Merge branch 'next' into for-linus

Prepare first round of input updates for 3.20.

8 files changed, 1030 insertions, 252 deletions

diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 37f87ff28f03..3dc1f68b322d 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4962,7 +4962,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_cmd |= PCI_COMMAND_PARITY;
 	pci_write_config_word(pdev, PCI_COMMAND, pci_cmd);
 	if (pci_try_set_mwi(pdev))
-		pr_warning("Could not enable MWI for %s\n", pci_name(pdev));
+		pr_warn("Could not enable MWI for %s\n", pci_name(pdev));
 
 	cas_program_bridge(pdev);
 
@@ -5179,8 +5179,7 @@ static void cas_remove_one(struct pci_dev *pdev)
 	cp = netdev_priv(dev);
 	unregister_netdev(dev);
 
-	if (cp->fw_data)
-		vfree(cp->fw_data);
+	vfree(cp->fw_data);
 
 	mutex_lock(&cp->pm_mutex);
 	cancel_work_sync(&cp->reset_task);
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 8216be46540f..0c6416213837 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6651,13 +6651,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
-	if (skb->len < ETH_ZLEN) {
-		unsigned int pad_bytes = ETH_ZLEN - skb->len;
-
-		if (skb_pad(skb, pad_bytes))
-			goto out;
-		skb_put(skb, pad_bytes);
-	}
+	if (eth_skb_pad(skb))
+		goto out;
 
 	len = sizeof(struct tx_pkt_hdr) + 15;
 	if (skb_headroom(skb) < len) {
@@ -8717,8 +8712,8 @@ static void niu_divide_channels(struct niu_parent *parent,
 			parent->txchan_per_port[i] = 1;
 	}
 	if (tot_rx < NIU_NUM_RXCHAN || tot_tx < NIU_NUM_TXCHAN) {
-		pr_warning("niu%d: Driver bug, wasted channels, RX[%d] TX[%d]\n",
-			   parent->index, tot_rx, tot_tx);
+		pr_warn("niu%d: Driver bug, wasted channels, RX[%d] TX[%d]\n",
+			parent->index, tot_rx, tot_tx);
 	}
 }
 
@@ -10185,7 +10180,6 @@ MODULE_DEVICE_TABLE(of, niu_match);
 static struct platform_driver niu_of_driver = {
 	.driver = {
 		.name = "niu",
-		.owner = THIS_MODULE,
 		.of_match_table = niu_match,
 	},
 	.probe		= niu_of_probe,
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 206c1063815a..aa4f9d2d8fa9 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -1273,7 +1273,6 @@ MODULE_DEVICE_TABLE(of, bigmac_sbus_match);
 static struct platform_driver bigmac_sbus_driver = {
 	.driver = {
 		.name = "sunbmac",
-		.owner = THIS_MODULE,
 		.of_match_table = bigmac_sbus_match,
 	},
 	.probe		= bigmac_sbus_probe,
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index f7415b6bf141..fef5dec2cffe 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -115,7 +115,7 @@ static const struct pci_device_id gem_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, gem_pci_tbl);
 
-static u16 __phy_read(struct gem *gp, int phy_addr, int reg)
+static u16 __sungem_phy_read(struct gem *gp, int phy_addr, int reg)
 {
 	u32 cmd;
 	int limit = 10000;
@@ -141,18 +141,18 @@ static u16 __phy_read(struct gem *gp, int phy_addr, int reg)
 	return cmd & MIF_FRAME_DATA;
 }
 
-static inline int _phy_read(struct net_device *dev, int mii_id, int reg)
+static inline int _sungem_phy_read(struct net_device *dev, int mii_id, int reg)
 {
 	struct gem *gp = netdev_priv(dev);
-	return __phy_read(gp, mii_id, reg);
+	return __sungem_phy_read(gp, mii_id, reg);
 }
 
-static inline u16 phy_read(struct gem *gp, int reg)
+static inline u16 sungem_phy_read(struct gem *gp, int reg)
 {
-	return __phy_read(gp, gp->mii_phy_addr, reg);
+	return __sungem_phy_read(gp, gp->mii_phy_addr, reg);
 }
 
-static void __phy_write(struct gem *gp, int phy_addr, int reg, u16 val)
+static void __sungem_phy_write(struct gem *gp, int phy_addr, int reg, u16 val)
 {
 	u32 cmd;
 	int limit = 10000;
@@ -174,15 +174,15 @@ static void __phy_write(struct gem *gp, int phy_addr, int reg, u16 val)
 	}
 }
 
-static inline void _phy_write(struct net_device *dev, int mii_id, int reg, int val)
+static inline void _sungem_phy_write(struct net_device *dev, int mii_id, int reg, int val)
 {
 	struct gem *gp = netdev_priv(dev);
-	__phy_write(gp, mii_id, reg, val & 0xffff);
+	__sungem_phy_write(gp, mii_id, reg, val & 0xffff);
 }
 
-static inline void phy_write(struct gem *gp, int reg, u16 val)
+static inline void sungem_phy_write(struct gem *gp, int reg, u16 val)
 {
-	__phy_write(gp, gp->mii_phy_addr, reg, val);
+	__sungem_phy_write(gp, gp->mii_phy_addr, reg, val);
 }
 
 static inline void gem_enable_ints(struct gem *gp)
@@ -1687,9 +1687,9 @@ static void gem_init_phy(struct gem *gp)
 			/* Some PHYs used by apple have problem getting back to us,
 			 * we do an additional reset here
 			 */
-			phy_write(gp, MII_BMCR, BMCR_RESET);
+			sungem_phy_write(gp, MII_BMCR, BMCR_RESET);
 			msleep(20);
-			if (phy_read(gp, MII_BMCR) != 0xffff)
+			if (sungem_phy_read(gp, MII_BMCR) != 0xffff)
 				break;
 			if (i == 2)
 				netdev_warn(gp->dev, "GMAC PHY not responding !\n");
@@ -2012,7 +2012,7 @@ static int gem_check_invariants(struct gem *gp)
 
 		for (i = 0; i < 32; i++) {
 			gp->mii_phy_addr = i;
-			if (phy_read(gp, MII_BMCR) != 0xffff)
+			if (sungem_phy_read(gp, MII_BMCR) != 0xffff)
 				break;
 		}
 		if (i == 32) {
@@ -2696,13 +2696,13 @@ static int gem_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		/* Fallthrough... */
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
-		data->val_out = __phy_read(gp, data->phy_id & 0x1f,
+		data->val_out = __sungem_phy_read(gp, data->phy_id & 0x1f,
 					   data->reg_num & 0x1f);
 		rc = 0;
 		break;
 
 	case SIOCSMIIREG:		/* Write MII PHY register. */
-		__phy_write(gp, data->phy_id & 0x1f, data->reg_num & 0x1f,
+		__sungem_phy_write(gp, data->phy_id & 0x1f, data->reg_num & 0x1f,
 			    data->val_in);
 		rc = 0;
 		break;
@@ -2933,8 +2933,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Fill up the mii_phy structure (even if we won't use it) */
 	gp->phy_mii.dev = dev;
-	gp->phy_mii.mdio_read = _phy_read;
-	gp->phy_mii.mdio_write = _phy_write;
+	gp->phy_mii.mdio_read = _sungem_phy_read;
+	gp->phy_mii.mdio_write = _sungem_phy_write;
 #ifdef CONFIG_PPC_PMAC
 	gp->phy_mii.platform_data = gp->of_node;
 #endif
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 72c8525d5457..7a8ca2c7b7df 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -1262,6 +1262,7 @@ static void happy_meal_init_rings(struct happy_meal *hp)
 	HMD(("init rxring, "));
 	for (i = 0; i < RX_RING_SIZE; i++) {
 		struct sk_buff *skb;
+		u32 mapping;
 
 		skb = happy_meal_alloc_skb(RX_BUF_ALLOC_SIZE, GFP_ATOMIC);
 		if (!skb) {
@@ -1272,10 +1273,16 @@ static void happy_meal_init_rings(struct happy_meal *hp)
 
 		/* Because we reserve afterwards. */
 		skb_put(skb, (ETH_FRAME_LEN + RX_OFFSET + 4));
+		mapping = dma_map_single(hp->dma_dev, skb->data, RX_BUF_ALLOC_SIZE,
+					 DMA_FROM_DEVICE);
+		if (dma_mapping_error(hp->dma_dev, mapping)) {
+			dev_kfree_skb_any(skb);
+			hme_write_rxd(hp, &hb->happy_meal_rxd[i], 0, 0);
+			continue;
+		}
 		hme_write_rxd(hp, &hb->happy_meal_rxd[i],
 			      (RXFLAG_OWN | ((RX_BUF_ALLOC_SIZE - RX_OFFSET) << 16)),
-			      dma_map_single(hp->dma_dev, skb->data, RX_BUF_ALLOC_SIZE,
-					     DMA_FROM_DEVICE));
+			      mapping);
 		skb_reserve(skb, RX_OFFSET);
 	}
 
@@ -2020,6 +2027,7 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
 		skb = hp->rx_skbs[elem];
 		if (len > RX_COPY_THRESHOLD) {
 			struct sk_buff *new_skb;
+			u32 mapping;
 
