1 files changed, 262 insertions, 310 deletions

diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 0f78544d043b..8e477f7f8850 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -23,14 +23,14 @@
 void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial,
 			enum rxrpc_propose_ack_trace why)
 {
-	unsigned long now = jiffies;
-	unsigned long ping_at = now + rxrpc_idle_ack_delay;
-
-	if (time_before(ping_at, call->ping_at)) {
-		WRITE_ONCE(call->ping_at, ping_at);
-		rxrpc_reduce_call_timer(call, ping_at, now,
-					rxrpc_timer_set_for_ping);
-		trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial);
+	ktime_t delay = ms_to_ktime(READ_ONCE(rxrpc_idle_ack_delay));
+	ktime_t now = ktime_get_real();
+	ktime_t ping_at = ktime_add(now, delay);
+
+	trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial);
+	if (ktime_before(ping_at, call->ping_at)) {
+		call->ping_at = ping_at;
+		trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_ping);
 	}
 }
 
@@ -40,215 +40,119 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial,
 void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial,
 			     enum rxrpc_propose_ack_trace why)
 {
-	unsigned long expiry = rxrpc_soft_ack_delay;
-	unsigned long now = jiffies, ack_at;
+	ktime_t now = ktime_get_real(), delay;
 
-	if (rxrpc_soft_ack_delay < expiry)
-		expiry = rxrpc_soft_ack_delay;
-	if (call->peer->srtt_us != 0)
-		ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3);
+	trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial);
+
+	if (call->srtt_us)
+		delay = (call->srtt_us >> 3) * NSEC_PER_USEC;
 	else
-		ack_at = expiry;
-
-	ack_at += READ_ONCE(call->tx_backoff);
-	ack_at += now;
-	if (time_before(ack_at, call->delay_ack_at)) {
-		WRITE_ONCE(call->delay_ack_at, ack_at);
-		rxrpc_reduce_call_timer(call, ack_at, now,
-					rxrpc_timer_set_for_ack);
-	}
+		delay = ms_to_ktime(READ_ONCE(rxrpc_soft_ack_delay));
+	ktime_add_ms(delay, call->tx_backoff);
 
-	trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial);
+	call->delay_ack_at = ktime_add(now, delay);
+	trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_delayed_ack);
 }
 
 /*
- * Queue an ACK for immediate transmission.
+ * Retransmit one or more packets.
  */
-void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason,
-		    rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why)
+static bool rxrpc_retransmit_data(struct rxrpc_call *call,
+				  struct rxrpc_send_data_req *req)
 {
-	struct rxrpc_txbuf *txb;
+	struct rxrpc_txqueue *tq = req->tq;
+	unsigned int ix = req->seq & RXRPC_TXQ_MASK;
+	struct rxrpc_txbuf *txb = tq->bufs[ix];
 
-	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
-		return;
+	_enter("%x,%x,%x,%x", tq->qbase, req->seq, ix, txb->debug_id);
 
-	rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]);
+	req->retrans = true;
+	trace_rxrpc_retransmit(call, req, txb);
 
-	txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK,
-				rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS);
-	if (!txb) {
-		kleave(" = -ENOMEM");
-		return;
-	}
-
-	txb->ack_why		= why;
-	txb->wire.seq		= 0;
-	txb->wire.type		= RXRPC_PACKET_TYPE_ACK;
-	txb->wire.flags		|= RXRPC_SLOW_START_OK;
-	txb->ack.bufferSpace	= 0;
-	txb->ack.maxSkew	= 0;
-	txb->ack.firstPacket	= 0;
-	txb->ack.previousPacket	= 0;
-	txb->ack.serial		= htonl(serial);
-	txb->ack.reason		= ack_reason;
-	txb->ack.nAcks		= 0;
-
-	trace_rxrpc_send_ack(call, why, ack_reason, serial);
-	rxrpc_send_ack_packet(call, txb);
-	rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx);
-}
+	txb->flags |= RXRPC_TXBUF_RESENT;
+	rxrpc_send_data_packet(call, req);
+	rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans);
 
-/*
- * Handle congestion being detected by the retransmit timeout.
- */
-static void rxrpc_congestion_timeout(struct rxrpc_call *call)
-{
-	set_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags);
+	req->tq		= NULL;
+	req->n		= 0;
+	req->did_send	= true;
+	req->now	= ktime_get_real();
+	return true;
 }
 
