rxrpc: Add a timeout for detecting lost ACKs/lost DATA

Add an extra timeout that is set/updated when we send a DATA packet that
has the request-ack flag set.  This allows us to detect if we don't get an
ACK in response to the latest flagged packet.

The ACK packet is adjudged to have been lost if it doesn't turn up within
2*RTT of the transmission.

If the timeout occurs, we schedule the sending of a PING ACK to find out
the state of the other side.  If a new DATA packet is ready to go sooner,
we cancel the sending of the ping and set the request-ack flag on that
instead.

If we get back a PING-RESPONSE ACK that indicates a lower tx_top than what
we had at the time of the ping transmission, we adjudge all the DATA
packets sent between the response tx_top and the ping-time tx_top to have
been lost and retransmit immediately.

Rather than sending a PING ACK, we could just pick a DATA packet and
speculatively retransmit that with request-ack set.  It should result in
either a REQUESTED ACK or a DUPLICATE ACK which we can then use in lieu the
a PING-RESPONSE ACK mentioned above.

Signed-off-by: David Howells <dhowells@redhat.com>

7 files changed, 89 insertions, 10 deletions

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 548411371048..7e7b817c69f0 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -471,6 +471,7 @@ enum rxrpc_call_event {
 	RXRPC_CALL_EV_RESEND,		/* Tx resend required */
 	RXRPC_CALL_EV_PING,		/* Ping send required */
 	RXRPC_CALL_EV_EXPIRED,		/* Expiry occurred */
+	RXRPC_CALL_EV_ACK_LOST,		/* ACK may be lost, send ping */
 };
 
 /*
@@ -515,6 +516,7 @@ struct rxrpc_call {
 	struct rxrpc_sock __rcu	*socket;	/* socket responsible */
 	struct mutex		user_mutex;	/* User access mutex */
 	unsigned long		ack_at;		/* When deferred ACK needs to happen */
+	unsigned long		ack_lost_at;	/* When ACK is figured as lost */
 	unsigned long		resend_at;	/* When next resend needs to happen */
 	unsigned long		ping_at;	/* When next to send a ping */
 	unsigned long		expect_rx_by;	/* When we expect to get a packet by */
@@ -624,6 +626,8 @@ struct rxrpc_call {
 	ktime_t			acks_latest_ts;	/* Timestamp of latest ACK received */
 	rxrpc_serial_t		acks_latest;	/* serial number of latest ACK received */
 	rxrpc_seq_t		acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */
+	rxrpc_seq_t		acks_lost_top;	/* tx_top at the time lost-ack ping sent */
+	rxrpc_serial_t		acks_lost_ping;	/* Serial number of probe ACK */
 };
 
 /*
@@ -1011,7 +1015,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net)
 /*
  * output.c
  */
-int rxrpc_send_ack_packet(struct rxrpc_call *, bool);
+int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *);
 int rxrpc_send_abort_packet(struct rxrpc_call *);
 int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool);
 void rxrpc_reject_packets(struct rxrpc_local *);
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index da91f16ac77c..c65666b2f39e 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -245,7 +245,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 			goto out;
 		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
 				  rxrpc_propose_ack_ping_for_lost_ack);
-		rxrpc_send_ack_packet(call, true);
+		rxrpc_send_ack_packet(call, true, NULL);
 		goto out;
 	}
 
@@ -310,6 +310,7 @@ void rxrpc_process_call(struct work_struct *work)
 {
 	struct rxrpc_call *call =
 		container_of(work, struct rxrpc_call, processor);
+	rxrpc_serial_t *send_ack;
 	unsigned long now, next, t;
 
 	rxrpc_see_call(call);
@@ -358,6 +359,13 @@ recheck_state:
 		set_bit(RXRPC_CALL_EV_ACK, &call->events);
 	}
 
+	t = READ_ONCE(call->ack_lost_at);
+	if (time_after_eq(now, t)) {
+		trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now);
+		cmpxchg(&call->ack_lost_at, t, now + MAX_JIFFY_OFFSET);
+		set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events);
+	}
+
 	t = READ_ONCE(call->ping_at);
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now);
@@ -379,15 +387,24 @@ recheck_state:
 		goto recheck_state;
 	}
 
-	if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events)) {
+	send_ack = NULL;
+	if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) {
+		call->acks_lost_top = call->tx_top;
+		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+				  rxrpc_propose_ack_ping_for_lost_ack);
+		send_ack = &call->acks_lost_ping;
+	}
+
+	if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) ||
+	    send_ack) {
 		if (call->ackr_reason) {
-			rxrpc_send_ack_packet(call, false);
+			rxrpc_send_ack_packet(call, false, send_ack);
 			goto recheck_state;
 		}
 	}
 
 	if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) {
-		rxrpc_send_ack_packet(call, true);
+		rxrpc_send_ack_packet(call, true, NULL);
 		goto recheck_state;
 	}
 
