Merge branch 'gianfar-next'

Claudiu Manoil says:

====================
gianfar: Tx timeout issue

There's an older Tx timeout issue showing up on etsec2 devices
with 2 CPUs. I pinned this issue down to processing overhead
incurred by supporting multiple Tx/Rx rings, as explained in
the 2nd patch below. But before this, there's also a concurency
issue leading to Rx/Tx spurrious interrupts, addressed by the
'Tx NAPI' patch below.
The Tx timeout can be triggered with multiple Tx flows,
'iperf -c -N 8' commands, on a 2 CPUs etsec2 based (P1020) board.

Before the patches:
"""
root@p1020rdb-pc:~# iperf -c 172.16.1.3 -n 1000M -P 8 &
[...]
root@p1020rdb-pc:~# NETDEV WATCHDOG: eth1 (fsl-gianfar): transmit queue 1 timed out
WARNING: at net/sched/sch_generic.c:279
Modules linked in:
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.13.0-rc3-03386-g89ea59c #23
task: ed84ef40 ti: ed868000 task.ti: ed868000
NIP: c04627a8 LR: c04627a8 CTR: c02fb270
REGS: ed869d00 TRAP: 0700 Not tainted (3.13.0-rc3-03386-g89ea59c)
MSR: 00029000 <CE,EE,ME> CR: 44000022 XER: 20000000
[...]

root@p1020rdb-pc:~# [ ID] Interval Transfer Bandwidth
[ 5] 0.0-19.3 sec 1000 MBytes 434 Mbits/sec
[ 8] 0.0-39.7 sec 1000 MBytes 211 Mbits/sec
[ 9] 0.0-40.1 sec 1000 MBytes 209 Mbits/sec
[ 3] 0.0-40.2 sec 1000 MBytes 209 Mbits/sec
[ 10] 0.0-59.0 sec 1000 MBytes 142 Mbits/sec
[ 7] 0.0-74.6 sec 1000 MBytes 112 Mbits/sec
[ 6] 0.0-74.7 sec 1000 MBytes 112 Mbits/sec
[ 4] 0.0-74.7 sec 1000 MBytes 112 Mbits/sec
[SUM] 0.0-74.7 sec 7.81 GBytes 898 Mbits/sec

root@p1020rdb-pc:~# ifconfig eth1
eth1 Link encap:Ethernet HWaddr 00:04:9f:00:13:01
inet addr:172.16.1.1 Bcast:172.16.255.255 Mask:255.255.0.0
inet6 addr: fe80::204:9fff:fe00:1301/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:708722 errors:0 dropped:0 overruns:0 frame:0
TX packets:8717849 errors:6 dropped:0 overruns:1470 carrier:0
collisions:0 txqueuelen:1000
RX bytes:58118018 (55.4 MiB) TX bytes:274069482 (261.3 MiB)
Base address:0xa000

"""

After applying the patches:
"""
root@p1020rdb-pc:~# iperf -c 172.16.1.3 -n 1000M -P 8 &
[...]
root@p1020rdb-pc:~# [ ID] Interval Transfer Bandwidth
[ 9] 0.0-70.5 sec 1000 MBytes 119 Mbits/sec
[ 5] 0.0-70.5 sec 1000 MBytes 119 Mbits/sec
[ 6] 0.0-70.7 sec 1000 MBytes 119 Mbits/sec
[ 4] 0.0-71.0 sec 1000 MBytes 118 Mbits/sec
[ 8] 0.0-71.1 sec 1000 MBytes 118 Mbits/sec
[ 3] 0.0-71.2 sec 1000 MBytes 118 Mbits/sec
[ 10] 0.0-71.3 sec 1000 MBytes 118 Mbits/sec
[ 7] 0.0-71.3 sec 1000 MBytes 118 Mbits/sec
[SUM] 0.0-71.3 sec 7.81 GBytes 942 Mbits/sec

root@p1020rdb-pc:~# ifconfig eth1
eth1 Link encap:Ethernet HWaddr 00:04:9f:00:13:01
inet addr:172.16.1.1 Bcast:172.16.255.255 Mask:255.255.0.0
inet6 addr: fe80::204:9fff:fe00:1301/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:728446 errors:0 dropped:0 overruns:0 frame:0
TX packets:8690057 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:59732650 (56.9 MiB) TX bytes:271554306 (258.9 MiB)
Base address:0xa000
"""
v2: PATCH 2:
Replaced CPP check with run-time condition to
limit the number of queues. Updated comments.
====================

