Linux-libre 4.4-gnupck-4.4-gnu

5 files changed, 420 insertions, 147 deletions

diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 80af9ffce..a1c862b46 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -44,6 +44,7 @@ config MVNETA
 	tristate "Marvell Armada 370/38x/XP network interface support"
 	depends on PLAT_ORION
 	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.
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index dfb6d5f79..4182290fd 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1618,7 +1618,6 @@ static void mv643xx_eth_get_drvinfo(struct net_device *dev,
 		sizeof(drvinfo->version));
 	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
-	drvinfo->n_stats = ARRAY_SIZE(mv643xx_eth_stats);
 }
 
 static int mv643xx_eth_nway_reset(struct net_device *dev)
@@ -1877,29 +1876,19 @@ static void mv643xx_eth_program_multicast_filter(struct net_device *dev)
 	struct netdev_hw_addr *ha;
 	int i;
 
-	if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
-		int port_num;
-		u32 accept;
+	if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI))
+		goto promiscuous;
 
-oom:
-		port_num = mp->port_num;
-		accept = 0x01010101;
-		for (i = 0; i < 0x100; i += 4) {
-			wrl(mp, SPECIAL_MCAST_TABLE(port_num) + i, accept);
-			wrl(mp, OTHER_MCAST_TABLE(port_num) + i, accept);
-		}
-		return;
-	}
-
-	mc_spec = kzalloc(0x200, GFP_ATOMIC);
-	if (mc_spec == NULL)
-		goto oom;
-	mc_other = mc_spec + (0x100 >> 2);
+	/* Allocate both mc_spec and mc_other tables */
+	mc_spec = kcalloc(128, sizeof(u32), GFP_ATOMIC);
+	if (!mc_spec)
+		goto promiscuous;
+	mc_other = &mc_spec[64];
 
 	netdev_for_each_mc_addr(ha, dev) {
 		u8 *a = ha->addr;
 		u32 *table;
-		int entry;
+		u8 entry;
 
 		if (memcmp(a, "\x01\x00\x5e\x00\x00", 5) == 0) {
 			table = mc_spec;
@@ -1912,12 +1901,23 @@ oom:
 		table[entry >> 2] |= 1 << (8 * (entry & 3));
 	}
 
-	for (i = 0; i < 0x100; i += 4) {
-		wrl(mp, SPECIAL_MCAST_TABLE(mp->port_num) + i, mc_spec[i >> 2]);
-		wrl(mp, OTHER_MCAST_TABLE(mp->port_num) + i, mc_other[i >> 2]);
+	for (i = 0; i < 64; i++) {
+		wrl(mp, SPECIAL_MCAST_TABLE(mp->port_num) + i * sizeof(u32),
+		    mc_spec[i]);
+		wrl(mp, OTHER_MCAST_TABLE(mp->port_num) + i * sizeof(u32),
+		    mc_other[i]);
 	}
 
 	kfree(mc_spec);
+	return;
+
+promiscuous:
+	for (i = 0; i < 64; i++) {
+		wrl(mp, SPECIAL_MCAST_TABLE(mp->port_num) + i * sizeof(u32),
+		    0x01010101u);
+		wrl(mp, OTHER_MCAST_TABLE(mp->port_num) + i * sizeof(u32),
+		    0x01010101u);
+	}
 }
 
 static void mv643xx_eth_set_rx_mode(struct net_device *dev)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 0e4924498..ed622fa29 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -32,10 +32,11 @@
 #include <linux/of_address.h>
 #include <linux/phy.h>
 #include <linux/clk.h>
+#include <linux/cpu.h>
 
 /* Registers */
 #define MVNETA_RXQ_CONFIG_REG(q)                (0x1400 + ((q) << 2))
-#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(1)
+#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(0)
 #define      MVNETA_RXQ_PKT_OFFSET_ALL_MASK     (0xf    << 8)
 #define      MVNETA_RXQ_PKT_OFFSET_MASK(offs)   ((offs) << 8)
 #define MVNETA_RXQ_THRESHOLD_REG(q)             (0x14c0 + ((q) << 2))
@@ -61,6 +62,7 @@
 #define MVNETA_WIN_SIZE(w)                      (0x2204 + ((w) << 3))
 #define MVNETA_WIN_REMAP(w)                     (0x2280 + ((w) << 2))
 #define MVNETA_BASE_ADDR_ENABLE                 0x2290
+#define MVNETA_ACCESS_PROTECT_ENABLE            0x2294
 #define MVNETA_PORT_CONFIG                      0x2400
 #define      MVNETA_UNI_PROMISC_MODE            BIT(0)
 #define      MVNETA_DEF_RXQ(q)                  ((q) << 1)
@@ -100,6 +102,8 @@
 #define MVNETA_TXQ_CMD                           0x2448
 #define      MVNETA_TXQ_DISABLE_SHIFT            8
 #define      MVNETA_TXQ_ENABLE_MASK              0x000000ff
+#define MVNETA_RX_DISCARD_FRAME_COUNT		 0x2484
+#define MVNETA_OVERRUN_FRAME_COUNT		 0x2488
 #define MVNETA_GMAC_CLOCK_DIVIDER                0x24f4
 #define      MVNETA_GMAC_1MS_CLOCK_ENABLE        BIT(31)
 #define MVNETA_ACC_MODE                          0x2500
@@ -156,7 +160,7 @@
 