 			/* Now refill the entry, if we can. */
 			new_skb = happy_meal_alloc_skb(RX_BUF_ALLOC_SIZE, GFP_ATOMIC);
@@ -2027,13 +2035,21 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
 				drops++;
 				goto drop_it;
 			}
+			skb_put(new_skb, (ETH_FRAME_LEN + RX_OFFSET + 4));
+			mapping = dma_map_single(hp->dma_dev, new_skb->data,
+						 RX_BUF_ALLOC_SIZE,
+						 DMA_FROM_DEVICE);
+			if (unlikely(dma_mapping_error(hp->dma_dev, mapping))) {
+				dev_kfree_skb_any(new_skb);
+				drops++;
+				goto drop_it;
+			}
+
 			dma_unmap_single(hp->dma_dev, dma_addr, RX_BUF_ALLOC_SIZE, DMA_FROM_DEVICE);
 			hp->rx_skbs[elem] = new_skb;
-			skb_put(new_skb, (ETH_FRAME_LEN + RX_OFFSET + 4));
 			hme_write_rxd(hp, this,
 				      (RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)),
-				      dma_map_single(hp->dma_dev, new_skb->data, RX_BUF_ALLOC_SIZE,
-						     DMA_FROM_DEVICE));
+				      mapping);
 			skb_reserve(new_skb, RX_OFFSET);
 
 			/* Trim the original skb for the netif. */
@@ -2248,6 +2264,25 @@ static void happy_meal_tx_timeout(struct net_device *dev)
 	netif_wake_queue(dev);
 }
 
+static void unmap_partial_tx_skb(struct happy_meal *hp, u32 first_mapping,
+				 u32 first_len, u32 first_entry, u32 entry)
+{
+	struct happy_meal_txd *txbase = &hp->happy_block->happy_meal_txd[0];
+
+	dma_unmap_single(hp->dma_dev, first_mapping, first_len, DMA_TO_DEVICE);
+
+	first_entry = NEXT_TX(first_entry);
+	while (first_entry != entry) {
+		struct happy_meal_txd *this = &txbase[first_entry];
+		u32 addr, len;
+
+		addr = hme_read_desc32(hp, &this->tx_addr);
+		len = hme_read_desc32(hp, &this->tx_flags);
+		len &= TXFLAG_SIZE;
+		dma_unmap_page(hp->dma_dev, addr, len, DMA_TO_DEVICE);
+	}
+}
+
 static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
@@ -2284,6 +2319,8 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 
 		len = skb->len;
 		mapping = dma_map_single(hp->dma_dev, skb->data, len, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(hp->dma_dev, mapping)))
+			goto out_dma_error;
 		tx_flags |= (TXFLAG_SOP | TXFLAG_EOP);
 		hme_write_txd(hp, &hp->happy_block->happy_meal_txd[entry],
 			      (tx_flags | (len & TXFLAG_SIZE)),
@@ -2299,6 +2336,8 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 		first_len = skb_headlen(skb);
 		first_mapping = dma_map_single(hp->dma_dev, skb->data, first_len,
 					       DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(hp->dma_dev, first_mapping)))
+			goto out_dma_error;
 		entry = NEXT_TX(entry);
 
 		for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) {
@@ -2308,6 +2347,11 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 			len = skb_frag_size(this_frag);
 			mapping = skb_frag_dma_map(hp->dma_dev, this_frag,
 						   0, len, DMA_TO_DEVICE);
+			if (unlikely(dma_mapping_error(hp->dma_dev, mapping))) {
+				unmap_partial_tx_skb(hp, first_mapping, first_len,
+						     first_entry, entry);
+				goto out_dma_error;
+			}
 			this_txflags = tx_flags;
 			if (frag == skb_shinfo(skb)->nr_frags - 1)
 				this_txflags |= TXFLAG_EOP;
@@ -2333,6 +2377,14 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb,
 
 	tx_add_log(hp, TXLOG_ACTION_TXMIT, 0);
 	return NETDEV_TX_OK;
+
+out_dma_error:
+	hp->tx_skbs[hp->tx_new] = NULL;
+	spin_unlock_irq(&hp->happy_lock);
+
+	dev_kfree_skb_any(skb);
+	dev->stats.tx_dropped++;
+	return NETDEV_TX_OK;
 }
 
 static struct net_device_stats *happy_meal_get_stats(struct net_device *dev)
@@ -3271,7 +3323,6 @@ MODULE_DEVICE_TABLE(of, hme_sbus_match);
 static struct platform_driver hme_sbus_driver = {
 	.driver = {
 		.name = "hme",
-		.owner = THIS_MODULE,
 		.of_match_table = hme_sbus_match,
 	},
 	.probe		= hme_sbus_probe,
diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c
index 5695ae2411de..9b825780b3be 100644
--- a/drivers/net/ethernet/sun/sunqe.c
+++ b/drivers/net/ethernet/sun/sunqe.c
@@ -963,7 +963,6 @@ MODULE_DEVICE_TABLE(of, qec_sbus_match);
 static struct platform_driver qec_sbus_driver = {
 	.driver = {
 		.name = "qec",
-		.owner = THIS_MODULE,
 		.of_match_table = qec_sbus_match,
 	},
 	.probe		= qec_sbus_probe,
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index f67539650c38..d2835bf7b4fb 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -15,6 +15,16 @@
 #include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/mutex.h>
+#include <linux/highmem.h>
+#include <linux/if_vlan.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/icmpv6.h>
+#endif
+
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/route.h>
 
 #include <asm/vio.h>
 #include <asm/ldc.h>
@@ -32,13 +42,20 @@ MODULE_DESCRIPTION("Sun LDOM virtual network driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);
 
+#define	VNET_MAX_TXQS		16
+
 /* Heuristic for the number of times to exponentially backoff and
  * retry sending an LDC trigger when EAGAIN is encountered
  */
 #define	VNET_MAX_RETRIES	10
 
+static int __vnet_tx_trigger(struct vnet_port *port, u32 start);
+
 /* Ordered from largest major to lowest */
 static struct vio_version vnet_versions[] = {
+	{ .major = 1, .minor = 8 },
+	{ .major = 1, .minor = 7 },
+	{ .major = 1, .minor = 6 },
 	{ .major = 1, .minor = 0 },
 };
 
@@ -60,31 +77,67 @@ static int vnet_handle_unknown(struct vnet_port *port, void *arg)
 	return -ECONNRESET;
 }
 
+static int vnet_port_alloc_tx_ring(struct vnet_port *port);
+
 static int vnet_send_attr(struct vio_driver_state *vio)
 {
 	struct vnet_port *port = to_vnet_port(vio);
 	struct net_device *dev = port->vp->dev;
 	struct vio_net_attr_info pkt;
-	int i;
+	int framelen = ETH_FRAME_LEN;
+	int i, err;
+
+	err = vnet_port_alloc_tx_ring(to_vnet_port(vio));
+	if (err)
+		return err;
 
 	memset(&pkt, 0, sizeof(pkt));
 	pkt.tag.type = VIO_TYPE_CTRL;
 	pkt.tag.stype = VIO_SUBTYPE_INFO;
 	pkt.tag.stype_env = VIO_ATTR_INFO;
 	pkt.tag.sid = vio_send_sid(vio);
-	pkt.xfer_mode = VIO_DRING_MODE;
+	if (vio_version_before(vio, 1, 2))
+		pkt.xfer_mode = VIO_DRING_MODE;
+	else
+		pkt.xfer_mode = VIO_NEW_DRING_MODE;
 	pkt.addr_type = VNET_ADDR_ETHERMAC;
 	pkt.ack_freq = 0;
 	for (i = 0; i < 6; i++)
 		pkt.addr |= (u64)dev->dev_addr[i] << ((5 - i) * 8);
-	pkt.mtu = ETH_FRAME_LEN;
+	if (vio_version_after(vio, 1, 3)) {
+		if (port->rmtu) {
+			port->rmtu = min(VNET_MAXPACKET, port->rmtu);
+			pkt.mtu = port->rmtu;
+		} else {
+			port->rmtu = VNET_MAXPACKET;
+			pkt.mtu = port->rmtu;
+		}
+		if (vio_version_after_eq(vio, 1, 6))
+			pkt.options = VIO_TX_DRING;
+	} else if (vio_version_before(vio, 1, 3)) {
+		pkt.mtu = framelen;
+	} else { /* v1.3 */
+		pkt.mtu = framelen + VLAN_HLEN;
+	}
+
+	pkt.cflags = 0;
+	if (vio_version_after_eq(vio, 1, 7) && port->tso) {
+		pkt.cflags |= VNET_LSO_IPV4_CAPAB;
+		if (!port->tsolen)
+			port->tsolen = VNET_MAXTSO;
+		pkt.ipv4_lso_maxlen = port->tsolen;
+	}
+
+	pkt.plnk_updt = PHYSLINK_UPDATE_NONE;
 
 	viodbg(HS, "SEND NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] "
-	       "ackfreq[%u] mtu[%llu]\n",
+	       "ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] mtu[%llu] "
+	       "cflags[0x%04x] lso_max[%u]\n",
 	       pkt.xfer_mode, pkt.addr_type,
-	       (unsigned long long) pkt.addr,
-	       pkt.ack_freq,
-	       (unsigned long long) pkt.mtu);
+	       (unsigned long long)pkt.addr,
+	       pkt.ack_freq, pkt.plnk_updt, pkt.options,
+	       (unsigned long long)pkt.mtu, pkt.cflags, pkt.ipv4_lso_maxlen);
+
 
 	return vio_ldc_send(vio, &pkt, sizeof(pkt));
 }
@@ -92,18 +145,72 @@ static int vnet_send_attr(struct vio_driver_state *vio)
 static int handle_attr_info(struct vio_driver_state *vio,
 			    struct vio_net_attr_info *pkt)
 {
-	viodbg(HS, "GOT NET ATTR INFO xmode[0x%x] atype[0x%x] addr[%llx] "
-	       "ackfreq[%u] mtu[%llu]\n",
+	struct vnet_port *port = to_vnet_port(vio);
+	u64	localmtu;
+	u8	xfer_mode;
+
+	viodbg(HS, "GOT NET ATTR xmode[0x%x] atype[0x%x] addr[%llx] "
+	       "ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] mtu[%llu] "
+	       " (rmtu[%llu]) cflags[0x%04x] lso_max[%u]\n",
 	       pkt->xfer_mode, pkt->addr_type,
-	       (unsigned long long) pkt->addr,
-	       pkt->ack_freq,
-	       (unsigned long long) pkt->mtu);
+	       (unsigned long long)pkt->addr,
+	       pkt->ack_freq, pkt->plnk_updt, pkt->options,
+	       (unsigned long long)pkt->mtu, port->rmtu, pkt->cflags,
+	       pkt->ipv4_lso_maxlen);
 
 	pkt->tag.sid = vio_send_sid(vio);
 
