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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

6 files changed, 483 insertions, 48 deletions

diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index 8cdbb63d1bb0..c5a167a1c85c 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) 2007-2016, VMware, Inc. All Rights Reserved.
+# Copyright (C) 2007-2020, 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
diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h
index db9f1fde3aac..8c014c98471c 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) 2008-2016, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2020, 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
@@ -92,5 +92,8 @@ enum {
 	UPT1_F_RSS		= cpu_to_le64(0x0002),
 	UPT1_F_RXVLAN		= cpu_to_le64(0x0004),   /* VLAN tag stripping */
 	UPT1_F_LRO		= cpu_to_le64(0x0008),
+	UPT1_F_RXINNEROFLD      = cpu_to_le64(0x00010),  /* Geneve/Vxlan rx csum
+							  * offloading
+							  */
 };
 #endif
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index c3a31646189f..a8d5ebd47c71 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) 2008-2016, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2020, 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
@@ -82,6 +82,7 @@ enum {
 	VMXNET3_CMD_RESERVED3,
 	VMXNET3_CMD_SET_COALESCE,
 	VMXNET3_CMD_REGISTER_MEMREGS,
+	VMXNET3_CMD_SET_RSS_FIELDS,
 
 	VMXNET3_CMD_FIRST_GET = 0xF00D0000,
 	VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET,
@@ -96,19 +97,20 @@ enum {
 	VMXNET3_CMD_GET_RESERVED1,
 	VMXNET3_CMD_GET_TXDATA_DESC_SIZE,
 	VMXNET3_CMD_GET_COALESCE,
+	VMXNET3_CMD_GET_RSS_FIELDS,
 };
 
 /*
  *	Little Endian layout of bitfields -
  *	Byte 0 :	7.....len.....0
- *	Byte 1 :	rsvd gen 13.len.8
+ *	Byte 1 :	oco gen 13.len.8
  *	Byte 2 : 	5.msscof.0 ext1  dtype
  *	Byte 3 : 	13...msscof...6
  *
  *	Big Endian layout of bitfields -
  *	Byte 0:		13...msscof...6
  *	Byte 1 : 	5.msscof.0 ext1  dtype
- *	Byte 2 :	rsvd gen 13.len.8
+ *	Byte 2 :	oco gen 13.len.8
  *	Byte 3 :	7.....len.....0
  *
  *	Thus, le32_to_cpu on the dword will allow the big endian driver to read
@@ -123,13 +125,13 @@ struct Vmxnet3_TxDesc {
 	u32 msscof:14;  /* MSS, checksum offset, flags */
 	u32 ext1:1;
 	u32 dtype:1;    /* descriptor type */
-	u32 rsvd:1;
+	u32 oco:1;
 	u32 gen:1;      /* generation bit */
 	u32 len:14;
 #else
 	u32 len:14;
 	u32 gen:1;      /* generation bit */
-	u32 rsvd:1;
+	u32 oco:1;
 	u32 dtype:1;    /* descriptor type */
 	u32 ext1:1;
 	u32 msscof:14;  /* MSS, checksum offset, flags */
@@ -155,9 +157,10 @@ struct Vmxnet3_TxDesc {
 };
 
 /* TxDesc.OM values */
-#define VMXNET3_OM_NONE		0
-#define VMXNET3_OM_CSUM		2
-#define VMXNET3_OM_TSO		3
+#define VMXNET3_OM_NONE         0
+#define VMXNET3_OM_ENCAP        1
+#define VMXNET3_OM_CSUM         2
+#define VMXNET3_OM_TSO          3
 
 /* fields in TxDesc we access w/o using bit fields */
 #define VMXNET3_TXD_EOP_SHIFT	12
@@ -224,6 +227,8 @@ struct Vmxnet3_RxDesc {
 #define VMXNET3_RXD_BTYPE_SHIFT  14
 #define VMXNET3_RXD_GEN_SHIFT    31
 
+#define VMXNET3_RCD_HDR_INNER_SHIFT  13
+
 struct Vmxnet3_RxCompDesc {
 #ifdef __BIG_ENDIAN_BITFIELD
 	u32		ext2:1;
@@ -685,12 +690,22 @@ struct Vmxnet3_MemRegs {
 	struct Vmxnet3_MemoryRegion		memRegs[1];
 };
 
