rxrpc: Clean up ACK handling

Clean up the rxrpc_propose_ACK() function.  If deferred PING ACK proposal
is split out, it's only really needed for deferred DELAY ACKs.  All other
ACKs, bar terminal IDLE ACK are sent immediately.  The deferred IDLE ACK
submission can be handled by conversion of a DELAY ACK into an IDLE ACK if
there's nothing to be SACK'd.

Also, because there's a delay between an ACK being generated and being
transmitted, it's possible that other ACKs of the same type will be
generated during that interval.  Apart from the ACK time and the serial
number responded to, most of the ACK body, including window and SACK
parameters, are not filled out till the point of transmission - so we can
avoid generating a new ACK if there's one pending that will cover the SACK
data we need to convey.

Therefore, don't propose a new DELAY or IDLE ACK for a call if there's one
already pending.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org

10 files changed, 50 insertions, 122 deletions

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 802a8f372af269..5a81545a58d5ca 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -516,6 +516,8 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 	RXRPC_CALL_KERNEL,		/* The call was made by the kernel */
 	RXRPC_CALL_UPGRADE,		/* Service upgrade was requested for the call */
+	RXRPC_CALL_DELAY_ACK_PENDING,	/* DELAY ACK generation is pending */
+	RXRPC_CALL_IDLE_ACK_PENDING,	/* IDLE ACK generation is pending */
 };
 
 /*
@@ -582,7 +584,7 @@ struct rxrpc_call {
 	struct rxrpc_net	*rxnet;		/* Network namespace to which call belongs */
 	const struct rxrpc_security *security;	/* applied security module */
 	struct mutex		user_mutex;	/* User access mutex */
-	unsigned long		ack_at;		/* When deferred ACK needs to happen */
+	unsigned long		delay_ack_at;	/* When DELAY 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 */
@@ -834,7 +836,8 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long);
 void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial,
 			enum rxrpc_propose_ack_trace why);
 void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace);
-void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, enum rxrpc_propose_ack_trace);
+void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t,
+			     enum rxrpc_propose_ack_trace);
 void rxrpc_process_call(struct work_struct *);
 
 void rxrpc_reduce_call_timer(struct rxrpc_call *call,
@@ -1016,15 +1019,12 @@ static inline bool __rxrpc_use_local(struct rxrpc_local *local)
  * misc.c
  */
 extern unsigned int rxrpc_max_backlog __read_mostly;
-extern unsigned long rxrpc_requested_ack_delay;
 extern unsigned long rxrpc_soft_ack_delay;
 extern unsigned long rxrpc_idle_ack_delay;
 extern unsigned int rxrpc_rx_window_size;
 extern unsigned int rxrpc_rx_mtu;
 extern unsigned int rxrpc_rx_jumbo_max;
 
-extern const s8 rxrpc_ack_priority[];
-
 /*
  * net_ns.c
  */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 67b54ad914a1eb..36f60ac1d95d6b 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -29,70 +29,29 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial,
 	spin_lock_bh(&call->lock);
 
 	if (time_before(ping_at, call->ping_at)) {
-		rxrpc_inc_stat(call->rxnet, stat_tx_acks[RXRPC_ACK_PING]);
 		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,
-					rxrpc_propose_ack_use);
+		trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial);
 	}
 
 	spin_unlock_bh(&call->lock);
 }
 
 /*
- * propose an ACK be sent
+ * Propose a DELAY ACK be sent in the future.
  */
-static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
-				u32 serial, enum rxrpc_propose_ack_trace why)
+static void __rxrpc_propose_delay_ACK(struct rxrpc_call *call,
+				      rxrpc_serial_t serial,
+				      enum rxrpc_propose_ack_trace why)
 {
-	enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
 	unsigned long expiry = rxrpc_soft_ack_delay;
 	unsigned long now = jiffies, ack_at;
-	s8 prior = rxrpc_ack_priority[ack_reason];
-
-	rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]);
-
-	/* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial
-	 * numbers, but we don't alter the timeout.
-	 */
-	_debug("prior %u %u vs %u %u",
-	       ack_reason, prior,
-	       call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]);
-	if (ack_reason == call->ackr_reason) {
-		if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) {
-			outcome = rxrpc_propose_ack_update;
-			call->ackr_serial = serial;
-		}
-	} else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
-		call->ackr_reason = ack_reason;
-		call->ackr_serial = serial;
-	} else {
-		outcome = rxrpc_propose_ack_subsume;
-	}
-
-	switch (ack_reason) {
-	case RXRPC_ACK_REQUESTED:
-		if (rxrpc_requested_ack_delay < expiry)
-			expiry = rxrpc_requested_ack_delay;
-		break;
-
-	case RXRPC_ACK_DELAY:
-		if (rxrpc_soft_ack_delay < expiry)
-			expiry = rxrpc_soft_ack_delay;
-		break;
-
-	case RXRPC_ACK_IDLE:
-		if (rxrpc_idle_ack_delay < expiry)
-			expiry = rxrpc_idle_ack_delay;
-		break;
-
-	default:
-		WARN_ON(1);
-		return;
-	}
 