-	if (pkt->xfer_mode != VIO_DRING_MODE ||
+	xfer_mode = pkt->xfer_mode;
+	/* for version < 1.2, VIO_DRING_MODE = 0x3 and no bitmask */
+	if (vio_version_before(vio, 1, 2) && xfer_mode == VIO_DRING_MODE)
+		xfer_mode = VIO_NEW_DRING_MODE;
+
+	/* MTU negotiation:
+	 *	< v1.3 - ETH_FRAME_LEN exactly
+	 *	> v1.3 - MIN(pkt.mtu, VNET_MAXPACKET, port->rmtu) and change
+	 *			pkt->mtu for ACK
+	 *	= v1.3 - ETH_FRAME_LEN + VLAN_HLEN exactly
+	 */
+	if (vio_version_before(vio, 1, 3)) {
+		localmtu = ETH_FRAME_LEN;
+	} else if (vio_version_after(vio, 1, 3)) {
+		localmtu = port->rmtu ? port->rmtu : VNET_MAXPACKET;
+		localmtu = min(pkt->mtu, localmtu);
+		pkt->mtu = localmtu;
+	} else { /* v1.3 */
+		localmtu = ETH_FRAME_LEN + VLAN_HLEN;
+	}
+	port->rmtu = localmtu;
+
+	/* LSO negotiation */
+	if (vio_version_after_eq(vio, 1, 7))
+		port->tso &= !!(pkt->cflags & VNET_LSO_IPV4_CAPAB);
+	else
+		port->tso = false;
+	if (port->tso) {
+		if (!port->tsolen)
+			port->tsolen = VNET_MAXTSO;
+		port->tsolen = min(port->tsolen, pkt->ipv4_lso_maxlen);
+		if (port->tsolen < VNET_MINTSO) {
+			port->tso = false;
+			port->tsolen = 0;
+			pkt->cflags &= ~VNET_LSO_IPV4_CAPAB;
+		}
+		pkt->ipv4_lso_maxlen = port->tsolen;
+	} else {
+		pkt->cflags &= ~VNET_LSO_IPV4_CAPAB;
+		pkt->ipv4_lso_maxlen = 0;
+	}
+
+	/* for version >= 1.6, ACK packet mode we support */
+	if (vio_version_after_eq(vio, 1, 6)) {
+		pkt->xfer_mode = VIO_NEW_DRING_MODE;
+		pkt->options = VIO_TX_DRING;
+	}
+
+	if (!(xfer_mode | VIO_NEW_DRING_MODE) ||
 	    pkt->addr_type != VNET_ADDR_ETHERMAC ||
-	    pkt->mtu != ETH_FRAME_LEN) {
+	    pkt->mtu != localmtu) {
 		viodbg(HS, "SEND NET ATTR NACK\n");
 
 		pkt->tag.stype = VIO_SUBTYPE_NACK;
@@ -112,7 +219,14 @@ static int handle_attr_info(struct vio_driver_state *vio,
 
 		return -ECONNRESET;
 	} else {
-		viodbg(HS, "SEND NET ATTR ACK\n");
+		viodbg(HS, "SEND NET ATTR ACK xmode[0x%x] atype[0x%x] "
+		       "addr[%llx] ackfreq[%u] plnk_updt[0x%02x] opts[0x%02x] "
+		       "mtu[%llu] (rmtu[%llu]) cflags[0x%04x] lso_max[%u]\n",
+		       pkt->xfer_mode, pkt->addr_type,
+		       (unsigned long long)pkt->addr,
+		       pkt->ack_freq, pkt->plnk_updt, pkt->options,
+		       (unsigned long long)pkt->mtu, port->rmtu, pkt->cflags,
+		       pkt->ipv4_lso_maxlen);
 
 		pkt->tag.stype = VIO_SUBTYPE_ACK;
 
@@ -199,16 +313,48 @@ static struct sk_buff *alloc_and_align_skb(struct net_device *dev,
 	return skb;
 }
 
-static int vnet_rx_one(struct vnet_port *port, unsigned int len,
-		       struct ldc_trans_cookie *cookies, int ncookies)
+static inline void vnet_fullcsum(struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	int offset = skb_transport_offset(skb);
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return;
+	if (iph->protocol != IPPROTO_TCP &&
+	    iph->protocol != IPPROTO_UDP)
+		return;
+	skb->ip_summed = CHECKSUM_NONE;
+	skb->csum_level = 1;
+	skb->csum = 0;
+	if (iph->protocol == IPPROTO_TCP) {
+		struct tcphdr *ptcp = tcp_hdr(skb);
+
+		ptcp->check = 0;
+		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+		ptcp->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
+						skb->len - offset, IPPROTO_TCP,
+						skb->csum);
+	} else if (iph->protocol == IPPROTO_UDP) {
+		struct udphdr *pudp = udp_hdr(skb);
+
+		pudp->check = 0;
+		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+		pudp->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
+						skb->len - offset, IPPROTO_UDP,
+						skb->csum);
+	}
+}
+
+static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc)
 {
 	struct net_device *dev = port->vp->dev;
+	unsigned int len = desc->size;
 	unsigned int copy_len;
 	struct sk_buff *skb;
 	int err;
 
 	err = -EMSGSIZE;
-	if (unlikely(len < ETH_ZLEN || len > ETH_FRAME_LEN)) {
+	if (unlikely(len < ETH_ZLEN || len > port->rmtu)) {
 		dev->stats.rx_length_errors++;
 		goto out_dropped;
 	}
@@ -224,7 +370,7 @@ static int vnet_rx_one(struct vnet_port *port, unsigned int len,
 	skb_put(skb, copy_len);
 	err = ldc_copy(port->vio.lp, LDC_COPY_IN,
 		       skb->data, copy_len, 0,
-		       cookies, ncookies);
+		       desc->cookies, desc->ncookies);
 	if (unlikely(err < 0)) {
 		dev->stats.rx_frame_errors++;
 		goto out_free_skb;
@@ -234,11 +380,33 @@ static int vnet_rx_one(struct vnet_port *port, unsigned int len,
 	skb_trim(skb, len);
 	skb->protocol = eth_type_trans(skb, dev);
 
-	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += len;
+	if (vio_version_after_eq(&port->vio, 1, 8)) {
+		struct vio_net_dext *dext = vio_net_ext(desc);
 
-	netif_rx(skb);
+		if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM) {
+			if (skb->protocol == ETH_P_IP) {
+				struct iphdr *iph = (struct iphdr *)skb->data;
 
+				iph->check = 0;
+				ip_send_check(iph);
+			}
+		}
+		if ((dext->flags & VNET_PKT_HCK_FULLCKSUM) &&
+		    skb->ip_summed == CHECKSUM_NONE)
+			vnet_fullcsum(skb);
+		if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM_OK) {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_level = 0;
+			if (dext->flags & VNET_PKT_HCK_FULLCKSUM_OK)
+				skb->csum_level = 1;
+		}
+	}
+
+	skb->ip_summed = port->switch_port ? CHECKSUM_NONE : CHECKSUM_PARTIAL;
+
+	dev->stats.rx_packets++;
+	dev->stats.rx_bytes += len;
+	napi_gro_receive(&port->napi, skb);
 	return 0;
 
 out_free_skb:
@@ -283,28 +451,19 @@ static int vnet_send_ack(struct vnet_port *port, struct vio_dring_state *dr,
 				port->raddr[0], port->raddr[1],
 				port->raddr[2], port->raddr[3],
 				port->raddr[4], port->raddr[5]);
-			err = -ECONNRESET;
+			break;
 		}
 	} while (err == -EAGAIN);
 
-	return err;
-}
-
-static u32 next_idx(u32 idx, struct vio_dring_state *dr)
-{
-	if (++idx == dr->num_entries)
-		idx = 0;
-	return idx;
-}
-
-static u32 prev_idx(u32 idx, struct vio_dring_state *dr)
-{
-	if (idx == 0)
-		idx = dr->num_entries - 1;
-	else
-		idx--;
+	if (err <= 0 && vio_dring_state == VIO_DRING_STOPPED) {
+		port->stop_rx_idx = end;
+		port->stop_rx = true;
+	} else {
+		port->stop_rx_idx = 0;
+		port->stop_rx = false;
+	}
 
-	return idx;
+	return err;
 }
 
 static struct vio_net_desc *get_rx_desc(struct vnet_port *port,
@@ -347,6 +506,7 @@ static int vnet_walk_rx_one(struct vnet_port *port,
 	struct vio_driver_state *vio = &port->vio;
 	int err;
 
+	BUG_ON(desc == NULL);
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
 
@@ -361,7 +521,7 @@ static int vnet_walk_rx_one(struct vnet_port *port,
 	       desc->cookies[0].cookie_addr,
 	       desc->cookies[0].cookie_size);
 