Signed-off-by: David S. Miller <[e-mail]>

drivers/net/ethernet/freescale/gianfar.c

···
 static void gfar_set_multi(struct net_device *dev);
 static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr);
 static void gfar_configure_serdes(struct net_device *dev);
-static int gfar_poll(struct napi_struct *napi, int budget);
-static int gfar_poll_sq(struct napi_struct *napi, int budget);
+static int gfar_poll_rx(struct napi_struct *napi, int budget);
+static int gfar_poll_tx(struct napi_struct *napi, int budget);
+static int gfar_poll_rx_sq(struct napi_struct *napi, int budget);
+static int gfar_poll_tx_sq(struct napi_struct *napi, int budget);
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void gfar_netpoll(struct net_device *dev);
 #endif
···
 	if (priv->rx_filer_enable) {
 		rctrl |= RCTRL_FILREN;
 		/* Program the RIR0 reg with the required distribution */
-		gfar_write(&regs->rir0, DEFAULT_RIR0);
+		if (priv->poll_mode == GFAR_SQ_POLLING)
+			gfar_write(&regs->rir0, DEFAULT_2RXQ_RIR0);
+		else /* GFAR_MQ_POLLING */
+			gfar_write(&regs->rir0, DEFAULT_8RXQ_RIR0);
 	}
 
 	/* Restore PROMISC mode */
···
 {
 	int i;
 
-	for (i = 0; i < priv->num_grps; i++)
-		napi_disable(&priv->gfargrp[i].napi);
+	for (i = 0; i < priv->num_grps; i++) {
+		napi_disable(&priv->gfargrp[i].napi_rx);
+		napi_disable(&priv->gfargrp[i].napi_tx);
+	}
 }
 
 static void enable_napi(struct gfar_private *priv)
 {
 	int i;
 
-	for (i = 0; i < priv->num_grps; i++)
-		napi_enable(&priv->gfargrp[i].napi);
+	for (i = 0; i < priv->num_grps; i++) {
+		napi_enable(&priv->gfargrp[i].napi_rx);
+		napi_enable(&priv->gfargrp[i].napi_tx);
+	}
 }
 
 static int gfar_parse_group(struct device_node *np,
 			    struct gfar_private *priv, const char *model)
 {
 	struct gfar_priv_grp *grp = &priv->gfargrp[priv->num_grps];
-	u32 *queue_mask;
 	int i;
 
 	for (i = 0; i < GFAR_NUM_IRQS; i++) {
···
 	grp->priv = priv;
 	spin_lock_init(&grp->grplock);
 	if (priv->mode == MQ_MG_MODE) {
-		queue_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL);
-		grp->rx_bit_map = queue_mask ?
-			*queue_mask : (DEFAULT_MAPPING >> priv->num_grps);
-		queue_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL);
-		grp->tx_bit_map = queue_mask ?
-			*queue_mask : (DEFAULT_MAPPING >> priv->num_grps);
+		u32 *rxq_mask, *txq_mask;
+		rxq_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL);
+		txq_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL);
+
+		if (priv->poll_mode == GFAR_SQ_POLLING) {
+			/* One Q per interrupt group: Q0 to G0, Q1 to G1 */
+			grp->rx_bit_map = (DEFAULT_MAPPING >> priv->num_grps);
+			grp->tx_bit_map = (DEFAULT_MAPPING >> priv->num_grps);
+		} else { /* GFAR_MQ_POLLING */
+			grp->rx_bit_map = rxq_mask ?
+			*rxq_mask : (DEFAULT_MAPPING >> priv->num_grps);
+			grp->tx_bit_map = txq_mask ?
+			*txq_mask : (DEFAULT_MAPPING >> priv->num_grps);
+		}
 	} else {
 		grp->rx_bit_map = 0xFF;
 		grp->tx_bit_map = 0xFF;
···
 	 * also assign queues to groups
 	 */
 	for_each_set_bit(i, &grp->rx_bit_map, priv->num_rx_queues) {
+		if (!grp->rx_queue)
+			grp->rx_queue = priv->rx_queue[i];
 		grp->num_rx_queues++;
 		grp->rstat |= (RSTAT_CLEAR_RHALT >> i);
 		priv->rqueue |= ((RQUEUE_EN0 | RQUEUE_EX0) >> i);
···
 	}
 
 	for_each_set_bit(i, &grp->tx_bit_map, priv->num_tx_queues) {
+		if (!grp->tx_queue)
+			grp->tx_queue = priv->tx_queue[i];
 		grp->num_tx_queues++;
 		grp->tstat |= (TSTAT_CLEAR_THALT >> i);
 		priv->tqueue |= (TQUEUE_EN0 >> i);
···
 	if (!np || !of_device_is_available(np))
 		return -ENODEV;
 
