Merge branch 'mvneta-64bit'

Gregory CLEMENT says:

====================
Support Armada 37xx SoC (ARMv8 64-bits) in mvneta driver

The Armada 37xx is a new ARMv8 SoC from Marvell using same network
controller as the older Armada 370/38x/XP SoCs. This series adapts the
driver in order to be able to use it on this new SoC. The main changes
are:

- 64-bits support: the first patches allow using the driver on a 64-bit
  architecture.

- MBUS support: the mbus configuration is different on Armada 37xx
  from the older SoCs.

- per cpu interrupt: Armada 37xx do not support per cpu interrupt for
  the NETA IP, the non-per-CPU behavior was added back.

The first patch is an optimization in the rx path in swbm mode.
The second patch remove unnecessary allocation for HWBM.
The first item is solved by patches 4 and 5.
The 2 last items are solved by patch 6.
In patch 7 the dt support is added.

Beside Armada 37xx, this series have been again tested on Armada XP
and Armada 38x (with Hardware Buffer Management and with Software
Buffer Management).

This is the 6th version of the series:
- 1st version:
http://lists.infradead.org/pipermail/linux-arm-kernel/2016-November/469588.html

- 2nd version:
http://lists.infradead.org/pipermail/linux-arm-kernel/2016-November/470476.html

- 3rd version:
http://lists.infradead.org/pipermail/linux-arm-kernel/2016-November/470901.html

- 4th version:
http://lists.infradead.org/pipermail/linux-arm-kernel/2016-November/471039.html

- 5th version:
http://lists.infradead.org/pipermail/linux-arm-kernel/2016-November/471478.html

Changelog:
v5 -> v6:
 - Added Tested-by from  Marcin Wojtas on the series
 - Added Reviewed-by from Jisheng Zhang on patch 3
 - Fix eth1 phy mode for Armada 3720 DB board on patch 7

v4 -> v5:
 - remove unnecessary cast in patch 3

v3 -> v4:
 - Adding new patch: "net: mvneta: do not allocate buffer in rxq init
   with HWBM"

 - Simplify the HWBM case in patch 3 as suggested by Marcin

v2 -> v3:
 - Adding patch 1 "Optimize rx path for small frame"

 - Fix the kbuild error by moving the "phys_addr += pp->rx_offset_correction;"
  line from patch 2 to patch 3 where rx_offset_correction is introduced.

 - Move the memory allocation of the buf_virt_addr of the rxq to be
   called by the probe function in order to avoid a memory leak.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 254 insertions, 100 deletions

diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 66fd9dbb2ca7..3b8f11fe5e13 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -44,6 +44,7 @@ config MVMDIO
 config MVNETA_BM_ENABLE
 	tristate "Marvell Armada 38x/XP network interface BM support"
 	depends on MVNETA
+	depends on !64BIT
 	---help---
 	  This driver supports auxiliary block of the network
 	  interface units in the Marvell ARMADA XP and ARMADA 38x SoC
@@ -55,15 +56,15 @@ config MVNETA_BM_ENABLE
 	  buffer management.
 
 config MVNETA
-	tristate "Marvell Armada 370/38x/XP network interface support"
-	depends on PLAT_ORION || COMPILE_TEST
+	tristate "Marvell Armada 370/38x/XP/37xx network interface support"
+	depends on ARCH_MVEBU || COMPILE_TEST
 	depends on HAS_DMA
-	depends on !64BIT
 	select MVMDIO
 	select FIXED_PHY
 	---help---
 	  This driver supports the network interface units in the
-	  Marvell ARMADA XP, ARMADA 370 and ARMADA 38x SoC family.
+	  Marvell ARMADA XP, ARMADA 370, ARMADA 38x and
+	  ARMADA 37xx SoC family.
 
