These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

4 files changed, 340 insertions, 70 deletions

diff --git a/kernel/drivers/net/vmxnet3/vmxnet3_defs.h b/kernel/drivers/net/vmxnet3/vmxnet3_defs.h
index 3718d024f..221a53025 100644
--- a/kernel/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/kernel/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2015, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -277,6 +277,40 @@ struct Vmxnet3_RxCompDesc {
 #endif  /* __BIG_ENDIAN_BITFIELD */
 };
 
+struct Vmxnet3_RxCompDescExt {
+	__le32		dword1;
+	u8		segCnt;       /* Number of aggregated packets */
+	u8		dupAckCnt;    /* Number of duplicate Acks */
+	__le16		tsDelta;      /* TCP timestamp difference */
+	__le32		dword2;
+#ifdef __BIG_ENDIAN_BITFIELD
+	u32		gen:1;        /* generation bit */
+	u32		type:7;       /* completion type */
+	u32		fcs:1;        /* Frame CRC correct */
+	u32		frg:1;        /* IP Fragment */
+	u32		v4:1;         /* IPv4 */
+	u32		v6:1;         /* IPv6 */
+	u32		ipc:1;        /* IP Checksum Correct */
+	u32		tcp:1;        /* TCP packet */
+	u32		udp:1;        /* UDP packet */
+	u32		tuc:1;        /* TCP/UDP Checksum Correct */
+	u32		mss:16;
+#else
+	u32		mss:16;
+	u32		tuc:1;        /* TCP/UDP Checksum Correct */
+	u32		udp:1;        /* UDP packet */
+	u32		tcp:1;        /* TCP packet */
+	u32		ipc:1;        /* IP Checksum Correct */
+	u32		v6:1;         /* IPv6 */
+	u32		v4:1;         /* IPv4 */
+	u32		frg:1;        /* IP Fragment */
+	u32		fcs:1;        /* Frame CRC correct */
+	u32		type:7;       /* completion type */
+	u32		gen:1;        /* generation bit */
+#endif  /* __BIG_ENDIAN_BITFIELD */
+};
+
+
 /* fields in RxCompDesc we access via Vmxnet3_GenericDesc.dword[3] */
 #define VMXNET3_RCD_TUC_SHIFT	16
 #define VMXNET3_RCD_IPC_SHIFT	19
@@ -310,6 +344,7 @@ union Vmxnet3_GenericDesc {
 	struct Vmxnet3_RxDesc		rxd;
 	struct Vmxnet3_TxCompDesc	tcd;
 	struct Vmxnet3_RxCompDesc	rcd;
+	struct Vmxnet3_RxCompDescExt 	rcdExt;
 };
 
 #define VMXNET3_INIT_GEN       1
@@ -361,6 +396,7 @@ enum {
 /* completion descriptor types */
 #define VMXNET3_CDTYPE_TXCOMP      0    /* Tx Completion Descriptor */
 #define VMXNET3_CDTYPE_RXCOMP      3    /* Rx Completion Descriptor */
+#define VMXNET3_CDTYPE_RXCOMP_LRO  4    /* Rx Completion Descriptor for LRO */
 
 enum {
 	VMXNET3_GOS_BITS_UNK    = 0,   /* unknown */
diff --git a/kernel/drivers/net/vmxnet3/vmxnet3_drv.c b/kernel/drivers/net/vmxnet3/vmxnet3_drv.c
index 61c0840c4..0cbf520ce 100644
--- a/kernel/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/kernel/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -587,6 +587,12 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 						&adapter->pdev->dev,
 						rbi->skb->data, rbi->len,
 						PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      rbi->dma_addr)) {
+					dev_kfree_skb_any(rbi->skb);
+					rq->stats.rx_buf_alloc_failure++;
+					break;
+				}
 			} else {
 				/* rx buffer skipped by the device */
 			}
@@ -605,13 +611,18 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 						&adapter->pdev->dev,
 						rbi->page, 0, PAGE_SIZE,
 						PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      rbi->dma_addr)) {
+					put_page(rbi->page);
+					rq->stats.rx_buf_alloc_failure++;
+					break;
+				}
 			} else {
 				/* rx buffers skipped by the device */
 			}
 			val = VMXNET3_RXD_BTYPE_BODY << VMXNET3_RXD_BTYPE_SHIFT;
 		}
 