-	err = vnet_rx_one(port, desc->size, desc->cookies, desc->ncookies);
+	err = vnet_rx_one(port, desc);
 	if (err == -ECONNRESET)
 		return err;
 	desc->hdr.state = VIO_DESC_DONE;
@@ -373,12 +533,14 @@ static int vnet_walk_rx_one(struct vnet_port *port,
 }
 
 static int vnet_walk_rx(struct vnet_port *port, struct vio_dring_state *dr,
-			u32 start, u32 end)
+			u32 start, u32 end, int *npkts, int budget)
 {
 	struct vio_driver_state *vio = &port->vio;
 	int ack_start = -1, ack_end = -1;
+	bool send_ack = true;
 
-	end = (end == (u32) -1) ? prev_idx(start, dr) : next_idx(end, dr);
+	end = (end == (u32) -1) ? vio_dring_prev(dr, start)
+				: vio_dring_next(dr, end);
 
 	viodbg(DATA, "vnet_walk_rx start[%08x] end[%08x]\n", start, end);
 
@@ -388,10 +550,11 @@ static int vnet_walk_rx(struct vnet_port *port, struct vio_dring_state *dr,
 			return err;
 		if (err != 0)
 			break;
+		(*npkts)++;
 		if (ack_start == -1)
 			ack_start = start;
 		ack_end = start;
-		start = next_idx(start, dr);
+		start = vio_dring_next(dr, start);
 		if (ack && start != end) {
 			err = vnet_send_ack(port, dr, ack_start, ack_end,
 					    VIO_DRING_ACTIVE);
@@ -399,13 +562,26 @@ static int vnet_walk_rx(struct vnet_port *port, struct vio_dring_state *dr,
 				return err;
 			ack_start = -1;
 		}
+		if ((*npkts) >= budget) {
+			send_ack = false;
+			break;
+		}
 	}
 	if (unlikely(ack_start == -1))
-		ack_start = ack_end = prev_idx(start, dr);
-	return vnet_send_ack(port, dr, ack_start, ack_end, VIO_DRING_STOPPED);
+		ack_start = ack_end = vio_dring_prev(dr, start);
+	if (send_ack) {
+		port->napi_resume = false;
+		return vnet_send_ack(port, dr, ack_start, ack_end,
+				     VIO_DRING_STOPPED);
+	} else  {
+		port->napi_resume = true;
+		port->napi_stop_idx = ack_end;
+		return 1;
+	}
 }
 
-static int vnet_rx(struct vnet_port *port, void *msgbuf)
+static int vnet_rx(struct vnet_port *port, void *msgbuf, int *npkts,
+		   int budget)
 {
 	struct vio_dring_data *pkt = msgbuf;
 	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_RX_RING];
@@ -422,11 +598,13 @@ static int vnet_rx(struct vnet_port *port, void *msgbuf)
 		return 0;
 	}
 
-	dr->rcv_nxt++;
+	if (!port->napi_resume)
+		dr->rcv_nxt++;
 
 	/* XXX Validate pkt->start_idx and pkt->end_idx XXX */
 
-	return vnet_walk_rx(port, dr, pkt->start_idx, pkt->end_idx);
+	return vnet_walk_rx(port, dr, pkt->start_idx, pkt->end_idx,
+			    npkts, budget);
 }
 
 static int idx_is_pending(struct vio_dring_state *dr, u32 end)
@@ -439,7 +617,7 @@ static int idx_is_pending(struct vio_dring_state *dr, u32 end)
 			found = 1;
 			break;
 		}
-		idx = next_idx(idx, dr);
+		idx = vio_dring_next(dr, idx);
 	}
 	return found;
 }
@@ -451,19 +629,42 @@ static int vnet_ack(struct vnet_port *port, void *msgbuf)
 	struct net_device *dev;
 	struct vnet *vp;
 	u32 end;
+	struct vio_net_desc *desc;
+	struct netdev_queue *txq;
 
 	if (unlikely(pkt->tag.stype_env != VIO_DRING_DATA))
 		return 0;
 
 	end = pkt->end_idx;
-	if (unlikely(!idx_is_pending(dr, end)))
+	vp = port->vp;
+	dev = vp->dev;
+	netif_tx_lock(dev);
+	if (unlikely(!idx_is_pending(dr, end))) {
+		netif_tx_unlock(dev);
 		return 0;
+	}
 
-	dr->cons = next_idx(end, dr);
+	/* sync for race conditions with vnet_start_xmit() and tell xmit it
+	 * is time to send a trigger.
+	 */
+	dr->cons = vio_dring_next(dr, end);
+	desc = vio_dring_entry(dr, dr->cons);
+	if (desc->hdr.state == VIO_DESC_READY && !port->start_cons) {
+		/* vnet_start_xmit() just populated this dring but missed
+		 * sending the "start" LDC message to the consumer.
+		 * Send a "start" trigger on its behalf.
+		 */
+		if (__vnet_tx_trigger(port, dr->cons) > 0)
+			port->start_cons = false;
+		else
+			port->start_cons = true;
+	} else {
+		port->start_cons = true;
+	}
+	netif_tx_unlock(dev);
 
-	vp = port->vp;
-	dev = vp->dev;
-	if (unlikely(netif_queue_stopped(dev) &&
+	txq = netdev_get_tx_queue(dev, port->q_index);
+	if (unlikely(netif_tx_queue_stopped(txq) &&
 		     vnet_tx_dring_avail(dr) >= VNET_TX_WAKEUP_THRESH(dr)))
 		return 1;
 
@@ -491,56 +692,64 @@ static int handle_mcast(struct vnet_port *port, void *msgbuf)
 	return 0;
 }
 
-static void maybe_tx_wakeup(unsigned long param)
+/* Got back a STOPPED LDC message on port. If the queue is stopped,
+ * wake it up so that we'll send out another START message at the
+ * next TX.
+ */
+static void maybe_tx_wakeup(struct vnet_port *port)
 {
-	struct vnet *vp = (struct vnet *)param;
-	struct net_device *dev = vp->dev;
-
-	netif_tx_lock(dev);
-	if (likely(netif_queue_stopped(dev))) {
-		struct vnet_port *port;
-		int wake = 1;
+	struct netdev_queue *txq;
 
-		list_for_each_entry(port, &vp->port_list, list) {
-			struct vio_dring_state *dr;
+	txq = netdev_get_tx_queue(port->vp->dev, port->q_index);
+	__netif_tx_lock(txq, smp_processor_id());
+	if (likely(netif_tx_queue_stopped(txq))) {
+		struct vio_dring_state *dr;
 
-			dr = &port->vio.drings[VIO_DRIVER_TX_RING];
-			if (vnet_tx_dring_avail(dr) <
-			    VNET_TX_WAKEUP_THRESH(dr)) {
-				wake = 0;
-				break;
-			}
-		}
-		if (wake)
-			netif_wake_queue(dev);
+		dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+		netif_tx_wake_queue(txq);
 	}
-	netif_tx_unlock(dev);
+	__netif_tx_unlock(txq);
 }
 
-static void vnet_event(void *arg, int event)
+static inline bool port_is_up(struct vnet_port *vnet)
+{
+	struct vio_driver_state *vio = &vnet->vio;
+
+	return !!(vio->hs_state & VIO_HS_COMPLETE);
+}
+
+static int vnet_event_napi(struct vnet_port *port, int budget)
 {
-	struct vnet_port *port = arg;
 	struct vio_driver_state *vio = &port->vio;
-	unsigned long flags;
 	int tx_wakeup, err;
+	int npkts = 0;
+	int event = (port->rx_event & LDC_EVENT_RESET);
 
-	spin_lock_irqsave(&vio->lock, flags);
-
+ldc_ctrl:
 	if (unlikely(event == LDC_EVENT_RESET ||
 		     event == LDC_EVENT_UP)) {
 		vio_link_state_change(vio, event);
-		spin_unlock_irqrestore(&vio->lock, flags);
 
-		if (event == LDC_EVENT_RESET)
+		if (event == LDC_EVENT_RESET) {
+			port->rmtu = 0;
+			port->tso = true;
+			port->tsolen = 0;
 			vio_port_up(vio);
-		return;
+		}
+		port->rx_event = 0;
+		return 0;
 	}
+	/* We may have multiple LDC events in rx_event. Unroll send_events() */
+	event = (port->rx_event & LDC_EVENT_UP);
+	port->rx_event &= ~(LDC_EVENT_RESET|LDC_EVENT_UP);
+	if (event == LDC_EVENT_UP)
+		goto ldc_ctrl;
+	event = port->rx_event;
+	if (!(event & LDC_EVENT_DATA_READY))
+		return 0;
 
-	if (unlikely(event != LDC_EVENT_DATA_READY)) {
-		pr_warning("Unexpected LDC event %d\n", event);
-		spin_unlock_irqrestore(&vio->lock, flags);
-		return;
-	}
+	/* we dont expect any other bits than RESET, UP, DATA_READY */
+	BUG_ON(event != LDC_EVENT_DATA_READY);
 
 	tx_wakeup = err = 0;
 	while (1) {
@@ -549,6 +758,20 @@ static void vnet_event(void *arg, int event)
 			u64 raw[8];
 		} msgbuf;
 
