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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 198 insertions, 170 deletions

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 93ff8ef39352..9a18e7930b31 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -86,6 +86,7 @@ static const char * const ue_status_low_desc[] = {
 	"JTAG ",
 	"MPU_INTPEND "
 };
+
 /* UE Status High CSR */
 static const char * const ue_status_hi_desc[] = {
 	"LPCMEMHOST",
@@ -122,10 +123,10 @@ static const char * const ue_status_hi_desc[] = {
 	"Unknown"
 };
 
-
 static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q)
 {
 	struct be_dma_mem *mem = &q->dma_mem;
+
 	if (mem->va) {
 		dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va,
 				  mem->dma);
@@ -187,6 +188,7 @@ static void be_intr_set(struct be_adapter *adapter, bool enable)
 static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
 {
 	u32 val = 0;
+
 	val |= qid & DB_RQ_RING_ID_MASK;
 	val |= posted << DB_RQ_NUM_POSTED_SHIFT;
 
@@ -198,6 +200,7 @@ static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo,
 			  u16 posted)
 {
 	u32 val = 0;
+
 	val |= txo->q.id & DB_TXULP_RING_ID_MASK;
 	val |= (posted & DB_TXULP_NUM_POSTED_MASK) << DB_TXULP_NUM_POSTED_SHIFT;
 
@@ -209,6 +212,7 @@ static void be_eq_notify(struct be_adapter *adapter, u16 qid,
 			 bool arm, bool clear_int, u16 num_popped)
 {
 	u32 val = 0;
+
 	val |= qid & DB_EQ_RING_ID_MASK;
 	val |= ((qid & DB_EQ_RING_ID_EXT_MASK) << DB_EQ_RING_ID_EXT_MASK_SHIFT);
 
@@ -227,6 +231,7 @@ static void be_eq_notify(struct be_adapter *adapter, u16 qid,
 void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped)
 {
 	u32 val = 0;
+
 	val |= qid & DB_CQ_RING_ID_MASK;
 	val |= ((qid & DB_CQ_RING_ID_EXT_MASK) <<
 			DB_CQ_RING_ID_EXT_MASK_SHIFT);
@@ -488,7 +493,6 @@ static void populate_be_v2_stats(struct be_adapter *adapter)
 
 static void populate_lancer_stats(struct be_adapter *adapter)
 {
-
 	struct be_drv_stats *drvs = &adapter->drv_stats;
 	struct lancer_pport_stats *pport_stats = pport_stats_from_cmd(adapter);
 
@@ -588,6 +592,7 @@ static struct rtnl_link_stats64 *be_get_stats64(struct net_device *netdev,
 
 	for_all_rx_queues(adapter, rxo, i) {
 		const struct be_rx_stats *rx_stats = rx_stats(rxo);
+
 		do {
 			start = u64_stats_fetch_begin_irq(&rx_stats->sync);
 			pkts = rx_stats(rxo)->rx_pkts;
@@ -602,6 +607,7 @@ static struct rtnl_link_stats64 *be_get_stats64(struct net_device *netdev,
 
 	for_all_tx_queues(adapter, txo, i) {
 		const struct be_tx_stats *tx_stats = tx_stats(txo);
+
 		do {
 			start = u64_stats_fetch_begin_irq(&tx_stats->sync);
 			pkts = tx_stats(txo)->tx_pkts;
@@ -738,38 +744,37 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 
 	memset(hdr, 0, sizeof(*hdr));
 
