Merge branch 'tcp-rack'

Neal Cardwell says:

====================
more accurate DSACK processing for RACK-TLP

This patch series includes two minor improvements to tighten up the accuracy of
the processing of incoming DSACK information, so that RACK-TLP behavior is
faster and more precise: first, to ensure we detect packet loss in some extra
corner cases; and second, to avoid growing the RACK reordering window (and
delaying fast recovery) in cases where it seems clear we don't need to.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/tcp_input.c

@@ -100,6 +100,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
 #define FLAG_NO_CHALLENGE_ACK	0x8000 /* do not call tcp_send_challenge_ack()	*/
 #define FLAG_ACK_MAYBE_DELAYED	0x10000 /* Likely a delayed ACK */
+#define FLAG_DSACK_TLP		0x20000 /* DSACK for tail loss probe */
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -991,6 +992,8 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
 		return 0;
 	if (seq_len > tp->mss_cache)
 		dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache);
+	else if (tp->tlp_high_seq && tp->tlp_high_seq == end_seq)
+		state->flag |= FLAG_DSACK_TLP;
 
 	tp->dsack_dups += dup_segs;
 	/* Skip the DSACK if dup segs weren't retransmitted by sender */
@@ -998,7 +1001,14 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
 		return 0;
 
 	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
-	tp->rack.dsack_seen = 1;
+	/* We increase the RACK ordering window in rounds where we receive
+	 * DSACKs that may have been due to reordering causing RACK to trigger
+	 * a spurious fast recovery. Thus RACK ignores DSACKs that happen
+	 * without having seen reordering, or that match TLP probes (TLP
+	 * is timer-driven, not triggered by RACK).
+	 */
+	if (tp->reord_seen && !(state->flag & FLAG_DSACK_TLP))
+		tp->rack.dsack_seen = 1;
 
 	state->flag |= FLAG_DSACKING_ACK;
 	/* A spurious retransmission is delivered */
@@ -3650,7 +3660,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	if (!tp->tlp_retrans) {
 		/* TLP of new data has been acknowledged */
 		tp->tlp_high_seq = 0;
-	} else if (flag & FLAG_DSACKING_ACK) {
+	} else if (flag & FLAG_DSACK_TLP) {
 		/* This DSACK means original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
 	} else if (after(ack, tp->tlp_high_seq)) {

net/ipv4/tcp_recovery.c

@@ -172,7 +172,8 @@ void tcp_rack_reo_timeout(struct sock *sk)
 
 /* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
  *
- * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded
+ * If a DSACK is received that seems like it may have been due to reordering
+ * triggering fast recovery, increment reo_wnd by min_rtt/4 (upper bounded
  * by srtt), since there is possibility that spurious retransmission was
  * due to reordering delay longer than reo_wnd.
  *