+enum Vmxnet3_RSSField {
+	VMXNET3_RSS_FIELDS_TCPIP4 = 0x0001,
+	VMXNET3_RSS_FIELDS_TCPIP6 = 0x0002,
+	VMXNET3_RSS_FIELDS_UDPIP4 = 0x0004,
+	VMXNET3_RSS_FIELDS_UDPIP6 = 0x0008,
+	VMXNET3_RSS_FIELDS_ESPIP4 = 0x0010,
+	VMXNET3_RSS_FIELDS_ESPIP6 = 0x0020,
+};
+
 /* 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;
+	enum   Vmxnet3_RSSField                 setRssFields;
 	__le64					data[2];
 };
 
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 722cb054a5cd..ca395f9679d0 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) 2008-2016, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2020, 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
@@ -842,21 +842,46 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	u8 protocol = 0;
 
 	if (ctx->mss) {	/* TSO */
-		ctx->eth_ip_hdr_size = skb_transport_offset(skb);
-		ctx->l4_hdr_size = tcp_hdrlen(skb);
-		ctx->copy_size = ctx->eth_ip_hdr_size + ctx->l4_hdr_size;
+		if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation) {
+			ctx->l4_offset = skb_inner_transport_offset(skb);
+			ctx->l4_hdr_size = inner_tcp_hdrlen(skb);
+			ctx->copy_size = ctx->l4_offset + ctx->l4_hdr_size;
+		} else {
+			ctx->l4_offset = skb_transport_offset(skb);
+			ctx->l4_hdr_size = tcp_hdrlen(skb);
+			ctx->copy_size = ctx->l4_offset + ctx->l4_hdr_size;
+		}
 	} else {
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			ctx->eth_ip_hdr_size = skb_checksum_start_offset(skb);
+			/* For encap packets, skb_checksum_start_offset refers
+			 * to inner L4 offset. Thus, below works for encap as
+			 * well as non-encap case
+			 */
+			ctx->l4_offset = skb_checksum_start_offset(skb);
+
+			if (VMXNET3_VERSION_GE_4(adapter) &&
+			    skb->encapsulation) {
+				struct iphdr *iph = inner_ip_hdr(skb);
 
-			if (ctx->ipv4) {
-				const struct iphdr *iph = ip_hdr(skb);
+				if (iph->version == 4) {
+					protocol = iph->protocol;
+				} else {
+					const struct ipv6hdr *ipv6h;
+
+					ipv6h = inner_ipv6_hdr(skb);
+					protocol = ipv6h->nexthdr;
+				}
+			} else {
+				if (ctx->ipv4) {
+					const struct iphdr *iph = ip_hdr(skb);
 
-				protocol = iph->protocol;
-			} else if (ctx->ipv6) {
-				const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+					protocol = iph->protocol;
+				} else if (ctx->ipv6) {
+					const struct ipv6hdr *ipv6h;
 
-				protocol = ipv6h->nexthdr;
+					ipv6h = ipv6_hdr(skb);
+					protocol = ipv6h->nexthdr;
+				}
 			}
 
 			switch (protocol) {
@@ -871,10 +896,10 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 				break;
 			}
 
-			ctx->copy_size = min(ctx->eth_ip_hdr_size +
+			ctx->copy_size = min(ctx->l4_offset +
 					 ctx->l4_hdr_size, skb->len);
 		} else {
-			ctx->eth_ip_hdr_size = 0;
+			ctx->l4_offset = 0;
 			ctx->l4_hdr_size = 0;
 			/* copy as much as allowed */
 			ctx->copy_size = min_t(unsigned int,
@@ -930,6 +955,25 @@ vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 
 
 static void
+vmxnet3_prepare_inner_tso(struct sk_buff *skb,
+			  struct vmxnet3_tx_ctx *ctx)
+{
+	struct tcphdr *tcph = inner_tcp_hdr(skb);
+	struct iphdr *iph = inner_ip_hdr(skb);
+
+	if (iph->version == 4) {
+		iph->check = 0;
+		tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, 0,
+						 IPPROTO_TCP, 0);
+	} else {
+		struct ipv6hdr *iph = inner_ipv6_hdr(skb);
+
+		tcph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, 0,
+					       IPPROTO_TCP, 0);
+	}
+}
+
+static void
 vmxnet3_prepare_tso(struct sk_buff *skb,
 		    struct vmxnet3_tx_ctx *ctx)
 {
@@ -987,6 +1031,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	/* Use temporary descriptor to avoid touching bits multiple times */
 	union Vmxnet3_GenericDesc tempTxDesc;
 #endif
+	struct udphdr *udph;
 
 	count = txd_estimate(skb);
 