-	/* parse the num of tx and rx queues */
+	/* parse the num of HW tx and rx queues */
 	tx_queues = (u32 *)of_get_property(np, "fsl,num_tx_queues", NULL);
-	num_tx_qs = tx_queues ? *tx_queues : 1;
+	rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL);
+
+	if (priv->mode == SQ_SG_MODE) {
+		num_tx_qs = 1;
+		num_rx_qs = 1;
+	} else { /* MQ_MG_MODE */
+		if (priv->poll_mode == GFAR_SQ_POLLING) {
+			num_tx_qs = 2; /* one q per int group */
+			num_rx_qs = 2; /* one q per int group */
+		} else { /* GFAR_MQ_POLLING */
+			num_tx_qs = tx_queues ? *tx_queues : 1;
+			num_rx_qs = rx_queues ? *rx_queues : 1;
+		}
+	}
 
 	if (num_tx_qs > MAX_TX_QS) {
 		pr_err("num_tx_qs(=%d) greater than MAX_TX_QS(=%d)\n",
···
 		pr_err("Cannot do alloc_etherdev, aborting\n");
 		return -EINVAL;
 	}
-
-	rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL);
-	num_rx_qs = rx_queues ? *rx_queues : 1;
 
 	if (num_rx_qs > MAX_RX_QS) {
 		pr_err("num_rx_qs(=%d) greater than MAX_RX_QS(=%d)\n",
···
 	/* Parse and initialize group specific information */
 	if (of_device_is_compatible(np, "fsl,etsec2")) {
 		priv->mode = MQ_MG_MODE;
+		priv->poll_mode = GFAR_SQ_POLLING;
 		for_each_child_of_node(np, child) {
 			err = gfar_parse_group(child, priv, model);
 			if (err)
···
 		}
 	} else {
 		priv->mode = SQ_SG_MODE;
+		priv->poll_mode = GFAR_SQ_POLLING;
 		err = gfar_parse_group(np, priv, model);
 		if (err)
 			goto err_grp_init;
···
 	dev->ethtool_ops = &gfar_ethtool_ops;
 
 	/* Register for napi ...We are registering NAPI for each grp */
-	if (priv->mode == SQ_SG_MODE)
-		netif_napi_add(dev, &priv->gfargrp[0].napi, gfar_poll_sq,
-			       GFAR_DEV_WEIGHT);
-	else
-		for (i = 0; i < priv->num_grps; i++)
-			netif_napi_add(dev, &priv->gfargrp[i].napi, gfar_poll,
-				       GFAR_DEV_WEIGHT);
+	for (i = 0; i < priv->num_grps; i++) {
+		if (priv->poll_mode == GFAR_SQ_POLLING) {
+			netif_napi_add(dev, &priv->gfargrp[i].napi_rx,
+				       gfar_poll_rx_sq, GFAR_DEV_WEIGHT);
+			netif_napi_add(dev, &priv->gfargrp[i].napi_tx,
+				       gfar_poll_tx_sq, 2);
+		} else {
+			netif_napi_add(dev, &priv->gfargrp[i].napi_rx,
+				       gfar_poll_rx, GFAR_DEV_WEIGHT);
+			netif_napi_add(dev, &priv->gfargrp[i].napi_tx,
+				       gfar_poll_tx, 2);
+		}
+	}
 
 	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) {
 		dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
···
 	netdev_tx_completed_queue(txq, howmany, bytes_sent);
 }
 
-static void gfar_schedule_cleanup(struct gfar_priv_grp *gfargrp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&gfargrp->grplock, flags);
-	if (napi_schedule_prep(&gfargrp->napi)) {
-		gfar_write(&gfargrp->regs->imask, IMASK_RTX_DISABLED);
-		__napi_schedule(&gfargrp->napi);
-	} else {
-		/* Clear IEVENT, so interrupts aren't called again
-		 * because of the packets that have already arrived.
-		 */
-		gfar_write(&gfargrp->regs->ievent, IEVENT_RTX_MASK);
-	}
-	spin_unlock_irqrestore(&gfargrp->grplock, flags);
-
-}
-
-/* Interrupt Handler for Transmit complete */
-static irqreturn_t gfar_transmit(int irq, void *grp_id)
-{
-	gfar_schedule_cleanup((struct gfar_priv_grp *)grp_id);
-	return IRQ_HANDLED;
-}
-
 static void gfar_new_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp,
 			   struct sk_buff *skb)
 {
···
 
