp->frto_counter == 1) {
+ tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
+ tp->frto_counter = 2;
+ return 1;
+ } else /* frto_counter == 2 */ {
+ tcp_conservative_spur_to_response(tp);
+ tp->frto_counter = 0;
+ }
+ return 0;
}
/* This routine deals with incoming acks, but not outgoing ones. */
u32 prior_in_flight;
s32 seq_rtt;
int prior_packets;
+ int frto_cwnd = 0;
/* If the ack is newer than sent or older than previous acks
* then we can probably ignore it.
flag |= tcp_clean_rtx_queue(sk, &seq_rtt);
if (tp->frto_counter)
- tcp_process_frto(sk, prior_snd_una);
+ frto_cwnd = tcp_process_frto(sk, prior_snd_una, flag);
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
- if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
+ if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
+ tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 0);
tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag);
} else {
- if ((flag & FLAG_DATA_ACKED))
+ if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 1);
}