Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

6 files changed, 585 insertions, 82 deletions

diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index 880f5098eac9..8cdbb63d1bb0 100644
--- a/drivers/net/vmxnet3/Makefile
+++ b/drivers/net/vmxnet3/Makefile
@@ -2,7 +2,7 @@
 #
 # Linux driver for VMware's vmxnet3 ethernet NIC.
 #
-# Copyright (C) 2007-2009, VMware, Inc. All Rights Reserved.
+# Copyright (C) 2007-2016, 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
@@ -21,7 +21,7 @@
 # The full GNU General Public License is included in this distribution in
 # the file called "COPYING".
 #
-# Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+# Maintained by: pv-drivers@vmware.com
 #
 #
 ################################################################################
diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h
index 969c751ee404..db9f1fde3aac 100644
--- a/drivers/net/vmxnet3/upt1_defs.h
+++ b/drivers/net/vmxnet3/upt1_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) 2008-2016, 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
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 72ba8ae7f09a..c3a31646189f 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2015, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, 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
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -76,7 +76,12 @@ enum {
 	VMXNET3_CMD_UPDATE_IML,
 	VMXNET3_CMD_UPDATE_PMCFG,
 	VMXNET3_CMD_UPDATE_FEATURE,
+	VMXNET3_CMD_RESERVED1,
 	VMXNET3_CMD_LOAD_PLUGIN,
+	VMXNET3_CMD_RESERVED2,
+	VMXNET3_CMD_RESERVED3,
+	VMXNET3_CMD_SET_COALESCE,
+	VMXNET3_CMD_REGISTER_MEMREGS,
 
 	VMXNET3_CMD_FIRST_GET = 0xF00D0000,
 	VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET,
@@ -87,7 +92,10 @@ enum {
 	VMXNET3_CMD_GET_DID_LO,
 	VMXNET3_CMD_GET_DID_HI,
 	VMXNET3_CMD_GET_DEV_EXTRA_INFO,
-	VMXNET3_CMD_GET_CONF_INTR
+	VMXNET3_CMD_GET_CONF_INTR,
+	VMXNET3_CMD_GET_RESERVED1,
+	VMXNET3_CMD_GET_TXDATA_DESC_SIZE,
+	VMXNET3_CMD_GET_COALESCE,
 };
 
 /*
@@ -169,6 +177,8 @@ struct Vmxnet3_TxDataDesc {
 	u8		data[VMXNET3_HDR_COPY_SIZE];
 };
 
+typedef u8 Vmxnet3_RxDataDesc;
+
 #define VMXNET3_TCD_GEN_SHIFT	31
 #define VMXNET3_TCD_GEN_SIZE	1
 #define VMXNET3_TCD_TXIDX_SHIFT	0
@@ -373,6 +383,14 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_RING_SIZE_ALIGN 32
 #define VMXNET3_RING_SIZE_MASK  (VMXNET3_RING_SIZE_ALIGN - 1)
 
+/* Tx Data Ring buffer size must be a multiple of 64 */
+#define VMXNET3_TXDATA_DESC_SIZE_ALIGN 64
+#define VMXNET3_TXDATA_DESC_SIZE_MASK  (VMXNET3_TXDATA_DESC_SIZE_ALIGN - 1)
+
+/* Rx Data Ring buffer size must be a multiple of 64 */
+#define VMXNET3_RXDATA_DESC_SIZE_ALIGN 64
+#define VMXNET3_RXDATA_DESC_SIZE_MASK  (VMXNET3_RXDATA_DESC_SIZE_ALIGN - 1)
+
 /* Max ring size */
 #define VMXNET3_TX_RING_MAX_SIZE   4096
 #define VMXNET3_TC_RING_MAX_SIZE   4096
@@ -380,6 +398,11 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_RX_RING2_MAX_SIZE  4096
 #define VMXNET3_RC_RING_MAX_SIZE   8192
 
+#define VMXNET3_TXDATA_DESC_MIN_SIZE 128
+#define VMXNET3_TXDATA_DESC_MAX_SIZE 2048
+
+#define VMXNET3_RXDATA_DESC_MAX_SIZE 2048
+
 /* a list of reasons for queue stop */
 
 enum {
@@ -466,7 +489,9 @@ struct Vmxnet3_TxQueueConf {
 	__le32		compRingSize; /* # of comp desc */
 	__le32		ddLen;        /* size of driver data */
 	u8		intrIdx;
-	u8		_pad[7];
+	u8		_pad1[1];
+	__le16		txDataRingDescSize;
+	u8		_pad2[4];
 };
 
 
@@ -474,12 +499,14 @@ struct Vmxnet3_RxQueueConf {
 	__le64		rxRingBasePA[2];
 	__le64		compRingBasePA;
 	__le64		ddPA;            /* driver data */
-	__le64		reserved;
+	__le64		rxDataRingBasePA;
 	__le32		rxRingSize[2];   /* # of rx desc */
 	__le32		compRingSize;    /* # of rx comp desc */
 	__le32		ddLen;           /* size of driver data */
 	u8		intrIdx;
-	u8		_pad[7];
+	u8		_pad1[1];
+	__le16		rxDataRingDescSize;  /* size of rx data ring buffer */
+	u8		_pad2[4];
 };
 
