rxrpc: Keep the call timeouts as ktimes rather than jiffies

Keep that call timeouts as ktimes rather than jiffies so that they can be
expressed as functions of RTT.

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

8 files changed, 82 insertions, 74 deletions

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 67f03946ea4a..0383e5e9a0f3 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -453,17 +453,18 @@ TRACE_EVENT(rxrpc_rtt_rx,
 
 TRACE_EVENT(rxrpc_timer,
 	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_timer_trace why,
-		     unsigned long now),
+		     ktime_t now, unsigned long now_j),
 
-	    TP_ARGS(call, why, now),
+	    TP_ARGS(call, why, now, now_j),
 
 	    TP_STRUCT__entry(
 		    __field(struct rxrpc_call *,		call		)
 		    __field(enum rxrpc_timer_trace,		why		)
-		    __field(unsigned long,			now		)
-		    __field(unsigned long,			expire_at	)
-		    __field(unsigned long,			ack_at		)
-		    __field(unsigned long,			resend_at	)
+		    __field_struct(ktime_t,			now		)
+		    __field_struct(ktime_t,			expire_at	)
+		    __field_struct(ktime_t,			ack_at		)
+		    __field_struct(ktime_t,			resend_at	)
+		    __field(unsigned long,			now_j		)
 		    __field(unsigned long,			timer		)
 			     ),
 
@@ -474,17 +475,17 @@ TRACE_EVENT(rxrpc_timer,
 		    __entry->expire_at	= call->expire_at;
 		    __entry->ack_at	= call->ack_at;
 		    __entry->resend_at	= call->resend_at;
+		    __entry->now_j	= now_j;
 		    __entry->timer	= call->timer.expires;
 			   ),
 
-	    TP_printk("c=%p %s now=%lx x=%ld a=%ld r=%ld t=%ld",
+	    TP_printk("c=%p %s x=%lld a=%lld r=%lld t=%ld",
 		      __entry->call,
 		      rxrpc_timer_traces[__entry->why],
-		      __entry->now,
-		      __entry->expire_at - __entry->now,
-		      __entry->ack_at - __entry->now,
-		      __entry->resend_at - __entry->now,
-		      __entry->timer - __entry->now)
+		      ktime_to_ns(ktime_sub(__entry->expire_at, __entry->now)),
+		      ktime_to_ns(ktime_sub(__entry->ack_at, __entry->now)),
+		      ktime_to_ns(ktime_sub(__entry->resend_at, __entry->now)),
+		      __entry->timer - __entry->now_j)
 	    );
 
 TRACE_EVENT(rxrpc_rx_lose,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 141c1458e719..d38dffd78085 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -464,9 +464,9 @@ struct rxrpc_call {
 	struct rxrpc_connection	*conn;		/* connection carrying call */
 	struct rxrpc_peer	*peer;		/* Peer record for remote address */
 	struct rxrpc_sock __rcu	*socket;	/* socket responsible */
-	unsigned long		ack_at;		/* When deferred ACK needs to happen */
-	unsigned long		resend_at;	/* When next resend needs to happen */
-	unsigned long		expire_at;	/* When the call times out */
+	ktime_t			ack_at;		/* When deferred ACK needs to happen */
+	ktime_t			resend_at;	/* When next resend needs to happen */
+	ktime_t			expire_at;	/* When the call times out */
 	struct timer_list	timer;		/* Combined event timer */
 	struct work_struct	processor;	/* Event processor */
 	rxrpc_notify_rx_t	notify_rx;	/* kernel service Rx notification function */
@@ -805,7 +805,7 @@ int rxrpc_reject_call(struct rxrpc_sock *);
 /*
  * call_event.c
  */
-void rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace);
+void rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t);
 void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool,
 		       enum rxrpc_propose_ack_trace);
 void rxrpc_process_call(struct work_struct *);
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 1f6c7633b964..9ff3bb3ffb41 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -24,28 +24,40 @@
 /*
  * Set the timer
  */
-void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why)
+void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why,
+		     ktime_t now)
 {
-	unsigned long t, now = jiffies;
+	unsigned long t_j, now_j = jiffies;
+	ktime_t t;
 
 	read_lock_bh(&call->state_lock);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		t = call->expire_at;
-		if (time_before_eq(t, now))
+		if (!ktime_after(t, now))
 			goto out;
 