@@ -1003,7 +1048,11 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 			}
 			tq->stats.copy_skb_header++;
 		}
-		vmxnet3_prepare_tso(skb, &ctx);
+		if (skb->encapsulation) {
+			vmxnet3_prepare_inner_tso(skb, &ctx);
+		} else {
+			vmxnet3_prepare_tso(skb, &ctx);
+		}
 	} else {
 		if (unlikely(count > VMXNET3_MAX_TXD_PER_PKT)) {
 
@@ -1026,14 +1075,14 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		BUG_ON(ret <= 0 && ctx.copy_size != 0);
 		/* hdrs parsed, check against other limits */
 		if (ctx.mss) {
-			if (unlikely(ctx.eth_ip_hdr_size + ctx.l4_hdr_size >
+			if (unlikely(ctx.l4_offset + ctx.l4_hdr_size >
 				     VMXNET3_MAX_TX_BUF_SIZE)) {
 				tq->stats.drop_oversized_hdr++;
 				goto drop_pkt;
 			}
 		} else {
 			if (skb->ip_summed == CHECKSUM_PARTIAL) {
-				if (unlikely(ctx.eth_ip_hdr_size +
+				if (unlikely(ctx.l4_offset +
 					     skb->csum_offset >
 					     VMXNET3_MAX_CSUM_OFFSET)) {
 					tq->stats.drop_oversized_hdr++;
@@ -1080,16 +1129,34 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 #endif
 	tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred);
 	if (ctx.mss) {
-		gdesc->txd.hlen = ctx.eth_ip_hdr_size + ctx.l4_hdr_size;
-		gdesc->txd.om = VMXNET3_OM_TSO;
-		gdesc->txd.msscof = ctx.mss;
+		if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation) {
+			gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size;
+			gdesc->txd.om = VMXNET3_OM_ENCAP;
+			gdesc->txd.msscof = ctx.mss;
+
+			udph = udp_hdr(skb);
+			if (udph->check)
+				gdesc->txd.oco = 1;
+		} else {
+			gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size;
+			gdesc->txd.om = VMXNET3_OM_TSO;
+			gdesc->txd.msscof = ctx.mss;
+		}
 		num_pkts = (skb->len - gdesc->txd.hlen + ctx.mss - 1) / ctx.mss;
 	} else {
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			gdesc->txd.hlen = ctx.eth_ip_hdr_size;
-			gdesc->txd.om = VMXNET3_OM_CSUM;
-			gdesc->txd.msscof = ctx.eth_ip_hdr_size +
-					    skb->csum_offset;
+			if (VMXNET3_VERSION_GE_4(adapter) &&
+			    skb->encapsulation) {
+				gdesc->txd.hlen = ctx.l4_offset +
+						  ctx.l4_hdr_size;
+				gdesc->txd.om = VMXNET3_OM_ENCAP;
+				gdesc->txd.msscof = 0;		/* Reserved */
+			} else {
+				gdesc->txd.hlen = ctx.l4_offset;
+				gdesc->txd.om = VMXNET3_OM_CSUM;
+				gdesc->txd.msscof = ctx.l4_offset +
+						    skb->csum_offset;
+			}
 		} else {
 			gdesc->txd.om = 0;
 			gdesc->txd.msscof = 0;
@@ -1168,13 +1235,21 @@ vmxnet3_rx_csum(struct vmxnet3_adapter *adapter,
 		    (le32_to_cpu(gdesc->dword[3]) &
 		     VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			BUG_ON(!(gdesc->rcd.tcp || gdesc->rcd.udp));
-			BUG_ON(gdesc->rcd.frg);
+			WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
+				     !(le32_to_cpu(gdesc->dword[0]) &
+				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
+			WARN_ON_ONCE(gdesc->rcd.frg &&
+				     !(le32_to_cpu(gdesc->dword[0]) &
+				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
 		} else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) &
 					     (1 << VMXNET3_RCD_TUC_SHIFT))) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			BUG_ON(!(gdesc->rcd.tcp || gdesc->rcd.udp));
-			BUG_ON(gdesc->rcd.frg);
+			WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
+				     !(le32_to_cpu(gdesc->dword[0]) &
+				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
+			WARN_ON_ONCE(gdesc->rcd.frg &&
+				     !(le32_to_cpu(gdesc->dword[0]) &
+				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
 		} else {
 			if (gdesc->rcd.csum) {
 				skb->csum = htons(gdesc->rcd.csum);
@@ -2429,6 +2504,10 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 	if (adapter->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
 		devRead->misc.uptFeatures |= UPT1_F_RXVLAN;
 