 	  Note that this driver is distinct from the mv643xx_eth
 	  driver, which should be used for the older Marvell SoCs
@@ -71,6 +72,7 @@ config MVNETA
 
 config MVNETA_BM
 	tristate
+	depends on !64BIT
 	default y if MVNETA=y && MVNETA_BM_ENABLE!=n
 	default MVNETA_BM_ENABLE
 	select HWBM
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 0a24571e44b9..aa87c6858478 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -296,6 +296,12 @@
 /* descriptor aligned size */
 #define MVNETA_DESC_ALIGNED_SIZE	32
 
+/* Number of bytes to be taken into account by HW when putting incoming data
+ * to the buffers. It is needed in case NET_SKB_PAD exceeds maximum packet
+ * offset supported in MVNETA_RXQ_CONFIG_REG(q) registers.
+ */
+#define MVNETA_RX_PKT_OFFSET_CORRECTION		64
+
 #define MVNETA_RX_PKT_SIZE(mtu) \
 	ALIGN((mtu) + MVNETA_MH_SIZE + MVNETA_VLAN_TAG_LEN + \
 	      ETH_HLEN + ETH_FCS_LEN,			     \
@@ -391,6 +397,9 @@ struct mvneta_port {
 	spinlock_t lock;
 	bool is_stopped;
 
+	u32 cause_rx_tx;
+	struct napi_struct napi;
+
 	/* Core clock */
 	struct clk *clk;
 	/* AXI clock */
@@ -416,6 +425,10 @@ struct mvneta_port {
 	u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
 
 	u32 indir[MVNETA_RSS_LU_TABLE_SIZE];
+
+	/* Flags for special SoC configurations */
+	bool neta_armada3700;
+	u16 rx_offset_correction;
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -561,6 +574,9 @@ struct mvneta_rx_queue {
 	u32 pkts_coal;
 	u32 time_coal;
 
+	/* Virtual address of the RX buffer */
+	void  **buf_virt_addr;
+
 	/* Virtual address of the RX DMA descriptors array */
 	struct mvneta_rx_desc *descs;
 
@@ -955,14 +971,9 @@ static int mvneta_mbus_io_win_set(struct mvneta_port *pp, u32 base, u32 wsize,
 	return 0;
 }
 
-/* Assign and initialize pools for port. In case of fail
- * buffer manager will remain disabled for current port.
- */
-static int mvneta_bm_port_init(struct platform_device *pdev,
-			       struct mvneta_port *pp)
+static  int mvneta_bm_port_mbus_init(struct mvneta_port *pp)
 {
-	struct device_node *dn = pdev->dev.of_node;
-	u32 long_pool_id, short_pool_id, wsize;
+	u32 wsize;
 	u8 target, attr;
 	int err;
 
@@ -981,6 +992,25 @@ static int mvneta_bm_port_init(struct platform_device *pdev,
 		netdev_info(pp->dev, "fail to configure mbus window to BM\n");
 		return err;
 	}
+	return 0;
+}
+
+/* Assign and initialize pools for port. In case of fail
+ * buffer manager will remain disabled for current port.
+ */
+static int mvneta_bm_port_init(struct platform_device *pdev,
+			       struct mvneta_port *pp)
+{
+	struct device_node *dn = pdev->dev.of_node;
+	u32 long_pool_id, short_pool_id;
+
+	if (!pp->neta_armada3700) {
+		int ret;
+
+		ret = mvneta_bm_port_mbus_init(pp);
+		if (ret)
+			return ret;
+	}
 
 	if (of_property_read_u32(dn, "bm,pool-long", &long_pool_id)) {
 		netdev_info(pp->dev, "missing long pool id\n");
@@ -1349,22 +1379,27 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 	for_each_present_cpu(cpu) {
 		int rxq_map = 0, txq_map = 0;
 		int rxq, txq;
+		if (!pp->neta_armada3700) {
+			for (rxq = 0; rxq < rxq_number; rxq++)
+				if ((rxq % max_cpu) == cpu)
+					rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+			for (txq = 0; txq < txq_number; txq++)
+				if ((txq % max_cpu) == cpu)
+					txq_map |= MVNETA_CPU_TXQ_ACCESS(txq);
+
+			/* With only one TX queue we configure a special case
+			 * which will allow to get all the irq on a single
+			 * CPU
+			 */
+			if (txq_number == 1)
+				txq_map = (cpu == pp->rxq_def) ?
+					MVNETA_CPU_TXQ_ACCESS(1) : 0;
 
