1 files changed, 214 insertions, 213 deletions

diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 2a93e7b5fbd0..1e21a708390e 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -20,127 +20,103 @@
 /*
  * Propose a PING ACK be sent.
  */
-static void rxrpc_propose_ping(struct rxrpc_call *call,
-			       bool immediate, bool background)
+void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial,
+			enum rxrpc_propose_ack_trace why)
 {
-	if (immediate) {
-		if (background &&
-		    !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events))
-			rxrpc_queue_call(call);
-	} else {
-		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);
-		}
+	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);
 	}
 }
 
 /*
- * 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, bool immediate, bool background,
-				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)
 {
-	enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
 	unsigned long expiry = rxrpc_soft_ack_delay;
-	s8 prior = rxrpc_ack_priority[ack_reason];
-
-	/* Pings are handled specially because we don't want to accidentally
-	 * lose a ping response by subsuming it into a ping.
-	 */
-	if (ack_reason == RXRPC_ACK_PING) {
-		rxrpc_propose_ping(call, immediate, background);
-		goto trace;
+	unsigned long now = jiffies, ack_at;
+
+	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
+		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);
 	}
 
-	/* 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;
-		}
-		if (!immediate)
-			goto trace;
-	} else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
-		call->ackr_reason = ack_reason;
-		call->ackr_serial = serial;
-	} else {
-		outcome = rxrpc_propose_ack_subsume;
+	trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial);
+}
+
+/*
+ * Queue an ACK for immediate transmission.
+ */
+void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason,
+		    rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why)
+{
+	struct rxrpc_local *local = call->conn->params.local;
+	struct rxrpc_txbuf *txb;
+
+	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;
 	}
 
-	switch (ack_reason) {
-	case RXRPC_ACK_REQUESTED:
-		if (rxrpc_requested_ack_delay < expiry)
-			expiry = rxrpc_requested_ack_delay;
-		if (serial == 1)
-			immediate = false;
-		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:
-		immediate = true;
-		break;
+	rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]);
+
+	txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK,
+				in_softirq() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS);
+	if (!txb) {
+		kleave(" = -ENOMEM");
+		return;
 	}
 
-	if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) {
-		_debug("already scheduled");
-	} else if (immediate || expiry == 0) {
-		_debug("immediate ACK %lx", call->events);
-		if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) &&
-		    background)
-			rxrpc_queue_call(call);
-	} else {
-		unsigned long now = jiffies, ack_at;
-
-		if (call->peer->srtt_us != 0)
-			ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3);
-		else
-			ack_at = expiry;
-
-		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);
-			rxrpc_reduce_call_timer(call, ack_at, now,
-						rxrpc_timer_set_for_ack);
-		}
+	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;
+
+	if (!rxrpc_try_get_call(call, rxrpc_call_got)) {
+		rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem);
+		return;
 	}
 
-trace:
-	trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate,
-				background, outcome);
-}
+	spin_lock_bh(&local->ack_tx_lock);
+	list_add_tail(&txb->tx_link, &local->ack_tx_queue);
+	spin_unlock_bh(&local->ack_tx_lock);
+	trace_rxrpc_send_ack(call, why, ack_reason, serial);
 
-/*
- * propose an ACK be sent, locking the call structure
- */
-void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
-		       u32 serial, bool immediate, bool background,
-		       enum rxrpc_propose_ack_trace why)
-{
-	spin_lock_bh(&call->lock);
-	__rxrpc_propose_ACK(call, ack_reason, serial,
-			    immediate, background, why);
-	spin_unlock_bh(&call->lock);
+	if (in_task()) {
+		rxrpc_transmit_ack_packets(call->peer->local);
+	} else {
+		rxrpc_get_local(local);
+		rxrpc_queue_local(local);
+	}
 }
 
 /*
@@ -156,62 +132,131 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
  */
 static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 {
-	struct sk_buff *skb;
+	struct rxrpc_ackpacket *ack = NULL;
+	struct rxrpc_txbuf *txb;
+	struct sk_buff *ack_skb = NULL;
 	unsigned long resend_at;
-	rxrpc_seq_t cursor, seq, top;
+	rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted);
 	ktime_t now, max_age, oldest, ack_ts;
-	int ix;
-	u8 annotation, anno_type, retrans = 0, unacked = 0;
+	bool unacked = false;
+	unsigned int i;
+	LIST_HEAD(retrans_queue);
 