 
@@ -609,6 +636,63 @@ struct Vmxnet3_RxQueueDesc {
 	u8				      __pad[88]; /* 128 aligned */
 };
 
+struct Vmxnet3_SetPolling {
+	u8					enablePolling;
+};
+
+#define VMXNET3_COAL_STATIC_MAX_DEPTH		128
+#define VMXNET3_COAL_RBC_MIN_RATE		100
+#define VMXNET3_COAL_RBC_MAX_RATE		100000
+
+enum Vmxnet3_CoalesceMode {
+	VMXNET3_COALESCE_DISABLED   = 0,
+	VMXNET3_COALESCE_ADAPT      = 1,
+	VMXNET3_COALESCE_STATIC     = 2,
+	VMXNET3_COALESCE_RBC        = 3
+};
+
+struct Vmxnet3_CoalesceRbc {
+	u32					rbc_rate;
+};
+
+struct Vmxnet3_CoalesceStatic {
+	u32					tx_depth;
+	u32					tx_comp_depth;
+	u32					rx_depth;
+};
+
+struct Vmxnet3_CoalesceScheme {
+	enum Vmxnet3_CoalesceMode		coalMode;
+	union {
+		struct Vmxnet3_CoalesceRbc	coalRbc;
+		struct Vmxnet3_CoalesceStatic	coalStatic;
+	} coalPara;
+};
+
+struct Vmxnet3_MemoryRegion {
+	__le64					startPA;
+	__le32					length;
+	__le16					txQueueBits;
+	__le16					rxQueueBits;
+};
+
+#define MAX_MEMORY_REGION_PER_QUEUE 16
+#define MAX_MEMORY_REGION_PER_DEVICE 256
+
+struct Vmxnet3_MemRegs {
+	__le16					numRegs;
+	__le16					pad[3];
+	struct Vmxnet3_MemoryRegion		memRegs[1];
+};
+
+/* If the command data <= 16 bytes, use the shared memory directly.
+ * otherwise, use variable length configuration descriptor.
+ */
+union Vmxnet3_CmdInfo {
+	struct Vmxnet3_VariableLenConfDesc	varConf;
+	struct Vmxnet3_SetPolling		setPolling;
+	__le64					data[2];
+};
 
 struct Vmxnet3_DSDevRead {
 	/* read-only region for device, read by dev in response to a SET cmd */
@@ -627,7 +711,14 @@ struct Vmxnet3_DriverShared {
 	__le32				pad;
 	struct Vmxnet3_DSDevRead	devRead;
 	__le32				ecr;
-	__le32				reserved[5];
+	__le32				reserved;
+	union {
+		__le32			reserved1[4];
+		union Vmxnet3_CmdInfo	cmdInfo; /* only valid in the context of
+						  * executing the relevant
+						  * command
+						  */
+	} cu;
 };
 
 
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 08885bc8d6db..c68fe495d3f9 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, 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
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -435,8 +435,8 @@ vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq,
 		tq->tx_ring.base = NULL;
 	}
 	if (tq->data_ring.base) {
-		dma_free_coherent(&adapter->pdev->dev, tq->data_ring.size *
-				  sizeof(struct Vmxnet3_TxDataDesc),
+		dma_free_coherent(&adapter->pdev->dev,
+				  tq->data_ring.size * tq->txdata_desc_size,
 				  tq->data_ring.base, tq->data_ring.basePA);
 		tq->data_ring.base = NULL;
 	}
@@ -478,8 +478,8 @@ vmxnet3_tq_init(struct vmxnet3_tx_queue *tq,
 	tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0;
 	tq->tx_ring.gen = VMXNET3_INIT_GEN;
 
-	memset(tq->data_ring.base, 0, tq->data_ring.size *
-	       sizeof(struct Vmxnet3_TxDataDesc));
+	memset(tq->data_ring.base, 0,
+	       tq->data_ring.size * tq->txdata_desc_size);
 
 	/* reset the tx comp ring contents to 0 and reset comp ring states */
 	memset(tq->comp_ring.base, 0, tq->comp_ring.size *
@@ -514,10 +514,10 @@ vmxnet3_tq_create(struct vmxnet3_tx_queue *tq,
 	}
 
 	tq->data_ring.base = dma_alloc_coherent(&adapter->pdev->dev,
-			tq->data_ring.size * sizeof(struct Vmxnet3_TxDataDesc),
+			tq->data_ring.size * tq->txdata_desc_size,
 			&tq->data_ring.basePA, GFP_KERNEL);
 	if (!tq->data_ring.base) {
-		netdev_err(adapter->netdev, "failed to allocate data ring\n");
+		netdev_err(adapter->netdev, "failed to allocate tx data ring\n");
 		goto err;
 	}
 