 #define MVNETA_INTR_ENABLE                       0x25b8
 #define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
-#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000  // note: neta says it's 0x000000FF
+#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0x000000ff
 
 #define MVNETA_RXQ_CMD                           0x2680
 #define      MVNETA_RXQ_DISABLE_SHIFT            8
@@ -191,7 +195,7 @@
 #define      MVNETA_GMAC_AN_FLOW_CTRL_EN         BIT(11)
 #define      MVNETA_GMAC_CONFIG_FULL_DUPLEX      BIT(12)
 #define      MVNETA_GMAC_AN_DUPLEX_EN            BIT(13)
-#define MVNETA_MIB_COUNTERS_BASE                 0x3080
+#define MVNETA_MIB_COUNTERS_BASE                 0x3000
 #define      MVNETA_MIB_LATE_COLLISION           0x7c
 #define MVNETA_DA_FILT_SPEC_MCAST                0x3400
 #define MVNETA_DA_FILT_OTH_MCAST                 0x3500
@@ -239,6 +243,7 @@
 #define MVNETA_VLAN_TAG_LEN             4
 
 #define MVNETA_CPU_D_CACHE_LINE_SIZE    32
+#define MVNETA_TX_CSUM_DEF_SIZE		1600
 #define MVNETA_TX_CSUM_MAX_SIZE		9800
 #define MVNETA_ACC_MODE_EXT		1
 
@@ -277,6 +282,50 @@
 
 #define MVNETA_RX_BUF_SIZE(pkt_size)   ((pkt_size) + NET_SKB_PAD)
 
+struct mvneta_statistic {
+	unsigned short offset;
+	unsigned short type;
+	const char name[ETH_GSTRING_LEN];
+};
+
+#define T_REG_32	32
+#define T_REG_64	64
+
+static const struct mvneta_statistic mvneta_statistics[] = {
+	{ 0x3000, T_REG_64, "good_octets_received", },
+	{ 0x3010, T_REG_32, "good_frames_received", },
+	{ 0x3008, T_REG_32, "bad_octets_received", },
+	{ 0x3014, T_REG_32, "bad_frames_received", },
+	{ 0x3018, T_REG_32, "broadcast_frames_received", },
+	{ 0x301c, T_REG_32, "multicast_frames_received", },
+	{ 0x3050, T_REG_32, "unrec_mac_control_received", },
+	{ 0x3058, T_REG_32, "good_fc_received", },
+	{ 0x305c, T_REG_32, "bad_fc_received", },
+	{ 0x3060, T_REG_32, "undersize_received", },
+	{ 0x3064, T_REG_32, "fragments_received", },
+	{ 0x3068, T_REG_32, "oversize_received", },
+	{ 0x306c, T_REG_32, "jabber_received", },
+	{ 0x3070, T_REG_32, "mac_receive_error", },
+	{ 0x3074, T_REG_32, "bad_crc_event", },
+	{ 0x3078, T_REG_32, "collision", },
+	{ 0x307c, T_REG_32, "late_collision", },
+	{ 0x2484, T_REG_32, "rx_discard", },
+	{ 0x2488, T_REG_32, "rx_overrun", },
+	{ 0x3020, T_REG_32, "frames_64_octets", },
+	{ 0x3024, T_REG_32, "frames_65_to_127_octets", },
+	{ 0x3028, T_REG_32, "frames_128_to_255_octets", },
+	{ 0x302c, T_REG_32, "frames_256_to_511_octets", },
+	{ 0x3030, T_REG_32, "frames_512_to_1023_octets", },
+	{ 0x3034, T_REG_32, "frames_1024_to_max_octets", },
+	{ 0x3038, T_REG_64, "good_octets_sent", },
+	{ 0x3040, T_REG_32, "good_frames_sent", },
+	{ 0x3044, T_REG_32, "excessive_collision", },
+	{ 0x3048, T_REG_32, "multicast_frames_sent", },
+	{ 0x304c, T_REG_32, "broadcast_frames_sent", },
+	{ 0x3054, T_REG_32, "fc_sent", },
+	{ 0x300c, T_REG_32, "internal_mac_transmit_err", },
+};
+
 struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
 	u64	rx_packets;
@@ -285,23 +334,34 @@ struct mvneta_pcpu_stats {
 	u64	tx_bytes;
 };
 