-		BUG_ON(rbi->dma_addr == 0);
 		gd->rxd.addr = cpu_to_le64(rbi->dma_addr);
 		gd->dword[2] = cpu_to_le32((!ring->gen << VMXNET3_RXD_GEN_SHIFT)
 					   | val | rbi->len);
@@ -655,7 +666,7 @@ vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd,
 }
 
 
-static void
+static int
 vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		struct vmxnet3_tx_queue *tq, struct pci_dev *pdev,
 		struct vmxnet3_adapter *adapter)
@@ -715,6 +726,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
 				skb->data + buf_offset, buf_size,
 				PCI_DMA_TODEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+			return -EFAULT;
 
 		tbi->len = buf_size;
 
@@ -755,6 +768,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 			tbi->dma_addr = skb_frag_dma_map(&adapter->pdev->dev, frag,
 							 buf_offset, buf_size,
 							 DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+				return -EFAULT;
 
 			tbi->len = buf_size;
 
@@ -782,6 +797,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 	/* set the last buf_info for the pkt */
 	tbi->skb = skb;
 	tbi->sop_idx = ctx->sop_txd - tq->tx_ring.base;
+
+	return 0;
 }
 
 
@@ -861,6 +878,9 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 					     , skb_headlen(skb));
 		}
 
+		if (skb->len <= VMXNET3_HDR_COPY_SIZE)
+			ctx->copy_size = skb->len;
+
 		/* make sure headers are accessible directly */
 		if (unlikely(!pskb_may_pull(skb, ctx->copy_size)))
 			goto err;
@@ -1017,7 +1037,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	}
 
 	/* fill tx descs related to addr & len */
-	vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter);
+	if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter))
+		goto unlock_drop_pkt;
 
 	/* setup the EOP desc */
 	ctx.eop_txd->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP);
@@ -1160,6 +1181,52 @@ vmxnet3_rx_error(struct vmxnet3_rx_queue *rq, struct Vmxnet3_RxCompDesc *rcd,
 }
 
 
+static u32
+vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
+		    union Vmxnet3_GenericDesc *gdesc)
+{
+	u32 hlen, maplen;
+	union {
+		void *ptr;
+		struct ethhdr *eth;
+		struct iphdr *ipv4;
+		struct ipv6hdr *ipv6;
+		struct tcphdr *tcp;
+	} hdr;
+	BUG_ON(gdesc->rcd.tcp == 0);
+
+	maplen = skb_headlen(skb);
+	if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen))
+		return 0;
+
+	hdr.eth = eth_hdr(skb);
+	if (gdesc->rcd.v4) {
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP));
+		hdr.ptr += sizeof(struct ethhdr);
+		BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP);
+		hlen = hdr.ipv4->ihl << 2;
+		hdr.ptr += hdr.ipv4->ihl << 2;
+	} else if (gdesc->rcd.v6) {
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6));
+		hdr.ptr += sizeof(struct ethhdr);
+		/* Use an estimated value, since we also need to handle
+		 * TSO case.
+		 */
+		if (hdr.ipv6->nexthdr != IPPROTO_TCP)
+			return sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
+		hlen = sizeof(struct ipv6hdr);
+		hdr.ptr += sizeof(struct ipv6hdr);
+	} else {
+		/* Non-IP pkt, dont estimate header length */
+		return 0;
+	}
+
+	if (hlen + sizeof(struct tcphdr) > maplen)
+		return 0;
+
+	return (hlen + (hdr.tcp->doff << 2));
+}
+
 static int
 vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		       struct vmxnet3_adapter *adapter, int quota)
@@ -1167,10 +1234,11 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 	static const u32 rxprod_reg[2] = {
 		VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2
 	};
-	u32 num_rxd = 0;
+	u32 num_pkts = 0;
 	bool skip_page_frags = false;
 	struct Vmxnet3_RxCompDesc *rcd;
 	struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx;
+	u16 segCnt = 0, mss = 0;
 #ifdef __BIG_ENDIAN_BITFIELD
 	struct Vmxnet3_RxDesc rxCmdDesc;
 	struct Vmxnet3_RxCompDesc rxComp;
@@ -1181,17 +1249,17 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		struct vmxnet3_rx_buf_info *rbi;
 		struct sk_buff *skb, *new_skb = NULL;
 		struct page *new_page = NULL;
+		dma_addr_t new_dma_addr;
 		int num_to_alloc;
 		struct Vmxnet3_RxDesc *rxd;
 		u32 idx, ring_idx;
 		struct vmxnet3_cmd_ring	*ring = NULL;
-		if (num_rxd >= quota) {
+		if (num_pkts >= quota) {
 			/* we may stop even before we see the EOP desc of
 			 * the current pkt
 			 */
 			break;
 		}
-		num_rxd++;
 		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2);
 		idx = rcd->rxdIdx;
 		ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1;
@@ -1238,6 +1306,21 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				skip_page_frags = true;
 				goto rcd_done;
 			}
+			new_dma_addr = dma_map_single(&adapter->pdev->dev,
+						      new_skb->data, rbi->len,
+						      PCI_DMA_FROMDEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev,
+					      new_dma_addr)) {
+				dev_kfree_skb(new_skb);
+				/* Skb allocation failed, do not handover this
+				 * skb to stack. Reuse it. Drop the existing pkt
+				 */
+				rq->stats.rx_buf_alloc_failure++;
+				ctx->skb = NULL;
+				rq->stats.drop_total++;
+				skip_page_frags = true;
+				goto rcd_done;
+			}
 