+	call->ackr_serial = serial;
 
+	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);
 	else
@@ -100,23 +59,23 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 
 	ack_at += READ_ONCE(call->tx_backoff);
 	ack_at += now;
-	if (time_before(ack_at, call->ack_at)) {
-		WRITE_ONCE(call->ack_at, ack_at);
+	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);
 	}
 
-	trace_rxrpc_propose_ack(call, why, ack_reason, serial, outcome);
+	trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial);
 }
 
 /*
- * propose an ACK be sent, locking the call structure
+ * Propose a DELAY ACK be sent, locking the call structure
  */
-void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, u32 serial,
-		       enum rxrpc_propose_ack_trace why)
+void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t  serial,
+			     enum rxrpc_propose_ack_trace why)
 {
 	spin_lock_bh(&call->lock);
-	__rxrpc_propose_ACK(call, ack_reason, serial, why);
+	__rxrpc_propose_delay_ACK(call, serial, why);
 	spin_unlock_bh(&call->lock);
 }
 
@@ -131,6 +90,11 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason,
 
 	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return;
+	if (ack_reason == RXRPC_ACK_DELAY &&
+	    test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) {
+		trace_rxrpc_drop_ack(call, why, ack_reason, serial, false);
+		return;
+	}
 
 	rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]);
 
@@ -319,7 +283,6 @@ void rxrpc_process_call(struct work_struct *work)
 	unsigned long now, next, t;
 	unsigned int iterations = 0;
 	rxrpc_serial_t ackr_serial;
-	u8 ackr_reason;
 
 	rxrpc_see_call(call);
 
@@ -364,19 +327,13 @@ recheck_state:
 		set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
 	}
 
-	t = READ_ONCE(call->ack_at);
+	t = READ_ONCE(call->delay_ack_at);
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
-		cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET);
-		spin_lock_bh(&call->lock);
-		ackr_reason = call->ackr_reason;
-		ackr_serial = call->ackr_serial;
-		call->ackr_reason = 0;
-		call->ackr_serial = 0;
-		spin_unlock_bh(&call->lock);
-		if (ackr_reason)
-			rxrpc_send_ACK(call, ackr_reason, ackr_serial,
-				       rxrpc_propose_ack_ping_for_lost_ack);
+		cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET);
+		ackr_serial = xchg(&call->ackr_serial, 0);
+		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial,
+			       rxrpc_propose_ack_ping_for_lost_ack);
 	}
 
 	t = READ_ONCE(call->ack_lost_at);
@@ -441,7 +398,7 @@ recheck_state:
 
 	set(call->expect_req_by);
 	set(call->expect_term_by);
-	set(call->ack_at);
+	set(call->delay_ack_at);
 	set(call->ack_lost_at);
 	set(call->resend_at);
 	set(call->keepalive_at);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8290d94e92332f..8f9e8889719739 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -222,7 +222,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call)
 	unsigned long now = jiffies;
 	unsigned long j = now + MAX_JIFFY_OFFSET;
 
-	call->ack_at = j;
+	call->delay_ack_at = j;
 	call->ack_lost_at = j;
 	call->resend_at = j;
 	call->ping_at = j;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index e23f66ef8c06ba..4df1bdc4de6cea 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -299,7 +299,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
 		now = jiffies;
 		timo = now + MAX_JIFFY_OFFSET;
 		WRITE_ONCE(call->resend_at, timo);
-		WRITE_ONCE(call->ack_at, timo);
+		WRITE_ONCE(call->delay_ack_at, timo);
 		trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
 	}
 
@@ -542,7 +542,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 			/* Send an immediate ACK if we fill in a hole */
 			if (!acked) {
 				rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial,
-					       rxrpc_propose_ack_input_data);
+					       rxrpc_propose_ack_input_data_hole);
 				acked = true;
 			}
 		}
@@ -584,8 +584,8 @@ unlock:
 		rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial,
 			       rxrpc_propose_ack_input_data);
 	else
-		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, ack_serial,
-				  rxrpc_propose_ack_input_data);
+		rxrpc_propose_delay_ACK(call, ack_serial,
+					rxrpc_propose_ack_input_data);
 
 	trace_rxrpc_notify_socket(call->debug_id, serial);
 	rxrpc_notify_socket(call);
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index d4144fd86f847c..f5f03f27bd6ca9 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -17,12 +17,6 @@
 unsigned int rxrpc_max_backlog __read_mostly = 10;
 