-		for (rxq = 0; rxq < rxq_number; rxq++)
-			if ((rxq % max_cpu) == cpu)
-				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
-
-		for (txq = 0; txq < txq_number; txq++)
-			if ((txq % max_cpu) == cpu)
-				txq_map |= MVNETA_CPU_TXQ_ACCESS(txq);
-
-		/* With only one TX queue we configure a special case
-		 * which will allow to get all the irq on a single
-		 * CPU
-		 */
-		if (txq_number == 1)
-			txq_map = (cpu == pp->rxq_def) ?
-				MVNETA_CPU_TXQ_ACCESS(1) : 0;
+		} else {
+			txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+			rxq_map = MVNETA_CPU_RXQ_ACCESS_ALL_MASK;
+		}
 
 		mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
 	}
@@ -1573,10 +1608,14 @@ static void mvneta_tx_done_pkts_coal_set(struct mvneta_port *pp,
 
 /* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */
 static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc,
-				u32 phys_addr, u32 cookie)
+				u32 phys_addr, void *virt_addr,
+				struct mvneta_rx_queue *rxq)
 {
-	rx_desc->buf_cookie = cookie;
+	int i;
+
 	rx_desc->buf_phys_addr = phys_addr;
+	i = rx_desc - rxq->descs;
+	rxq->buf_virt_addr[i] = virt_addr;
 }
 
 /* Decrement sent descriptors counter */
@@ -1781,7 +1820,8 @@ EXPORT_SYMBOL_GPL(mvneta_frag_free);
 
 /* Refill processing for SW buffer management */
 static int mvneta_rx_refill(struct mvneta_port *pp,
-			    struct mvneta_rx_desc *rx_desc)
+			    struct mvneta_rx_desc *rx_desc,
+			    struct mvneta_rx_queue *rxq)
 
 {
 	dma_addr_t phys_addr;
@@ -1799,7 +1839,8 @@ static int mvneta_rx_refill(struct mvneta_port *pp,
 		return -ENOMEM;
 	}
 
-	mvneta_rx_desc_fill(rx_desc, phys_addr, (u32)data);
+	phys_addr += pp->rx_offset_correction;
+	mvneta_rx_desc_fill(rx_desc, phys_addr, data, rxq);
 	return 0;
 }
 
@@ -1861,7 +1902,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 
 	for (i = 0; i < rxq->size; i++) {
 		struct mvneta_rx_desc *rx_desc = rxq->descs + i;
-		void *data = (void *)rx_desc->buf_cookie;
+		void *data = rxq->buf_virt_addr[i];
 
 		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
@@ -1894,12 +1935,13 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
 		unsigned char *data;
 		dma_addr_t phys_addr;
 		u32 rx_status, frag_size;
-		int rx_bytes, err;
+		int rx_bytes, err, index;
 
 		rx_done++;
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
-		data = (unsigned char *)rx_desc->buf_cookie;
+		index = rx_desc - rxq->descs;
+		data = rxq->buf_virt_addr[index];
 		phys_addr = rx_desc->buf_phys_addr;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
@@ -1918,7 +1960,7 @@ err_drop_frame:
 				goto err_drop_frame;
 
 			dma_sync_single_range_for_cpu(dev->dev.parent,
-						      rx_desc->buf_phys_addr,
+						      phys_addr,
 						      MVNETA_MH_SIZE + NET_SKB_PAD,
 						      rx_bytes,
 						      DMA_FROM_DEVICE);
@@ -1938,7 +1980,7 @@ err_drop_frame:
 		}
 