 irqreturn_t gfar_receive(int irq, void *grp_id)
 {
-	gfar_schedule_cleanup((struct gfar_priv_grp *)grp_id);
+	struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id;
+	unsigned long flags;
+	u32 imask;
+
+	if (likely(napi_schedule_prep(&grp->napi_rx))) {
+		spin_lock_irqsave(&grp->grplock, flags);
+		imask = gfar_read(&grp->regs->imask);
+		imask &= IMASK_RX_DISABLED;
+		gfar_write(&grp->regs->imask, imask);
+		spin_unlock_irqrestore(&grp->grplock, flags);
+		__napi_schedule(&grp->napi_rx);
+	} else {
+		/* Clear IEVENT, so interrupts aren't called again
+		 * because of the packets that have already arrived.
+		 */
+		gfar_write(&grp->regs->ievent, IEVENT_RX_MASK);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* Interrupt Handler for Transmit complete */
+static irqreturn_t gfar_transmit(int irq, void *grp_id)
+{
+	struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id;
+	unsigned long flags;
+	u32 imask;
+
+	if (likely(napi_schedule_prep(&grp->napi_tx))) {
+		spin_lock_irqsave(&grp->grplock, flags);
+		imask = gfar_read(&grp->regs->imask);
+		imask &= IMASK_TX_DISABLED;
+		gfar_write(&grp->regs->imask, imask);
+		spin_unlock_irqrestore(&grp->grplock, flags);
+		__napi_schedule(&grp->napi_tx);
+	} else {
+		/* Clear IEVENT, so interrupts aren't called again
+		 * because of the packets that have already arrived.
+		 */
+		gfar_write(&grp->regs->ievent, IEVENT_TX_MASK);
+	}
+
 	return IRQ_HANDLED;
 }
 
···
 				rx_queue->stats.rx_bytes += pkt_len;
 				skb_record_rx_queue(skb, rx_queue->qindex);
 				gfar_process_frame(dev, skb, amount_pull,
-						   &rx_queue->grp->napi);
+						   &rx_queue->grp->napi_rx);
 
 			} else {
 				netif_warn(priv, rx_err, dev, "Missing skb!\n");
···
 	return howmany;
 }
 
-static int gfar_poll_sq(struct napi_struct *napi, int budget)
+static int gfar_poll_rx_sq(struct napi_struct *napi, int budget)
 {
 	struct gfar_priv_grp *gfargrp =
-		container_of(napi, struct gfar_priv_grp, napi);
+		container_of(napi, struct gfar_priv_grp, napi_rx);
 	struct gfar __iomem *regs = gfargrp->regs;
-	struct gfar_priv_tx_q *tx_queue = gfargrp->priv->tx_queue[0];
-	struct gfar_priv_rx_q *rx_queue = gfargrp->priv->rx_queue[0];
+	struct gfar_priv_rx_q *rx_queue = gfargrp->rx_queue;
 	int work_done = 0;
 
 	/* Clear IEVENT, so interrupts aren't called again
 	 * because of the packets that have already arrived
 	 */
-	gfar_write(&regs->ievent, IEVENT_RTX_MASK);
-
-	/* run Tx cleanup to completion */
-	if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx])
-		gfar_clean_tx_ring(tx_queue);
+	gfar_write(&regs->ievent, IEVENT_RX_MASK);
 
 	work_done = gfar_clean_rx_ring(rx_queue, budget);
 
 	if (work_done < budget) {
+		u32 imask;
 		napi_complete(napi);
 		/* Clear the halt bit in RSTAT */
 		gfar_write(&regs->rstat, gfargrp->rstat);
 