-	_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
+	_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;
+
+	/* See if there's an ACK saved with a soft-ACK table in it. */
+	if (call->acks_soft_tbl) {
+		spin_lock_bh(&call->acks_ack_lock);
+		ack_skb = call->acks_soft_tbl;
+		if (ack_skb) {
+			rxrpc_get_skb(ack_skb, rxrpc_skb_ack);
+			ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header);
+		}
+		spin_unlock_bh(&call->acks_ack_lock);
+	}
 
-	spin_lock_bh(&call->lock);
+	if (list_empty(&call->tx_buffer))
+		goto no_resend;
 
-	cursor = call->tx_hard_ack;
-	top = call->tx_top;
-	ASSERT(before_eq(cursor, top));
-	if (cursor == top)
-		goto out_unlock;
+	spin_lock(&call->tx_lock);
 
-	/* Scan the packet list without dropping the lock and decide which of
-	 * the packets in the Tx buffer we're going to resend and what the new
-	 * resend timeout will be.
-	 */
-	trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK);
-	oldest = now;
-	for (seq = cursor + 1; before_eq(seq, top); seq++) {
-		ix = seq & RXRPC_RXTX_BUFF_MASK;
-		annotation = call->rxtx_annotations[ix];
-		anno_type = annotation & RXRPC_TX_ANNO_MASK;
-		annotation &= ~RXRPC_TX_ANNO_MASK;
-		if (anno_type == RXRPC_TX_ANNO_ACK)
-			continue;
+	if (list_empty(&call->tx_buffer))
+		goto no_further_resend;
+
+	trace_rxrpc_resend(call);
+	txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link);
 
-		skb = call->rxtx_buffer[ix];
-		rxrpc_see_skb(skb, rxrpc_skb_seen);
+	/* Scan the soft ACK table without dropping the lock and resend any
+	 * explicitly NAK'd packets.
+	 */
+	if (ack) {
+		for (i = 0; i < ack->nAcks; i++) {
+			rxrpc_seq_t seq;
 
-		if (anno_type == RXRPC_TX_ANNO_UNACK) {
-			if (ktime_after(skb->tstamp, max_age)) {
-				if (ktime_before(skb->tstamp, oldest))
-					oldest = skb->tstamp;
+			if (ack->acks[i] & 1)
 				continue;
+			seq = ntohl(ack->firstPacket) + 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 */
+
+			rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked);
+
+			if (list_empty(&txb->tx_link)) {
+				rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans);
+				rxrpc_get_call(call, rxrpc_call_got_tx);
+				list_add_tail(&txb->tx_link, &retrans_queue);
+				set_bit(RXRPC_TXBUF_RESENT, &txb->flags);
 			}
-			if (!(annotation & RXRPC_TX_ANNO_RESENT))
-				unacked++;
+
+			trace_rxrpc_retransmit(call, txb->seq,
+					       ktime_to_ns(ktime_sub(txb->last_sent,
+								     max_age)));
+
+			if (list_is_last(&txb->call_link, &call->tx_buffer))
+				goto no_further_resend;
+			txb = list_next_entry(txb, call_link);
+		}
+	}
+
+	/* 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;
 		}
 
-		/* Okay, we need to retransmit a packet. */
-		call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation;
-		retrans++;
-		trace_rxrpc_retransmit(call, seq, annotation | anno_type,
-				       ktime_to_ns(ktime_sub(skb->tstamp, max_age)));
+	do_resend:
+		unacked = true;
+		if (list_empty(&txb->tx_link)) {
+			rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans);
+			list_add_tail(&txb->tx_link, &retrans_queue);
+			set_bit(RXRPC_TXBUF_RESENT, &txb->flags);
+			rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans);
+		}
 	}
 