-	AMAP_SET_BITS(struct amap_eth_hdr_wrb, crc, hdr, 1);
+	SET_TX_WRB_HDR_BITS(crc, hdr, 1);
 
 	if (skb_is_gso(skb)) {
-		AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso, hdr, 1);
-		AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso_mss,
-			hdr, skb_shinfo(skb)->gso_size);
+		SET_TX_WRB_HDR_BITS(lso, hdr, 1);
+		SET_TX_WRB_HDR_BITS(lso_mss, hdr, skb_shinfo(skb)->gso_size);
 		if (skb_is_gso_v6(skb) && !lancer_chip(adapter))
-			AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso6, hdr, 1);
+			SET_TX_WRB_HDR_BITS(lso6, hdr, 1);
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		if (skb->encapsulation) {
-			AMAP_SET_BITS(struct amap_eth_hdr_wrb, ipcs, hdr, 1);
+			SET_TX_WRB_HDR_BITS(ipcs, hdr, 1);
 			proto = skb_inner_ip_proto(skb);
 		} else {
 			proto = skb_ip_proto(skb);
 		}
 		if (proto == IPPROTO_TCP)
-			AMAP_SET_BITS(struct amap_eth_hdr_wrb, tcpcs, hdr, 1);
+			SET_TX_WRB_HDR_BITS(tcpcs, hdr, 1);
 		else if (proto == IPPROTO_UDP)
-			AMAP_SET_BITS(struct amap_eth_hdr_wrb, udpcs, hdr, 1);
+			SET_TX_WRB_HDR_BITS(udpcs, hdr, 1);
 	}
 
 	if (vlan_tx_tag_present(skb)) {
-		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan, hdr, 1);
+		SET_TX_WRB_HDR_BITS(vlan, hdr, 1);
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
-		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan_tag, hdr, vlan_tag);
+		SET_TX_WRB_HDR_BITS(vlan_tag, hdr, vlan_tag);
 	}
 
 	/* To skip HW VLAN tagging: evt = 1, compl = 0 */
-	AMAP_SET_BITS(struct amap_eth_hdr_wrb, complete, hdr, !skip_hw_vlan);
-	AMAP_SET_BITS(struct amap_eth_hdr_wrb, event, hdr, 1);
-	AMAP_SET_BITS(struct amap_eth_hdr_wrb, num_wrb, hdr, wrb_cnt);
-	AMAP_SET_BITS(struct amap_eth_hdr_wrb, len, hdr, len);
+	SET_TX_WRB_HDR_BITS(complete, hdr, !skip_hw_vlan);
+	SET_TX_WRB_HDR_BITS(event, hdr, 1);
+	SET_TX_WRB_HDR_BITS(num_wrb, hdr, wrb_cnt);
+	SET_TX_WRB_HDR_BITS(len, hdr, len);
 }
 
 static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
@@ -808,6 +813,7 @@ static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
 
 	if (skb->len > skb->data_len) {
 		int len = skb_headlen(skb);
+
 		busaddr = dma_map_single(dev, skb->data, len, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, busaddr))
 			goto dma_err;
@@ -821,6 +827,7 @@ static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
+
 		busaddr = skb_frag_dma_map(dev, frag, 0,
 					   skb_frag_size(frag), DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, busaddr))
@@ -850,6 +857,7 @@ dma_err:
 		unmap_tx_frag(dev, wrb, map_single);
 		map_single = false;
 		copied -= wrb->frag_len;
+		adapter->drv_stats.dma_map_errors++;
 		queue_head_inc(txq);
 	}
 	return 0;
@@ -910,7 +918,7 @@ static bool be_ipv6_exthdr_check(struct sk_buff *skb)
 		if (ip6h->nexthdr != NEXTHDR_TCP &&
 		    ip6h->nexthdr != NEXTHDR_UDP) {
 			struct ipv6_opt_hdr *ehdr =
-				(struct ipv6_opt_hdr *) (skb->data + offset);
+				(struct ipv6_opt_hdr *)(skb->data + offset);
 
 			/* offending pkt: 2nd byte following IPv6 hdr is 0xff */
 			if (ehdr->hdrlen == 0xff)
@@ -974,8 +982,8 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
 	 * skip HW tagging is not enabled by FW.
 	 */
 	if (unlikely(be_ipv6_tx_stall_chk(adapter, skb) &&
-	    (adapter->pvid || adapter->qnq_vid) &&
-	    !qnq_async_evt_rcvd(adapter)))
+		     (adapter->pvid || adapter->qnq_vid) &&
+		     !qnq_async_evt_rcvd(adapter)))
 		goto tx_drop;
 