 		/* Refill processing */
-		err = mvneta_rx_refill(pp, rx_desc);
+		err = mvneta_rx_refill(pp, rx_desc, rxq);
 		if (err) {
 			netdev_err(dev, "Linux processing - Can't refill\n");
 			rxq->missed++;
@@ -2020,7 +2062,7 @@ static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
 		rx_done++;
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
-		data = (unsigned char *)rx_desc->buf_cookie;
+		data = (u8 *)(uintptr_t)rx_desc->buf_cookie;
 		phys_addr = rx_desc->buf_phys_addr;
 		pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
 		bm_pool = &pp->bm_priv->bm_pools[pool_id];
@@ -2610,6 +2652,17 @@ static void mvneta_set_rx_mode(struct net_device *dev)
 /* Interrupt handling - the callback for request_irq() */
 static irqreturn_t mvneta_isr(int irq, void *dev_id)
 {
+	struct mvneta_port *pp = (struct mvneta_port *)dev_id;
+
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+	napi_schedule(&pp->napi);
+
+	return IRQ_HANDLED;
+}
+
+/* Interrupt handling - the callback for request_percpu_irq() */
+static irqreturn_t mvneta_percpu_isr(int irq, void *dev_id)
+{
 	struct mvneta_pcpu_port *port = (struct mvneta_pcpu_port *)dev_id;
 
 	disable_percpu_irq(port->pp->dev->irq);
@@ -2657,7 +2710,7 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 
 	if (!netif_running(pp->dev)) {
-		napi_complete(&port->napi);
+		napi_complete(napi);
 		return rx_done;
 	}
 
@@ -2686,7 +2739,8 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	 */
 	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
 
-	cause_rx_tx |= port->cause_rx_tx;
+	cause_rx_tx |= pp->neta_armada3700 ? pp->cause_rx_tx :
+		port->cause_rx_tx;
 
 	if (rx_queue) {
 		rx_queue = rx_queue - 1;
@@ -2700,11 +2754,27 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 
 	if (budget > 0) {
 		cause_rx_tx = 0;
-		napi_complete(&port->napi);
-		enable_percpu_irq(pp->dev->irq, 0);
+		napi_complete(napi);
+
+		if (pp->neta_armada3700) {
+			unsigned long flags;
+
+			local_irq_save(flags);
+			mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+				    MVNETA_RX_INTR_MASK(rxq_number) |
+				    MVNETA_TX_INTR_MASK(txq_number) |
+				    MVNETA_MISCINTR_INTR_MASK);
+			local_irq_restore(flags);
+		} else {
+			enable_percpu_irq(pp->dev->irq, 0);
+		}
 	}
 
-	port->cause_rx_tx = cause_rx_tx;
+	if (pp->neta_armada3700)
+		pp->cause_rx_tx = cause_rx_tx;
+	else
+		port->cause_rx_tx = cause_rx_tx;
+
 	return rx_done;
 }
 
@@ -2716,7 +2786,7 @@ static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 
 	for (i = 0; i < num; i++) {
 		memset(rxq->descs + i, 0, sizeof(struct mvneta_rx_desc));
-		if (mvneta_rx_refill(pp, rxq->descs + i) != 0) {
+		if (mvneta_rx_refill(pp, rxq->descs + i, rxq) != 0) {
 			netdev_err(pp->dev, "%s:rxq %d, %d of %d buffs  filled\n",
 				__func__, rxq->id, i, num);
 			break;
@@ -2773,7 +2843,7 @@ static int mvneta_rxq_init(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size);
 
 	/* Set Offset */
-	mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD);
+	mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD - pp->rx_offset_correction);
 