+	if (adapter->netdev->features & (NETIF_F_GSO_UDP_TUNNEL |
+					 NETIF_F_GSO_UDP_TUNNEL_CSUM))
+		devRead->misc.uptFeatures |= UPT1_F_RXINNEROFLD;
+
 	devRead->misc.mtu = cpu_to_le32(adapter->netdev->mtu);
 	devRead->misc.queueDescPA = cpu_to_le64(adapter->queue_desc_pa);
 	devRead->misc.queueDescLen = cpu_to_le32(
@@ -2554,6 +2633,39 @@ vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
 }
 
+static void
+vmxnet3_init_rssfields(struct vmxnet3_adapter *adapter)
+{
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_4(adapter))
+		return;
+
+	spin_lock_irqsave(&adapter->cmd_lock, flags);
+
+	if (adapter->default_rss_fields) {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_RSS_FIELDS);
+		adapter->rss_fields =
+			VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+	} else {
+		cmdInfo->setRssFields = adapter->rss_fields;
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_RSS_FIELDS);
+		/* Not all requested RSS may get applied, so get and
+		 * cache what was actually applied.
+		 */
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_RSS_FIELDS);
+		adapter->rss_fields =
+			VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+	}
+
+	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+}
+
 int
 vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 {
@@ -2603,6 +2715,7 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
 	}
 
 	vmxnet3_init_coalesce(adapter);
+	vmxnet3_init_rssfields(adapter);
 
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		VMXNET3_WRITE_BAR0_REG(adapter,
@@ -3039,6 +3152,18 @@ vmxnet3_declare_features(struct vmxnet3_adapter *adapter, bool dma64)
 		NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
 		NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 |
 		NETIF_F_LRO;
+
+	if (VMXNET3_VERSION_GE_4(adapter)) {
+		netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL |
+				NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+		netdev->hw_enc_features = NETIF_F_SG | NETIF_F_RXCSUM |
+			NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
+			NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 |
+			NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL |
+			NETIF_F_GSO_UDP_TUNNEL_CSUM;
+	}
+
 	if (dma64)
 		netdev->hw_features |= NETIF_F_HIGHDMA;
 	netdev->vlan_features = netdev->hw_features &
@@ -3382,7 +3507,12 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & (1 << VMXNET3_REV_3)) {
+	if (ver & (1 << VMXNET3_REV_4)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_4);
+		adapter->version = VMXNET3_REV_4 + 1;
+	} else if (ver & (1 << VMXNET3_REV_3)) {
 		VMXNET3_WRITE_BAR1_REG(adapter,
 				       VMXNET3_REG_VRRS,
 				       1 << VMXNET3_REV_3);
@@ -3430,6 +3560,11 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		adapter->default_coal_mode = true;
 	}
 
+	if (VMXNET3_VERSION_GE_4(adapter)) {
+		adapter->default_rss_fields = true;
+		adapter->rss_fields = VMXNET3_RSS_FIELDS_DEFAULT;
+	}
+
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	vmxnet3_declare_features(adapter, dma64);
 
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 6528940ce5f3..def27afa1c69 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) 2008-2016, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2020, 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
@@ -267,14 +267,43 @@ netdev_features_t vmxnet3_fix_features(struct net_device *netdev,
 	return features;
 }
 
+static void vmxnet3_enable_encap_offloads(struct net_device *netdev)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+	if (VMXNET3_VERSION_GE_4(adapter)) {
+		netdev->hw_enc_features |= NETIF_F_SG | NETIF_F_RXCSUM |
+			NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
+			NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 |
+			NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL |
+			NETIF_F_GSO_UDP_TUNNEL_CSUM;
+	}
+}
+
+static void vmxnet3_disable_encap_offloads(struct net_device *netdev)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+	if (VMXNET3_VERSION_GE_4(adapter)) {
+		netdev->hw_enc_features &= ~(NETIF_F_SG | NETIF_F_RXCSUM |
+			NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
+			NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 |
+			NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL |
+			NETIF_F_GSO_UDP_TUNNEL_CSUM);
+	}
+}
+
 int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	unsigned long flags;
 	netdev_features_t changed = features ^ netdev->features;
+	netdev_features_t tun_offload_mask = NETIF_F_GSO_UDP_TUNNEL |
+					     NETIF_F_GSO_UDP_TUNNEL_CSUM;
+	u8 udp_tun_enabled = (netdev->features & tun_offload_mask) != 0;
 