 			dma_unmap_single(&adapter->pdev->dev, rbi->dma_addr,
 					 rbi->len,
@@ -1254,12 +1337,22 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 			/* Immediate refill */
 			rbi->skb = new_skb;
-			rbi->dma_addr = dma_map_single(&adapter->pdev->dev,
-						       rbi->skb->data, rbi->len,
-						       PCI_DMA_FROMDEVICE);
+			rbi->dma_addr = new_dma_addr;
 			rxd->addr = cpu_to_le64(rbi->dma_addr);
 			rxd->len = rbi->len;
-
+			if (adapter->version == 2 &&
+			    rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) {
+				struct Vmxnet3_RxCompDescExt *rcdlro;
+				rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd;
+
+				segCnt = rcdlro->segCnt;
+				BUG_ON(segCnt <= 1);
+				mss = rcdlro->mss;
+				if (unlikely(segCnt <= 1))
+					segCnt = 0;
+			} else {
+				segCnt = 0;
+			}
 		} else {
 			BUG_ON(ctx->skb == NULL && !skip_page_frags);
 
@@ -1273,47 +1366,85 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			if (skip_page_frags)
 				goto rcd_done;
 
-			new_page = alloc_page(GFP_ATOMIC);
-			if (unlikely(new_page == NULL)) {
+			if (rcd->len) {
+				new_page = alloc_page(GFP_ATOMIC);
 				/* Replacement page frag could not be allocated.
 				 * Reuse this page. Drop the pkt and free the
 				 * skb which contained this page as a frag. Skip
 				 * processing all the following non-sop frags.
 				 */
-				rq->stats.rx_buf_alloc_failure++;
-				dev_kfree_skb(ctx->skb);
-				ctx->skb = NULL;
-				skip_page_frags = true;
-				goto rcd_done;
-			}
+				if (unlikely(!new_page)) {
+					rq->stats.rx_buf_alloc_failure++;
+					dev_kfree_skb(ctx->skb);
+					ctx->skb = NULL;
+					skip_page_frags = true;
+					goto rcd_done;
+				}
+				new_dma_addr = dma_map_page(&adapter->pdev->dev,
+							    new_page,
+							    0, PAGE_SIZE,
+							    PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      new_dma_addr)) {
+					put_page(new_page);
+					rq->stats.rx_buf_alloc_failure++;
+					dev_kfree_skb(ctx->skb);
+					ctx->skb = NULL;
+					skip_page_frags = true;
+					goto rcd_done;
+				}
 