@@ -689,7 +689,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 	if (ctx->copy_size) {
 		ctx->sop_txd->txd.addr = cpu_to_le64(tq->data_ring.basePA +
 					tq->tx_ring.next2fill *
-					sizeof(struct Vmxnet3_TxDataDesc));
+					tq->txdata_desc_size);
 		ctx->sop_txd->dword[2] = cpu_to_le32(dw2 | ctx->copy_size);
 		ctx->sop_txd->dword[3] = 0;
 
@@ -873,8 +873,9 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 			ctx->eth_ip_hdr_size = 0;
 			ctx->l4_hdr_size = 0;
 			/* copy as much as allowed */
-			ctx->copy_size = min((unsigned int)VMXNET3_HDR_COPY_SIZE
-					     , skb_headlen(skb));
+			ctx->copy_size = min_t(unsigned int,
+					       tq->txdata_desc_size,
+					       skb_headlen(skb));
 		}
 
 		if (skb->len <= VMXNET3_HDR_COPY_SIZE)
@@ -885,7 +886,7 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 			goto err;
 	}
 
-	if (unlikely(ctx->copy_size > VMXNET3_HDR_COPY_SIZE)) {
+	if (unlikely(ctx->copy_size > tq->txdata_desc_size)) {
 		tq->stats.oversized_hdr++;
 		ctx->copy_size = 0;
 		return 0;
@@ -1283,9 +1284,10 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			 */
 			break;
 		}
-		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2);
+		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
+		       rcd->rqID != rq->dataRingQid);
 		idx = rcd->rxdIdx;
-		ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1;
+		ring_idx = VMXNET3_GET_RING_IDX(adapter, rcd->rqID);
 		ring = rq->rx_ring + ring_idx;
 		vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd,
 				  &rxCmdDesc);
@@ -1300,8 +1302,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		}
 
 		if (rcd->sop) { /* first buf of the pkt */
+			bool rxDataRingUsed;
+			u16 len;
+
 			BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_HEAD ||
-			       rcd->rqID != rq->qid);
+			       (rcd->rqID != rq->qid &&
+				rcd->rqID != rq->dataRingQid));
 
 			BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB);
 			BUG_ON(ctx->skb != NULL || rbi->skb == NULL);
@@ -1317,8 +1323,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 			skip_page_frags = false;
 			ctx->skb = rbi->skb;
+
+			rxDataRingUsed =
+				VMXNET3_RX_DATA_RING(adapter, rcd->rqID);
+			len = rxDataRingUsed ? rcd->len : rbi->len;
 			new_skb = netdev_alloc_skb_ip_align(adapter->netdev,
-							    rbi->len);
+							    len);
 			if (new_skb == NULL) {
 				/* Skb allocation failed, do not handover this
 				 * skb to stack. Reuse it. Drop the existing pkt
@@ -1329,25 +1339,48 @@ 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,
-					 PCI_DMA_FROMDEVICE);
+			if (rxDataRingUsed) {
+				size_t sz;
+
+				BUG_ON(rcd->len > rq->data_ring.desc_size);
+
+				ctx->skb = new_skb;
+				sz = rcd->rxdIdx * rq->data_ring.desc_size;
+				memcpy(new_skb->data,
+				       &rq->data_ring.base[sz], rcd->len);
+			} else {
+				ctx->skb = rbi->skb;
+
+				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,
+						 PCI_DMA_FROMDEVICE);
+
+				/* Immediate refill */
+				rbi->skb = new_skb;
+				rbi->dma_addr = new_dma_addr;
+				rxd->addr = cpu_to_le64(rbi->dma_addr);
+				rxd->len = rbi->len;
+			}
 
 #ifdef VMXNET3_RSS
 			if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE &&
@@ -1358,12 +1391,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 #endif
 			skb_put(ctx->skb, rcd->len);
 
-			/* Immediate refill */
-			rbi->skb = new_skb;
-			rbi->dma_addr = new_dma_addr;
-			rxd->addr = cpu_to_le64(rbi->dma_addr);
-			rxd->len = rbi->len;
-			if (adapter->version == 2 &&
+			if (VMXNET3_VERSION_GE_2(adapter) &&
 			    rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) {
 				struct Vmxnet3_RxCompDescExt *rcdlro;
 				rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd;
@@ -1589,6 +1617,13 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 		rq->buf_info[i] = NULL;
 	}
 
+	if (rq->data_ring.base) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  rq->rx_ring[0].size * rq->data_ring.desc_size,
+				  rq->data_ring.base, rq->data_ring.basePA);
+		rq->data_ring.base = NULL;
+	}
+
 	if (rq->comp_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev, rq->comp_ring.size
 				  * sizeof(struct Vmxnet3_RxCompDesc),
@@ -1604,6 +1639,25 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 	}
 }
 
+void
+vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+
+		if (rq->data_ring.base) {
+			dma_free_coherent(&adapter->pdev->dev,
+					  (rq->rx_ring[0].size *
+					  rq->data_ring.desc_size),
+					  rq->data_ring.base,
+					  rq->data_ring.basePA);
+			rq->data_ring.base = NULL;
+			rq->data_ring.desc_size = 0;
+		}
+	}
+}
 
 static int
 vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
@@ -1697,6 +1751,22 @@ vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter)
 		}
 	}
 