-		gfar_write(&regs->imask, IMASK_DEFAULT);
+		spin_lock_irq(&gfargrp->grplock);
+		imask = gfar_read(&regs->imask);
+		imask |= IMASK_RX_DEFAULT;
+		gfar_write(&regs->imask, imask);
+		spin_unlock_irq(&gfargrp->grplock);
 	}
 
 	return work_done;
 }
 
-static int gfar_poll(struct napi_struct *napi, int budget)
+static int gfar_poll_tx_sq(struct napi_struct *napi, int budget)
 {
 	struct gfar_priv_grp *gfargrp =
-		container_of(napi, struct gfar_priv_grp, napi);
+		container_of(napi, struct gfar_priv_grp, napi_tx);
+	struct gfar __iomem *regs = gfargrp->regs;
+	struct gfar_priv_tx_q *tx_queue = gfargrp->tx_queue;
+	u32 imask;
+
+	/* Clear IEVENT, so interrupts aren't called again
+	 * because of the packets that have already arrived
+	 */
+	gfar_write(&regs->ievent, IEVENT_TX_MASK);
+
+	/* run Tx cleanup to completion */
+	if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx])
+		gfar_clean_tx_ring(tx_queue);
+
+	napi_complete(napi);
+
+	spin_lock_irq(&gfargrp->grplock);
+	imask = gfar_read(&regs->imask);
+	imask |= IMASK_TX_DEFAULT;
+	gfar_write(&regs->imask, imask);
+	spin_unlock_irq(&gfargrp->grplock);
+
+	return 0;
+}
+
+static int gfar_poll_rx(struct napi_struct *napi, int budget)
+{
+	struct gfar_priv_grp *gfargrp =
+		container_of(napi, struct gfar_priv_grp, napi_rx);
 	struct gfar_private *priv = gfargrp->priv;
 	struct gfar __iomem *regs = gfargrp->regs;
-	struct gfar_priv_tx_q *tx_queue = NULL;
 	struct gfar_priv_rx_q *rx_queue = NULL;
 	int work_done = 0, work_done_per_q = 0;
 	int i, budget_per_q = 0;
-	int has_tx_work = 0;
 	unsigned long rstat_rxf;
 	int num_act_queues;
 
 	/* Clear IEVENT, so interrupts aren't called again
 	 * because of the packets that have already arrived
 	 */
-	gfar_write(&regs->ievent, IEVENT_RTX_MASK);
+	gfar_write(&regs->ievent, IEVENT_RX_MASK);
 
 	rstat_rxf = gfar_read(&regs->rstat) & RSTAT_RXF_MASK;
 
 	num_act_queues = bitmap_weight(&rstat_rxf, MAX_RX_QS);
 	if (num_act_queues)
 		budget_per_q = budget/num_act_queues;
-
-	for_each_set_bit(i, &gfargrp->tx_bit_map, priv->num_tx_queues) {
-		tx_queue = priv->tx_queue[i];
-		/* run Tx cleanup to completion */
-		if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) {
-			gfar_clean_tx_ring(tx_queue);
-			has_tx_work = 1;
-		}
-	}
 
 	for_each_set_bit(i, &gfargrp->rx_bit_map, priv->num_rx_queues) {
 		/* skip queue if not active */
···
 		}
 	}
 
-	if (!num_act_queues && !has_tx_work) {
-
+	if (!num_act_queues) {
+		u32 imask;
 		napi_complete(napi);
 
 		/* Clear the halt bit in RSTAT */
 		gfar_write(&regs->rstat, gfargrp->rstat);
 
-		gfar_write(&regs->imask, IMASK_DEFAULT);
+		spin_lock_irq(&gfargrp->grplock);
+		imask = gfar_read(&regs->imask);
+		imask |= IMASK_RX_DEFAULT;
+		gfar_write(&regs->imask, imask);
+		spin_unlock_irq(&gfargrp->grplock);
 	}
 
 	return work_done;
 }
+
+static int gfar_poll_tx(struct napi_struct *napi, int budget)
+{
+	struct gfar_priv_grp *gfargrp =
+		container_of(napi, struct gfar_priv_grp, napi_tx);
+	struct gfar_private *priv = gfargrp->priv;
+	struct gfar __iomem *regs = gfargrp->regs;
+	struct gfar_priv_tx_q *tx_queue = NULL;
+	int has_tx_work = 0;
+	int i;
+
+	/* Clear IEVENT, so interrupts aren't called again
+	 * because of the packets that have already arrived
+	 */
+	gfar_write(&regs->ievent, IEVENT_TX_MASK);
+
+	for_each_set_bit(i, &gfargrp->tx_bit_map, priv->num_tx_queues) {
+		tx_queue = priv->tx_queue[i];
+		/* run Tx cleanup to completion */
+		if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) {
+			gfar_clean_tx_ring(tx_queue);
+			has_tx_work = 1;
+		}
+	}
+
+	if (!has_tx_work) {
+		u32 imask;
+		napi_complete(napi);
+
+		spin_lock_irq(&gfargrp->grplock);
+		imask = gfar_read(&regs->imask);
+		imask |= IMASK_TX_DEFAULT;
+		gfar_write(&regs->imask, imask);
+		spin_unlock_irq(&gfargrp->grplock);
+	}
+
+	return 0;
+}
+
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /* Polling 'interrupt' - used by things like netconsole to send skbs