+struct mvneta_pcpu_port {
+	/* Pointer to the shared port */
+	struct mvneta_port	*pp;
+
+	/* Pointer to the CPU-local NAPI struct */
+	struct napi_struct	napi;
+
+	/* Cause of the previous interrupt */
+	u32			cause_rx_tx;
+};
+
 struct mvneta_port {
+	struct mvneta_pcpu_port __percpu	*ports;
+	struct mvneta_pcpu_stats __percpu	*stats;
+
 	int pkt_size;
 	unsigned int frag_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
 	struct mvneta_tx_queue *txqs;
 	struct net_device *dev;
-
-	u32 cause_rx_tx;
-	struct napi_struct napi;
+	struct notifier_block cpu_notifier;
 
 	/* Core clock */
 	struct clk *clk;
 	u8 mcast_count[256];
 	u16 tx_ring_size;
 	u16 rx_ring_size;
-	struct mvneta_pcpu_stats *stats;
 
 	struct mii_bus *mii_bus;
 	struct phy_device *phy_dev;
@@ -312,6 +372,8 @@ struct mvneta_port {
 	unsigned int speed;
 	unsigned int tx_csum_limit;
 	int use_inband_status:1;
+
+	u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -468,7 +530,7 @@ struct mvneta_rx_queue {
 /* The hardware supports eight (8) rx queues, but we are only allowing
  * the first one to be used. Therefore, let's just allocate one queue.
  */
-static int rxq_number = 1;
+static int rxq_number = 8;
 static int txq_number = 8;
 
 static int rxq_def;
@@ -518,6 +580,8 @@ static void mvneta_mib_counters_clear(struct mvneta_port *pp)
 	/* Perform dummy reads from MIB counters */
 	for (i = 0; i < MVNETA_MIB_LATE_COLLISION; i += 4)
 		dummy = mvreg_read(pp, (MVNETA_MIB_COUNTERS_BASE + i));
+	dummy = mvreg_read(pp, MVNETA_RX_DISCARD_FRAME_COUNT);
+	dummy = mvreg_read(pp, MVNETA_OVERRUN_FRAME_COUNT);
 }
 
 /* Get System Network Statistics */
@@ -746,7 +810,6 @@ static void mvneta_port_up(struct mvneta_port *pp)
 	u32 q_map;
 
 	/* Enable all initialized TXs. */
-	mvneta_mib_counters_clear(pp);
 	q_map = 0;
 	for (queue = 0; queue < txq_number; queue++) {
 		struct mvneta_tx_queue *txq = &pp->txqs[queue];
@@ -756,14 +819,7 @@ static void mvneta_port_up(struct mvneta_port *pp)
 	mvreg_write(pp, MVNETA_TXQ_CMD, q_map);
 
 	/* Enable all initialized RXQs. */
-	q_map = 0;
-	for (queue = 0; queue < rxq_number; queue++) {
-		struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
-		if (rxq->descs != NULL)
-			q_map |= (1 << queue);
-	}
-
-	mvreg_write(pp, MVNETA_RXQ_CMD, q_map);
+	mvreg_write(pp, MVNETA_RXQ_CMD, BIT(rxq_def));
 }
 
 /* Stop the Ethernet port activity */
@@ -1030,6 +1086,8 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 	mvreg_write(pp, MVNETA_INTR_ENABLE,
 		    (MVNETA_RXQ_INTR_ENABLE_ALL_MASK
 		     | MVNETA_TXQ_INTR_ENABLE_ALL_MASK));
+
+	mvneta_mib_counters_clear(pp);
 }
 
 /* Set max sizes for tx queues */
@@ -1426,17 +1484,6 @@ static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb)
 	return MVNETA_TX_L4_CSUM_NOT;
 }
 
-/* Returns rx queue pointer (find last set bit) according to causeRxTx
- * value
- */
-static struct mvneta_rx_queue *mvneta_rx_policy(struct mvneta_port *pp,
-						u32 cause)
-{
-	int queue = fls(cause >> 8) - 1;
-
-	return (queue < 0 || queue >= rxq_number) ? NULL : &pp->rxqs[queue];
-}
-
 /* Drop packets received by the RXQ and free buffers */
 static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 				 struct mvneta_rx_queue *rxq)
@@ -1448,9 +1495,9 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 		struct mvneta_rx_desc *rx_desc = rxq->descs + i;
 		void *data = (void *)rx_desc->buf_cookie;
 