+		if (port->napi_resume) {
+			struct vio_dring_data *pkt =
+				(struct vio_dring_data *)&msgbuf;
+			struct vio_dring_state *dr =
+				&port->vio.drings[VIO_DRIVER_RX_RING];
+
+			pkt->tag.type = VIO_TYPE_DATA;
+			pkt->tag.stype = VIO_SUBTYPE_INFO;
+			pkt->tag.stype_env = VIO_DRING_DATA;
+			pkt->seq = dr->rcv_nxt;
+			pkt->start_idx = vio_dring_next(dr, port->napi_stop_idx);
+			pkt->end_idx = -1;
+			goto napi_resume;
+		}
 		err = ldc_read(vio->lp, &msgbuf, sizeof(msgbuf));
 		if (unlikely(err < 0)) {
 			if (err == -ECONNRESET)
@@ -565,10 +788,22 @@ static void vnet_event(void *arg, int event)
 		err = vio_validate_sid(vio, &msgbuf.tag);
 		if (err < 0)
 			break;
-
+napi_resume:
 		if (likely(msgbuf.tag.type == VIO_TYPE_DATA)) {
 			if (msgbuf.tag.stype == VIO_SUBTYPE_INFO) {
-				err = vnet_rx(port, &msgbuf);
+				if (!port_is_up(port)) {
+					/* failures like handshake_failure()
+					 * may have cleaned up dring, but
+					 * NAPI polling may bring us here.
+					 */
+					err = -ECONNRESET;
+					break;
+				}
+				err = vnet_rx(port, &msgbuf, &npkts, budget);
+				if (npkts >= budget)
+					break;
+				if (npkts == 0)
+					break;
 			} else if (msgbuf.tag.stype == VIO_SUBTYPE_ACK) {
 				err = vnet_ack(port, &msgbuf);
 				if (err > 0)
@@ -589,18 +824,37 @@ static void vnet_event(void *arg, int event)
 		if (err == -ECONNRESET)
 			break;
 	}
-	spin_unlock(&vio->lock);
-	/* Kick off a tasklet to wake the queue.  We cannot call
-	 * maybe_tx_wakeup directly here because we could deadlock on
-	 * netif_tx_lock() with dev_watchdog()
-	 */
 	if (unlikely(tx_wakeup && err != -ECONNRESET))
-		tasklet_schedule(&port->vp->vnet_tx_wakeup);
+		maybe_tx_wakeup(port);
+	return npkts;
+}
 
-	local_irq_restore(flags);
+static int vnet_poll(struct napi_struct *napi, int budget)
+{
+	struct vnet_port *port = container_of(napi, struct vnet_port, napi);
+	struct vio_driver_state *vio = &port->vio;
+	int processed = vnet_event_napi(port, budget);
+
+	if (processed < budget) {
+		napi_complete(napi);
+		port->rx_event &= ~LDC_EVENT_DATA_READY;
+		vio_set_intr(vio->vdev->rx_ino, HV_INTR_ENABLED);
+	}
+	return processed;
 }
 
-static int __vnet_tx_trigger(struct vnet_port *port)
+static void vnet_event(void *arg, int event)
+{
+	struct vnet_port *port = arg;
+	struct vio_driver_state *vio = &port->vio;
+
+	port->rx_event |= event;
+	vio_set_intr(vio->vdev->rx_ino, HV_INTR_DISABLED);
+	napi_schedule(&port->napi);
+
+}
+
+static int __vnet_tx_trigger(struct vnet_port *port, u32 start)
 {
 	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
 	struct vio_dring_data hdr = {
@@ -611,12 +865,21 @@ static int __vnet_tx_trigger(struct vnet_port *port)
 			.sid		= vio_send_sid(&port->vio),
 		},
 		.dring_ident		= dr->ident,
-		.start_idx		= dr->prod,
+		.start_idx		= start,
 		.end_idx		= (u32) -1,
 	};
 	int err, delay;
 	int retries = 0;
 
+	if (port->stop_rx) {
+		err = vnet_send_ack(port,
+				    &port->vio.drings[VIO_DRIVER_RX_RING],
+				    port->stop_rx_idx, -1,
+				    VIO_DRING_STOPPED);
+		if (err <= 0)
+			return err;
+	}
+
 	hdr.seq = dr->snd_nxt;
 	delay = 1;
 	do {
@@ -635,26 +898,19 @@ static int __vnet_tx_trigger(struct vnet_port *port)
 	return err;
 }
 
-static inline bool port_is_up(struct vnet_port *vnet)
-{
-	struct vio_driver_state *vio = &vnet->vio;
-
-	return !!(vio->hs_state & VIO_HS_COMPLETE);
-}
-
 struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb)
 {
 	unsigned int hash = vnet_hashfn(skb->data);
 	struct hlist_head *hp = &vp->port_hash[hash];
 	struct vnet_port *port;
 
-	hlist_for_each_entry(port, hp, hash) {
+	hlist_for_each_entry_rcu(port, hp, hash) {
 		if (!port_is_up(port))
 			continue;
 		if (ether_addr_equal(port->raddr, skb->data))
 			return port;
 	}
-	list_for_each_entry(port, &vp->port_list, list) {
+	list_for_each_entry_rcu(port, &vp->port_list, list) {
 		if (!port->switch_port)
 			continue;
 		if (!port_is_up(port))
@@ -664,58 +920,432 @@ struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb)
 	return NULL;
 }
 
-struct vnet_port *tx_port_find(struct vnet *vp, struct sk_buff *skb)
+static struct sk_buff *vnet_clean_tx_ring(struct vnet_port *port,
+					  unsigned *pending)
 {
-	struct vnet_port *ret;
-	unsigned long flags;
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct sk_buff *skb = NULL;
+	int i, txi;
 
-	spin_lock_irqsave(&vp->lock, flags);
-	ret = __tx_port_find(vp, skb);
-	spin_unlock_irqrestore(&vp->lock, flags);
+	*pending = 0;
+
+	txi = dr->prod-1;
+	if (txi < 0)
+		txi = VNET_TX_RING_SIZE-1;
+
+	for (i = 0; i < VNET_TX_RING_SIZE; ++i) {
+		struct vio_net_desc *d;
+
+		d = vio_dring_entry(dr, txi);
+
+		if (d->hdr.state == VIO_DESC_DONE) {
+			if (port->tx_bufs[txi].skb) {
+				BUG_ON(port->tx_bufs[txi].skb->next);
+
+				port->tx_bufs[txi].skb->next = skb;
+				skb = port->tx_bufs[txi].skb;
+				port->tx_bufs[txi].skb = NULL;
+
+				ldc_unmap(port->vio.lp,
+					  port->tx_bufs[txi].cookies,
+					  port->tx_bufs[txi].ncookies);
+			}
+			d->hdr.state = VIO_DESC_FREE;
+		} else if (d->hdr.state == VIO_DESC_READY) {
+			(*pending)++;
+		} else if (d->hdr.state == VIO_DESC_FREE) {
+			break;
+		}
+		--txi;
+		if (txi < 0)
+			txi = VNET_TX_RING_SIZE-1;
+	}
+	return skb;
+}
+
+static inline void vnet_free_skbs(struct sk_buff *skb)
+{
+	struct sk_buff *next;
+
+	while (skb) {
+		next = skb->next;
+		skb->next = NULL;
+		dev_kfree_skb(skb);
+		skb = next;
+	}
+}
+
+static void vnet_clean_timer_expire(unsigned long port0)
+{
+	struct vnet_port *port = (struct vnet_port *)port0;
+	struct sk_buff *freeskbs;
+	unsigned pending;
+
+	netif_tx_lock(port->vp->dev);
+	freeskbs = vnet_clean_tx_ring(port, &pending);
+	netif_tx_unlock(port->vp->dev);
+
+	vnet_free_skbs(freeskbs);
 