 	/* Manual VLAN tag insertion to prevent:
@@ -1073,15 +1081,15 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 static int be_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	if (new_mtu < BE_MIN_MTU ||
-	    new_mtu > (BE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN))) {
-		dev_info(&adapter->pdev->dev,
-			 "MTU must be between %d and %d bytes\n",
-			 BE_MIN_MTU,
-			 (BE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN)));
+	struct device *dev = &adapter->pdev->dev;
+
+	if (new_mtu < BE_MIN_MTU || new_mtu > BE_MAX_MTU) {
+		dev_info(dev, "MTU must be between %d and %d bytes\n",
+			 BE_MIN_MTU, BE_MAX_MTU);
 		return -EINVAL;
 	}
-	dev_info(&adapter->pdev->dev, "MTU changed from %d to %d bytes\n",
+
+	dev_info(dev, "MTU changed from %d to %d bytes\n",
 		 netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 	return 0;
@@ -1093,6 +1101,7 @@ static int be_change_mtu(struct net_device *netdev, int new_mtu)
  */
 static int be_vid_config(struct be_adapter *adapter)
 {
+	struct device *dev = &adapter->pdev->dev;
 	u16 vids[BE_NUM_VLANS_SUPPORTED];
 	u16 num = 0, i = 0;
 	int status = 0;
@@ -1114,16 +1123,15 @@ static int be_vid_config(struct be_adapter *adapter)
 		if (addl_status(status) ==
 				MCC_ADDL_STATUS_INSUFFICIENT_RESOURCES)
 			goto set_vlan_promisc;
-		dev_err(&adapter->pdev->dev,
-			"Setting HW VLAN filtering failed.\n");
+		dev_err(dev, "Setting HW VLAN filtering failed\n");
 	} else {
 		if (adapter->flags & BE_FLAGS_VLAN_PROMISC) {
 			/* hw VLAN filtering re-enabled. */
 			status = be_cmd_rx_filter(adapter,
 						  BE_FLAGS_VLAN_PROMISC, OFF);
 			if (!status) {
-				dev_info(&adapter->pdev->dev,
-					 "Disabling VLAN Promiscuous mode.\n");
+				dev_info(dev,
+					 "Disabling VLAN Promiscuous mode\n");
 				adapter->flags &= ~BE_FLAGS_VLAN_PROMISC;
 			}
 		}
@@ -1137,11 +1145,10 @@ set_vlan_promisc:
 
 	status = be_cmd_rx_filter(adapter, BE_FLAGS_VLAN_PROMISC, ON);
 	if (!status) {
-		dev_info(&adapter->pdev->dev, "Enable VLAN Promiscuous mode\n");
+		dev_info(dev, "Enable VLAN Promiscuous mode\n");
 		adapter->flags |= BE_FLAGS_VLAN_PROMISC;
 	} else
-		dev_err(&adapter->pdev->dev,
-			"Failed to enable VLAN Promiscuous mode.\n");
+		dev_err(dev, "Failed to enable VLAN Promiscuous mode\n");
 	return status;
 }
 
@@ -1417,6 +1424,7 @@ err:
 		max_tx_rate, vf);
 	return be_cmd_status(status);
 }
+
 static int be_set_vf_link_state(struct net_device *netdev, int vf,
 				int link_state)
 {
@@ -1482,7 +1490,6 @@ static void be_eqd_update(struct be_adapter *adapter)
 			tx_pkts = txo->stats.tx_reqs;
 		} while (u64_stats_fetch_retry_irq(&txo->stats.sync, start));
 
-
 		/* Skip, if wrapped around or first calculation */
 		now = jiffies;
 		if (!aic->jiffies || time_before(now, aic->jiffies) ||
@@ -1683,7 +1690,7 @@ static void be_rx_compl_process(struct be_rx_obj *rxo, struct napi_struct *napi,
 	if (netdev->features & NETIF_F_RXHASH)
 		skb_set_hash(skb, rxcp->rss_hash, PKT_HASH_TYPE_L3);
 