-		mvneta_frag_free(pp, data);
 		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
+		mvneta_frag_free(pp, data);
 	}
 
 	if (rx_done)
@@ -1461,6 +1508,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		     struct mvneta_rx_queue *rxq)
 {
+	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 	struct net_device *dev = pp->dev;
 	int rx_done;
 	u32 rcvd_pkts = 0;
@@ -1515,7 +1563,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 
 			skb->protocol = eth_type_trans(skb, dev);
 			mvneta_rx_csum(pp, rx_status, skb);
-			napi_gro_receive(&pp->napi, skb);
+			napi_gro_receive(&port->napi, skb);
 
 			rcvd_pkts++;
 			rcvd_bytes += rx_bytes;
@@ -1554,7 +1602,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 
 		mvneta_rx_csum(pp, rx_status, skb);
 
-		napi_gro_receive(&pp->napi, skb);
+		napi_gro_receive(&port->napi, skb);
 	}
 
 	if (rcvd_pkts) {
@@ -2065,12 +2113,10 @@ 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;
-
-	/* Mask all interrupts */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+	struct mvneta_pcpu_port *port = (struct mvneta_pcpu_port *)dev_id;
 
-	napi_schedule(&pp->napi);
+	disable_percpu_irq(port->pp->dev->irq);
+	napi_schedule(&port->napi);
 
 	return IRQ_HANDLED;
 }
@@ -2108,11 +2154,11 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 {
 	int rx_done = 0;
 	u32 cause_rx_tx;
-	unsigned long flags;
 	struct mvneta_port *pp = netdev_priv(napi->dev);
+	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 
 	if (!netif_running(pp->dev)) {
-		napi_complete(napi);
+		napi_complete(&port->napi);
 		return rx_done;
 	}
 
@@ -2139,47 +2185,17 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
-	cause_rx_tx |= pp->cause_rx_tx;
-	if (rxq_number > 1) {
-		while ((cause_rx_tx & MVNETA_RX_INTR_MASK_ALL) && (budget > 0)) {
-			int count;
-			struct mvneta_rx_queue *rxq;
-			/* get rx queue number from cause_rx_tx */
-			rxq = mvneta_rx_policy(pp, cause_rx_tx);
-			if (!rxq)
-				break;
-
-			/* process the packet in that rx queue */
-			count = mvneta_rx(pp, budget, rxq);
-			rx_done += count;
-			budget -= count;
-			if (budget > 0) {
-				/* set off the rx bit of the
-				 * corresponding bit in the cause rx
-				 * tx register, so that next iteration
-				 * will find the next rx queue where
-				 * packets are received on
-				 */
-				cause_rx_tx &= ~((1 << rxq->id) << 8);
-			}
-		}
-	} else {
-		rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]);
-		budget -= rx_done;
-	}
+	cause_rx_tx |= port->cause_rx_tx;
+	rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]);
+	budget -= rx_done;
 
 	if (budget > 0) {
 		cause_rx_tx = 0;
-		napi_complete(napi);
-		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);
+		napi_complete(&port->napi);
+		enable_percpu_irq(pp->dev->irq, 0);
 	}
 
-	pp->cause_rx_tx = cause_rx_tx;
+	port->cause_rx_tx = cause_rx_tx;
 	return rx_done;
 }
 
@@ -2383,26 +2399,19 @@ static void mvneta_cleanup_txqs(struct mvneta_port *pp)
 /* Cleanup all Rx queues */
 static void mvneta_cleanup_rxqs(struct mvneta_port *pp)
 {
-	int queue;
-
-	for (queue = 0; queue < rxq_number; queue++)
-		mvneta_rxq_deinit(pp, &pp->rxqs[queue]);
+	mvneta_rxq_deinit(pp, &pp->rxqs[rxq_def]);
 }
 
 
 /* Init all Rx queues */
 static int mvneta_setup_rxqs(struct mvneta_port *pp)
 {
-	int queue;
-
-	for (queue = 0; queue < rxq_number; queue++) {
-		int err = mvneta_rxq_init(pp, &pp->rxqs[queue]);
-		if (err) {
-			netdev_err(pp->dev, "%s: can't create rxq=%d\n",
-				   __func__, queue);
-			mvneta_cleanup_rxqs(pp);
-			return err;
-		}
+	int err = mvneta_rxq_init(pp, &pp->rxqs[rxq_def]);
+	if (err) {
+		netdev_err(pp->dev, "%s: can't create rxq=%d\n",
+			   __func__, rxq_def);
+		mvneta_cleanup_rxqs(pp);
+		return err;
 	}
 
 	return 0;
@@ -2428,6 +2437,8 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
+	unsigned int cpu;
+
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
 
@@ -2435,7 +2446,11 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 	mvneta_port_enable(pp);
 
 	/* Enable polling on the port */
-	napi_enable(&pp->napi);
+	for_each_present_cpu(cpu) {
+		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+
+		napi_enable(&port->napi);
+	}
 
