1 files changed, 134 insertions, 67 deletions

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 92495e73b869..3dedb8c0618c 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -45,11 +45,9 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 	}
 
 	cumulative_acks += summary->nr_new_acks;
-	cumulative_acks += summary->nr_rot_new_acks;
 	if (cumulative_acks > 255)
 		cumulative_acks = 255;
 
-	summary->mode = call->cong_mode;
 	summary->cwnd = call->cong_cwnd;
 	summary->ssthresh = call->cong_ssthresh;
 	summary->cumulative_acks = cumulative_acks;
@@ -151,6 +149,7 @@ out_no_clear_ca:
 		cwnd = RXRPC_TX_MAX_WINDOW;
 	call->cong_cwnd = cwnd;
 	call->cong_cumul_acks = cumulative_acks;
+	summary->mode = call->cong_mode;
 	trace_rxrpc_congest(call, summary, acked_serial, change);
 	if (resend)
 		rxrpc_resend(call, skb);
@@ -213,8 +212,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 	list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) {
 		if (before_eq(txb->seq, call->acks_hard_ack))
 			continue;
-		summary->nr_rot_new_acks++;
-		if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) {
+		if (txb->flags & RXRPC_LAST_PACKET) {
 			set_bit(RXRPC_CALL_TX_LAST, &call->flags);
 			rot_last = true;
 		}
@@ -254,6 +252,14 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 {
 	ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
 
+	call->resend_at = KTIME_MAX;
+	trace_rxrpc_timer_can(call, rxrpc_timer_trace_resend);
+
+	if (unlikely(call->cong_last_nack)) {
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	}
+
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
@@ -285,15 +291,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 static bool rxrpc_receiving_reply(struct rxrpc_call *call)
 {
 	struct rxrpc_ack_summary summary = { 0 };
-	unsigned long now, timo;
 	rxrpc_seq_t top = READ_ONCE(call->tx_top);
 
 	if (call->ackr_reason) {
-		now = jiffies;
-		timo = now + MAX_JIFFY_OFFSET;
-
-		WRITE_ONCE(call->delay_ack_at, timo);
-		trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
+		call->delay_ack_at = KTIME_MAX;
+		trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack);
 	}
 
 	if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
@@ -326,7 +328,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 
 	case RXRPC_CALL_SERVER_RECV_REQUEST:
 		rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST);
-		call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
+		call->expect_req_by = KTIME_MAX;
 		rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op);
 		break;
 
@@ -586,14 +588,12 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 
 	case RXRPC_CALL_SERVER_RECV_REQUEST: {
 		unsigned long timo = READ_ONCE(call->next_req_timo);
-		unsigned long now, expect_req_by;
 
 		if (timo) {
-			now = jiffies;
-			expect_req_by = now + timo;
-			WRITE_ONCE(call->expect_req_by, expect_req_by);
-			rxrpc_reduce_call_timer(call, expect_req_by, now,
-						rxrpc_timer_set_for_idle);
+			ktime_t delay = ms_to_ktime(timo);
+
+			call->expect_req_by = ktime_add(ktime_get_real(), delay);
+			trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_idle);
 		}
 		break;
 	}
@@ -667,14 +667,14 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call,
 /*
  * Process the extra information that may be appended to an ACK packet
  */
-static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
-				struct rxrpc_ackinfo *ackinfo)
+static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb,
+				    struct rxrpc_acktrailer *trailer)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_peer *peer;
 	unsigned int mtu;
 	bool wake = false;
-	u32 rwind = ntohl(ackinfo->rwind);
+	u32 rwind = ntohl(trailer->rwind);
 
 	if (rwind > RXRPC_TX_MAX_WINDOW)
 		rwind = RXRPC_TX_MAX_WINDOW;
@@ -688,7 +688,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 	if (call->cong_ssthresh > rwind)
 		call->cong_ssthresh = rwind;
 
-	mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU));
+	mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU));
 
 	peer = call->peer;
 	if (mtu < peer->maxdata) {
@@ -703,6 +703,42 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 }
 