-	skb->encapsulation = rxcp->tunneled;
+	skb->csum_level = rxcp->tunneled;
 	skb_mark_napi_id(skb, napi);
 
 	if (rxcp->vlanf)
@@ -1741,7 +1748,7 @@ static void be_rx_compl_process_gro(struct be_rx_obj *rxo,
 	if (adapter->netdev->features & NETIF_F_RXHASH)
 		skb_set_hash(skb, rxcp->rss_hash, PKT_HASH_TYPE_L3);
 
-	skb->encapsulation = rxcp->tunneled;
+	skb->csum_level = rxcp->tunneled;
 	skb_mark_napi_id(skb, napi);
 
 	if (rxcp->vlanf)
@@ -1753,65 +1760,46 @@ static void be_rx_compl_process_gro(struct be_rx_obj *rxo,
 static void be_parse_rx_compl_v1(struct be_eth_rx_compl *compl,
 				 struct be_rx_compl_info *rxcp)
 {
-	rxcp->pkt_size =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, pktsize, compl);
-	rxcp->vlanf = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vtp, compl);
-	rxcp->err = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, err, compl);
-	rxcp->tcpf = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, tcpf, compl);
-	rxcp->udpf = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, udpf, compl);
-	rxcp->ip_csum =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, ipcksm, compl);
-	rxcp->l4_csum =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, l4_cksm, compl);
-	rxcp->ipv6 =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, ip_version, compl);
-	rxcp->num_rcvd =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, numfrags, compl);
-	rxcp->pkt_type =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, cast_enc, compl);
-	rxcp->rss_hash =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, rsshash, compl);
+	rxcp->pkt_size = GET_RX_COMPL_V1_BITS(pktsize, compl);
+	rxcp->vlanf = GET_RX_COMPL_V1_BITS(vtp, compl);
+	rxcp->err = GET_RX_COMPL_V1_BITS(err, compl);
+	rxcp->tcpf = GET_RX_COMPL_V1_BITS(tcpf, compl);
+	rxcp->udpf = GET_RX_COMPL_V1_BITS(udpf, compl);
+	rxcp->ip_csum = GET_RX_COMPL_V1_BITS(ipcksm, compl);
+	rxcp->l4_csum = GET_RX_COMPL_V1_BITS(l4_cksm, compl);
+	rxcp->ipv6 = GET_RX_COMPL_V1_BITS(ip_version, compl);
+	rxcp->num_rcvd = GET_RX_COMPL_V1_BITS(numfrags, compl);
+	rxcp->pkt_type = GET_RX_COMPL_V1_BITS(cast_enc, compl);
+	rxcp->rss_hash = GET_RX_COMPL_V1_BITS(rsshash, compl);
 	if (rxcp->vlanf) {
-		rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, qnq,
-					  compl);
-		rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1,
-					       vlan_tag, compl);
+		rxcp->qnq = GET_RX_COMPL_V1_BITS(qnq, compl);
+		rxcp->vlan_tag = GET_RX_COMPL_V1_BITS(vlan_tag, compl);
 	}
-	rxcp->port = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, port, compl);
+	rxcp->port = GET_RX_COMPL_V1_BITS(port, compl);
 	rxcp->tunneled =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v1, tunneled, compl);
+		GET_RX_COMPL_V1_BITS(tunneled, compl);
 }
 