 	/* Unmask interrupts */
 	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
@@ -2453,9 +2468,15 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 static void mvneta_stop_dev(struct mvneta_port *pp)
 {
+	unsigned int cpu;
+
 	phy_stop(pp->phy_dev);
 
-	napi_disable(&pp->napi);
+	for_each_present_cpu(cpu) {
+		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+
+		napi_disable(&port->napi);
+	}
 
 	netif_carrier_off(pp->dev);
 
@@ -2695,6 +2716,125 @@ static void mvneta_mdio_remove(struct mvneta_port *pp)
 	pp->phy_dev = NULL;
 }
 
+static void mvneta_percpu_enable(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	enable_percpu_irq(pp->dev->irq, IRQ_TYPE_NONE);
+}
+
+static void mvneta_percpu_disable(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	disable_percpu_irq(pp->dev->irq);
+}
+
+static void mvneta_percpu_elect(struct mvneta_port *pp)
+{
+	int online_cpu_idx, cpu, i = 0;
+
+	online_cpu_idx = rxq_def % num_online_cpus();
+
+	for_each_online_cpu(cpu) {
+		if (i == online_cpu_idx)
+			/* Enable per-CPU interrupt on the one CPU we
+			 * just elected
+			 */
+			smp_call_function_single(cpu, mvneta_percpu_enable,
+						pp, true);
+		else
+			/* Disable per-CPU interrupt on all the other CPU */
+			smp_call_function_single(cpu, mvneta_percpu_disable,
+						pp, true);
+		i++;
+	}
+};
+
+static int mvneta_percpu_notifier(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
+{
+	struct mvneta_port *pp = container_of(nfb, struct mvneta_port,
+					      cpu_notifier);
+	int cpu = (unsigned long)hcpu, other_cpu;
+	struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		netif_tx_stop_all_queues(pp->dev);
+
+		/* We have to synchronise on tha napi of each CPU
+		 * except the one just being waked up
+		 */
+		for_each_online_cpu(other_cpu) {
+			if (other_cpu != cpu) {
+				struct mvneta_pcpu_port *other_port =
+					per_cpu_ptr(pp->ports, other_cpu);
+
+				napi_synchronize(&other_port->napi);
+			}
+		}
+
+		/* Mask all ethernet port interrupts */
+		mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+		mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+		napi_enable(&port->napi);
+
+		/* Enable per-CPU interrupt on the one CPU we care
+		 * about.
+		 */
+		mvneta_percpu_elect(pp);
+
+		/* Unmask all ethernet port interrupts */
+		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+			MVNETA_RX_INTR_MASK(rxq_number) |
+			MVNETA_TX_INTR_MASK(txq_number) |
+			MVNETA_MISCINTR_INTR_MASK);
+		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+			MVNETA_CAUSE_PHY_STATUS_CHANGE |
+			MVNETA_CAUSE_LINK_CHANGE |
+			MVNETA_CAUSE_PSC_SYNC_CHANGE);
+		netif_tx_start_all_queues(pp->dev);
+		break;
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		netif_tx_stop_all_queues(pp->dev);
+		/* Mask all ethernet port interrupts */
+		mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+		mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+
+		napi_synchronize(&port->napi);
+		napi_disable(&port->napi);
+		/* Disable per-CPU interrupts on the CPU that is
+		 * brought down.
+		 */
+		smp_call_function_single(cpu, mvneta_percpu_disable,
+					 pp, true);
+
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		/* Check if a new CPU must be elected now this on is down */
+		mvneta_percpu_elect(pp);
+		/* Unmask all ethernet port interrupts */
+		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+			MVNETA_RX_INTR_MASK(rxq_number) |
+			MVNETA_TX_INTR_MASK(txq_number) |
+			MVNETA_MISCINTR_INTR_MASK);
+		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+			MVNETA_CAUSE_PHY_STATUS_CHANGE |
+			MVNETA_CAUSE_LINK_CHANGE |
+			MVNETA_CAUSE_PSC_SYNC_CHANGE);
+		netif_tx_start_all_queues(pp->dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
 static int mvneta_open(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
@@ -2713,13 +2853,29 @@ static int mvneta_open(struct net_device *dev)
 		goto err_cleanup_rxqs;
 
 	/* Connect to port interrupt line */
-	ret = request_irq(pp->dev->irq, mvneta_isr, 0,
-			  MVNETA_DRIVER_NAME, pp);
+	ret = request_percpu_irq(pp->dev->irq, mvneta_isr,
+				 MVNETA_DRIVER_NAME, pp->ports);
 	if (ret) {
 		netdev_err(pp->dev, "cannot request irq %d\n", pp->dev->irq);
 		goto err_cleanup_txqs;
 	}
 