 /*
  * Perform retransmission of NAK'd and unack'd packets.
  */
-void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
+static void rxrpc_resend(struct rxrpc_call *call)
 {
-	struct rxrpc_ackpacket *ack = NULL;
-	struct rxrpc_skb_priv *sp;
-	struct rxrpc_txbuf *txb;
-	unsigned long resend_at;
-	rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted);
-	ktime_t now, max_age, oldest, ack_ts;
-	bool unacked = false;
-	unsigned int i;
-	LIST_HEAD(retrans_queue);
-
-	_enter("{%d,%d}", call->acks_hard_ack, call->tx_top);
-
-	now = ktime_get_real();
-	max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j));
-	oldest = now;
-
-	if (list_empty(&call->tx_buffer))
-		goto no_resend;
-
-	if (list_empty(&call->tx_buffer))
-		goto no_further_resend;
+	struct rxrpc_send_data_req req = {
+		.now	= ktime_get_real(),
+		.trace	= rxrpc_txdata_retransmit,
+	};
+	struct rxrpc_txqueue *tq;
 
-	trace_rxrpc_resend(call, ack_skb);
-	txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link);
+	_enter("{%d,%d}", call->tx_bottom, call->tx_top);
 
-	/* Scan the soft ACK table without dropping the lock and resend any
-	 * explicitly NAK'd packets.
-	 */
-	if (ack_skb) {
-		sp = rxrpc_skb(ack_skb);
-		ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header);
+	trace_rxrpc_resend(call, call->acks_highest_serial);
 
-		for (i = 0; i < sp->nr_acks; i++) {
-			rxrpc_seq_t seq;
+	/* Scan the transmission queue, looking for lost packets. */
+	for (tq = call->tx_queue; tq; tq = tq->next) {
+		unsigned long lost = tq->segment_lost;
 
-			if (ack->acks[i] & 1)
-				continue;
-			seq = sp->first_ack + i;
-			if (after(txb->seq, transmitted))
-				break;
-			if (after(txb->seq, seq))
-				continue; /* A new hard ACK probably came in */
-			list_for_each_entry_from(txb, &call->tx_buffer, call_link) {
-				if (txb->seq == seq)
-					goto found_txb;
-			}
-			goto no_further_resend;
-
-		found_txb:
-			if (after(ntohl(txb->wire.serial), call->acks_highest_serial))
-				continue; /* Ack point not yet reached */
+		if (after(tq->qbase, call->tx_transmitted))
+			break;
 
-			rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked);
+		_debug("retr %16lx %u c=%08x [%x]",
+		       tq->segment_acked, tq->nr_reported_acks, call->debug_id, tq->qbase);
+		_debug("lost %16lx", lost);
 
-			if (list_empty(&txb->tx_link)) {
-				list_add_tail(&txb->tx_link, &retrans_queue);
-				set_bit(RXRPC_TXBUF_RESENT, &txb->flags);
-			}
+		trace_rxrpc_resend_lost(call, tq, lost);
+		while (lost) {
+			unsigned int ix = __ffs(lost);
+			struct rxrpc_txbuf *txb = tq->bufs[ix];
 
-			trace_rxrpc_retransmit(call, txb->seq,
-					       ktime_to_ns(ktime_sub(txb->last_sent,
-								     max_age)));
+			__clear_bit(ix, &lost);
+			rxrpc_see_txbuf(txb, rxrpc_txbuf_see_lost);
 
-			if (list_is_last(&txb->call_link, &call->tx_buffer))
-				goto no_further_resend;
-			txb = list_next_entry(txb, call_link);
+			req.tq  = tq;
+			req.seq = tq->qbase + ix;
+			req.n   = 1;
+			rxrpc_retransmit_data(call, &req);
 		}
 	}
 