+	if ((adapter->rxdataring_enabled) && (rq->data_ring.desc_size != 0)) {
+		sz = rq->rx_ring[0].size * rq->data_ring.desc_size;
+		rq->data_ring.base =
+			dma_alloc_coherent(&adapter->pdev->dev, sz,
+					   &rq->data_ring.basePA,
+					   GFP_KERNEL);
+		if (!rq->data_ring.base) {
+			netdev_err(adapter->netdev,
+				   "rx data ring will be disabled\n");
+			adapter->rxdataring_enabled = false;
+		}
+	} else {
+		rq->data_ring.base = NULL;
+		rq->data_ring.desc_size = 0;
+	}
+
 	sz = rq->comp_ring.size * sizeof(struct Vmxnet3_RxCompDesc);
 	rq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, sz,
 						&rq->comp_ring.basePA,
@@ -1729,6 +1799,8 @@ vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter)
 {
 	int i, err = 0;
 
+	adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter);
+
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		err = vmxnet3_rq_create(&adapter->rx_queue[i], adapter);
 		if (unlikely(err)) {
@@ -1738,6 +1810,10 @@ vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter)
 			goto err_out;
 		}
 	}
+
+	if (!adapter->rxdataring_enabled)
+		vmxnet3_rq_destroy_all_rxdataring(adapter);
+
 	return err;
 err_out:
 	vmxnet3_rq_destroy_all(adapter);
@@ -2045,10 +2121,9 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
 			struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 			rq->qid = i;
 			rq->qid2 = i + adapter->num_rx_queues;
+			rq->dataRingQid = i + 2 * adapter->num_rx_queues;
 		}
 
-
-
 		/* init our intr settings */
 		for (i = 0; i < intr->num_intrs; i++)
 			intr->mod_levels[i] = UPT1_IML_ADAPTIVE;
@@ -2336,6 +2411,7 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 		tqc->ddPA           = cpu_to_le64(tq->buf_info_pa);
 		tqc->txRingSize     = cpu_to_le32(tq->tx_ring.size);
 		tqc->dataRingSize   = cpu_to_le32(tq->data_ring.size);
+		tqc->txDataRingDescSize = cpu_to_le32(tq->txdata_desc_size);
 		tqc->compRingSize   = cpu_to_le32(tq->comp_ring.size);
 		tqc->ddLen          = cpu_to_le32(
 					sizeof(struct vmxnet3_tx_buf_info) *
@@ -2360,6 +2436,12 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 					(rqc->rxRingSize[0] +
 					 rqc->rxRingSize[1]));
 		rqc->intrIdx         = rq->comp_ring.intr_idx;
+		if (VMXNET3_VERSION_GE_3(adapter)) {
+			rqc->rxDataRingBasePA =
+				cpu_to_le64(rq->data_ring.basePA);
+			rqc->rxDataRingDescSize =
+				cpu_to_le16(rq->data_ring.desc_size);
+		}
 	}
 
 #ifdef VMXNET3_RSS
@@ -2409,6 +2491,32 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 	/* the rest are already zeroed */
 }
 
+static void
+vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter)
+{
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return;
+
+	spin_lock_irqsave(&adapter->cmd_lock, flags);
+	cmdInfo->varConf.confVer = 1;
+	cmdInfo->varConf.confLen =
+		cpu_to_le32(sizeof(*adapter->coal_conf));
+	cmdInfo->varConf.confPA  = cpu_to_le64(adapter->coal_conf_pa);
+
+	if (adapter->default_coal_mode) {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_COALESCE);
+	} else {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_COALESCE);
+	}
+
+	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+}
 
 int
 vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
@@ -2458,6 +2566,8 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 		goto activate_err;
 	}
 
+	vmxnet3_init_coalesce(adapter);
+
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		VMXNET3_WRITE_BAR0_REG(adapter,
 				VMXNET3_REG_RXPROD + i * VMXNET3_REG_ALIGN,
@@ -2689,7 +2799,8 @@ vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter)
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
-		      u32 rx_ring_size, u32 rx_ring2_size)
+		      u32 rx_ring_size, u32 rx_ring2_size,
+		      u16 txdata_desc_size, u16 rxdata_desc_size)
 {
 	int err = 0, i;
 