+	/* Even though the documentation says that request_percpu_irq
+	 * doesn't enable the interrupts automatically, it actually
+	 * does so on the local CPU.
+	 *
+	 * Make sure it's disabled.
+	 */
+	mvneta_percpu_disable(pp);
+
+	/* Elect a CPU to handle our RX queue interrupt */
+	mvneta_percpu_elect(pp);
+
+	/* Register a CPU notifier to handle the case where our CPU
+	 * might be taken offline.
+	 */
+	register_cpu_notifier(&pp->cpu_notifier);
+
 	/* In default link is down */
 	netif_carrier_off(pp->dev);
 
@@ -2734,7 +2890,7 @@ static int mvneta_open(struct net_device *dev)
 	return 0;
 
 err_free_irq:
-	free_irq(pp->dev->irq, pp);
+	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);
 err_cleanup_rxqs:
@@ -2746,10 +2902,14 @@ err_cleanup_rxqs:
 static int mvneta_stop(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
+	int cpu;
 
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
-	free_irq(dev->irq, pp);
+	unregister_cpu_notifier(&pp->cpu_notifier);
+	for_each_present_cpu(cpu)
+		smp_call_function_single(cpu, mvneta_percpu_disable, pp, true);
+	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
 
@@ -2879,6 +3039,65 @@ static int mvneta_ethtool_set_ringparam(struct net_device *dev,
 	return 0;
 }
 
+static void mvneta_ethtool_get_strings(struct net_device *netdev, u32 sset,
+				       u8 *data)
+{
+	if (sset == ETH_SS_STATS) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++)
+			memcpy(data + i * ETH_GSTRING_LEN,
+			       mvneta_statistics[i].name, ETH_GSTRING_LEN);
+	}
+}
+
+static void mvneta_ethtool_update_stats(struct mvneta_port *pp)
+{
+	const struct mvneta_statistic *s;
+	void __iomem *base = pp->base;
+	u32 high, low, val;
+	int i;
+
+	for (i = 0, s = mvneta_statistics;
+	     s < mvneta_statistics + ARRAY_SIZE(mvneta_statistics);
+	     s++, i++) {
+		val = 0;
+
+		switch (s->type) {
+		case T_REG_32:
+			val = readl_relaxed(base + s->offset);
+			break;
+		case T_REG_64:
+			/* Docs say to read low 32-bit then high */
+			low = readl_relaxed(base + s->offset);
+			high = readl_relaxed(base + s->offset + 4);
+			val = (u64)high << 32 | low;
+			break;
+		}
+
+		pp->ethtool_stats[i] += val;
+	}
+}
+
+static void mvneta_ethtool_get_stats(struct net_device *dev,
+				     struct ethtool_stats *stats, u64 *data)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+	int i;
+
+	mvneta_ethtool_update_stats(pp);
+
+	for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++)
+		*data++ = pp->ethtool_stats[i];
+}
+
+static int mvneta_ethtool_get_sset_count(struct net_device *dev, int sset)
+{
+	if (sset == ETH_SS_STATS)
+		return ARRAY_SIZE(mvneta_statistics);
+	return -EOPNOTSUPP;
+}
+
 static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_open            = mvneta_open,
 	.ndo_stop            = mvneta_stop,
@@ -2900,6 +3119,9 @@ const struct ethtool_ops mvneta_eth_tool_ops = {
 	.get_drvinfo    = mvneta_ethtool_get_drvinfo,
 	.get_ringparam  = mvneta_ethtool_get_ringparam,
 	.set_ringparam	= mvneta_ethtool_set_ringparam,
+	.get_strings	= mvneta_ethtool_get_strings,
+	.get_ethtool_stats = mvneta_ethtool_get_stats,
+	.get_sset_count	= mvneta_ethtool_get_sset_count,
 };
 
 /* Initialize hw */
@@ -2975,6 +3197,7 @@ static void mvneta_conf_mbus_windows(struct mvneta_port *pp,
 	}
 
 	mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);
+	mvreg_write(pp, MVNETA_ACCESS_PROTECT_ENABLE, win_protect);
 }
 