 	/* Set coalescing pkts and time */
 	mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
@@ -2784,14 +2854,14 @@ static int mvneta_rxq_init(struct mvneta_port *pp,
 		mvneta_rxq_buf_size_set(pp, rxq,
 					MVNETA_RX_BUF_SIZE(pp->pkt_size));
 		mvneta_rxq_bm_disable(pp, rxq);
+		mvneta_rxq_fill(pp, rxq, rxq->size);
 	} else {
 		mvneta_rxq_bm_enable(pp, rxq);
 		mvneta_rxq_long_pool_set(pp, rxq);
 		mvneta_rxq_short_pool_set(pp, rxq);
+		mvneta_rxq_non_occup_desc_add(pp, rxq, rxq->size);
 	}
 
-	mvneta_rxq_fill(pp, rxq, rxq->size);
-
 	return 0;
 }
 
@@ -2974,11 +3044,16 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 	/* start the Rx/Tx activity */
 	mvneta_port_enable(pp);
 
-	/* Enable polling on the port */
-	for_each_online_cpu(cpu) {
-		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+	if (!pp->neta_armada3700) {
+		/* Enable polling on the port */
+		for_each_online_cpu(cpu) {
+			struct mvneta_pcpu_port *port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		napi_enable(&port->napi);
+			napi_enable(&port->napi);
+		}
+	} else {
+		napi_enable(&pp->napi);
 	}
 
 	/* Unmask interrupts. It has to be done from each CPU */
@@ -3000,10 +3075,15 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 
 	phy_stop(ndev->phydev);
 
-	for_each_online_cpu(cpu) {
-		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+	if (!pp->neta_armada3700) {
+		for_each_online_cpu(cpu) {
+			struct mvneta_pcpu_port *port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		napi_disable(&port->napi);
+			napi_disable(&port->napi);
+		}
+	} else {
+		napi_disable(&pp->napi);
 	}
 
 	netif_carrier_off(pp->dev);
@@ -3413,31 +3493,37 @@ static int mvneta_open(struct net_device *dev)
 		goto err_cleanup_rxqs;
 
 	/* Connect to port interrupt line */
-	ret = request_percpu_irq(pp->dev->irq, mvneta_isr,
-				 MVNETA_DRIVER_NAME, pp->ports);
+	if (pp->neta_armada3700)
+		ret = request_irq(pp->dev->irq, mvneta_isr, 0,
+				  dev->name, pp);
+	else
+		ret = request_percpu_irq(pp->dev->irq, mvneta_percpu_isr,
+					 dev->name, pp->ports);
 	if (ret) {
 		netdev_err(pp->dev, "cannot request irq %d\n", pp->dev->irq);
 		goto err_cleanup_txqs;
 	}
 
-	/* Enable per-CPU interrupt on all the CPU to handle our RX
-	 * queue interrupts
-	 */
-	on_each_cpu(mvneta_percpu_enable, pp, true);
+	if (!pp->neta_armada3700) {
+		/* Enable per-CPU interrupt on all the CPU to handle our RX
+		 * queue interrupts
+		 */
+		on_each_cpu(mvneta_percpu_enable, pp, true);
 
-	pp->is_stopped = false;
-	/* Register a CPU notifier to handle the case where our CPU
-	 * might be taken offline.
-	 */
-	ret = cpuhp_state_add_instance_nocalls(online_hpstate,
-					       &pp->node_online);
-	if (ret)
-		goto err_free_irq;
+		pp->is_stopped = false;
+		/* Register a CPU notifier to handle the case where our CPU
+		 * might be taken offline.
+		 */
+		ret = cpuhp_state_add_instance_nocalls(online_hpstate,
+						       &pp->node_online);
+		if (ret)
+			goto err_free_irq;
 
-	ret = cpuhp_state_add_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
-					       &pp->node_dead);
-	if (ret)
-		goto err_free_online_hp;
+		ret = cpuhp_state_add_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+						       &pp->node_dead);
+		if (ret)
+			goto err_free_online_hp;
+	}
 