-		if (time_after(call->resend_at, now) &&
-		    time_before(call->resend_at, t))
+		if (ktime_after(call->resend_at, now) &&
+		    ktime_before(call->resend_at, t))
 			t = call->resend_at;
 
-		if (time_after(call->ack_at, now) &&
-		    time_before(call->ack_at, t))
+		if (ktime_after(call->ack_at, now) &&
+		    ktime_before(call->ack_at, t))
 			t = call->ack_at;
 
-		if (call->timer.expires != t || !timer_pending(&call->timer)) {
-			mod_timer(&call->timer, t);
-			trace_rxrpc_timer(call, why, now);
+		t_j = nsecs_to_jiffies(ktime_to_ns(ktime_sub(t, now)));
+		t_j += jiffies;
+
+		/* We have to make sure that the calculated jiffies value falls
+		 * at or after the nsec value, or we may loop ceaselessly
+		 * because the timer times out, but we haven't reached the nsec
+		 * timeout yet.
+		 */
+		t_j++;
+
+		if (call->timer.expires != t_j || !timer_pending(&call->timer)) {
+			mod_timer(&call->timer, t_j);
+			trace_rxrpc_timer(call, why, now, now_j);
 		}
 	}
 
@@ -62,7 +74,8 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 				enum rxrpc_propose_ack_trace why)
 {
 	enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
-	unsigned long now, ack_at, expiry = rxrpc_soft_ack_delay;
+	unsigned int expiry = rxrpc_soft_ack_delay;
+	ktime_t now, ack_at;
 	s8 prior = rxrpc_ack_priority[ack_reason];
 
 	/* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial
@@ -111,7 +124,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		break;
 	}
 
-	now = jiffies;
 	if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) {
 		_debug("already scheduled");
 	} else if (immediate || expiry == 0) {
@@ -120,11 +132,11 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		    background)
 			rxrpc_queue_call(call);
 	} else {
-		ack_at = now + expiry;
-		_debug("deferred ACK %ld < %ld", expiry, call->ack_at - now);
-		if (time_before(ack_at, call->ack_at)) {
+		now = ktime_get_real();
+		ack_at = ktime_add_ms(now, expiry);
+		if (ktime_before(ack_at, call->ack_at)) {
 			call->ack_at = ack_at;
-			rxrpc_set_timer(call, rxrpc_timer_set_for_ack);
+			rxrpc_set_timer(call, rxrpc_timer_set_for_ack, now);
 		}
 	}
 
@@ -157,12 +169,12 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
 /*
  * Perform retransmission of NAK'd and unack'd packets.
  */
-static void rxrpc_resend(struct rxrpc_call *call)
+static void rxrpc_resend(struct rxrpc_call *call, ktime_t now)
 {
 	struct rxrpc_skb_priv *sp;
 	struct sk_buff *skb;
 	rxrpc_seq_t cursor, seq, top;
-	ktime_t now = ktime_get_real(), max_age, oldest, resend_at, ack_ts;
+	ktime_t max_age, oldest, ack_ts;
 	int ix;
 	u8 annotation, anno_type, retrans = 0, unacked = 0;
 
@@ -212,14 +224,7 @@ static void rxrpc_resend(struct rxrpc_call *call)
 				       ktime_to_ns(ktime_sub(skb->tstamp, max_age)));
 	}
 