-	return ret;
+	if (pending)
+		(void)mod_timer(&port->clean_timer,
+				jiffies + VNET_CLEAN_TIMEOUT);
+	 else
+		del_timer(&port->clean_timer);
+}
+
+static inline int vnet_skb_map(struct ldc_channel *lp, struct sk_buff *skb,
+			       struct ldc_trans_cookie *cookies, int ncookies,
+			       unsigned int map_perm)
+{
+	int i, nc, err, blen;
+
+	/* header */
+	blen = skb_headlen(skb);
+	if (blen < ETH_ZLEN)
+		blen = ETH_ZLEN;
+	blen += VNET_PACKET_SKIP;
+	blen += 8 - (blen & 7);
+
+	err = ldc_map_single(lp, skb->data-VNET_PACKET_SKIP, blen, cookies,
+			     ncookies, map_perm);
+	if (err < 0)
+		return err;
+	nc = err;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+		u8 *vaddr;
+
+		if (nc < ncookies) {
+			vaddr = kmap_atomic(skb_frag_page(f));
+			blen = skb_frag_size(f);
+			blen += 8 - (blen & 7);
+			err = ldc_map_single(lp, vaddr + f->page_offset,
+					     blen, cookies + nc, ncookies - nc,
+					     map_perm);
+			kunmap_atomic(vaddr);
+		} else {
+			err = -EMSGSIZE;
+		}
+
+		if (err < 0) {
+			ldc_unmap(lp, cookies, nc);
+			return err;
+		}
+		nc += err;
+	}
+	return nc;
+}
+
+static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies)
+{
+	struct sk_buff *nskb;
+	int i, len, pad, docopy;
+
+	len = skb->len;
+	pad = 0;
+	if (len < ETH_ZLEN) {
+		pad += ETH_ZLEN - skb->len;
+		len += pad;
+	}
+	len += VNET_PACKET_SKIP;
+	pad += 8 - (len & 7);
+
+	/* make sure we have enough cookies and alignment in every frag */
+	docopy = skb_shinfo(skb)->nr_frags >= ncookies;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+
+		docopy |= f->page_offset & 7;
+	}
+	if (((unsigned long)skb->data & 7) != VNET_PACKET_SKIP ||
+	    skb_tailroom(skb) < pad ||
+	    skb_headroom(skb) < VNET_PACKET_SKIP || docopy) {
+		int start = 0, offset;
+		__wsum csum;
+
+		len = skb->len > ETH_ZLEN ? skb->len : ETH_ZLEN;
+		nskb = alloc_and_align_skb(skb->dev, len);
+		if (nskb == NULL) {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
+		skb_reserve(nskb, VNET_PACKET_SKIP);
+
+		nskb->protocol = skb->protocol;
+		offset = skb_mac_header(skb) - skb->data;
+		skb_set_mac_header(nskb, offset);
+		offset = skb_network_header(skb) - skb->data;
+		skb_set_network_header(nskb, offset);
+		offset = skb_transport_header(skb) - skb->data;
+		skb_set_transport_header(nskb, offset);
+
+		offset = 0;
+		nskb->csum_offset = skb->csum_offset;
+		nskb->ip_summed = skb->ip_summed;
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			start = skb_checksum_start_offset(skb);
+		if (start) {
+			struct iphdr *iph = ip_hdr(nskb);
+			int offset = start + nskb->csum_offset;
+
+			if (skb_copy_bits(skb, 0, nskb->data, start)) {
+				dev_kfree_skb(nskb);
+				dev_kfree_skb(skb);
+				return NULL;
+			}
+			*(__sum16 *)(skb->data + offset) = 0;
+			csum = skb_copy_and_csum_bits(skb, start,
+						      nskb->data + start,
+						      skb->len - start, 0);
+			if (iph->protocol == IPPROTO_TCP ||
+			    iph->protocol == IPPROTO_UDP) {
+				csum = csum_tcpudp_magic(iph->saddr, iph->daddr,
+							 skb->len - start,
+							 iph->protocol, csum);
+			}
+			*(__sum16 *)(nskb->data + offset) = csum;
+
+			nskb->ip_summed = CHECKSUM_NONE;
+		} else if (skb_copy_bits(skb, 0, nskb->data, skb->len)) {
+			dev_kfree_skb(nskb);
+			dev_kfree_skb(skb);
+			return NULL;
+		}
+		(void)skb_put(nskb, skb->len);
+		if (skb_is_gso(skb)) {
+			skb_shinfo(nskb)->gso_size = skb_shinfo(skb)->gso_size;
+			skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type;
+		}
+		dev_kfree_skb(skb);
+		skb = nskb;
+	}
+	return skb;
+}
+
+static u16
+vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
+		  void *accel_priv, select_queue_fallback_t fallback)
+{
+	struct vnet *vp = netdev_priv(dev);
+	struct vnet_port *port = __tx_port_find(vp, skb);
+
+	if (port == NULL)
+		return 0;
+	return port->q_index;
+}
+
+static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev);
+
+static int vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb)
+{
+	struct net_device *dev = port->vp->dev;
+	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+	struct sk_buff *segs;
+	int maclen, datalen;
+	int status;
+	int gso_size, gso_type, gso_segs;
+	int hlen = skb_transport_header(skb) - skb_mac_header(skb);
+	int proto = IPPROTO_IP;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		proto = ip_hdr(skb)->protocol;
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		proto = ipv6_hdr(skb)->nexthdr;
+
+	if (proto == IPPROTO_TCP)
+		hlen += tcp_hdr(skb)->doff * 4;
+	else if (proto == IPPROTO_UDP)
+		hlen += sizeof(struct udphdr);
+	else {
+		pr_err("vnet_handle_offloads GSO with unknown transport "
+		       "protocol %d tproto %d\n", skb->protocol, proto);
+		hlen = 128; /* XXX */
+	}
+	datalen = port->tsolen - hlen;
+
+	gso_size = skb_shinfo(skb)->gso_size;
+	gso_type = skb_shinfo(skb)->gso_type;
+	gso_segs = skb_shinfo(skb)->gso_segs;
+
+	if (port->tso && gso_size < datalen)
+		gso_segs = DIV_ROUND_UP(skb->len - hlen, datalen);
+
+	if (unlikely(vnet_tx_dring_avail(dr) < gso_segs)) {
+		struct netdev_queue *txq;
+
+		txq  = netdev_get_tx_queue(dev, port->q_index);
+		netif_tx_stop_queue(txq);
+		if (vnet_tx_dring_avail(dr) < skb_shinfo(skb)->gso_segs)
+			return NETDEV_TX_BUSY;
+		netif_tx_wake_queue(txq);
+	}
+
+	maclen = skb_network_header(skb) - skb_mac_header(skb);
+	skb_pull(skb, maclen);
+
+	if (port->tso && gso_size < datalen) {
+		/* segment to TSO size */
+		skb_shinfo(skb)->gso_size = datalen;
+		skb_shinfo(skb)->gso_segs = gso_segs;
+
+		segs = skb_gso_segment(skb, dev->features & ~NETIF_F_TSO);
+
+		/* restore gso_size & gso_segs */
+		skb_shinfo(skb)->gso_size = gso_size;
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len - hlen,
+							 gso_size);
+	} else
+		segs = skb_gso_segment(skb, dev->features & ~NETIF_F_TSO);
+	if (IS_ERR(segs)) {
+		dev->stats.tx_dropped++;
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	skb_push(skb, maclen);
+	skb_reset_mac_header(skb);
+
+	status = 0;
+	while (segs) {
+		struct sk_buff *curr = segs;
+
+		segs = segs->next;
+		curr->next = NULL;
+		if (port->tso && curr->len > dev->mtu) {
+			skb_shinfo(curr)->gso_size = gso_size;
+			skb_shinfo(curr)->gso_type = gso_type;
+			skb_shinfo(curr)->gso_segs =
+				DIV_ROUND_UP(curr->len - hlen, gso_size);
+		} else
+			skb_shinfo(curr)->gso_size = 0;
+
+		skb_push(curr, maclen);
+		skb_reset_mac_header(curr);
+		memcpy(skb_mac_header(curr), skb_mac_header(skb),
+		       maclen);
+		curr->csum_start = skb_transport_header(curr) - curr->head;
+		if (ip_hdr(curr)->protocol == IPPROTO_TCP)
+			curr->csum_offset = offsetof(struct tcphdr, check);
+		else if (ip_hdr(curr)->protocol == IPPROTO_UDP)
+			curr->csum_offset = offsetof(struct udphdr, check);
+
+		if (!(status & NETDEV_TX_MASK))
+			status = vnet_start_xmit(curr, dev);
+		if (status & NETDEV_TX_MASK)
+			dev_kfree_skb_any(curr);
+	}
+
+	if (!(status & NETDEV_TX_MASK))
+		dev_kfree_skb_any(skb);
+	return status;
 }
 
 static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct vnet *vp = netdev_priv(dev);
-	struct vnet_port *port = tx_port_find(vp, skb);
+	struct vnet_port *port = NULL;
 	struct vio_dring_state *dr;
 	struct vio_net_desc *d;
-	unsigned long flags;
 	unsigned int len;
-	void *tx_buf;
-	int i, err;
+	struct sk_buff *freeskbs = NULL;
+	int i, err, txi;
+	unsigned pending = 0;
+	struct netdev_queue *txq;
+
+	rcu_read_lock();
+	port = __tx_port_find(vp, skb);
+	if (unlikely(!port)) {
+		rcu_read_unlock();
+		goto out_dropped;
+	}
+
+	if (skb_is_gso(skb) && skb->len > port->tsolen) {
+		err = vnet_handle_offloads(port, skb);
+		rcu_read_unlock();
+		return err;
+	}
+
+	if (!skb_is_gso(skb) && skb->len > port->rmtu) {
+		unsigned long localmtu = port->rmtu - ETH_HLEN;
+
+		if (vio_version_after_eq(&port->vio, 1, 3))
+			localmtu -= VLAN_HLEN;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			struct flowi4 fl4;
+			struct rtable *rt = NULL;
+
+			memset(&fl4, 0, sizeof(fl4));
+			fl4.flowi4_oif = dev->ifindex;
+			fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
+			fl4.daddr = ip_hdr(skb)->daddr;
+			fl4.saddr = ip_hdr(skb)->saddr;
+
+			rt = ip_route_output_key(dev_net(dev), &fl4);
+			rcu_read_unlock();
+			if (!IS_ERR(rt)) {
+				skb_dst_set(skb, &rt->dst);
+				icmp_send(skb, ICMP_DEST_UNREACH,
+					  ICMP_FRAG_NEEDED,
+					  htonl(localmtu));
+			}
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+		else if (skb->protocol == htons(ETH_P_IPV6))
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, localmtu);
+#endif
+		goto out_dropped;
+	}
+
+	skb = vnet_skb_shape(skb, 2);
 
-	if (unlikely(!port))
+	if (unlikely(!skb))
 		goto out_dropped;
 
-	spin_lock_irqsave(&port->vio.lock, flags);
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		vnet_fullcsum(skb);
 
 	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
-		if (!netif_queue_stopped(dev)) {
-			netif_stop_queue(dev);
+	i = skb_get_queue_mapping(skb);
+	txq = netdev_get_tx_queue(dev, i);
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
+		if (!netif_tx_queue_stopped(txq)) {
+			netif_tx_stop_queue(txq);
 
 			/* This is a hard error, log it. */
 			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
 			dev->stats.tx_errors++;
 		}
-		spin_unlock_irqrestore(&port->vio.lock, flags);
+		rcu_read_unlock();
 		return NETDEV_TX_BUSY;
 	}
 
 	d = vio_dring_cur(dr);
 
-	tx_buf = port->tx_bufs[dr->prod].buf;
-	skb_copy_from_linear_data(skb, tx_buf + VNET_PACKET_SKIP, skb->len);
+	txi = dr->prod;
+
+	freeskbs = vnet_clean_tx_ring(port, &pending);
+
+	BUG_ON(port->tx_bufs[txi].skb);
 
 	len = skb->len;
-	if (len < ETH_ZLEN) {
+	if (len < ETH_ZLEN)
 		len = ETH_ZLEN;
-		memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len);
+
+	err = vnet_skb_map(port->vio.lp, skb, port->tx_bufs[txi].cookies, 2,
+			   (LDC_MAP_SHADOW | LDC_MAP_DIRECT | LDC_MAP_RW));
+	if (err < 0) {
+		netdev_info(dev, "tx buffer map error %d\n", err);
+		goto out_dropped;
 	}
 