 /*
+ * Determine how many nacks from the previous ACK have now been satisfied.
+ */
+static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call,
+					      struct rxrpc_ack_summary *summary,
+					      rxrpc_seq_t seq)
+{
+	struct sk_buff *skb = call->cong_last_nack;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, new_acks = 0, retained_nacks = 0;
+	rxrpc_seq_t old_seq = sp->ack.first_ack;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
+
+	if (after_eq(seq, old_seq + sp->ack.nr_acks)) {
+		summary->nr_new_acks += sp->ack.nr_nacks;
+		summary->nr_new_acks += seq - (old_seq + sp->ack.nr_acks);
+		summary->nr_retained_nacks = 0;
+	} else if (seq == old_seq) {
+		summary->nr_retained_nacks = sp->ack.nr_nacks;
+	} else {
+		for (i = 0; i < sp->ack.nr_acks; i++) {
+			if (acks[i] == RXRPC_ACK_TYPE_NACK) {
+				if (before(old_seq + i, seq))
+					new_acks++;
+				else
+					retained_nacks++;
+			}
+		}
+
+		summary->nr_new_acks += new_acks;
+		summary->nr_retained_nacks = retained_nacks;
+	}
+
+	return old_seq + sp->ack.nr_acks;
+}
+
+/*
  * Process individual soft ACKs.
  *
  * Each ACK in the array corresponds to one packet and can be either an ACK or
@@ -711,25 +747,51 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
  * the timer on the basis that the peer might just not have processed them at
  * the time the ACK was sent.
  */
-static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
-				  rxrpc_seq_t seq, int nr_acks,
-				  struct rxrpc_ack_summary *summary)
+static void rxrpc_input_soft_acks(struct rxrpc_call *call,
+				  struct rxrpc_ack_summary *summary,
+				  struct sk_buff *skb,
+				  rxrpc_seq_t seq,
+				  rxrpc_seq_t since)
 {
-	unsigned int i;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, old_nacks = 0;
+	rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
 
-	for (i = 0; i < nr_acks; i++) {
+	for (i = 0; i < sp->ack.nr_acks; i++) {
 		if (acks[i] == RXRPC_ACK_TYPE_ACK) {
 			summary->nr_acks++;
-			summary->nr_new_acks++;
+			if (after_eq(seq, since))
+				summary->nr_new_acks++;
 		} else {
-			if (!summary->saw_nacks &&
-			    call->acks_lowest_nak != seq + i) {
-				call->acks_lowest_nak = seq + i;
-				summary->new_low_nack = true;
-			}
 			summary->saw_nacks = true;
+			if (before(seq, since)) {
+				/* Overlap with previous ACK */
+				old_nacks++;
+			} else {
+				summary->nr_new_nacks++;
+				sp->ack.nr_nacks++;
+			}
+
+			if (before(seq, lowest_nak))
+				lowest_nak = seq;
 		}
+		seq++;
 	}
+
+	if (lowest_nak != call->acks_lowest_nak) {
+		call->acks_lowest_nak = lowest_nak;
+		summary->new_low_nack = true;
+	}
+
+	/* We *can* have more nacks than we did - the peer is permitted to drop
+	 * packets it has soft-acked and re-request them.  Further, it is
+	 * possible for the nack distribution to change whilst the number of
+	 * nacks stays the same or goes down.
+	 */
+	if (old_nacks < summary->nr_retained_nacks)
+		summary->nr_new_acks += summary->nr_retained_nacks - old_nacks;
+	summary->nr_retained_nacks = old_nacks;
 }
 
 /*
@@ -769,36 +831,32 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call,
 static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_ack_summary summary = { 0 };
-	struct rxrpc_ackpacket ack;
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	struct rxrpc_ackinfo info;
+	struct rxrpc_acktrailer trailer;
 	rxrpc_serial_t ack_serial, acked_serial;
-	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
+	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since;
 	int nr_acks, offset, ioffset;
 
 	_enter("");
 
-	offset = sizeof(struct rxrpc_wire_header);
-	if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0)
-		return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack);
-	offset += sizeof(ack);
+	offset = sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
 
-	ack_serial = sp->hdr.serial;
-	acked_serial = ntohl(ack.serial);
-	first_soft_ack = ntohl(ack.firstPacket);
-	prev_pkt = ntohl(ack.previousPacket);
-	hard_ack = first_soft_ack - 1;
-	nr_acks = ack.nAcks;
-	summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ?
-			      ack.reason : RXRPC_ACK__INVALID);
+	ack_serial	= sp->hdr.serial;
+	acked_serial	= sp->ack.acked_serial;
+	first_soft_ack	= sp->ack.first_ack;
+	prev_pkt	= sp->ack.prev_ack;
+	nr_acks		= sp->ack.nr_acks;
+	hard_ack	= first_soft_ack - 1;
+	summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ?
+			      sp->ack.reason : RXRPC_ACK__INVALID);
 