@@ -2698,6 +2809,7 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 		tq->tx_ring.size   = tx_ring_size;
 		tq->data_ring.size = tx_ring_size;
 		tq->comp_ring.size = tx_ring_size;
+		tq->txdata_desc_size = txdata_desc_size;
 		tq->shared = &adapter->tqd_start[i].ctrl;
 		tq->stopped = true;
 		tq->adapter = adapter;
@@ -2714,12 +2826,15 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 	adapter->rx_queue[0].rx_ring[0].size = rx_ring_size;
 	adapter->rx_queue[0].rx_ring[1].size = rx_ring2_size;
 	vmxnet3_adjust_rx_ring_size(adapter);
+
+	adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter);
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 		/* qid and qid2 for rx queues will be assigned later when num
 		 * of rx queues is finalized after allocating intrs */
 		rq->shared = &adapter->rqd_start[i].ctrl;
 		rq->adapter = adapter;
+		rq->data_ring.desc_size = rxdata_desc_size;
 		err = vmxnet3_rq_create(rq, adapter);
 		if (err) {
 			if (i == 0) {
@@ -2737,6 +2852,10 @@ vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
 			}
 		}
 	}
+
+	if (!adapter->rxdataring_enabled)
+		vmxnet3_rq_destroy_all_rxdataring(adapter);
+
 	return err;
 queue_err:
 	vmxnet3_tq_destroy_all(adapter);
@@ -2754,9 +2873,35 @@ vmxnet3_open(struct net_device *netdev)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		spin_lock_init(&adapter->tx_queue[i].tx_lock);
 
-	err = vmxnet3_create_queues(adapter, adapter->tx_ring_size,
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		unsigned long flags;
+		u16 txdata_desc_size;
+
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_TXDATA_DESC_SIZE);
+		txdata_desc_size = VMXNET3_READ_BAR1_REG(adapter,
+							 VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+
+		if ((txdata_desc_size < VMXNET3_TXDATA_DESC_MIN_SIZE) ||
+		    (txdata_desc_size > VMXNET3_TXDATA_DESC_MAX_SIZE) ||
+		    (txdata_desc_size & VMXNET3_TXDATA_DESC_SIZE_MASK)) {
+			adapter->txdata_desc_size =
+				sizeof(struct Vmxnet3_TxDataDesc);
+		} else {
+			adapter->txdata_desc_size = txdata_desc_size;
+		}
+	} else {
+		adapter->txdata_desc_size = sizeof(struct Vmxnet3_TxDataDesc);
+	}
+
+	err = vmxnet3_create_queues(adapter,
+				    adapter->tx_ring_size,
 				    adapter->rx_ring_size,
-				    adapter->rx_ring2_size);
+				    adapter->rx_ring2_size,
+				    adapter->txdata_desc_size,
+				    adapter->rxdata_desc_size);
 	if (err)
 		goto queue_err;
 
@@ -3200,12 +3345,21 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	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;
+	if (ver & (1 << VMXNET3_REV_3)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_3);
+		adapter->version = VMXNET3_REV_3 + 1;
+	} else if (ver & (1 << VMXNET3_REV_2)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_2);
+		adapter->version = VMXNET3_REV_2 + 1;
+	} else if (ver & (1 << VMXNET3_REV_1)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_1);
+		adapter->version = VMXNET3_REV_1 + 1;
 	} else {
 		dev_err(&pdev->dev,
 			"Incompatible h/w version (0x%x) for adapter\n", ver);
@@ -3224,9 +3378,28 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_ver;
 	}
 
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		adapter->coal_conf =
+			dma_alloc_coherent(&adapter->pdev->dev,
+					   sizeof(struct Vmxnet3_CoalesceScheme)
+					   ,
+					   &adapter->coal_conf_pa,
+					   GFP_KERNEL);
+		if (!adapter->coal_conf) {
+			err = -ENOMEM;
+			goto err_ver;
+		}
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
+		adapter->default_coal_mode = true;
+	}
+
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	vmxnet3_declare_features(adapter, dma64);
 
+	adapter->rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
+		VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
+
 	if (adapter->num_tx_queues == adapter->num_rx_queues)
 		adapter->share_intr = VMXNET3_INTR_BUDDYSHARE;
 	else
@@ -3283,6 +3456,11 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	return 0;
 
 err_register:
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  sizeof(struct Vmxnet3_CoalesceScheme),
+				  adapter->coal_conf, adapter->coal_conf_pa);
+	}
 	vmxnet3_free_intr_resources(adapter);
 err_ver:
 	vmxnet3_free_pci_resources(adapter);
@@ -3333,6 +3511,11 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 
 	vmxnet3_free_intr_resources(adapter);
 	vmxnet3_free_pci_resources(adapter);
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  sizeof(struct Vmxnet3_CoalesceScheme),
+				  adapter->coal_conf, adapter->coal_conf_pa);
+	}
 #ifdef VMXNET3_RSS
 	dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf),
 			  adapter->rss_conf, adapter->rss_conf_pa);
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 9ba11d737753..aabc6ef366b4 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, 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
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -396,8 +396,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 		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++] = tq->txdata_desc_size;
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA);
@@ -431,11 +430,10 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
 		buf[j++] = rq->rx_ring[1].next2comp;
 		buf[j++] = rq->rx_ring[1].gen;
 