-	/* Fast-forward through the Tx queue to the point the peer says it has
-	 * seen.  Anything between the soft-ACK table and that point will get
-	 * ACK'd or NACK'd in due course, so don't worry about it here; here we
-	 * need to consider retransmitting anything beyond that point.
-	 *
-	 * Note that ACK for a packet can beat the update of tx_transmitted.
-	 */
-	if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted)))
-		goto no_further_resend;
-
-	list_for_each_entry_from(txb, &call->tx_buffer, call_link) {
-		if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq)))
-			continue;
-		if (after(txb->seq, READ_ONCE(call->tx_transmitted)))
-			break; /* Not transmitted yet */
-
-		if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE &&
-		    before(ntohl(txb->wire.serial), ntohl(ack->serial)))
-			goto do_resend; /* Wasn't accounted for by a more recent ping. */
-
-		if (ktime_after(txb->last_sent, max_age)) {
-			if (ktime_before(txb->last_sent, oldest))
-				oldest = txb->last_sent;
-			continue;
-		}
-
-	do_resend:
-		unacked = true;
-		if (list_empty(&txb->tx_link)) {
-			list_add_tail(&txb->tx_link, &retrans_queue);
-			set_bit(RXRPC_TXBUF_RESENT, &txb->flags);
-			rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans);
-		}
-	}
+	rxrpc_get_rto_backoff(call, req.did_send);
+	_leave("");
+}
 
-no_further_resend:
-no_resend:
-	resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
-	resend_at += jiffies + rxrpc_get_rto_backoff(call->peer,
-						     !list_empty(&retrans_queue));
-	WRITE_ONCE(call->resend_at, resend_at);
-
-	if (unacked)
-		rxrpc_congestion_timeout(call);
-
-	/* If there was nothing that needed retransmission then it's likely
-	 * that an ACK got lost somewhere.  Send a ping to find out instead of
-	 * retransmitting data.
-	 */
-	if (list_empty(&retrans_queue)) {
-		rxrpc_reduce_call_timer(call, resend_at, jiffies,
-					rxrpc_timer_set_for_resend);
-		ack_ts = ktime_sub(now, call->acks_latest_ts);
-		if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
-			goto out;
-		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
-			       rxrpc_propose_ack_ping_for_lost_ack);
-		goto out;
+/*
+ * Resend the highest-seq DATA packet so far transmitted for RACK-TLP [RFC8985 7.3].
+ */
+void rxrpc_resend_tlp(struct rxrpc_call *call)
+{
+	struct rxrpc_send_data_req req = {
+		.now		= ktime_get_real(),
+		.seq		= call->tx_transmitted,
+		.n		= 1,
+		.tlp_probe	= true,
+		.trace		= rxrpc_txdata_tlp_retransmit,
+	};
+
+	/* There's a chance it'll be on the tail segment of the queue. */
+	req.tq = READ_ONCE(call->tx_qtail);
+	if (req.tq &&
+	    before(call->tx_transmitted, req.tq->qbase + RXRPC_NR_TXQUEUE)) {
+		rxrpc_retransmit_data(call, &req);
+		return;
 	}
 
-	/* Retransmit the queue */
-	while ((txb = list_first_entry_or_null(&retrans_queue,
-					       struct rxrpc_txbuf, tx_link))) {
-		list_del_init(&txb->tx_link);
-		rxrpc_transmit_one(call, txb);
+	for (req.tq = call->tx_queue; req.tq; req.tq = req.tq->next) {
+		if (after_eq(call->tx_transmitted, req.tq->qbase) &&
+		    before(call->tx_transmitted, req.tq->qbase + RXRPC_NR_TXQUEUE)) {
+			rxrpc_retransmit_data(call, &req);
+			return;
+		}
 	}
-
-out:
-	_leave("");
 }
 
 /*
@@ -257,13 +161,11 @@ out:
  */
 static void rxrpc_begin_service_reply(struct rxrpc_call *call)
 {
-	unsigned long now = jiffies;
-
 	rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY);
-	WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
 	if (call->ackr_reason == RXRPC_ACK_DELAY)
 		call->ackr_reason = 0;
-	trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
+	call->delay_ack_at = KTIME_MAX;
+	trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack);
 }
 
 /*
@@ -286,68 +188,93 @@ static void rxrpc_close_tx_phase(struct rxrpc_call *call)
 	}
 }
 