-			if (rcd->len) {
 				dma_unmap_page(&adapter->pdev->dev,
 					       rbi->dma_addr, rbi->len,
 					       PCI_DMA_FROMDEVICE);
 
 				vmxnet3_append_frag(ctx->skb, rcd, rbi);
-			}
 
-			/* Immediate refill */
-			rbi->page = new_page;
-			rbi->dma_addr = dma_map_page(&adapter->pdev->dev,
-						     rbi->page,
-						     0, PAGE_SIZE,
-						     PCI_DMA_FROMDEVICE);
-			rxd->addr = cpu_to_le64(rbi->dma_addr);
-			rxd->len = rbi->len;
+				/* Immediate refill */
+				rbi->page = new_page;
+				rbi->dma_addr = new_dma_addr;
+				rxd->addr = cpu_to_le64(rbi->dma_addr);
+				rxd->len = rbi->len;
+			}
 		}
 
 
 		skb = ctx->skb;
 		if (rcd->eop) {
+			u32 mtu = adapter->netdev->mtu;
 			skb->len += skb->data_len;
 
 			vmxnet3_rx_csum(adapter, skb,
 					(union Vmxnet3_GenericDesc *)rcd);
 			skb->protocol = eth_type_trans(skb, adapter->netdev);
-
+			if (!rcd->tcp || !adapter->lro)
+				goto not_lro;
+
+			if (segCnt != 0 && mss != 0) {
+				skb_shinfo(skb)->gso_type = rcd->v4 ?
+					SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+				skb_shinfo(skb)->gso_size = mss;
+				skb_shinfo(skb)->gso_segs = segCnt;
+			} else if (segCnt != 0 || skb->len > mtu) {
+				u32 hlen;
+
+				hlen = vmxnet3_get_hdr_len(adapter, skb,
+					(union Vmxnet3_GenericDesc *)rcd);
+				if (hlen == 0)
+					goto not_lro;
+
+				skb_shinfo(skb)->gso_type =
+					rcd->v4 ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+				if (segCnt != 0) {
+					skb_shinfo(skb)->gso_segs = segCnt;
+					skb_shinfo(skb)->gso_size =
+						DIV_ROUND_UP(skb->len -
+							hlen, segCnt);
+				} else {
+					skb_shinfo(skb)->gso_size = mtu - hlen;
+				}
+			}
+not_lro:
 			if (unlikely(rcd->ts))
 				__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rcd->tci);
 
@@ -1323,6 +1454,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				napi_gro_receive(&rq->napi, skb);
 
 			ctx->skb = NULL;
+			num_pkts++;
 		}
 
 rcd_done:
@@ -1353,7 +1485,7 @@ rcd_done:
 				  &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp);
 	}
 
-	return num_rxd;
+	return num_pkts;
 }
 
 
@@ -2067,16 +2199,18 @@ vmxnet3_set_mc(struct net_device *netdev)
 		if (!netdev_mc_empty(netdev)) {
 			new_table = vmxnet3_copy_mc(netdev);
 			if (new_table) {
-				rxConf->mfTableLen = cpu_to_le16(
-					netdev_mc_count(netdev) * ETH_ALEN);
+				size_t sz = netdev_mc_count(netdev) * ETH_ALEN;
+
+				rxConf->mfTableLen = cpu_to_le16(sz);
 				new_table_pa = dma_map_single(
 							&adapter->pdev->dev,
 							new_table,
-							rxConf->mfTableLen,
+							sz,
 							PCI_DMA_TODEVICE);
 			}
 
-			if (new_table_pa) {
+			if (!dma_mapping_error(&adapter->pdev->dev,
+					       new_table_pa)) {
 				new_mode |= VMXNET3_RXM_MCAST;
 				rxConf->mfTablePA = cpu_to_le64(new_table_pa);
 			} else {
@@ -2984,6 +3118,11 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
 					     sizeof(struct vmxnet3_adapter),
 					     PCI_DMA_TODEVICE);
+	if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
+		dev_err(&pdev->dev, "Failed to map dma\n");
+		err = -EFAULT;
+		goto err_dma_map;
+	}
 	adapter->shared = dma_alloc_coherent(
 				&adapter->pdev->dev,
 				sizeof(struct Vmxnet3_DriverShared),
@@ -3038,14 +3177,19 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & 1) {
+	if (ver & 2) {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 2);
+		adapter->version = 2;
+	} else if (ver & 1) {
 		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1);
+		adapter->version = 1;
 	} else {
 		dev_err(&pdev->dev,
 			"Incompatible h/w version (0x%x) for adapter\n", ver);
 		err = -EBUSY;
 		goto err_ver;
 	}
+	dev_dbg(&pdev->dev, "Using device version %d\n", adapter->version);
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS);
 	if (ver & 1) {
@@ -3137,6 +3281,7 @@ err_alloc_queue_desc:
 err_alloc_shared:
 	dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
 			 sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
+err_dma_map:
 	free_netdev(netdev);
 	return err;
 }
@@ -3184,6 +3329,32 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 	free_netdev(netdev);
 }
 