drivers/net/ethernet/freescale/gianfar.h

···
 		IMASK_RXFEN0 | IMASK_BSY | IMASK_EBERR | IMASK_BABR | \
 		IMASK_XFUN | IMASK_RXC | IMASK_BABT | IMASK_DPE \
 		| IMASK_PERR)
-#define IMASK_RTX_DISABLED ((~(IMASK_RXFEN0 | IMASK_TXFEN | IMASK_BSY)) \
-			   & IMASK_DEFAULT)
+#define IMASK_RX_DEFAULT (IMASK_RXFEN0 | IMASK_BSY)
+#define IMASK_TX_DEFAULT (IMASK_TXFEN | IMASK_TXBEN)
+
+#define IMASK_RX_DISABLED ((~(IMASK_RX_DEFAULT)) & IMASK_DEFAULT)
+#define IMASK_TX_DISABLED ((~(IMASK_TX_DEFAULT)) & IMASK_DEFAULT)
 
 /* Fifo management */
 #define FIFO_TX_THR_MASK	0x01ff
···
 
 /* This default RIR value directly corresponds
  * to the 3-bit hash value generated */
-#define DEFAULT_RIR0	0x05397700
+#define DEFAULT_8RXQ_RIR0	0x05397700
+/* Map even hash values to Q0, and odd ones to Q1 */
+#define DEFAULT_2RXQ_RIR0	0x04104100
 
 /* RQFCR register bits */
 #define RQFCR_GPI		0x80000000
···
 	MQ_MG_MODE
 };
 
+/* GFAR_SQ_POLLING: Single Queue NAPI polling mode
+ *	The driver supports a single pair of RX/Tx queues
+ *	per interrupt group (Rx/Tx int line). MQ_MG mode
+ *	devices have 2 interrupt groups, so the device will
+ *	have a total of 2 Tx and 2 Rx queues in this case.
+ * GFAR_MQ_POLLING: Multi Queue NAPI polling mode
+ *	The driver supports all the 8 Rx and Tx HW queues
+ *	each queue mapped by the Device Tree to one of
+ *	the 2 interrupt groups. This mode implies significant
+ *	processing overhead (CPU and controller level).
+ */
+enum gfar_poll_mode {
+	GFAR_SQ_POLLING = 0,
+	GFAR_MQ_POLLING
+};
+
 /*
  * Per TX queue stats
  */
···
  */
 
 struct gfar_priv_grp {
-	spinlock_t grplock __attribute__ ((aligned (SMP_CACHE_BYTES)));
-	struct	napi_struct napi;
-	struct gfar_private *priv;
+	spinlock_t grplock __aligned(SMP_CACHE_BYTES);
+	struct	napi_struct napi_rx;
+	struct	napi_struct napi_tx;
 	struct gfar __iomem *regs;
-	unsigned int rstat;
-	unsigned long num_rx_queues;
-	unsigned long rx_bit_map;
-	/* cacheline 3 */
+	struct gfar_priv_tx_q *tx_queue;
+	struct gfar_priv_rx_q *rx_queue;
 	unsigned int tstat;
+	unsigned int rstat;
+
+	struct gfar_private *priv;
 	unsigned long num_tx_queues;
 	unsigned long tx_bit_map;
+	unsigned long num_rx_queues;
+	unsigned long rx_bit_map;
 
 	struct gfar_irqinfo *irqinfo[GFAR_NUM_IRQS];
 };
···
  * the buffer descriptor determines the actual condition.
  */
 struct gfar_private {
-	unsigned int num_rx_queues;
-
 	struct device *dev;
 	struct net_device *ndev;
 	enum gfar_errata errata;
···
 
 	u16 uses_rxfcb;
 	u16 padding;
+	u32 device_flags;
 
 	/* HW time stamping enabled flag */
 	int hwts_rx_en;
···
 	struct gfar_priv_grp gfargrp[MAXGROUPS];
 
 	unsigned long state;
-	u32 device_flags;
 
-	unsigned int mode;
+	unsigned short mode;
+	unsigned short poll_mode;
 	unsigned int num_tx_queues;
+	unsigned int num_rx_queues;
 	unsigned int num_grps;
 
 	/* Network Statistics */