 	trace_rxrpc_rx_ack(call, ack_serial, acked_serial,
 			   first_soft_ack, prev_pkt,
 			   summary.ack_reason, nr_acks);
-	rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]);
+	rxrpc_inc_stat(call->rxnet, stat_rx_acks[summary.ack_reason]);
 
 	if (acked_serial != 0) {
-		switch (ack.reason) {
+		switch (summary.ack_reason) {
 		case RXRPC_ACK_PING_RESPONSE:
 			rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial,
 						 rxrpc_rtt_rx_ping_response);
@@ -818,7 +876,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	 * indicates that the client address changed due to NAT.  The server
 	 * lost the call because it switched to a different peer.
 	 */
-	if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) &&
+	if (unlikely(summary.ack_reason == RXRPC_ACK_EXCEEDS_WINDOW) &&
 	    first_soft_ack == 1 &&
 	    prev_pkt == 0 &&
 	    rxrpc_is_client_call(call)) {
@@ -831,7 +889,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	 * indicate a change of address.  However, we can retransmit the call
 	 * if we still have it buffered to the beginning.
 	 */
-	if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) &&
+	if (unlikely(summary.ack_reason == RXRPC_ACK_OUT_OF_SEQUENCE) &&
 	    first_soft_ack == 1 &&
 	    prev_pkt == 0 &&
 	    call->acks_hard_ack == 0 &&
@@ -849,31 +907,41 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 		goto send_response;
 	}
 
-	info.rxMTU = 0;
+	trailer.maxMTU = 0;
 	ioffset = offset + nr_acks + 3;
-	if (skb->len >= ioffset + sizeof(info) &&
-	    skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0)
-		return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info);
+	if (skb->len >= ioffset + sizeof(trailer) &&
+	    skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0)
+		return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer);
 
 	if (nr_acks > 0)
 		skb_condense(skb);
 
+	if (call->cong_last_nack) {
+		since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack);
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	} else {
+		summary.nr_new_acks = first_soft_ack - call->acks_first_seq;
+		call->acks_lowest_nak = first_soft_ack + nr_acks;
+		since = first_soft_ack;
+	}
+
 	call->acks_latest_ts = skb->tstamp;
 	call->acks_first_seq = first_soft_ack;
 	call->acks_prev_seq = prev_pkt;
 
-	switch (ack.reason) {
+	switch (summary.ack_reason) {
 	case RXRPC_ACK_PING:
 		break;
 	default:
-		if (after(acked_serial, call->acks_highest_serial))
+		if (acked_serial && after(acked_serial, call->acks_highest_serial))
 			call->acks_highest_serial = acked_serial;
 		break;
 	}
 
 	/* Parse rwind and mtu sizes if provided. */
-	if (info.rxMTU)
-		rxrpc_input_ackinfo(call, skb, &info);
+	if (trailer.maxMTU)
+		rxrpc_input_ack_trailer(call, skb, &trailer);
 
 	if (first_soft_ack == 0)
 		return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
@@ -905,8 +973,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0) {
 		if (offset > (int)skb->len - nr_acks)
 			return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
-		rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
-				      nr_acks, &summary);
+		rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since);
+		rxrpc_get_skb(skb, rxrpc_skb_get_last_nack);
+		call->cong_last_nack = skb;
 	}
 
 	if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) &&
@@ -918,7 +987,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	rxrpc_congestion_management(call, skb, &summary, acked_serial);
 
 send_response:
-	if (ack.reason == RXRPC_ACK_PING)
+	if (summary.ack_reason == RXRPC_ACK_PING)
 		rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial,
 			       rxrpc_propose_ack_respond_to_ping);
 	else if (sp->hdr.flags & RXRPC_REQUEST_ACK)
@@ -969,12 +1038,10 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb)
 
 	timo = READ_ONCE(call->next_rx_timo);
 	if (timo) {
-		unsigned long now = jiffies, expect_rx_by;
+		ktime_t delay = ms_to_ktime(timo);
 
-		expect_rx_by = now + timo;
-		WRITE_ONCE(call->expect_rx_by, expect_rx_by);
-		rxrpc_reduce_call_timer(call, expect_rx_by, now,
-					rxrpc_timer_set_for_normal);
+		call->expect_rx_by = ktime_add(ktime_get_real(), delay);
+		trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx);
 	}
 
 	switch (sp->hdr.type) {