 	/* In default link is down */
 	netif_carrier_off(pp->dev);
@@ -3453,13 +3539,20 @@ static int mvneta_open(struct net_device *dev)
 	return 0;
 
 err_free_dead_hp:
-	cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
-					    &pp->node_dead);
+	if (!pp->neta_armada3700)
+		cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+						    &pp->node_dead);
 err_free_online_hp:
-	cpuhp_state_remove_instance_nocalls(online_hpstate, &pp->node_online);
+	if (!pp->neta_armada3700)
+		cpuhp_state_remove_instance_nocalls(online_hpstate,
+						    &pp->node_online);
 err_free_irq:
-	on_each_cpu(mvneta_percpu_disable, pp, true);
-	free_percpu_irq(pp->dev->irq, pp->ports);
+	if (pp->neta_armada3700) {
+		free_irq(pp->dev->irq, pp);
+	} else {
+		on_each_cpu(mvneta_percpu_disable, pp, true);
+		free_percpu_irq(pp->dev->irq, pp->ports);
+	}
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);
 err_cleanup_rxqs:
@@ -3472,23 +3565,30 @@ static int mvneta_stop(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
-	/* Inform that we are stopping so we don't want to setup the
-	 * driver for new CPUs in the notifiers. The code of the
-	 * notifier for CPU online is protected by the same spinlock,
-	 * so when we get the lock, the notifer work is done.
-	 */
-	spin_lock(&pp->lock);
-	pp->is_stopped = true;
-	spin_unlock(&pp->lock);
+	if (!pp->neta_armada3700) {
+		/* Inform that we are stopping so we don't want to setup the
+		 * driver for new CPUs in the notifiers. The code of the
+		 * notifier for CPU online is protected by the same spinlock,
+		 * so when we get the lock, the notifer work is done.
+		 */
+		spin_lock(&pp->lock);
+		pp->is_stopped = true;
+		spin_unlock(&pp->lock);
 
-	mvneta_stop_dev(pp);
-	mvneta_mdio_remove(pp);
+		mvneta_stop_dev(pp);
+		mvneta_mdio_remove(pp);
 
 	cpuhp_state_remove_instance_nocalls(online_hpstate, &pp->node_online);
 	cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
 					    &pp->node_dead);
-	on_each_cpu(mvneta_percpu_disable, pp, true);
-	free_percpu_irq(dev->irq, pp->ports);
+		on_each_cpu(mvneta_percpu_disable, pp, true);
+		free_percpu_irq(dev->irq, pp->ports);
+	} else {
+		mvneta_stop_dev(pp);
+		mvneta_mdio_remove(pp);
+		free_irq(dev->irq, pp);
+	}
+
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
 
@@ -3767,6 +3867,11 @@ static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
 				   const u8 *key, const u8 hfunc)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
+
+	/* Current code for Armada 3700 doesn't support RSS features yet */
+	if (pp->neta_armada3700)
+		return -EOPNOTSUPP;
+
 	/* We require at least one supported parameter to be changed
 	 * and no change in any of the unsupported parameters
 	 */
@@ -3787,6 +3892,10 @@ static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
+	/* Current code for Armada 3700 doesn't support RSS features yet */
+	if (pp->neta_armada3700)
+		return -EOPNOTSUPP;
+
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;
 
@@ -3865,6 +3974,11 @@ static int mvneta_init(struct device *dev, struct mvneta_port *pp)
 		rxq->size = pp->rx_ring_size;
 		rxq->pkts_coal = MVNETA_RX_COAL_PKTS;
 		rxq->time_coal = MVNETA_RX_COAL_USEC;
+		rxq->buf_virt_addr = devm_kmalloc(pp->dev->dev.parent,
+						  rxq->size * sizeof(void *),
+						  GFP_KERNEL);
+		if (!rxq->buf_virt_addr)
+			return -ENOMEM;
 	}
 
 	return 0;
@@ -3889,16 +4003,29 @@ static void mvneta_conf_mbus_windows(struct mvneta_port *pp,
 	win_enable = 0x3f;
 	win_protect = 0;
 