 	if (changed & (NETIF_F_RXCSUM | NETIF_F_LRO |
-		       NETIF_F_HW_VLAN_CTAG_RX)) {
+		       NETIF_F_HW_VLAN_CTAG_RX | tun_offload_mask)) {
 		if (features & NETIF_F_RXCSUM)
 			adapter->shared->devRead.misc.uptFeatures |=
 			UPT1_F_RXCSUM;
@@ -297,6 +326,17 @@ int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features)
 			adapter->shared->devRead.misc.uptFeatures &=
 			~UPT1_F_RXVLAN;
 
+		if ((features & tun_offload_mask) != 0 && !udp_tun_enabled) {
+			vmxnet3_enable_encap_offloads(netdev);
+			adapter->shared->devRead.misc.uptFeatures |=
+			UPT1_F_RXINNEROFLD;
+		} else if ((features & tun_offload_mask) == 0 &&
+			   udp_tun_enabled) {
+			vmxnet3_disable_encap_offloads(netdev);
+			adapter->shared->devRead.misc.uptFeatures &=
+			~UPT1_F_RXINNEROFLD;
+		}
+
 		spin_lock_irqsave(&adapter->cmd_lock, flags);
 		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
 				       VMXNET3_CMD_UPDATE_FEATURE);
@@ -665,18 +705,244 @@ out:
 	return err;
 }
 
+static int
+vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter,
+			  struct ethtool_rxnfc *info)
+{
+	enum Vmxnet3_RSSField rss_fields;
+
+	if (netif_running(adapter->netdev)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_RSS_FIELDS);
+		rss_fields = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	} else {
+		rss_fields = adapter->rss_fields;
+	}
+
+	info->data = 0;
+
+	/* Report default options for RSS on vmxnet3 */
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 |
+			      RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case UDP_V4_FLOW:
+		if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP4)
+			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+		if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4)
+			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+			/* fallthrough */
+	case SCTP_V4_FLOW:
+	case IPV4_FLOW:
+		info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case UDP_V6_FLOW:
+		if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP6)
+			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV6_FLOW:
+		info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_set_rss_hash_opt(struct net_device *netdev,
+			 struct vmxnet3_adapter *adapter,
+			 struct ethtool_rxnfc *nfc)
+{
+	enum Vmxnet3_RSSField rss_fields = adapter->rss_fields;
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    !(nfc->data & RXH_L4_B_0_1) ||
+		    !(nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	case UDP_V4_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_fields &= ~VMXNET3_RSS_FIELDS_UDPIP4;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_fields |= VMXNET3_RSS_FIELDS_UDPIP4;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case UDP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_fields &= ~VMXNET3_RSS_FIELDS_UDPIP6;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_fields |= VMXNET3_RSS_FIELDS_UDPIP6;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_fields &= ~VMXNET3_RSS_FIELDS_ESPIP4;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_fields |= VMXNET3_RSS_FIELDS_ESPIP4;
+		break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    (nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* if we changed something we need to update flags */
+	if (rss_fields != adapter->rss_fields) {
+		adapter->default_rss_fields = false;
+		if (netif_running(netdev)) {
+			struct Vmxnet3_DriverShared *shared = adapter->shared;
+			union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+			unsigned long flags;
+
+			spin_lock_irqsave(&adapter->cmd_lock, flags);
+			cmdInfo->setRssFields = rss_fields;
+			VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+					       VMXNET3_CMD_SET_RSS_FIELDS);
+
+			/* Not all requested RSS may get applied, so get and
+			 * cache what was actually applied.
+			 */
+			VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+					       VMXNET3_CMD_GET_RSS_FIELDS);
+			adapter->rss_fields =
+				VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
+			spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+		} else {
+			/* When the device is activated, we will try to apply
+			 * these rules and cache the applied value later.
+			 */
+			adapter->rss_fields = rss_fields;
+		}
+	}
+	return 0;
+}
 