 /* Power up the port */
@@ -3034,16 +3257,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	char hw_mac_addr[ETH_ALEN];
 	const char *mac_from;
 	const char *managed;
+	int tx_csum_limit;
 	int phy_mode;
 	int err;
-
-	/* Our multiqueue support is not complete, so for now, only
-	 * allow the usage of the first RX queue
-	 */
-	if (rxq_def != 0) {
-		dev_err(&pdev->dev, "Invalid rxq_def argument: %d\n", rxq_def);
-		return -EINVAL;
-	}
+	int cpu;
 
 	dev = alloc_etherdev_mqs(sizeof(struct mvneta_port), txq_number, rxq_number);
 	if (!dev)
@@ -3095,6 +3312,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = of_property_read_string(dn, "managed", &managed);
 	pp->use_inband_status = (err == 0 &&
 				 strcmp(managed, "in-band-status") == 0);
+	pp->cpu_notifier.notifier_call = mvneta_percpu_notifier;
 
 	pp->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pp->clk)) {
@@ -3111,11 +3329,18 @@ static int mvneta_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 
+	/* Alloc per-cpu port structure */
+	pp->ports = alloc_percpu(struct mvneta_pcpu_port);
+	if (!pp->ports) {
+		err = -ENOMEM;
+		goto err_clk;
+	}
+
 	/* Alloc per-cpu stats */
 	pp->stats = netdev_alloc_pcpu_stats(struct mvneta_pcpu_stats);
 	if (!pp->stats) {
 		err = -ENOMEM;
-		goto err_clk;
+		goto err_free_ports;
 	}
 
 	dt_mac_addr = of_get_mac_address(dn);
@@ -3133,8 +3358,21 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
-		pp->tx_csum_limit = 1600;
+	if (!of_property_read_u32(dn, "tx-csum-limit", &tx_csum_limit)) {
+		if (tx_csum_limit < 0 ||
+		    tx_csum_limit > MVNETA_TX_CSUM_MAX_SIZE) {
+			tx_csum_limit = MVNETA_TX_CSUM_DEF_SIZE;
+			dev_info(&pdev->dev,
+				 "Wrong TX csum limit in DT, set to %dB\n",
+				 MVNETA_TX_CSUM_DEF_SIZE);
+		}
+	} else if (of_device_is_compatible(dn, "marvell,armada-370-neta")) {
+		tx_csum_limit = MVNETA_TX_CSUM_DEF_SIZE;
+	} else {
+		tx_csum_limit = MVNETA_TX_CSUM_MAX_SIZE;
+	}
+
+	pp->tx_csum_limit = tx_csum_limit;
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -3156,7 +3394,12 @@ static int mvneta_probe(struct platform_device *pdev)
 	if (dram_target_info)
 		mvneta_conf_mbus_windows(pp, dram_target_info);
 
-	netif_napi_add(dev, &pp->napi, mvneta_poll, NAPI_POLL_WEIGHT);
+	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;
+	}
 
 	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 	dev->hw_features |= dev->features;
@@ -3187,6 +3430,8 @@ static int mvneta_probe(struct platform_device *pdev)
 
 err_free_stats:
 	free_percpu(pp->stats);
+err_free_ports:
+	free_percpu(pp->ports);
 err_clk:
 	clk_disable_unprepare(pp->clk);
 err_put_phy_node:
@@ -3206,6 +3451,7 @@ static int mvneta_remove(struct platform_device *pdev)
 
 	unregister_netdev(dev);
 	clk_disable_unprepare(pp->clk);
+	free_percpu(pp->ports);
 	free_percpu(pp->stats);
 	irq_dispose_mapping(dev->irq);
 	of_node_put(pp->phy_node);
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index d9884fd15..a4beccf1f 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -3413,16 +3413,23 @@ static void mvpp2_bm_pool_bufsize_set(struct mvpp2 *priv,
 }
 
 /* Free all buffers from the pool */
-static void mvpp2_bm_bufs_free(struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool)
+static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv,
+			       struct mvpp2_bm_pool *bm_pool)
 {
 	int i;
 
 	for (i = 0; i < bm_pool->buf_num; i++) {
+		dma_addr_t buf_phys_addr;
 		u32 vaddr;
 
 		/* Get buffer virtual address (indirect access) */
-		mvpp2_read(priv, MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
+		buf_phys_addr = mvpp2_read(priv,
+					   MVPP2_BM_PHY_ALLOC_REG(bm_pool->id));
 		vaddr = mvpp2_read(priv, MVPP2_BM_VIRT_ALLOC_REG);
+
+		dma_unmap_single(dev, buf_phys_addr,
+				 bm_pool->buf_size, DMA_FROM_DEVICE);
+
 		if (!vaddr)
 			break;
 		dev_kfree_skb_any((struct sk_buff *)vaddr);
@@ -3439,7 +3446,7 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev,
 {
 	u32 val;
 
-	mvpp2_bm_bufs_free(priv, bm_pool);
+	mvpp2_bm_bufs_free(&pdev->dev, priv, bm_pool);
 	if (bm_pool->buf_num) {
 		WARN(1, "cannot free all buffers in pool %d\n", bm_pool->id);
 		return 0;
@@ -3692,7 +3699,8 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type,
 				   MVPP2_BM_LONG_BUF_NUM :
 				   MVPP2_BM_SHORT_BUF_NUM;
 		else
-			mvpp2_bm_bufs_free(port->priv, new_pool);
+			mvpp2_bm_bufs_free(port->dev->dev.parent,
+					   port->priv, new_pool);
 
 		new_pool->pkt_size = pkt_size;
 
