rxrpc: Use ktimes for call timeout tracking and set the timer lazily

Track the call timeouts as ktimes rather than jiffies as the latter's
granularity is too high and only set the timer at the end of the event
handling function.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org

1 files changed, 94 insertions, 95 deletions

diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index bc1a5abb7d6f..2a9f74eb7c46 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;
+	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);
 
-	if (time_before(ping_at, call->ping_at)) {
+	trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial);
+	if (ktime_before(ping_at, call->ping_at)) {
 		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);
+		trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_ping);
 	}
 }
 
@@ -40,25 +40,18 @@ 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->peer->srtt_us)
+		delay = (call->peer->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)) {
-		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);
 }
 
 /*
@@ -77,9 +70,8 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 	struct rxrpc_ackpacket *ack = NULL;
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_txbuf *txb;
-	unsigned long resend_at;
 	rxrpc_seq_t transmitted = call->tx_transmitted;
-	ktime_t now, max_age, oldest, ack_ts;
+	ktime_t now, max_age, oldest, ack_ts, delay;
 	bool unacked = false;
 	unsigned int i;
 	LIST_HEAD(retrans_queue);
@@ -87,7 +79,7 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 	_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));
+	max_age = ktime_sub_us(now, call->peer->rto_us);
 	oldest = now;
 
 	if (list_empty(&call->tx_buffer))
@@ -178,10 +170,8 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 
 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));
-	call->resend_at = resend_at;
+	delay = rxrpc_get_rto_backoff(call->peer, !list_empty(&retrans_queue));
+	call->resend_at = ktime_add(oldest, delay);
 
 	if (unacked)
 		rxrpc_congestion_timeout(call);
@@ -191,8 +181,7 @@ no_resend:
 	 * retransmitting data.
 	 */
 	if (list_empty(&retrans_queue)) {
-		rxrpc_reduce_call_timer(call, resend_at, jiffies,
-					rxrpc_timer_set_for_resend);
+		trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_resend_reset);
 		ack_ts = ktime_sub(now, call->acks_latest_ts);
 		if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
 			goto out;
@@ -218,13 +207,11 @@ 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);
-	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);
 }
 
 /*
@@ -333,8 +320,8 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
  */
 bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 {
-	unsigned long now, next, t;
-	bool resend = false, expired = false;
+	ktime_t now, t;
+	bool resend = false;
 	s32 abort_code;
 
 	rxrpc_see_call(call, rxrpc_call_see_input);
@@ -362,66 +349,69 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 		rxrpc_input_call_packet(call, skb);
 
 	/* If we see our async-event poke, check for timeout trippage. */
-	now = jiffies;
-	t = 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 = 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 = call->delay_ack_at;
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
-		call->delay_ack_at = 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_delayed_ack);
 	}
 
-	t = call->ack_lost_at;
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now);
-		call->ack_lost_at = now + MAX_JIFFY_OFFSET;
+	t = ktime_sub(call->ack_lost_at, now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_lost_ack);
+		call->ack_lost_at = KTIME_MAX;
 		set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events);
 	}
 
-	t = call->keepalive_at;
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
-		call->keepalive_at = 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 = call->ping_at;
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now);
-		call->ping_at = now + MAX_JIFFY_OFFSET;
-		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
-			       rxrpc_propose_ack_ping_for_keepalive);
-	}
-
-	t = call->resend_at;
-	if (time_after_eq(now, t)) {
-		trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now);
-		call->resend_at = now + MAX_JIFFY_OFFSET;
+	t = ktime_sub(call->resend_at, now);
+	if (t <= 0) {
+		trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_resend);
+		call->resend_at = KTIME_MAX;
 		resend = true;
 	}
 
 	rxrpc_transmit_some_data(call);
 
+	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);
+	}
+
 	if (skb) {
 		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 
@@ -433,19 +423,6 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 		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);
@@ -474,23 +451,33 @@ 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->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 = max(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:
@@ -505,4 +492,16 @@ out:
 		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;
 }