 static int
 vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info,
 		  u32 *rules)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	int err = 0;
+
 	switch (info->cmd) {
 	case ETHTOOL_GRXRINGS:
 		info->data = adapter->num_rx_queues;
-		return 0;
+		break;
+	case ETHTOOL_GRXFH:
+		if (!VMXNET3_VERSION_GE_4(adapter)) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+#ifdef VMXNET3_RSS
+		if (!adapter->rss) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+#endif
+		err = vmxnet3_get_rss_hash_opts(adapter, info);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int
+vmxnet3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	int err = 0;
+
+	if (!VMXNET3_VERSION_GE_4(adapter)) {
+		err = -EOPNOTSUPP;
+		goto done;
+	}
+#ifdef VMXNET3_RSS
+	if (!adapter->rss) {
+		err = -EOPNOTSUPP;
+		goto done;
 	}
-	return -EOPNOTSUPP;
+#endif
+
+	switch (info->cmd) {
+	case ETHTOOL_SRXFH:
+		err = vmxnet3_set_rss_hash_opt(netdev, adapter, info);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+done:
+	return err;
 }
 
 #ifdef VMXNET3_RSS
@@ -700,6 +966,8 @@ vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;
 	if (!p)
 		return 0;
+	if (n > UPT1_RSS_MAX_IND_TABLE_SIZE)
+		return 0;
 	while (n--)
 		p[n] = rssConf->indTable[n];
 	return 0;
@@ -887,6 +1155,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_ringparam     = vmxnet3_get_ringparam,
 	.set_ringparam     = vmxnet3_set_ringparam,
 	.get_rxnfc         = vmxnet3_get_rxnfc,
+	.set_rxnfc         = vmxnet3_set_rxnfc,
 #ifdef VMXNET3_RSS
 	.get_rxfh_indir_size = vmxnet3_get_rss_indir_size,
 	.get_rxfh          = vmxnet3_get_rss,
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 1cc1cd4aaa59..5d2b062215a2 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) 2008-2016, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2020, 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
@@ -69,18 +69,19 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.17.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.5.0.0-k"
 
 /* Each byte of this 32-bit integer encodes a version number in
  * VMXNET3_DRIVER_VERSION_STRING.
  */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01041100
+#define VMXNET3_DRIVER_VERSION_NUM      0x01050000
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
 	#define VMXNET3_RSS
 #endif
 
+#define VMXNET3_REV_4		3	/* Vmxnet3 Rev. 4 */
 #define VMXNET3_REV_3		2	/* Vmxnet3 Rev. 3 */
 #define VMXNET3_REV_2		1	/* Vmxnet3 Rev. 2 */
 #define VMXNET3_REV_1		0	/* Vmxnet3 Rev. 1 */
@@ -218,10 +219,16 @@ struct vmxnet3_tx_ctx {
 	bool   ipv4;
 	bool   ipv6;
 	u16 mss;
-	u32 eth_ip_hdr_size; /* only valid for pkts requesting tso or csum
-				 * offloading
+	u32    l4_offset;	/* only valid for pkts requesting tso or csum
+				 * offloading. For encap offload, it refers to
+				 * inner L4 offset i.e. it includes outer header
+				 * encap header and inner eth and ip header size
+				 */
+
+	u32	l4_hdr_size;	/* only valid if mss != 0
+				 * Refers to inner L4 hdr size for encap
+				 * offload
 				 */
-	u32 l4_hdr_size;     /* only valid if mss != 0 */
 	u32 copy_size;       /* # of bytes copied into the data ring */
 	union Vmxnet3_GenericDesc *sop_txd;
 	union Vmxnet3_GenericDesc *eop_txd;
@@ -376,6 +383,8 @@ struct vmxnet3_adapter {
 	u16 rxdata_desc_size;
 
 	bool rxdataring_enabled;
+	bool default_rss_fields;
+	enum Vmxnet3_RSSField rss_fields;
 
 	struct work_struct work;
 
@@ -412,6 +421,8 @@ struct vmxnet3_adapter {
 	(adapter->version >= VMXNET3_REV_2 + 1)
 #define VMXNET3_VERSION_GE_3(adapter) \
 	(adapter->version >= VMXNET3_REV_3 + 1)
+#define VMXNET3_VERSION_GE_4(adapter) \
+	(adapter->version >= VMXNET3_REV_4 + 1)
 
 /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */
 #define VMXNET3_DEF_TX_RING_SIZE    512
@@ -435,6 +446,8 @@ struct vmxnet3_adapter {
 
 #define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs)
 #define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate)
+#define VMXNET3_RSS_FIELDS_DEFAULT (VMXNET3_RSS_FIELDS_TCPIP4 | \
+				    VMXNET3_RSS_FIELDS_TCPIP6)
 
 int
 vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter);