[PATCH net v2 3/3] rxrpc: Fix RACK-TLP implementation

[David Howells <dhowells@redhat.com>]

Fix the RACK-TLP implementation in the following ways:

 (1) Move the "in/exiting Fast or RTO recovery" flags to the rxrpc_call
     struct rather than rxrpc_ack_summary so that they persist beyond ACK
     parsing to the next time rxrpc_congestion_management() happens (when
     the next ACK is parsed).  This allows those values to be accessed by
     RACK-TLP when invoked by the Reorder timer expiring.

 (2) In rxrpc_input_call_event(), rearm the RTO timer before the function
     returns if no other timer is running and if DATA packets have been
     sent but not yet ACK'd.  This prevents us not having a timer set to
     drive retransmission.

 (3) In rxrpc_congestion_management(), initialise the TLP state when
     entering the FAST_RETRANSMIT congestion control state, not every time
     we process that state - otherwise TLP doesn't happen in that state.

 (4) Don't reset segment_xmit_ts in rxrpc_rack_mark_lost() as that's called
     from two places, one of which shouldn't do that.  Instead, do it in
     rxrpc_rack_detect_loss().

 (5) In rxrpc_tlp_calc_pto(), check flight_size is at most one jumbo
     packet's worth of subpackets in size, not just any non-zero value
     (RFC8985 7.2 has a comparison against 1, so this is approximated
     because we'll be sending jumbo packets if possible).

 (6) In rxrpc_prepare_data_packet(), only increment call->tx_nr_resent if
     the DATA packet being retransmitted was not previously transmitted
     otherwise tx_nr_resent will keep getting bigger and cause RACK-TLP to
     malfunction (the value is used in the in-flight calculation).
     tx_nr_resent is decremented when a packet that has been retransmitted
     is discarded - but only by 1 per packet.

Fixes: 7c482665931b ("rxrpc: Implement RACK/TLP to deal with transmission stalls [RFC8985]")
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@vger.kernel.org
---
 net/rxrpc/ar-internal.h |  2 +-
 net/rxrpc/call_event.c  | 13 +++++++++++++
 net/rxrpc/input.c       |  7 ++++---
 net/rxrpc/input_rack.c  |  6 +++---
 4 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index d0e18eb6301e..d3b1b095192d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -811,6 +811,7 @@ struct rxrpc_call {
 #define RXRPC_TX_SMSS		RXRPC_JUMBO_DATALEN
 #define RXRPC_MIN_CWND		4
 	enum rxrpc_ca_state	cong_ca_state;	/* Congestion control state */
+	bool			cong_in_recovery:1; /* If we're in Fast/RTO recovery */
 	u8			cong_extra;	/* Extra to send for congestion management */
 	u16			cong_cwnd;	/* Congestion window size */
 	u16			cong_ssthresh;	/* Slow-start threshold */
@@ -895,7 +896,6 @@ struct rxrpc_ack_summary {
 	bool		retrans_timeo:1;	/* T if reTx due to timeout happened */
 	bool		need_retransmit:1;	/* T if we need transmission */
 	bool		rtt_sample_avail:1;	/* T if RTT sample available */
-	bool		in_fast_or_rto_recovery:1;
 	bool		exiting_fast_or_rto_recovery:1;
 	bool		tlp_probe_acked:1;	/* T if the TLP probe seq was acked */
 	u8 /*enum rxrpc_congest_change*/ change;
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 21be9c86d7a7..f83db83df89d 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -440,6 +440,19 @@ bool rxrpc_input_call_event(struct rxrpc_call *call)
 				       rxrpc_propose_ack_input_data);
 	}
 
+	/* Need to rearm the RTO timer if we don't start the TLP-PTO
+	 * timer [RFC8985 7.3].
+	 */
+	if (call->rack_timer_mode == RXRPC_CALL_RACKTIMER_OFF &&
+	    call->tx_in_flight > 0) {
+		ktime_t rto = rxrpc_get_rto_backoff(call, false);
+
+		call->rack_timer_mode = RXRPC_CALL_RACKTIMER_RTO;
+		call->rack_timo_at = ktime_add(ktime_get_real(), rto);
+		trace_rxrpc_rack_timer(call, rto, false);
+		trace_rxrpc_timer_set(call, rto, rxrpc_timer_trace_rack_rto);
+	}
+
 	/* Make sure the timer is restarted */
 	if (!__rxrpc_call_is_complete(call)) {
 		ktime_t next = READ_ONCE(call->expect_term_by), delay;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index f497eba59cf6..815749c7abeb 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -34,6 +34,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 {
 	summary->change = rxrpc_cong_no_change;
 	summary->in_flight = call->tx_in_flight;
+	call->cong_in_recovery = false;
 
 	if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) {
 		summary->retrans_timeo = true;
@@ -106,12 +107,12 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 		call->cong_extra = 0;
 		call->cong_dup_acks = 0;
 		summary->need_retransmit = true;
-		summary->in_fast_or_rto_recovery = true;
+		call->cong_in_recovery = true;
+		rxrpc_tlp_init(call);
 		goto out;
 
 	case RXRPC_CA_FAST_RETRANSMIT:
-		rxrpc_tlp_init(call);
-		summary->in_fast_or_rto_recovery = true;
+		call->cong_in_recovery = true;
 		if (!summary->new_low_snack) {
 			if (summary->nr_new_sacks == 0)
 				call->cong_cwnd += 1;
diff --git a/net/rxrpc/input_rack.c b/net/rxrpc/input_rack.c
index e43ce032a261..1f6b51fa9721 100644
--- a/net/rxrpc/input_rack.c
+++ b/net/rxrpc/input_rack.c
@@ -30,7 +30,6 @@ static void rxrpc_rack_mark_lost(struct rxrpc_call *call,
 
 	if (__test_and_clear_bit(ix, &tq->in_flight))
 		call->tx_in_flight--;
-	tq->segment_xmit_ts[ix] = UINT_MAX;
 }
 
 /*
@@ -184,7 +183,7 @@ static ktime_t rxrpc_rack_update_reo_wnd(struct rxrpc_call *call,
 	}
 
 	if (!call->rack_reordering_seen) {
-		if (summary->in_fast_or_rto_recovery)
+		if (call->cong_in_recovery)
 			return 0;
 		if (call->acks_nr_sacks >= dup_thresh)
 			return 0;
@@ -230,6 +229,7 @@ static ktime_t rxrpc_rack_detect_loss(struct rxrpc_call *call,
 				remaining = ktime_sub(ktime_add(xmit_ts, lost_after), now);
 				if (remaining <= 0) {
 					rxrpc_rack_mark_lost(call, tq, ix);
+					tq->segment_xmit_ts[ix] = UINT_MAX;
 					trace_rxrpc_rack_detect_loss(call, summary, seq);
 				} else {
 					timeout = max(remaining, timeout);
@@ -300,7 +300,7 @@ ktime_t rxrpc_tlp_calc_pto(struct rxrpc_call *call, ktime_t now)
 	if (call->rtt_count > 0) {
 		/* Use 2*SRTT as the timeout. */
 		pto = ns_to_ktime(call->srtt_us * NSEC_PER_USEC / 4);
-		if (flight_size)
+		if (flight_size <= max(call->peer->pmtud_jumbo, 1))
 			pto = ktime_add(pto, call->tlp_max_ack_delay);
 	} else {
 		pto = NSEC_PER_SEC;