+static void vmxnet3_shutdown_device(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	unsigned long flags;
+
+	/* Reset_work may be in the middle of resetting the device, wait for its
+	 * completion.
+	 */
+	while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))
+		msleep(1);
+
+	if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED,
+			     &adapter->state)) {
+		clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
+		return;
+	}
+	spin_lock_irqsave(&adapter->cmd_lock, flags);
+	VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+			       VMXNET3_CMD_QUIESCE_DEV);
+	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	vmxnet3_disable_all_intrs(adapter);
+
+	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
+}
+
 
 #ifdef CONFIG_PM
 
@@ -3360,6 +3531,7 @@ static struct pci_driver vmxnet3_driver = {
 	.id_table	= vmxnet3_pciid_table,
 	.probe		= vmxnet3_probe_device,
 	.remove		= vmxnet3_remove_device,
+	.shutdown	= vmxnet3_shutdown_device,
 #ifdef CONFIG_PM
 	.driver.pm	= &vmxnet3_pm_ops,
 #endif
diff --git a/kernel/drivers/net/vmxnet3/vmxnet3_ethtool.c b/kernel/drivers/net/vmxnet3/vmxnet3_ethtool.c
index c1d0e7a9d..9ba11d737 100644
--- a/kernel/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/kernel/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -183,16 +183,22 @@ vmxnet3_get_sset_count(struct net_device *netdev, int sset)
 }
 
 
-/* Should be multiple of 4 */
-#define NUM_TX_REGS	8
-#define NUM_RX_REGS	12
-
+/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with
+ * the version 2 of the vmxnet3 support for ethtool(8) --register-dump.
+ * Therefore, if any registers are added, removed or modified, then a version
+ * bump and a corresponding change in the vmxnet3 support for ethtool(8)
+ * --register-dump would be required.
+ */
 static int
 vmxnet3_get_regs_len(struct net_device *netdev)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
-	return (adapter->num_tx_queues * NUM_TX_REGS * sizeof(u32) +
-		adapter->num_rx_queues * NUM_RX_REGS * sizeof(u32));
+
+	return ((9 /* BAR1 registers */ +
+		(1 + adapter->intr.num_intrs) +
+		(1 + adapter->num_tx_queues * 17 /* Tx queue registers */) +
+		(1 + adapter->num_rx_queues * 23 /* Rx queue registers */)) *
+		sizeof(u32));
 }
 
 
@@ -208,10 +214,6 @@ vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
-	drvinfo->n_stats = vmxnet3_get_sset_count(netdev, ETH_SS_STATS);
-	drvinfo->testinfo_len = 0;
-	drvinfo->eedump_len   = 0;
-	drvinfo->regdump_len  = vmxnet3_get_regs_len(netdev);
 }
 
 
@@ -342,6 +344,12 @@ vmxnet3_get_ethtool_stats(struct net_device *netdev,
 }
 
 
+/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with
+ * the version 2 of the vmxnet3 support for ethtool(8) --register-dump.
+ * Therefore, if any registers are added, removed or modified, then a version
+ * bump and a corresponding change in the vmxnet3 support for ethtool(8)
+ * --register-dump would be required.
+ */
 static void
 vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 {
@@ -351,40 +359,90 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 
 	memset(p, 0, vmxnet3_get_regs_len(netdev));
 
-	regs->version = 1;
+	regs->version = 2;
 
 	/* Update vmxnet3_get_regs_len if we want to dump more registers */
 
-	/* make each ring use multiple of 16 bytes */
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		buf[j++] = adapter->tx_queue[i].tx_ring.next2fill;
-		buf[j++] = adapter->tx_queue[i].tx_ring.next2comp;
-		buf[j++] = adapter->tx_queue[i].tx_ring.gen;
-		buf[j++] = 0;
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAL);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAH);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACL);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACH);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR);
+	buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ECR);
+
+	buf[j++] = adapter->intr.num_intrs;
+	for (i = 0; i < adapter->intr.num_intrs; i++) {
+		buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_IMR
+						 + i * VMXNET3_REG_ALIGN);
+	}
 