 static void be_parse_rx_compl_v0(struct be_eth_rx_compl *compl,
 				 struct be_rx_compl_info *rxcp)
 {
-	rxcp->pkt_size =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, pktsize, compl);
-	rxcp->vlanf = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vtp, compl);
-	rxcp->err = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, err, compl);
-	rxcp->tcpf = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, tcpf, compl);
-	rxcp->udpf = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, udpf, compl);
-	rxcp->ip_csum =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, ipcksm, compl);
-	rxcp->l4_csum =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, l4_cksm, compl);
-	rxcp->ipv6 =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, ip_version, compl);
-	rxcp->num_rcvd =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, numfrags, compl);
-	rxcp->pkt_type =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, cast_enc, compl);
-	rxcp->rss_hash =
-		AMAP_GET_BITS(struct amap_eth_rx_compl_v0, rsshash, compl);
+	rxcp->pkt_size = GET_RX_COMPL_V0_BITS(pktsize, compl);
+	rxcp->vlanf = GET_RX_COMPL_V0_BITS(vtp, compl);
+	rxcp->err = GET_RX_COMPL_V0_BITS(err, compl);
+	rxcp->tcpf = GET_RX_COMPL_V0_BITS(tcpf, compl);
+	rxcp->udpf = GET_RX_COMPL_V0_BITS(udpf, compl);
+	rxcp->ip_csum = GET_RX_COMPL_V0_BITS(ipcksm, compl);
+	rxcp->l4_csum = GET_RX_COMPL_V0_BITS(l4_cksm, compl);
+	rxcp->ipv6 = GET_RX_COMPL_V0_BITS(ip_version, compl);
+	rxcp->num_rcvd = GET_RX_COMPL_V0_BITS(numfrags, compl);
+	rxcp->pkt_type = GET_RX_COMPL_V0_BITS(cast_enc, compl);
+	rxcp->rss_hash = GET_RX_COMPL_V0_BITS(rsshash, compl);
 	if (rxcp->vlanf) {
-		rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, qnq,
-					  compl);
-		rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0,
-					       vlan_tag, compl);
+		rxcp->qnq = GET_RX_COMPL_V0_BITS(qnq, compl);
+		rxcp->vlan_tag = GET_RX_COMPL_V0_BITS(vlan_tag, compl);
 	}
-	rxcp->port = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, port, compl);
-	rxcp->ip_frag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0,
-				      ip_frag, compl);
+	rxcp->port = GET_RX_COMPL_V0_BITS(port, compl);
+	rxcp->ip_frag = GET_RX_COMPL_V0_BITS(ip_frag, compl);
 }
 
 static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo)
@@ -1872,7 +1860,7 @@ static inline struct page *be_alloc_pages(u32 size, gfp_t gfp)
  * Allocate a page, split it to fragments of size rx_frag_size and post as
  * receive buffers to BE
  */
-static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp)
+static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp, u32 frags_needed)
 {
 	struct be_adapter *adapter = rxo->adapter;
 	struct be_rx_page_info *page_info = NULL, *prev_page_info = NULL;
@@ -1881,10 +1869,10 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp)
 	struct device *dev = &adapter->pdev->dev;
 	struct be_eth_rx_d *rxd;
 	u64 page_dmaaddr = 0, frag_dmaaddr;
-	u32 posted, page_offset = 0;
+	u32 posted, page_offset = 0, notify = 0;
 
 	page_info = &rxo->page_info_tbl[rxq->head];
-	for (posted = 0; posted < MAX_RX_POST && !page_info->page; posted++) {
+	for (posted = 0; posted < frags_needed && !page_info->page; posted++) {
 		if (!pagep) {
 			pagep = be_alloc_pages(adapter->big_page_size, gfp);
 			if (unlikely(!pagep)) {
@@ -1897,7 +1885,7 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp)
 			if (dma_mapping_error(dev, page_dmaaddr)) {
 				put_page(pagep);
 				pagep = NULL;
-				rx_stats(rxo)->rx_post_fail++;
+				adapter->drv_stats.dma_map_errors++;
 				break;
 			}
 			page_offset = 0;
@@ -1940,7 +1928,11 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp)
 		atomic_add(posted, &rxq->used);
 		if (rxo->rx_post_starved)
 			rxo->rx_post_starved = false;
-		be_rxq_notify(adapter, rxq->id, posted);
+		do {
+			notify = min(256u, posted);
+			be_rxq_notify(adapter, rxq->id, notify);
+			posted -= notify;
+		} while (posted);
 	} else if (atomic_read(&rxq->used) == 0) {
 		/* Let be_worker replenish when memory is available */
 		rxo->rx_post_starved = true;
@@ -1991,7 +1983,7 @@ static u16 be_tx_compl_process(struct be_adapter *adapter,
 		queue_tail_inc(txq);
 	} while (cur_index != last_index);
 