-static bool rxrpc_tx_window_has_space(struct rxrpc_call *call)
-{
-	unsigned int winsize = min_t(unsigned int, call->tx_winsize,
-				     call->cong_cwnd + call->cong_extra);
-	rxrpc_seq_t window = call->acks_hard_ack, wtop = window + winsize;
-	rxrpc_seq_t tx_top = call->tx_top;
-	int space;
-
-	space = wtop - tx_top;
-	return space > 0;
-}
-
 /*
- * Decant some if the sendmsg prepared queue into the transmission buffer.
+ * Transmit some as-yet untransmitted data, to a maximum of the supplied limit.
  */
-static void rxrpc_decant_prepared_tx(struct rxrpc_call *call)
+static void rxrpc_transmit_fresh_data(struct rxrpc_call *call, unsigned int limit,
+				      enum rxrpc_txdata_trace trace)
 {
-	struct rxrpc_txbuf *txb;
+	int space = rxrpc_tx_window_space(call);
 
 	if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
-		if (list_empty(&call->tx_sendmsg))
+		if (call->send_top == call->tx_top)
 			return;
 		rxrpc_expose_client_call(call);
 	}
 
-	while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
-					       struct rxrpc_txbuf, call_link))) {
-		spin_lock(&call->tx_lock);
-		list_del(&txb->call_link);
-		spin_unlock(&call->tx_lock);
+	while (space > 0) {
+		struct rxrpc_send_data_req req = {
+			.now	= ktime_get_real(),
+			.seq	= call->tx_transmitted + 1,
+			.n	= 0,
+			.trace	= trace,
+		};
+		struct rxrpc_txqueue *tq;
+		struct rxrpc_txbuf *txb;
+		rxrpc_seq_t send_top, seq;
+		int limit = min(space, max(call->peer->pmtud_jumbo, 1));
+
+		/* Order send_top before the contents of the new txbufs and
+		 * txqueue pointers
+		 */
+		send_top = smp_load_acquire(&call->send_top);
+		if (call->tx_top == send_top)
+			break;
 
-		call->tx_top = txb->seq;
-		list_add_tail(&txb->call_link, &call->tx_buffer);
+		trace_rxrpc_transmit(call, send_top, space);
 
-		if (txb->wire.flags & RXRPC_LAST_PACKET)
-			rxrpc_close_tx_phase(call);
+		tq = call->tx_qtail;
+		seq = call->tx_top;
+		trace_rxrpc_tq(call, tq, seq, rxrpc_tq_decant);
 
-		rxrpc_transmit_one(call, txb);
+		do {
+			int ix;
 
-		if (!rxrpc_tx_window_has_space(call))
-			break;
+			seq++;
+			ix = seq & RXRPC_TXQ_MASK;
+			if (!ix) {
+				tq = tq->next;
+				trace_rxrpc_tq(call, tq, seq, rxrpc_tq_decant_advance);
+			}
+			if (!req.tq)
+				req.tq = tq;
+			txb = tq->bufs[ix];
+			req.n++;
+			if (!txb->jumboable)
+				break;
+		} while (req.n < limit && before(seq, send_top));
+
+		if (txb->flags & RXRPC_LAST_PACKET) {
+			rxrpc_close_tx_phase(call);
+			tq = NULL;
+		}
+		call->tx_qtail = tq;
+		call->tx_top = seq;
+
+		space -= req.n;
+		rxrpc_send_data_packet(call, &req);
 	}
 }
 
-static void rxrpc_transmit_some_data(struct rxrpc_call *call)
+void rxrpc_transmit_some_data(struct rxrpc_call *call, unsigned int limit,
+			      enum rxrpc_txdata_trace trace)
 {
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
-		if (list_empty(&call->tx_sendmsg))
+		if (call->tx_bottom == READ_ONCE(call->send_top))
 			return;
 		rxrpc_begin_service_reply(call);
 		fallthrough;
 
 	case RXRPC_CALL_SERVER_SEND_REPLY:
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
-		if (!rxrpc_tx_window_has_space(call))
+		if (!rxrpc_tx_window_space(call))
 			return;
-		if (list_empty(&call->tx_sendmsg)) {
+		if (call->tx_bottom == READ_ONCE(call->send_top)) {
 			rxrpc_inc_stat(call->rxnet, stat_tx_data_underflow);
 			return;
 		}
-		rxrpc_decant_prepared_tx(call);
+		rxrpc_transmit_fresh_data(call, limit, trace);
 		break;
 	default:
 		return;
@@ -360,8 +287,8 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call)
  */
 static void rxrpc_send_initial_ping(struct rxrpc_call *call)
 {
-	if (call->peer->rtt_count < 3 ||
-	    ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
+	if (call->rtt_count < 3 ||
+	    ktime_before(ktime_add_ms(call->rtt_last_req, 1000),
 			 ktime_get_real()))
 		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
 			       rxrpc_propose_ack_ping_for_params);
@@ -370,10 +297,11 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
 /*
  * Handle retransmission and deferred ACK/abort generation.
  */
-bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
+bool rxrpc_input_call_event(struct rxrpc_call *call)
 {
-	unsigned long now, next, t;
-	bool resend = false, expired = false;
+	struct sk_buff *skb;
+	ktime_t now, t;
+	bool did_receive = false, saw_ack = false;
 	s32 abort_code;
 