-	resend_at = ktime_add_ms(oldest, rxrpc_resend_timeout);
-	call->resend_at = jiffies +
-		nsecs_to_jiffies(ktime_to_ns(ktime_sub(resend_at, now))) +
-		1; /* We have to make sure that the calculated jiffies value
-		    * falls at or after the nsec value, or we shall loop
-		    * ceaselessly because the timer times out, but we haven't
-		    * reached the nsec timeout yet.
-		    */
+	call->resend_at = ktime_add_ms(oldest, rxrpc_resend_timeout);
 
 	if (unacked)
 		rxrpc_congestion_timeout(call);
@@ -229,7 +234,7 @@ static void rxrpc_resend(struct rxrpc_call *call)
 	 * retransmitting data.
 	 */
 	if (!retrans) {
-		rxrpc_set_timer(call, rxrpc_timer_set_for_resend);
+		rxrpc_set_timer(call, rxrpc_timer_set_for_resend, now);
 		spin_unlock_bh(&call->lock);
 		ack_ts = ktime_sub(now, call->acks_latest_ts);
 		if (ktime_to_ns(ack_ts) < call->peer->rtt)
@@ -301,7 +306,7 @@ void rxrpc_process_call(struct work_struct *work)
 {
 	struct rxrpc_call *call =
 		container_of(work, struct rxrpc_call, processor);
-	unsigned long now;
+	ktime_t now;
 
 	rxrpc_see_call(call);
 
@@ -320,15 +325,15 @@ recheck_state:
 		goto out_put;
 	}
 
-	now = jiffies;
-	if (time_after_eq(now, call->expire_at)) {
+	now = ktime_get_real();
+	if (ktime_before(call->expire_at, now)) {
 		rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, ETIME);
 		set_bit(RXRPC_CALL_EV_ABORT, &call->events);
 		goto recheck_state;
 	}
 
 	if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) ||
-	    time_after_eq(now, call->ack_at)) {
+	    ktime_before(call->ack_at, now)) {
 		call->ack_at = call->expire_at;
 		if (call->ackr_reason) {
 			rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK);
@@ -337,12 +342,12 @@ recheck_state:
 	}
 
 	if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) ||
-	    time_after_eq(now, call->resend_at)) {
-		rxrpc_resend(call);
+	    ktime_before(call->resend_at, now)) {
+		rxrpc_resend(call, now);
 		goto recheck_state;
 	}
 
-	rxrpc_set_timer(call, rxrpc_timer_set_for_resend);
+	rxrpc_set_timer(call, rxrpc_timer_set_for_resend, now);
 
 	/* other events may have been raised since we started checking */
 	if (call->events && call->state < RXRPC_CALL_COMPLETE) {
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index d4b3293b78fa..456ab752d473 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -19,11 +19,6 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
-/*
- * Maximum lifetime of a call (in jiffies).
- */
-unsigned int rxrpc_max_call_lifetime = 60 * HZ;
-
 const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = {
 	[RXRPC_CALL_UNINITIALISED]		= "Uninit  ",
 	[RXRPC_CALL_CLIENT_AWAIT_CONN]		= "ClWtConn",
@@ -77,7 +72,8 @@ static void rxrpc_call_timer_expired(unsigned long _call)
 	_enter("%d", call->debug_id);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
-		trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies);
+		trace_rxrpc_timer(call, rxrpc_timer_expired,
+				  ktime_get_real(), jiffies);
 		rxrpc_queue_call(call);
 	}
 }
@@ -207,14 +203,14 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct sockaddr_rxrpc *srx,
  */
 static void rxrpc_start_call_timer(struct rxrpc_call *call)
 {
-	unsigned long expire_at;
+	ktime_t now = ktime_get_real(), expire_at;
 
-	expire_at = jiffies + rxrpc_max_call_lifetime;
+	expire_at = ktime_add_ms(now, rxrpc_max_call_lifetime);
 	call->expire_at = expire_at;
 	call->ack_at = expire_at;
 	call->resend_at = expire_at;
-	call->timer.expires = expire_at + 1;
-	rxrpc_set_timer(call, rxrpc_timer_begin);
+	call->timer.expires = jiffies + LONG_MAX / 2;
+	rxrpc_set_timer(call, rxrpc_timer_begin, now);
 }
 
