tcp: support DUPACK threshold in RACK

This patch adds support for the classic DUPACK threshold rule
(#DupThresh) in RACK.

When the number of packets SACKed is greater or equal to the
threshold, RACK sets the reordering window to zero which would
immediately mark all the unsacked packets below the highest SACKed
sequence lost. Since this approach is known to not work well with
reordering, RACK only uses it if no reordering has been observed.

The DUPACK threshold rule is a particularly useful extension to the
fast recoveries triggered by RACK reordering timer. For example
data-center transfers where the RTT is much smaller than a timer
tick, or high RTT path where the default RTT/4 may take too long.

Note that this patch differs slightly from RFC6675. RFC6675
considers a packet lost when at least #DupThresh higher-sequence
packets are SACKed.

With RACK, for connections that have seen reordering, RACK
continues to use a dynamically-adaptive time-based reordering
window to detect losses. But for connections on which we have not
yet seen reordering, this patch considers a packet lost when at
least one higher sequence packet is SACKed and the total number
of SACKed packets is at least DupThresh. For example, suppose a
connection has not seen reordering, and sends 10 packets, and
packets 3, 5, 7 are SACKed. RFC6675 considers packets 1 and 2
lost. RACK considers packets 1, 2, 4, 6 lost.

There is some small risk of spurious retransmits here due to
reordering. However, this is mostly limited to the first flight of
a connection on which the sender receives SACKs from reordering.
And RFC 6675 and FACK loss detection have a similar risk on the
first flight with reordering (it's just that the risk of spurious
retransmits from reordering was slightly narrower for those older
algorithms due to the margin of 3*MSS).

Also the minimum reordering window is reduced from 1 msec to 0
to recover quicker on short RTT transfers. Therefore RACK is more
aggressive in marking packets lost during recovery to reduce the
reordering window timeouts.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/ip-sysctl.txt

@@ -451,6 +451,7 @@ tcp_recovery - INTEGER
 	RACK: 0x1 enables the RACK loss detection for fast detection of lost
 	      retransmissions and tail drops.
 	RACK: 0x2 makes RACK's reordering window static (min_rtt/4).
+	RACK: 0x4 disables RACK's DUPACK threshold heuristic
 
 	Default: 0x1
 

include/net/tcp.h

@@ -245,6 +245,7 @@ extern long sysctl_tcp_mem[3];
 
 #define TCP_RACK_LOSS_DETECTION  0x1 /* Use RACK to detect losses */
 #define TCP_RACK_STATIC_REO_WND  0x2 /* Use static RACK reo wnd */
+#define TCP_RACK_NO_DUPTHRESH    0x4 /* Do not use DUPACK threshold in RACK */
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;

net/ipv4/tcp_recovery.c

@@ -21,6 +21,32 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 	return t1 > t2 || (t1 == t2 && after(seq1, seq2));
 }
 
+u32 tcp_rack_reo_wnd(const struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (!tp->rack.reord) {
+		/* If reordering has not been observed, be aggressive during
+		 * the recovery or starting the recovery by DUPACK threshold.
+		 */
+		if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery)
+			return 0;
+
+		if (tp->sacked_out >= tp->reordering &&
+		    !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH))
+			return 0;
+	}
+
+	/* To be more reordering resilient, allow min_rtt/4 settling delay.
+	 * Use min_rtt instead of the smoothed RTT because reordering is
+	 * often a path property and less related to queuing or delayed ACKs.
+	 * Upon receiving DSACKs, linearly increase the window up to the
+	 * smoothed RTT.
+	 */
+	return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps,
+		   tp->srtt_us >> 3);
+}
+
 /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01):
  *
  * Marks a packet lost, if some packet sent later has been (s)acked.
@@ -44,23 +70,11 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 min_rtt = tcp_min_rtt(tp);
 	struct sk_buff *skb, *n;
 	u32 reo_wnd;
 
 	*reo_timeout = 0;
-	/* To be more reordering resilient, allow min_rtt/4 settling delay
+	reo_wnd = tcp_rack_reo_wnd(sk);
-	 * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed
-	 * RTT because reordering is often a path property and less related
-	 * to queuing or delayed ACKs.
-	 */
-	reo_wnd = 1000;
-	if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) &&
-	    min_rtt != ~0U) {
-		reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
-		reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
-	}
-
 	list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
 				 tcp_tsorted_anchor) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);