 /*
- * How long to wait before scheduling ACK generation after seeing a
- * packet with RXRPC_REQUEST_ACK set (in jiffies).
- */
-unsigned long rxrpc_requested_ack_delay = 1;
-
-/*
  * How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
  *
  * We use this when we've received new data packets.  If those packets aren't
@@ -62,15 +56,3 @@ unsigned int rxrpc_rx_mtu = 5692;
  * sender that we're willing to handle.
  */
 unsigned int rxrpc_rx_jumbo_max = 4;
-
-const s8 rxrpc_ack_priority[] = {
-	[0]				= 0,
-	[RXRPC_ACK_DELAY]		= 1,
-	[RXRPC_ACK_REQUESTED]		= 2,
-	[RXRPC_ACK_IDLE]		= 3,
-	[RXRPC_ACK_DUPLICATE]		= 4,
-	[RXRPC_ACK_OUT_OF_SEQUENCE]	= 5,
-	[RXRPC_ACK_EXCEEDS_WINDOW]	= 6,
-	[RXRPC_ACK_NOSPACE]		= 7,
-	[RXRPC_ACK_PING_RESPONSE]	= 8,
-};
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 1edbc678e8be17..d35657b659add0 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -115,6 +115,8 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 				*ackp++ = RXRPC_ACK_TYPE_NACK;
 			seq++;
 		} while (before_eq(seq, top));
+	} else if (txb->ack.reason == RXRPC_ACK_DELAY) {
+		txb->ack.reason = RXRPC_ACK_IDLE;
 	}
 
 	mtu = conn->params.peer->if_mtu;
@@ -204,6 +206,11 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *
 	if (txb->ack.reason == RXRPC_ACK_PING)
 		txb->wire.flags |= RXRPC_REQUEST_ACK;
 
+	if (txb->ack.reason == RXRPC_ACK_DELAY)
+		clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags);
+	if (txb->ack.reason == RXRPC_ACK_IDLE)
+		clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags);
+
 	spin_lock_bh(&call->lock);
 	n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top);
 	spin_unlock_bh(&call->lock);
diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h
index d2cf8e1d218f92..f3d4e27009016d 100644
--- a/net/rxrpc/protocol.h
+++ b/net/rxrpc/protocol.h
@@ -132,13 +132,6 @@ struct rxrpc_ackpacket {
 
 } __packed;
 
-/* Some ACKs refer to specific packets and some are general and can be updated. */
-#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED)	|	\
-			      (1 << RXRPC_ACK_PING_RESPONSE)	|	\
-			      (1 << RXRPC_ACK_DELAY)		|	\
-			      (1 << RXRPC_ACK_IDLE))
-
-
 /*
  * ACK packets can have a further piece of information tagged on the end
  */
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 104dd4a29f059a..46e784edc0f441 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -188,11 +188,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 	trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top);
 	ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
 
-	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
-		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial,
-				  rxrpc_propose_ack_terminal_ack);
-		//rxrpc_send_ack_packet(call, false, NULL);
-	}
+	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY)
+		rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
 
 	write_lock_bh(&call->state_lock);
 
@@ -206,8 +203,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 		call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
 		call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
 		write_unlock_bh(&call->state_lock);
-		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
-				  rxrpc_propose_ack_processing_op);
+		rxrpc_propose_delay_ACK(call, serial,
+					rxrpc_propose_ack_processing_op);
 		break;
 	default:
 		write_unlock_bh(&call->state_lock);
@@ -259,7 +256,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
 		rxrpc_end_rx_phase(call, serial);
 	} else {
 		/* Check to see if there's an ACK that needs sending. */
-		if (atomic_inc_return(&call->ackr_nr_consumed) > 2) {
+		if (atomic_inc_return(&call->ackr_nr_consumed) > 2 &&
+		    !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) {
 			rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial,
 				       rxrpc_propose_ack_rotate_rx);
 			rxrpc_transmit_ack_packets(call->peer->local);
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index ef4949259020bf..e32805a493243d 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -234,7 +234,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 		case RXRPC_CALL_SERVER_ACK_REQUEST:
 			call->state = RXRPC_CALL_SERVER_SEND_REPLY;
 			now = jiffies;
-			WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET);
+			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);
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 555e0910786bc7..2bd987364e4400 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -27,15 +27,6 @@ static const unsigned long max_jiffies = MAX_JIFFY_OFFSET;
 static struct ctl_table rxrpc_sysctl_table[] = {
 	/* Values measured in milliseconds but used in jiffies */
 	{
-		.procname	= "req_ack_delay",
-		.data		= &rxrpc_requested_ack_delay,
-		.maxlen		= sizeof(unsigned long),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_ms_jiffies_minmax,
-		.extra1		= (void *)&one_jiffy,
-		.extra2		= (void *)&max_jiffies,
-	},
-	{
 		.procname	= "soft_ack_delay",
 		.data		= &rxrpc_soft_ack_delay,
 		.maxlen		= sizeof(unsigned long),