 /*
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 5ba35b4a907b..3ad9f75031e3 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -328,7 +328,8 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
 		call->resend_at = call->expire_at;
 		call->ack_at = call->expire_at;
 		spin_unlock_bh(&call->lock);
-		rxrpc_set_timer(call, rxrpc_timer_init_for_reply);
+		rxrpc_set_timer(call, rxrpc_timer_init_for_reply,
+				ktime_get_real());
 	}
 
 	if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags))
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 47dddacdbb91..9d1c721bc4e8 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -21,28 +21,33 @@
 unsigned int rxrpc_max_backlog __read_mostly = 10;
 
 /*
+ * Maximum lifetime of a call (in mx).
+ */
+unsigned int rxrpc_max_call_lifetime = 60 * 1000;
+
+/*
  * How long to wait before scheduling ACK generation after seeing a
- * packet with RXRPC_REQUEST_ACK set (in jiffies).
+ * packet with RXRPC_REQUEST_ACK set (in ms).
  */
 unsigned int rxrpc_requested_ack_delay = 1;
 
 /*
- * How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
+ * How long to wait before scheduling an ACK with subtype DELAY (in ms).
  *
  * We use this when we've received new data packets.  If those packets aren't
  * all consumed within this time we will send a DELAY ACK if an ACK was not
  * requested to let the sender know it doesn't need to resend.
  */
-unsigned int rxrpc_soft_ack_delay = 1 * HZ;
+unsigned int rxrpc_soft_ack_delay = 1 * 1000;
 
 /*
- * How long to wait before scheduling an ACK with subtype IDLE (in jiffies).
+ * How long to wait before scheduling an ACK with subtype IDLE (in ms).
  *
  * We use this when we've consumed some previously soft-ACK'd packets when
  * further packets aren't immediately received to decide when to send an IDLE
  * ACK let the other end know that it can free up its Tx buffer space.
  */
-unsigned int rxrpc_idle_ack_delay = 0.5 * HZ;
+unsigned int rxrpc_idle_ack_delay = 0.5 * 1000;
 
 /*
  * Receive window size in packets.  This indicates the maximum number of
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index d8dfdce874d8..3322543d460a 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -149,13 +149,13 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		_debug("need instant resend %d", ret);
 		rxrpc_instant_resend(call, ix);
 	} else {
-		unsigned long resend_at;
+		ktime_t now = ktime_get_real(), resend_at;
 
-		resend_at = jiffies + msecs_to_jiffies(rxrpc_resend_timeout);
+		resend_at = ktime_add_ms(now, rxrpc_resend_timeout);
 
-		if (time_before(resend_at, call->resend_at)) {
+		if (ktime_before(resend_at, call->resend_at)) {
 			call->resend_at = resend_at;
-			rxrpc_set_timer(call, rxrpc_timer_set_for_send);
+			rxrpc_set_timer(call, rxrpc_timer_set_for_send, now);
 		}
 	}
 
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 13d1df03ebac..34c706d2f79c 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -35,7 +35,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.data		= &rxrpc_requested_ack_delay,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_ms_jiffies,
+		.proc_handler	= proc_dointvec,
 		.extra1		= (void *)&zero,
 	},
 	{
@@ -43,7 +43,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.data		= &rxrpc_soft_ack_delay,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_ms_jiffies,
+		.proc_handler	= proc_dointvec,
 		.extra1		= (void *)&one,
 	},
 	{
@@ -51,7 +51,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.data		= &rxrpc_idle_ack_delay,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_ms_jiffies,
+		.proc_handler	= proc_dointvec,
 		.extra1		= (void *)&one,
 	},
 	{
@@ -85,7 +85,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.data		= &rxrpc_max_call_lifetime,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
+		.proc_handler	= proc_dointvec,
 		.extra1		= (void *)&one,
 	},