 	rxrpc_see_call(call, rxrpc_call_see_input);
@@ -383,9 +311,6 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 	       call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)],
 	       call->events);
 
-	if (__rxrpc_call_is_complete(call))
-		goto out;
-
 	/* Handle abort request locklessly, vs rxrpc_propose_abort(). */
 	abort_code = smp_load_acquire(&call->send_abort);
 	if (abort_code) {
@@ -394,113 +319,116 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 		goto out;
 	}
 
-	if (skb && skb->mark == RXRPC_SKB_MARK_ERROR)
-		goto out;
+	do {
+		skb = __skb_dequeue(&call->rx_queue);
+		if (skb) {
+			struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+			if (__rxrpc_call_is_complete(call) ||
+			    skb->mark == RXRPC_SKB_MARK_ERROR) {
+				rxrpc_free_skb(skb, rxrpc_skb_put_call_rx);
+				goto out;
+			}
+
+			saw_ack |= sp->hdr.type == RXRPC_PACKET_TYPE_ACK;
+
+			rxrpc_input_call_packet(call, skb);
+			rxrpc_free_skb(skb, rxrpc_skb_put_call_rx);
+			did_receive = true;
+		}
+
+		t = ktime_sub(call->rack_timo_at, ktime_get_real());
+		if (t <= 0) {
+			trace_rxrpc_timer_exp(call, t,
+					      rxrpc_timer_trace_rack_off + call->rack_timer_mode);
+			call->rack_timo_at = KTIME_MAX;
+			rxrpc_rack_timer_expired(call, t);
+		}
+
+	} while (!skb_queue_empty(&call->rx_queue));
 
 	/* If we see our async-event poke, check for timeout trippage. */
-	now = jiffies;
-	t = READ_ONCE(call->expect_rx_by);
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now);
-		expired = true;
+	now = ktime_get_real();
+	t = ktime_sub(call->expect_rx_by, now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_expect_rx);
+		goto expired;
 	}
 
-	t = READ_ONCE(call->expect_req_by);
-	if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST &&
-	    time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now);
-		expired = true;
+	t = ktime_sub(call->expect_req_by, now);
+	if (t <= 0) {
+		call->expect_req_by = KTIME_MAX;
+		if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST) {
+			trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_idle);
+			goto expired;
+		}
 	}
 
-	t = READ_ONCE(call->expect_term_by);
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now);
-		expired = true;
+	t = ktime_sub(READ_ONCE(call->expect_term_by), now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_hard);
+		goto expired;
 	}
 
-	t = READ_ONCE(call->delay_ack_at);
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
-		cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET);
+	t = ktime_sub(call->delay_ack_at, now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_delayed_ack);
+		call->delay_ack_at = KTIME_MAX;
 		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0,
-			       rxrpc_propose_ack_ping_for_lost_ack);
-	}
-
-	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);
+			       rxrpc_propose_ack_delayed_ack);
 	}
 
-	t = READ_ONCE(call->keepalive_at);
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
-		cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
+	t = ktime_sub(call->ping_at, now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_ping);
+		call->ping_at = KTIME_MAX;
 		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
 			       rxrpc_propose_ack_ping_for_keepalive);
 	}
 
-	t = READ_ONCE(call->ping_at);
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now);
-		cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET);
+	now = ktime_get_real();
+	t = ktime_sub(call->keepalive_at, now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_keepalive);
+		call->keepalive_at = KTIME_MAX;
 		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
 			       rxrpc_propose_ack_ping_for_keepalive);
 	}
 
-	t = READ_ONCE(call->resend_at);
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now);
-		cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET);
-		resend = true;
-	}
-
-	if (skb)
-		rxrpc_input_call_packet(call, skb);
+	if (test_and_clear_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events))
+		rxrpc_send_initial_ping(call);
 