+	port->tx_bufs[txi].skb = skb;
+	skb = NULL;
+	port->tx_bufs[txi].ncookies = err;
+
 	/* We don't rely on the ACKs to free the skb in vnet_start_xmit(),
 	 * thus it is safe to not set VIO_ACK_ENABLE for each transmission:
 	 * the protocol itself does not require it as long as the peer
@@ -726,9 +1356,24 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	d->hdr.ack = VIO_ACK_DISABLE;
 	d->size = len;
-	d->ncookies = port->tx_bufs[dr->prod].ncookies;
+	d->ncookies = port->tx_bufs[txi].ncookies;
 	for (i = 0; i < d->ncookies; i++)
-		d->cookies[i] = port->tx_bufs[dr->prod].cookies[i];
+		d->cookies[i] = port->tx_bufs[txi].cookies[i];
+	if (vio_version_after_eq(&port->vio, 1, 7)) {
+		struct vio_net_dext *dext = vio_net_ext(d);
+
+		memset(dext, 0, sizeof(*dext));
+		if (skb_is_gso(port->tx_bufs[txi].skb)) {
+			dext->ipv4_lso_mss = skb_shinfo(port->tx_bufs[txi].skb)
+					     ->gso_size;
+			dext->flags |= VNET_PKT_IPV4_LSO;
+		}
+		if (vio_version_after_eq(&port->vio, 1, 8) &&
+		    !port->switch_port) {
+			dext->flags |= VNET_PKT_HCK_IPV4_HDRCKSUM_OK;
+			dext->flags |= VNET_PKT_HCK_FULLCKSUM_OK;
+		}
+	}
 
 	/* This has to be a non-SMP write barrier because we are writing
 	 * to memory which is shared with the peer LDOM.
@@ -737,35 +1382,68 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	d->hdr.state = VIO_DESC_READY;
 
-	err = __vnet_tx_trigger(port);
+	/* Exactly one ldc "start" trigger (for dr->cons) needs to be sent
+	 * to notify the consumer that some descriptors are READY.
+	 * After that "start" trigger, no additional triggers are needed until
+	 * a DRING_STOPPED is received from the consumer. The dr->cons field
+	 * (set up by vnet_ack()) has the value of the next dring index
+	 * that has not yet been ack-ed. We send a "start" trigger here
+	 * if, and only if, start_cons is true (reset it afterward). Conversely,
+	 * vnet_ack() should check if the dring corresponding to cons
+	 * is marked READY, but start_cons was false.
+	 * If so, vnet_ack() should send out the missed "start" trigger.
+	 *
+	 * Note that the wmb() above makes sure the cookies et al. are
+	 * not globally visible before the VIO_DESC_READY, and that the
+	 * stores are ordered correctly by the compiler. The consumer will
+	 * not proceed until the VIO_DESC_READY is visible assuring that
+	 * the consumer does not observe anything related to descriptors
+	 * out of order. The HV trap from the LDC start trigger is the
+	 * producer to consumer announcement that work is available to the
+	 * consumer
+	 */
+	if (!port->start_cons)
+		goto ldc_start_done; /* previous trigger suffices */
+
+	err = __vnet_tx_trigger(port, dr->cons);
 	if (unlikely(err < 0)) {
 		netdev_info(dev, "TX trigger error %d\n", err);
 		d->hdr.state = VIO_DESC_FREE;
 		dev->stats.tx_carrier_errors++;
-		goto out_dropped_unlock;
+		goto out_dropped;
 	}
 
+ldc_start_done:
+	port->start_cons = false;
+
 	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
+	dev->stats.tx_bytes += port->tx_bufs[txi].skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
-		netif_stop_queue(dev);
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
+		netif_tx_stop_queue(txq);
 		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
-			netif_wake_queue(dev);
+			netif_tx_wake_queue(txq);
 	}
 
-	spin_unlock_irqrestore(&port->vio.lock, flags);
+	(void)mod_timer(&port->clean_timer, jiffies + VNET_CLEAN_TIMEOUT);
+	rcu_read_unlock();
 
-	dev_kfree_skb(skb);
+	vnet_free_skbs(freeskbs);
 
 	return NETDEV_TX_OK;
 
-out_dropped_unlock:
-	spin_unlock_irqrestore(&port->vio.lock, flags);
-
 out_dropped:
-	dev_kfree_skb(skb);
+	if (pending)
+		(void)mod_timer(&port->clean_timer,
+				jiffies + VNET_CLEAN_TIMEOUT);
+	else if (port)
+		del_timer(&port->clean_timer);
+	if (port)
+		rcu_read_unlock();
+	if (skb)
+		dev_kfree_skb(skb);
+	vnet_free_skbs(freeskbs);
 	dev->stats.tx_dropped++;
 	return NETDEV_TX_OK;
 }
@@ -778,14 +1456,14 @@ static void vnet_tx_timeout(struct net_device *dev)
 static int vnet_open(struct net_device *dev)
 {
 	netif_carrier_on(dev);
-	netif_start_queue(dev);
+	netif_tx_start_all_queues(dev);
 
 	return 0;
 }
 
 static int vnet_close(struct net_device *dev)
 {
-	netif_stop_queue(dev);
+	netif_tx_stop_all_queues(dev);
 	netif_carrier_off(dev);
 
 	return 0;
@@ -895,23 +1573,22 @@ static void vnet_set_rx_mode(struct net_device *dev)
 {
 	struct vnet *vp = netdev_priv(dev);
 	struct vnet_port *port;
-	unsigned long flags;
 
-	spin_lock_irqsave(&vp->lock, flags);
-	if (!list_empty(&vp->port_list)) {
-		port = list_entry(vp->port_list.next, struct vnet_port, list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &vp->port_list, list) {
 
 		if (port->switch_port) {
 			__update_mc_list(vp, dev);
 			__send_mc_list(vp, port);
+			break;
 		}
 	}
-	spin_unlock_irqrestore(&vp->lock, flags);
+	rcu_read_unlock();
 }
 
 static int vnet_change_mtu(struct net_device *dev, int new_mtu)
 {
-	if (new_mtu != ETH_DATA_LEN)
+	if (new_mtu < 68 || new_mtu > 65535)
 		return -EINVAL;
 
 	dev->mtu = new_mtu;
@@ -967,60 +1644,39 @@ static void vnet_port_free_tx_bufs(struct vnet_port *port)
 	}
 
 	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
-		void *buf = port->tx_bufs[i].buf;
+		struct vio_net_desc *d;
+		void *skb = port->tx_bufs[i].skb;
 
-		if (!buf)
+		if (!skb)
 			continue;
 
+		d = vio_dring_entry(dr, i);
+		if (d->hdr.state == VIO_DESC_READY)
+			pr_warn("active transmit buffers freed\n");
+
 		ldc_unmap(port->vio.lp,
 			  port->tx_bufs[i].cookies,
 			  port->tx_bufs[i].ncookies);
-
-		kfree(buf);
-		port->tx_bufs[i].buf = NULL;
+		dev_kfree_skb(skb);
+		port->tx_bufs[i].skb = NULL;
+		d->hdr.state = VIO_DESC_FREE;
 	}
 }
 
-static int vnet_port_alloc_tx_bufs(struct vnet_port *port)
+static int vnet_port_alloc_tx_ring(struct vnet_port *port)
 {
 	struct vio_dring_state *dr;
-	unsigned long len;
+	unsigned long len, elen;
 	int i, err, ncookies;
 	void *dring;
 
-	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
-		void *buf = kzalloc(ETH_FRAME_LEN + 8, GFP_KERNEL);
-		int map_len = (ETH_FRAME_LEN + 7) & ~7;
-
-		err = -ENOMEM;
-		if (!buf)
-			goto err_out;
-
-		err = -EFAULT;
-		if ((unsigned long)buf & (8UL - 1)) {
-			pr_err("TX buffer misaligned\n");
-			kfree(buf);
-			goto err_out;
-		}
-
-		err = ldc_map_single(port->vio.lp, buf, map_len,
-				     port->tx_bufs[i].cookies, 2,
-				     (LDC_MAP_SHADOW |
-				      LDC_MAP_DIRECT |
-				      LDC_MAP_RW));
-		if (err < 0) {
-			kfree(buf);
-			goto err_out;
-		}
-		port->tx_bufs[i].buf = buf;
-		port->tx_bufs[i].ncookies = err;
-	}
-
 	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
 
-	len = (VNET_TX_RING_SIZE *
-	       (sizeof(struct vio_net_desc) +
-		(sizeof(struct ldc_trans_cookie) * 2)));
+	elen = sizeof(struct vio_net_desc) +
+	       sizeof(struct ldc_trans_cookie) * 2;
+	if (vio_version_after_eq(&port->vio, 1, 7))
+		elen += sizeof(struct vio_net_dext);
+	len = VNET_TX_RING_SIZE * elen;
 
 	ncookies = VIO_MAX_RING_COOKIES;
 	dring = ldc_alloc_exp_dring(port->vio.lp, len,
@@ -1034,13 +1690,19 @@ static int vnet_port_alloc_tx_bufs(struct vnet_port *port)
 	}
 
 	dr->base = dring;
-	dr->entry_size = (sizeof(struct vio_net_desc) +
-			  (sizeof(struct ldc_trans_cookie) * 2));
+	dr->entry_size = elen;
 	dr->num_entries = VNET_TX_RING_SIZE;
 	dr->prod = dr->cons = 0;
+	port->start_cons  = true; /* need an initial trigger */
 	dr->pending = VNET_TX_RING_SIZE;
 	dr->ncookies = ncookies;
 