@@ -3756,7 +3764,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu)
 	int pkt_size = MVPP2_RX_PKT_SIZE(mtu);
 
 	/* Update BM pool with new buffer size */
-	mvpp2_bm_bufs_free(port->priv, port_pool);
+	mvpp2_bm_bufs_free(dev->dev.parent, port->priv, port_pool);
 	if (port_pool->buf_num) {
 		WARN(1, "cannot free all buffers in pool %d\n", port_pool->id);
 		return -EIO;
@@ -4401,11 +4409,10 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 
 		mvpp2_txq_inc_get(txq_pcpu);
 
-		if (!skb)
-			continue;
-
 		dma_unmap_single(port->dev->dev.parent, buf_phys_addr,
 				 skb_headlen(skb), DMA_TO_DEVICE);
+		if (!skb)
+			continue;
 		dev_kfree_skb_any(skb);
 	}
 }
@@ -5092,7 +5099,8 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		    struct mvpp2_rx_queue *rxq)
 {
 	struct net_device *dev = port->dev;
-	int rx_received, rx_filled, i;
+	int rx_received;
+	int rx_done = 0;
 	u32 rcvd_pkts = 0;
 	u32 rcvd_bytes = 0;
 
@@ -5101,17 +5109,18 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 	if (rx_todo > rx_received)
 		rx_todo = rx_received;
 
-	rx_filled = 0;
-	for (i = 0; i < rx_todo; i++) {
+	while (rx_done < rx_todo) {
 		struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
 		struct mvpp2_bm_pool *bm_pool;
 		struct sk_buff *skb;
+		dma_addr_t phys_addr;
 		u32 bm, rx_status;
 		int pool, rx_bytes, err;
 
-		rx_filled++;
+		rx_done++;
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - MVPP2_MH_SIZE;
+		phys_addr = rx_desc->buf_phys_addr;
 
 		bm = mvpp2_bm_cookie_build(rx_desc);
 		pool = mvpp2_bm_cookie_pool_get(bm);
@@ -5128,8 +5137,10 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		 * comprised by the RX descriptor.
 		 */
 		if (rx_status & MVPP2_RXD_ERR_SUMMARY) {
+		err_drop_frame:
 			dev->stats.rx_errors++;
 			mvpp2_rx_error(port, rx_desc);
+			/* Return the buffer to the pool */
 			mvpp2_pool_refill(port, bm, rx_desc->buf_phys_addr,
 					  rx_desc->buf_cookie);
 			continue;
@@ -5137,6 +5148,15 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 
 		skb = (struct sk_buff *)rx_desc->buf_cookie;
 
+		err = mvpp2_rx_refill(port, bm_pool, bm, 0);
+		if (err) {
+			netdev_err(port->dev, "failed to refill BM pools\n");
+			goto err_drop_frame;
+		}
+
+		dma_unmap_single(dev->dev.parent, phys_addr,
+				 bm_pool->buf_size, DMA_FROM_DEVICE);
+
 		rcvd_pkts++;
 		rcvd_bytes += rx_bytes;
 		atomic_inc(&bm_pool->in_use);
@@ -5147,12 +5167,6 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 		mvpp2_rx_csum(port, rx_status, skb);
 
 		napi_gro_receive(&port->napi, skb);
-
-		err = mvpp2_rx_refill(port, bm_pool, bm, 0);
-		if (err) {
-			netdev_err(port->dev, "failed to refill BM pools\n");
-			rx_filled--;
-		}
 	}
 
 	if (rcvd_pkts) {
@@ -5166,7 +5180,7 @@ static int mvpp2_rx(struct mvpp2_port *port, int rx_todo,
 
 	/* Update Rx queue management counters */
 	wmb();
-	mvpp2_rxq_status_update(port, rxq->id, rx_todo, rx_filled);
+	mvpp2_rxq_status_update(port, rxq->id, rx_done, rx_done);
 
 	return rx_todo;
 }
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index d9f449883..5606a0430 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4819,6 +4819,18 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port,
 		memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8,
 			      ETH_ALEN);
 
+	/* if the address is invalid, use a random value */
+	if (!is_valid_ether_addr(dev->dev_addr)) {
+		struct sockaddr sa = { AF_UNSPEC };
+
+		netdev_warn(dev,
+			    "Invalid MAC address, defaulting to random\n");
+		eth_hw_addr_random(dev);
+		memcpy(sa.sa_data, dev->dev_addr, ETH_ALEN);
+		if (sky2_set_mac_address(dev, &sa))
+			netdev_warn(dev, "Failed to set MAC address.\n");
+	}
+
 	return dev;
 }