-	rxrpc_transmit_some_data(call);
+	rxrpc_transmit_some_data(call, UINT_MAX, rxrpc_txdata_new_data);
 
-	if (skb) {
-		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	if (saw_ack)
+		rxrpc_congestion_degrade(call);
 
-		if (sp->hdr.type == RXRPC_PACKET_TYPE_ACK)
-			rxrpc_congestion_degrade(call);
+	if (did_receive &&
+	    (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_SEND_REQUEST ||
+	     __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SEND_REPLY)) {
+		t = ktime_sub(call->rack_timo_at, ktime_get_real());
+		trace_rxrpc_rack(call, t);
 	}
 
-	if (test_and_clear_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events))
-		rxrpc_send_initial_ping(call);
-
 	/* Process events */
-	if (expired) {
-		if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
-		    (int)call->conn->hi_serial - (int)call->rx_serial > 0) {
-			trace_rxrpc_call_reset(call);
-			rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET,
-					 rxrpc_abort_call_reset);
-		} else {
-			rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME,
-					 rxrpc_abort_call_timeout);
-		}
-		goto out;
-	}
-
 	if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events))
 		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
 			       rxrpc_propose_ack_ping_for_lost_ack);
 
-	if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY)
-		rxrpc_resend(call, NULL);
+	if (call->tx_nr_lost > 0 &&
+	    __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY &&
+	    !test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags))
+		rxrpc_resend(call);
 
 	if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags))
 		rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0,
 			       rxrpc_propose_ack_rx_idle);
 
 	if (call->ackr_nr_unacked > 2) {
-		if (call->peer->rtt_count < 3)
+		if (call->rtt_count < 3)
 			rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
 				       rxrpc_propose_ack_ping_for_rtt);
-		else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
+		else if (ktime_before(ktime_add_ms(call->rtt_last_req, 1000),
 				      ktime_get_real()))
 			rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
 				       rxrpc_propose_ack_ping_for_old_rtt);
@@ -511,23 +439,32 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 
 	/* Make sure the timer is restarted */
 	if (!__rxrpc_call_is_complete(call)) {
-		next = call->expect_rx_by;
+		ktime_t next = READ_ONCE(call->expect_term_by), delay;
 
-#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; }
+#define set(T) { ktime_t _t = (T); if (ktime_before(_t, next)) next = _t; }
 
 		set(call->expect_req_by);
-		set(call->expect_term_by);
+		set(call->expect_rx_by);
 		set(call->delay_ack_at);
-		set(call->ack_lost_at);
-		set(call->resend_at);
+		set(call->rack_timo_at);
 		set(call->keepalive_at);
 		set(call->ping_at);
 
-		now = jiffies;
-		if (time_after_eq(now, next))
+		now = ktime_get_real();
+		delay = ktime_sub(next, now);
+		if (delay <= 0) {
 			rxrpc_poke_call(call, rxrpc_call_poke_timer_now);
-
-		rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
+		} else {
+			unsigned long nowj = jiffies, delayj, nextj;
+
+			delayj = umax(nsecs_to_jiffies(delay), 1);
+			nextj = nowj + delayj;
+			if (time_before(nextj, call->timer.expires) ||
+			    !timer_pending(&call->timer)) {
+				trace_rxrpc_timer_restart(call, delay, delayj);
+				timer_reduce(&call->timer, nextj);
+			}
+		}
 	}
 
 out:
@@ -537,9 +474,24 @@ out:
 			rxrpc_disconnect_call(call);
 		if (call->security)
 			call->security->free_call_crypto(call);
+	} else {
+		if (did_receive &&
+		    call->peer->ackr_adv_pmtud &&
+		    call->peer->pmtud_pending)
+			rxrpc_send_probe_for_pmtud(call);
 	}
-	if (call->acks_hard_ack != call->tx_bottom)
-		rxrpc_shrink_call_tx_buffer(call);
 	_leave("");
 	return true;
+
+expired:
+	if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
+	    (int)call->conn->hi_serial - (int)call->rx_serial > 0) {
+		trace_rxrpc_call_reset(call);
+		rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET,
+				 rxrpc_abort_call_reset);
+	} else {
+		rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME,
+				 rxrpc_abort_call_timeout);
+	}
+	goto out;
 }