-		/* receive data ring */
-		buf[j++] = 0;
-		buf[j++] = 0;
-		buf[j++] = 0;
-		buf[j++] = 0;
+		buf[j++] = VMXNET3_GET_ADDR_LO(rq->data_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(rq->data_ring.basePA);
+		buf[j++] = rq->rx_ring[0].size;
+		buf[j++] = rq->data_ring.desc_size;
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA);
@@ -504,12 +502,14 @@ vmxnet3_get_ringparam(struct net_device *netdev,
 
 	param->rx_max_pending = VMXNET3_RX_RING_MAX_SIZE;
 	param->tx_max_pending = VMXNET3_TX_RING_MAX_SIZE;
-	param->rx_mini_max_pending = 0;
+	param->rx_mini_max_pending = VMXNET3_VERSION_GE_3(adapter) ?
+		VMXNET3_RXDATA_DESC_MAX_SIZE : 0;
 	param->rx_jumbo_max_pending = VMXNET3_RX_RING2_MAX_SIZE;
 
 	param->rx_pending = adapter->rx_ring_size;
 	param->tx_pending = adapter->tx_ring_size;
-	param->rx_mini_pending = 0;
+	param->rx_mini_pending = VMXNET3_VERSION_GE_3(adapter) ?
+		adapter->rxdata_desc_size : 0;
 	param->rx_jumbo_pending = adapter->rx_ring2_size;
 }
 
@@ -520,6 +520,7 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	u32 new_tx_ring_size, new_rx_ring_size, new_rx_ring2_size;
+	u16 new_rxdata_desc_size;
 	u32 sz;
 	int err = 0;
 
@@ -542,6 +543,15 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		if (param->rx_mini_pending < 0 ||
+		    param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE) {
+			return -EINVAL;
+		}
+	} else if (param->rx_mini_pending != 0) {
+		return -EINVAL;
+	}
+
 	/* round it up to a multiple of VMXNET3_RING_SIZE_ALIGN */
 	new_tx_ring_size = (param->tx_pending + VMXNET3_RING_SIZE_MASK) &
 							~VMXNET3_RING_SIZE_MASK;
@@ -568,9 +578,19 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 	new_rx_ring2_size = min_t(u32, new_rx_ring2_size,
 				  VMXNET3_RX_RING2_MAX_SIZE);
 
+	/* rx data ring buffer size has to be a multiple of
+	 * VMXNET3_RXDATA_DESC_SIZE_ALIGN
+	 */
+	new_rxdata_desc_size =
+		(param->rx_mini_pending + VMXNET3_RXDATA_DESC_SIZE_MASK) &
+		~VMXNET3_RXDATA_DESC_SIZE_MASK;
+	new_rxdata_desc_size = min_t(u16, new_rxdata_desc_size,
+				     VMXNET3_RXDATA_DESC_MAX_SIZE);
+
 	if (new_tx_ring_size == adapter->tx_ring_size &&
 	    new_rx_ring_size == adapter->rx_ring_size &&
-	    new_rx_ring2_size == adapter->rx_ring2_size) {
+	    new_rx_ring2_size == adapter->rx_ring2_size &&
+	    new_rxdata_desc_size == adapter->rxdata_desc_size) {
 		return 0;
 	}
 
@@ -591,8 +611,9 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 		vmxnet3_rq_destroy_all(adapter);
 
 		err = vmxnet3_create_queues(adapter, new_tx_ring_size,
-			new_rx_ring_size, new_rx_ring2_size);
-
+					    new_rx_ring_size, new_rx_ring2_size,
+					    adapter->txdata_desc_size,
+					    new_rxdata_desc_size);
 		if (err) {
 			/* failed, most likely because of OOM, try default
 			 * size */
@@ -601,10 +622,15 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 			new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
 			new_rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
 			new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE;
+			new_rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
+				VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
+
 			err = vmxnet3_create_queues(adapter,
 						    new_tx_ring_size,
 						    new_rx_ring_size,
-						    new_rx_ring2_size);
+						    new_rx_ring2_size,
+						    adapter->txdata_desc_size,
+						    new_rxdata_desc_size);
 			if (err) {
 				netdev_err(netdev, "failed to create queues "
 					   "with default sizes. Closing it\n");
@@ -620,6 +646,7 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 	adapter->tx_ring_size = new_tx_ring_size;
 	adapter->rx_ring_size = new_rx_ring_size;
 	adapter->rx_ring2_size = new_rx_ring2_size;
+	adapter->rxdata_desc_size = new_rxdata_desc_size;
 
 out:
 	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
@@ -698,6 +725,162 @@ vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
 }
 #endif
 