+	for (i = 0; i < VNET_TX_RING_SIZE; ++i) {
+		struct vio_net_desc *d;
+
+		d = vio_dring_entry(dr, i);
+		d->hdr.state = VIO_DESC_FREE;
+	}
 	return 0;
 
 err_out:
@@ -1049,6 +1711,21 @@ err_out:
 	return err;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void vnet_poll_controller(struct net_device *dev)
+{
+	struct vnet *vp = netdev_priv(dev);
+	struct vnet_port *port;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp->lock, flags);
+	if (!list_empty(&vp->port_list)) {
+		port = list_entry(vp->port_list.next, struct vnet_port, list);
+		napi_schedule(&port->napi);
+	}
+	spin_unlock_irqrestore(&vp->lock, flags);
+}
+#endif
 static LIST_HEAD(vnet_list);
 static DEFINE_MUTEX(vnet_list_mutex);
 
@@ -1061,6 +1738,10 @@ static const struct net_device_ops vnet_ops = {
 	.ndo_tx_timeout		= vnet_tx_timeout,
 	.ndo_change_mtu		= vnet_change_mtu,
 	.ndo_start_xmit		= vnet_start_xmit,
+	.ndo_select_queue	= vnet_select_queue,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= vnet_poll_controller,
+#endif
 };
 
 static struct vnet *vnet_new(const u64 *local_mac)
@@ -1069,9 +1750,11 @@ static struct vnet *vnet_new(const u64 *local_mac)
 	struct vnet *vp;
 	int err, i;
 
-	dev = alloc_etherdev(sizeof(*vp));
+	dev = alloc_etherdev_mqs(sizeof(*vp), VNET_MAX_TXQS, 1);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
+	dev->needed_headroom = VNET_PACKET_SKIP + 8;
+	dev->needed_tailroom = 8;
 
 	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = (*local_mac >> (5 - i) * 8) & 0xff;
@@ -1079,7 +1762,6 @@ static struct vnet *vnet_new(const u64 *local_mac)
 	vp = netdev_priv(dev);
 
 	spin_lock_init(&vp->lock);
-	tasklet_init(&vp->vnet_tx_wakeup, maybe_tx_wakeup, (unsigned long)vp);
 	vp->dev = dev;
 
 	INIT_LIST_HEAD(&vp->port_list);
@@ -1092,6 +1774,10 @@ static struct vnet *vnet_new(const u64 *local_mac)
 	dev->ethtool_ops = &vnet_ethtool_ops;
 	dev->watchdog_timeo = VNET_TX_TIMEOUT;
 
+	dev->hw_features = NETIF_F_TSO | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE |
+			   NETIF_F_HW_CSUM | NETIF_F_SG;
+	dev->features = dev->hw_features;
+
 	err = register_netdev(dev);
 	if (err) {
 		pr_err("Cannot register net device, aborting\n");
@@ -1139,7 +1825,6 @@ static void vnet_cleanup(void)
 		vp = list_first_entry(&vnet_list, struct vnet, list);
 		list_del(&vp->list);
 		dev = vp->dev;
-		tasklet_kill(&vp->vnet_tx_wakeup);
 		/* vio_unregister_driver() should have cleaned up port_list */
 		BUG_ON(!list_empty(&vp->port_list));
 		unregister_netdev(dev);
@@ -1194,6 +1879,25 @@ static void print_version(void)
 
 const char *remote_macaddr_prop = "remote-mac-address";
 
+static void
+vnet_port_add_txq(struct vnet_port *port)
+{
+	struct vnet *vp = port->vp;
+	int n;
+
+	n = vp->nports++;
+	n = n & (VNET_MAX_TXQS - 1);
+	port->q_index = n;
+	netif_tx_wake_queue(netdev_get_tx_queue(vp->dev, port->q_index));
+}
+
+static void
+vnet_port_rm_txq(struct vnet_port *port)
+{
+	port->vp->nports--;
+	netif_tx_stop_queue(netdev_get_tx_queue(port->vp->dev, port->q_index));
+}
+
 static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 {
 	struct mdesc_handle *hp;
@@ -1241,9 +1945,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	if (err)
 		goto err_out_free_port;
 
-	err = vnet_port_alloc_tx_bufs(port);
-	if (err)
-		goto err_out_free_ldc;
+	netif_napi_add(port->vp->dev, &port->napi, vnet_poll, NAPI_POLL_WEIGHT);
 
 	INIT_HLIST_NODE(&port->hash);
 	INIT_LIST_HEAD(&port->list);
@@ -1252,13 +1954,17 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	if (mdesc_get_property(hp, vdev->mp, "switch-port", NULL) != NULL)
 		switch_port = 1;
 	port->switch_port = switch_port;
+	port->tso = true;
+	port->tsolen = 0;
 
 	spin_lock_irqsave(&vp->lock, flags);
 	if (switch_port)
-		list_add(&port->list, &vp->port_list);
+		list_add_rcu(&port->list, &vp->port_list);
 	else
-		list_add_tail(&port->list, &vp->port_list);
-	hlist_add_head(&port->hash, &vp->port_hash[vnet_hashfn(port->raddr)]);
+		list_add_tail_rcu(&port->list, &vp->port_list);
+	hlist_add_head_rcu(&port->hash,
+			   &vp->port_hash[vnet_hashfn(port->raddr)]);
+	vnet_port_add_txq(port);
 	spin_unlock_irqrestore(&vp->lock, flags);
 
 	dev_set_drvdata(&vdev->dev, port);
@@ -1266,15 +1972,16 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	pr_info("%s: PORT ( remote-mac %pM%s )\n",
 		vp->dev->name, port->raddr, switch_port ? " switch-port" : "");
 
+	setup_timer(&port->clean_timer, vnet_clean_timer_expire,
+		    (unsigned long)port);
+
+	napi_enable(&port->napi);
 	vio_port_up(&port->vio);
 
 	mdesc_release(hp);
 
 	return 0;
 
-err_out_free_ldc:
-	vio_ldc_free(&port->vio);
-
 err_out_free_port:
 	kfree(port);
 
@@ -1288,16 +1995,18 @@ static int vnet_port_remove(struct vio_dev *vdev)
 	struct vnet_port *port = dev_get_drvdata(&vdev->dev);
 
 	if (port) {
-		struct vnet *vp = port->vp;
-		unsigned long flags;
 
 		del_timer_sync(&port->vio.timer);
 
-		spin_lock_irqsave(&vp->lock, flags);
-		list_del(&port->list);
-		hlist_del(&port->hash);
-		spin_unlock_irqrestore(&vp->lock, flags);
+		napi_disable(&port->napi);
+
+		list_del_rcu(&port->list);
+		hlist_del_rcu(&port->hash);
 
+		synchronize_rcu();
+		del_timer_sync(&port->clean_timer);
+		vnet_port_rm_txq(port);
+		netif_napi_del(&port->napi);
 		vnet_port_free_tx_bufs(port);
 		vio_ldc_free(&port->vio);
 
diff --git a/drivers/net/ethernet/sun/sunvnet.h b/drivers/net/ethernet/sun/sunvnet.h
index de5c2c64996f..01ca78191683 100644
--- a/drivers/net/ethernet/sun/sunvnet.h
+++ b/drivers/net/ethernet/sun/sunvnet.h
@@ -11,19 +11,30 @@
  */
 #define VNET_TX_TIMEOUT			(5 * HZ)
 
+/* length of time (or less) we expect pending descriptors to be marked
+ * as VIO_DESC_DONE and skbs ready to be freed
+ */
+#define	VNET_CLEAN_TIMEOUT		((HZ/100)+1)
+
+#define VNET_MAXPACKET			(65535ULL + ETH_HLEN + VLAN_HLEN)
 #define VNET_TX_RING_SIZE		512
 #define VNET_TX_WAKEUP_THRESH(dr)	((dr)->pending / 4)
 
+#define	VNET_MINTSO	 2048	/* VIO protocol's minimum TSO len */
+#define	VNET_MAXTSO	65535	/* VIO protocol's maximum TSO len */
+
 /* VNET packets are sent in buffers with the first 6 bytes skipped
  * so that after the ethernet header the IPv4/IPv6 headers are aligned
  * properly.
  */
 #define VNET_PACKET_SKIP		6
 
+#define VNET_MAXCOOKIES			(VNET_MAXPACKET/PAGE_SIZE + 1)
+
 struct vnet_tx_entry {
-	void			*buf;
+	struct sk_buff		*skb;
 	unsigned int		ncookies;
-	struct ldc_trans_cookie	cookies[2];
+	struct ldc_trans_cookie	cookies[VNET_MAXCOOKIES];
 };
 
 struct vnet;
@@ -32,14 +43,30 @@ struct vnet_port {
 
 	struct hlist_node	hash;
 	u8			raddr[ETH_ALEN];
-	u8			switch_port;
-	u8			__pad;
+	unsigned		switch_port:1;
+	unsigned		tso:1;
+	unsigned		__pad:14;
 
 	struct vnet		*vp;
 
 	struct vnet_tx_entry	tx_bufs[VNET_TX_RING_SIZE];
 
 	struct list_head	list;
+
+	u32			stop_rx_idx;
+	bool			stop_rx;
+	bool			start_cons;
+
+	struct timer_list	clean_timer;
+
+	u64			rmtu;
+	u16			tsolen;
+
+	struct napi_struct	napi;
+	u32			napi_stop_idx;
+	bool			napi_resume;
+	int			rx_event;
+	u16			q_index;
 };
 
 static inline struct vnet_port *to_vnet_port(struct vio_driver_state *vio)
@@ -81,7 +108,7 @@ struct vnet {
 	struct list_head	list;
 	u64			local_mac;
 
-	struct tasklet_struct	vnet_tx_wakeup;
+	int			nports;
 };
 
 #endif /* _SUNVNET_H */