+no_further_resend:
+	spin_unlock(&call->tx_lock);
+no_resend:
+	rxrpc_free_skb(ack_skb, rxrpc_skb_freed);
+
 	resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
-	resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans);
+	resend_at += jiffies + rxrpc_get_rto_backoff(call->peer,
+						     !list_empty(&retrans_queue));
 	WRITE_ONCE(call->resend_at, resend_at);
 
 	if (unacked)
@@ -221,62 +266,28 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 	 * that an ACK got lost somewhere.  Send a ping to find out instead of
 	 * retransmitting data.
 	 */
-	if (!retrans) {
+	if (list_empty(&retrans_queue)) {
 		rxrpc_reduce_call_timer(call, resend_at, now_j,
 					rxrpc_timer_set_for_resend);
-		spin_unlock_bh(&call->lock);
 		ack_ts = ktime_sub(now, call->acks_latest_ts);
 		if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
 			goto out;
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
-				  rxrpc_propose_ack_ping_for_lost_ack);
-		rxrpc_send_ack_packet(call, true, NULL);
+		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
+			       rxrpc_propose_ack_ping_for_lost_ack);
 		goto out;
 	}
 
-	/* Now go through the Tx window and perform the retransmissions.  We
-	 * have to drop the lock for each send.  If an ACK comes in whilst the
-	 * lock is dropped, it may clear some of the retransmission markers for
-	 * packets that it soft-ACKs.
-	 */
-	for (seq = cursor + 1; before_eq(seq, top); seq++) {
-		ix = seq & RXRPC_RXTX_BUFF_MASK;
-		annotation = call->rxtx_annotations[ix];
-		anno_type = annotation & RXRPC_TX_ANNO_MASK;
-		if (anno_type != RXRPC_TX_ANNO_RETRANS)
-			continue;
-
-		/* We need to reset the retransmission state, but we need to do
-		 * so before we drop the lock as a new ACK/NAK may come in and
-		 * confuse things
-		 */
-		annotation &= ~RXRPC_TX_ANNO_MASK;
-		annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT;
-		call->rxtx_annotations[ix] = annotation;
-
-		skb = call->rxtx_buffer[ix];
-		if (!skb)
-			continue;
-
-		rxrpc_get_skb(skb, rxrpc_skb_got);
-		spin_unlock_bh(&call->lock);
-
-		if (rxrpc_send_data_packet(call, skb, true) < 0) {
-			rxrpc_free_skb(skb, rxrpc_skb_freed);
-			return;
-		}
+	while ((txb = list_first_entry_or_null(&retrans_queue,
+					       struct rxrpc_txbuf, tx_link))) {
+		list_del_init(&txb->tx_link);
+		rxrpc_send_data_packet(call, txb);
+		rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans);
 
-		if (rxrpc_is_client_call(call))
-			rxrpc_expose_client_call(call);
-
-		rxrpc_free_skb(skb, rxrpc_skb_freed);
-		spin_lock_bh(&call->lock);
-		if (after(call->tx_hard_ack, seq))
-			seq = call->tx_hard_ack;
+		trace_rxrpc_retransmit(call, txb->seq,
+				       ktime_to_ns(ktime_sub(txb->last_sent,
+							     max_age)));
 	}
 
-out_unlock:
-	spin_unlock_bh(&call->lock);
 out:
 	_leave("");
 }
@@ -288,9 +299,9 @@ 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;
 	unsigned int iterations = 0;
+	rxrpc_serial_t ackr_serial;
 
 	rxrpc_see_call(call);
 
@@ -309,6 +320,9 @@ recheck_state:
 		goto recheck_state;
 	}
 
+	if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom)
+		rxrpc_shrink_call_tx_buffer(call);
+
 	if (call->state == RXRPC_CALL_COMPLETE) {
 		rxrpc_delete_call_timer(call);
 		goto out_put;
@@ -335,11 +349,13 @@ 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);
-		set_bit(RXRPC_CALL_EV_ACK, &call->events);
+		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);
@@ -353,16 +369,16 @@ recheck_state:
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
 		cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
-		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true,
-				  rxrpc_propose_ack_ping_for_keepalive);
-		set_bit(RXRPC_CALL_EV_PING, &call->events);
+		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);
-		set_bit(RXRPC_CALL_EV_PING, &call->events);
+		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
+			       rxrpc_propose_ack_ping_for_keepalive);
 	}
 
 	t = READ_ONCE(call->resend_at);
@@ -385,25 +401,10 @@ recheck_state:
 		goto recheck_state;
 	}
 
-	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, 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, send_ack);
-			goto recheck_state;
-		}
-	}
-
-	if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) {
-		rxrpc_send_ack_packet(call, true, NULL);
-		goto recheck_state;
+		rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
+			       rxrpc_propose_ack_ping_for_lost_ack);
 	}
 
 	if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) &&
@@ -419,7 +420,7 @@ 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);