+static int
+vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return -EOPNOTSUPP;
+
+	switch (adapter->coal_conf->coalMode) {
+	case VMXNET3_COALESCE_DISABLED:
+		/* struct ethtool_coalesce is already initialized to 0 */
+		break;
+	case VMXNET3_COALESCE_ADAPT:
+		ec->use_adaptive_rx_coalesce = true;
+		break;
+	case VMXNET3_COALESCE_STATIC:
+		ec->tx_max_coalesced_frames =
+			adapter->coal_conf->coalPara.coalStatic.tx_comp_depth;
+		ec->rx_max_coalesced_frames =
+			adapter->coal_conf->coalPara.coalStatic.rx_depth;
+		break;
+	case VMXNET3_COALESCE_RBC: {
+		u32 rbc_rate;
+
+		rbc_rate = adapter->coal_conf->coalPara.coalRbc.rbc_rate;
+		ec->rx_coalesce_usecs = VMXNET3_COAL_RBC_USECS(rbc_rate);
+	}
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return -EOPNOTSUPP;
+
+	if (ec->rx_coalesce_usecs_irq ||
+	    ec->rx_max_coalesced_frames_irq ||
+	    ec->tx_coalesce_usecs ||
+	    ec->tx_coalesce_usecs_irq ||
+	    ec->tx_max_coalesced_frames_irq ||
+	    ec->stats_block_coalesce_usecs ||
+	    ec->use_adaptive_tx_coalesce ||
+	    ec->pkt_rate_low ||
+	    ec->rx_coalesce_usecs_low ||
+	    ec->rx_max_coalesced_frames_low ||
+	    ec->tx_coalesce_usecs_low ||
+	    ec->tx_max_coalesced_frames_low ||
+	    ec->pkt_rate_high ||
+	    ec->rx_coalesce_usecs_high ||
+	    ec->rx_max_coalesced_frames_high ||
+	    ec->tx_coalesce_usecs_high ||
+	    ec->tx_max_coalesced_frames_high ||
+	    ec->rate_sample_interval) {
+		return -EINVAL;
+	}
+
+	if ((ec->rx_coalesce_usecs == 0) &&
+	    (ec->use_adaptive_rx_coalesce == 0) &&
+	    (ec->tx_max_coalesced_frames == 0) &&
+	    (ec->rx_max_coalesced_frames == 0)) {
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
+		goto done;
+	}
+
+	if (ec->rx_coalesce_usecs != 0) {
+		u32 rbc_rate;
+
+		if ((ec->use_adaptive_rx_coalesce != 0) ||
+		    (ec->tx_max_coalesced_frames != 0) ||
+		    (ec->rx_max_coalesced_frames != 0)) {
+			return -EINVAL;
+		}
+
+		rbc_rate = VMXNET3_COAL_RBC_RATE(ec->rx_coalesce_usecs);
+		if (rbc_rate < VMXNET3_COAL_RBC_MIN_RATE ||
+		    rbc_rate > VMXNET3_COAL_RBC_MAX_RATE) {
+			return -EINVAL;
+		}
+
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_RBC;
+		adapter->coal_conf->coalPara.coalRbc.rbc_rate = rbc_rate;
+		goto done;
+	}
+
+	if (ec->use_adaptive_rx_coalesce != 0) {
+		if ((ec->rx_coalesce_usecs != 0) ||
+		    (ec->tx_max_coalesced_frames != 0) ||
+		    (ec->rx_max_coalesced_frames != 0)) {
+			return -EINVAL;
+		}
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_ADAPT;
+		goto done;
+	}
+
+	if ((ec->tx_max_coalesced_frames != 0) ||
+	    (ec->rx_max_coalesced_frames != 0)) {
+		if ((ec->rx_coalesce_usecs != 0) ||
+		    (ec->use_adaptive_rx_coalesce != 0)) {
+			return -EINVAL;
+		}
+
+		if ((ec->tx_max_coalesced_frames >
+		    VMXNET3_COAL_STATIC_MAX_DEPTH) ||
+		    (ec->rx_max_coalesced_frames >
+		     VMXNET3_COAL_STATIC_MAX_DEPTH)) {
+			return -EINVAL;
+		}
+
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_STATIC;
+
+		adapter->coal_conf->coalPara.coalStatic.tx_comp_depth =
+			(ec->tx_max_coalesced_frames ?
+			 ec->tx_max_coalesced_frames :
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH);
+
+		adapter->coal_conf->coalPara.coalStatic.rx_depth =
+			(ec->rx_max_coalesced_frames ?
+			 ec->rx_max_coalesced_frames :
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH);
+
+		adapter->coal_conf->coalPara.coalStatic.tx_depth =
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH;
+		goto done;
+	}
+
+done:
+	adapter->default_coal_mode = false;
+	if (netif_running(netdev)) {
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		cmdInfo->varConf.confVer = 1;
+		cmdInfo->varConf.confLen =
+			cpu_to_le32(sizeof(*adapter->coal_conf));
+		cmdInfo->varConf.confPA  = cpu_to_le64(adapter->coal_conf_pa);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_COALESCE);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_settings      = vmxnet3_get_settings,
 	.get_drvinfo       = vmxnet3_get_drvinfo,
@@ -706,6 +889,8 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_wol           = vmxnet3_get_wol,
 	.set_wol           = vmxnet3_set_wol,
 	.get_link          = ethtool_op_get_link,
+	.get_coalesce      = vmxnet3_get_coalesce,
+	.set_coalesce      = vmxnet3_set_coalesce,
 	.get_strings       = vmxnet3_get_strings,
 	.get_sset_count	   = vmxnet3_get_sset_count,
 	.get_ethtool_stats = vmxnet3_get_ethtool_stats,
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 3d2b64e63408..74fc03072b87 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, 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
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -69,16 +69,20 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.8.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.9.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040800
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040900
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
 	#define VMXNET3_RSS
 #endif
 