@@ -404,6 +421,7 @@ recheck_state:
 	set(call->expect_req_by);
 	set(call->expect_term_by);
 	set(call->ack_at);
+	set(call->ack_lost_at);
 	set(call->resend_at);
 	set(call->ping_at);
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index b305970a9b63..7ee3d6ce5aa2 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -197,6 +197,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call)
 	unsigned long j = now + MAX_JIFFY_OFFSET;
 
 	call->ack_at = j;
+	call->ack_lost_at = j;
 	call->resend_at = j;
 	call->ping_at = j;
 	call->expect_rx_by = j;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index c89647eae86d..23a5e61d8f79 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -631,6 +631,43 @@ found:
 }
 
 /*
+ * Process the response to a ping that we sent to find out if we lost an ACK.
+ *
+ * If we got back a ping response that indicates a lower tx_top than what we
+ * had at the time of the ping transmission, we adjudge all the DATA packets
+ * sent between the response tx_top and the ping-time tx_top to have been lost.
+ */
+static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call)
+{
+	rxrpc_seq_t top, bottom, seq;
+	bool resend = false;
+
+	spin_lock_bh(&call->lock);
+
+	bottom = call->tx_hard_ack + 1;
+	top = call->acks_lost_top;
+	if (before(bottom, top)) {
+		for (seq = bottom; before_eq(seq, top); seq++) {
+			int ix = seq & RXRPC_RXTX_BUFF_MASK;
+			u8 annotation = call->rxtx_annotations[ix];
+			u8 anno_type = annotation & RXRPC_TX_ANNO_MASK;
+
+			if (anno_type != RXRPC_TX_ANNO_UNACK)
+				continue;
+			annotation &= ~RXRPC_TX_ANNO_MASK;
+			annotation |= RXRPC_TX_ANNO_RETRANS;
+			call->rxtx_annotations[ix] = annotation;
+			resend = true;
+		}
+	}
+
+	spin_unlock_bh(&call->lock);
+
+	if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
+		rxrpc_queue_call(call);
+}
+
+/*
  * Process a ping response.
  */
 static void rxrpc_input_ping_response(struct rxrpc_call *call,
@@ -645,6 +682,9 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call,
 	smp_rmb();
 	ping_serial = call->ping_serial;
 
+	if (orig_serial == call->acks_lost_ping)
+		rxrpc_input_check_for_lost_ack(call);
+
 	if (!test_bit(RXRPC_CALL_PINGING, &call->flags) ||
 	    before(orig_serial, ping_serial))
 		return;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index f47659c7b224..efe06edce189 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -95,7 +95,8 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 /*
  * Send an ACK call packet.
  */
-int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping)
+int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
+			  rxrpc_serial_t *_serial)
 {
 	struct rxrpc_connection *conn = NULL;
 	struct rxrpc_ack_buffer *pkt;
@@ -165,6 +166,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping)
 			   ntohl(pkt->ack.firstPacket),
 			   ntohl(pkt->ack.serial),
 			   pkt->ack.reason, pkt->ack.nAcks);
+	if (_serial)
+		*_serial = serial;
 
 	if (ping) {
 		call->ping_serial = serial;
@@ -323,7 +326,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	 * ACKs if a DATA packet appears to have been lost.
 	 */
 	if (!(sp->hdr.flags & RXRPC_LAST_PACKET) &&
-	    (retrans ||
+	    (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
+	     retrans ||
 	     call->cong_mode == RXRPC_CALL_SLOW_START ||
 	     (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
 	     ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
@@ -370,6 +374,18 @@ done:
 		if (whdr.flags & RXRPC_REQUEST_ACK) {
 			call->peer->rtt_last_req = now;
 			trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
+			if (call->peer->rtt_usage > 1) {
+				unsigned long nowj = jiffies, ack_lost_at;
+
+				ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
+				if (ack_lost_at < 1)
+					ack_lost_at = 1;
+
+				ack_lost_at += nowj;
+				WRITE_ONCE(call->ack_lost_at, ack_lost_at);
+				rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
+							rxrpc_timer_set_for_lost_ack);
+			}
 		}
 	}
 	_leave(" = %d [%u]", ret, call->peer->maxdata);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index fad5f42a3abd..cc21e8db25b0 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -148,7 +148,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
 		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false,
 				  rxrpc_propose_ack_terminal_ack);
-		rxrpc_send_ack_packet(call, false);
+		rxrpc_send_ack_packet(call, false, NULL);
 	}
 #endif
 
@@ -222,7 +222,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
 					  true, true,
 					  rxrpc_propose_ack_rotate_rx);
 		if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY)
-			rxrpc_send_ack_packet(call, false);
+			rxrpc_send_ack_packet(call, false, NULL);
 	}
 }
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index c56ee54fdd1f..a1c53ac066a1 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -285,7 +285,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	do {
 		/* Check to see if there's a ping ACK to reply to. */
 		if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
-			rxrpc_send_ack_packet(call, false);
+			rxrpc_send_ack_packet(call, false, NULL);
 
 		if (!skb) {
 			size_t size, chunk, max, space;