-		buf[j++] = adapter->tx_queue[i].comp_ring.next2proc;
-		buf[j++] = adapter->tx_queue[i].comp_ring.gen;
-		buf[j++] = adapter->tx_queue[i].stopped;
-		buf[j++] = 0;
+	buf[j++] = adapter->num_tx_queues;
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i];
+
+		buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_TXPROD +
+						 i * VMXNET3_REG_ALIGN);
+
+		buf[j++] = VMXNET3_GET_ADDR_LO(tq->tx_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(tq->tx_ring.basePA);
+		buf[j++] = tq->tx_ring.size;
+		buf[j++] = tq->tx_ring.next2fill;
+		buf[j++] = tq->tx_ring.next2comp;
+		buf[j++] = tq->tx_ring.gen;
+
+		buf[j++] = VMXNET3_GET_ADDR_LO(tq->data_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(tq->data_ring.basePA);
+		buf[j++] = tq->data_ring.size;
+		/* transmit data ring buffer size */
+		buf[j++] = VMXNET3_HDR_COPY_SIZE;
+
+		buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA);
+		buf[j++] = tq->comp_ring.size;
+		buf[j++] = tq->comp_ring.next2proc;
+		buf[j++] = tq->comp_ring.gen;
+
+		buf[j++] = tq->stopped;
 	}
 
+	buf[j++] = adapter->num_rx_queues;
 	for (i = 0; i < adapter->num_rx_queues; i++) {
-		buf[j++] = adapter->rx_queue[i].rx_ring[0].next2fill;
-		buf[j++] = adapter->rx_queue[i].rx_ring[0].next2comp;
-		buf[j++] = adapter->rx_queue[i].rx_ring[0].gen;
+		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+
+		buf[j++] =  VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD +
+						  i * VMXNET3_REG_ALIGN);
+		buf[j++] =  VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD2 +
+						  i * VMXNET3_REG_ALIGN);
+
+		buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[0].basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[0].basePA);
+		buf[j++] = rq->rx_ring[0].size;
+		buf[j++] = rq->rx_ring[0].next2fill;
+		buf[j++] = rq->rx_ring[0].next2comp;
+		buf[j++] = rq->rx_ring[0].gen;
+
+		buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[1].basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[1].basePA);
+		buf[j++] = rq->rx_ring[1].size;
+		buf[j++] = rq->rx_ring[1].next2fill;
+		buf[j++] = rq->rx_ring[1].next2comp;
+		buf[j++] = rq->rx_ring[1].gen;
+
+		/* receive data ring */
 		buf[j++] = 0;
-
-		buf[j++] = adapter->rx_queue[i].rx_ring[1].next2fill;
-		buf[j++] = adapter->rx_queue[i].rx_ring[1].next2comp;
-		buf[j++] = adapter->rx_queue[i].rx_ring[1].gen;
 		buf[j++] = 0;
-
-		buf[j++] = adapter->rx_queue[i].comp_ring.next2proc;
-		buf[j++] = adapter->rx_queue[i].comp_ring.gen;
 		buf[j++] = 0;
 		buf[j++] = 0;
-	}
 
+		buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA);
+		buf[j++] = rq->comp_ring.size;
+		buf[j++] = rq->comp_ring.next2proc;
+		buf[j++] = rq->comp_ring.gen;
+	}
 }
 
 
diff --git a/kernel/drivers/net/vmxnet3/vmxnet3_int.h b/kernel/drivers/net/vmxnet3/vmxnet3_int.h
index 6bb769ae7..bdb8a6c0f 100644
--- a/kernel/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/kernel/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.3.5.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.5.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01030500
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040500
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
@@ -328,6 +328,10 @@ struct vmxnet3_adapter {
 
 	u8			__iomem *hw_addr0; /* for BAR 0 */
 	u8			__iomem *hw_addr1; /* for BAR 1 */
+	u8                              version;
+
+	bool				rxcsum;
+	bool				lro;
 
 #ifdef VMXNET3_RSS
 	struct UPT1_RSSConf		*rss_conf;