+#define VMXNET3_REV_3		2	/* Vmxnet3 Rev. 3 */
+#define VMXNET3_REV_2		1	/* Vmxnet3 Rev. 2 */
+#define VMXNET3_REV_1		0	/* Vmxnet3 Rev. 1 */
+
 /*
  * Capabilities
  */
@@ -237,6 +241,7 @@ struct vmxnet3_tx_queue {
 	int                             num_stop;  /* # of times the queue is
 						    * stopped */
 	int				qid;
+	u16				txdata_desc_size;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 enum vmxnet3_rx_buf_type {
@@ -267,15 +272,23 @@ struct vmxnet3_rq_driver_stats {
 	u64 rx_buf_alloc_failure;
 };
 
+struct vmxnet3_rx_data_ring {
+	Vmxnet3_RxDataDesc *base;
+	dma_addr_t basePA;
+	u16 desc_size;
+};
+
 struct vmxnet3_rx_queue {
 	char			name[IFNAMSIZ + 8]; /* To identify interrupt */
 	struct vmxnet3_adapter	  *adapter;
 	struct napi_struct        napi;
 	struct vmxnet3_cmd_ring   rx_ring[2];
+	struct vmxnet3_rx_data_ring data_ring;
 	struct vmxnet3_comp_ring  comp_ring;
 	struct vmxnet3_rx_ctx     rx_ctx;
 	u32 qid;            /* rqID in RCD for buffer from 1st ring */
 	u32 qid2;           /* rqID in RCD for buffer from 2nd ring */
+	u32 dataRingQid;    /* rqID in RCD for buffer from data ring */
 	struct vmxnet3_rx_buf_info     *buf_info[2];
 	dma_addr_t                      buf_info_pa;
 	struct Vmxnet3_RxQueueCtrl            *shared;
@@ -345,6 +358,7 @@ struct vmxnet3_adapter {
 	int		rx_buf_per_pkt;  /* only apply to the 1st ring */
 	dma_addr_t			shared_pa;
 	dma_addr_t queue_desc_pa;
+	dma_addr_t coal_conf_pa;
 
 	/* Wake-on-LAN */
 	u32     wol;
@@ -359,12 +373,21 @@ struct vmxnet3_adapter {
 	u32 rx_ring_size;
 	u32 rx_ring2_size;
 
+	/* Size of buffer in the data ring */
+	u16 txdata_desc_size;
+	u16 rxdata_desc_size;
+
+	bool rxdataring_enabled;
+
 	struct work_struct work;
 
 	unsigned long  state;    /* VMXNET3_STATE_BIT_xxx */
 
 	int share_intr;
 
+	struct Vmxnet3_CoalesceScheme *coal_conf;
+	bool   default_coal_mode;
+
 	dma_addr_t adapter_pa;
 	dma_addr_t pm_conf_pa;
 	dma_addr_t rss_conf_pa;
@@ -387,14 +410,34 @@ struct vmxnet3_adapter {
 #define VMXNET3_GET_ADDR_LO(dma)   ((u32)(dma))
 #define VMXNET3_GET_ADDR_HI(dma)   ((u32)(((u64)(dma)) >> 32))
 
+#define VMXNET3_VERSION_GE_2(adapter) \
+	(adapter->version >= VMXNET3_REV_2 + 1)
+#define VMXNET3_VERSION_GE_3(adapter) \
+	(adapter->version >= VMXNET3_REV_3 + 1)
+
 /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */
 #define VMXNET3_DEF_TX_RING_SIZE    512
 #define VMXNET3_DEF_RX_RING_SIZE    256
 #define VMXNET3_DEF_RX_RING2_SIZE   128
 
+#define VMXNET3_DEF_RXDATA_DESC_SIZE 128
+
 #define VMXNET3_MAX_ETH_HDR_SIZE    22
 #define VMXNET3_MAX_SKB_BUF_SIZE    (3*1024)
 
+#define VMXNET3_GET_RING_IDX(adapter, rqID)		\
+	((rqID >= adapter->num_rx_queues &&		\
+	 rqID < 2 * adapter->num_rx_queues) ? 1 : 0)	\
+
+#define VMXNET3_RX_DATA_RING(adapter, rqID)		\
+	(rqID >= 2 * adapter->num_rx_queues &&		\
+	rqID < 3 * adapter->num_rx_queues)		\
+
+#define VMXNET3_COAL_STATIC_DEFAULT_DEPTH	64
+
+#define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs)
+#define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate)
+
 int
 vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter);
 
@@ -418,7 +461,8 @@ vmxnet3_set_features(struct net_device *netdev, netdev_features_t features);
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter,
-		      u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size);
+		      u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size,
+		      u16 txdata_desc_size, u16 rxdata_desc_size);
 
 void vmxnet3_set_ethtool_ops(struct net_device *netdev);