-	for (i = 0; i < dram->num_cs; i++) {
-		const struct mbus_dram_window *cs = dram->cs + i;
-		mvreg_write(pp, MVNETA_WIN_BASE(i), (cs->base & 0xffff0000) |
-			    (cs->mbus_attr << 8) | dram->mbus_dram_target_id);
+	if (dram) {
+		for (i = 0; i < dram->num_cs; i++) {
+			const struct mbus_dram_window *cs = dram->cs + i;
+
+			mvreg_write(pp, MVNETA_WIN_BASE(i),
+				    (cs->base & 0xffff0000) |
+				    (cs->mbus_attr << 8) |
+				    dram->mbus_dram_target_id);
 
-		mvreg_write(pp, MVNETA_WIN_SIZE(i),
-			    (cs->size - 1) & 0xffff0000);
+			mvreg_write(pp, MVNETA_WIN_SIZE(i),
+				    (cs->size - 1) & 0xffff0000);
 
-		win_enable &= ~(1 << i);
-		win_protect |= 3 << (2 * i);
+			win_enable &= ~(1 << i);
+			win_protect |= 3 << (2 * i);
+		}
+	} else {
+		/* For Armada3700 open default 4GB Mbus window, leaving
+		 * arbitration of target/attribute to a different layer
+		 * of configuration.
+		 */
+		mvreg_write(pp, MVNETA_WIN_SIZE(0), 0xffff0000);
+		win_enable &= ~BIT(0);
+		win_protect = 3;
 	}
 
 	mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);
@@ -4019,8 +4146,19 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp->rxq_def = rxq_def;
 
+	/* Set RX packet offset correction for platforms, whose
+	 * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
+	 * platforms and 0B for 32-bit ones.
+	 */
+	pp->rx_offset_correction =
+		max(0, NET_SKB_PAD - MVNETA_RX_PKT_OFFSET_CORRECTION);
+
 	pp->indir[0] = rxq_def;
 
+	/* Get special SoC configurations */
+	if (of_device_is_compatible(dn, "marvell,armada-3700-neta"))
+		pp->neta_armada3700 = true;
+
 	pp->clk = devm_clk_get(&pdev->dev, "core");
 	if (IS_ERR(pp->clk))
 		pp->clk = devm_clk_get(&pdev->dev, NULL);
@@ -4088,7 +4226,11 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp->tx_csum_limit = tx_csum_limit;
 
 	dram_target_info = mv_mbus_dram_info();
-	if (dram_target_info)
+	/* Armada3700 requires setting default configuration of Mbus
+	 * windows, however without using filled mbus_dram_target_info
+	 * structure.
+	 */
+	if (dram_target_info || pp->neta_armada3700)
 		mvneta_conf_mbus_windows(pp, dram_target_info);
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
@@ -4121,11 +4263,20 @@ static int mvneta_probe(struct platform_device *pdev)
 		goto err_netdev;
 	}
 
-	for_each_present_cpu(cpu) {
-		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+	/* Armada3700 network controller does not support per-cpu
+	 * operation, so only single NAPI should be initialized.
+	 */
+	if (pp->neta_armada3700) {
+		netif_napi_add(dev, &pp->napi, mvneta_poll, NAPI_POLL_WEIGHT);
+	} else {
+		for_each_present_cpu(cpu) {
+			struct mvneta_pcpu_port *port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		netif_napi_add(dev, &port->napi, mvneta_poll, NAPI_POLL_WEIGHT);
-		port->pp = pp;
+			netif_napi_add(dev, &port->napi, mvneta_poll,
+				       NAPI_POLL_WEIGHT);
+			port->pp = pp;
+		}
 	}
 
 	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
@@ -4210,6 +4361,7 @@ static int mvneta_remove(struct platform_device *pdev)
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
 	{ .compatible = "marvell,armada-xp-neta" },
+	{ .compatible = "marvell,armada-3700-neta" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvneta_match);