-	dev_kfree_skb_any(sent_skb);
+	dev_consume_skb_any(sent_skb);
 	return num_wrbs;
 }
 
@@ -2069,7 +2061,8 @@ static void be_rx_cq_clean(struct be_rx_obj *rxo)
 		memset(page_info, 0, sizeof(*page_info));
 	}
 	BUG_ON(atomic_read(&rxq->used));
-	rxq->tail = rxq->head = 0;
+	rxq->tail = 0;
+	rxq->head = 0;
 }
 
 static void be_tx_compl_clean(struct be_adapter *adapter)
@@ -2091,9 +2084,7 @@ static void be_tx_compl_clean(struct be_adapter *adapter)
 			num_wrbs = 0;
 			txq = &txo->q;
 			while ((txcp = be_tx_compl_get(&txo->cq))) {
-				end_idx =
-					AMAP_GET_BITS(struct amap_eth_tx_compl,
-						      wrb_index, txcp);
+				end_idx = GET_TX_COMPL_BITS(wrb_index, txcp);
 				num_wrbs += be_tx_compl_process(adapter, txo,
 								end_idx);
 				cmpl++;
@@ -2164,7 +2155,6 @@ static int be_evt_queues_create(struct be_adapter *adapter)
 		napi_hash_add(&eqo->napi);
 		aic = &adapter->aic_obj[i];
 		eqo->adapter = adapter;
-		eqo->tx_budget = BE_TX_BUDGET;
 		eqo->idx = i;
 		aic->max_eqd = BE_MAX_EQD;
 		aic->enable = true;
@@ -2394,6 +2384,7 @@ static int be_process_rx(struct be_rx_obj *rxo, struct napi_struct *napi,
 	struct be_queue_info *rx_cq = &rxo->cq;
 	struct be_rx_compl_info *rxcp;
 	u32 work_done;
+	u32 frags_consumed = 0;
 
 	for (work_done = 0; work_done < budget; work_done++) {
 		rxcp = be_rx_compl_get(rxo);
@@ -2426,6 +2417,7 @@ static int be_process_rx(struct be_rx_obj *rxo, struct napi_struct *napi,
 			be_rx_compl_process(rxo, napi, rxcp);
 
 loop_continue:
+		frags_consumed += rxcp->num_rcvd;
 		be_rx_stats_update(rxo, rxcp);
 	}
 
@@ -2437,26 +2429,71 @@ loop_continue:
 		 */
 		if (atomic_read(&rxo->q.used) < RX_FRAGS_REFILL_WM &&
 		    !rxo->rx_post_starved)
-			be_post_rx_frags(rxo, GFP_ATOMIC);
+			be_post_rx_frags(rxo, GFP_ATOMIC,
+					 max_t(u32, MAX_RX_POST,
+					       frags_consumed));
 	}
 
 	return work_done;
 }
 
-static bool be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
-			  int budget, int idx)
+static inline void be_update_tx_err(struct be_tx_obj *txo, u32 status)
+{
+	switch (status) {
+	case BE_TX_COMP_HDR_PARSE_ERR:
+		tx_stats(txo)->tx_hdr_parse_err++;
+		break;
+	case BE_TX_COMP_NDMA_ERR:
+		tx_stats(txo)->tx_dma_err++;
+		break;
+	case BE_TX_COMP_ACL_ERR:
+		tx_stats(txo)->tx_spoof_check_err++;
+		break;
+	}
+}
+
+static inline void lancer_update_tx_err(struct be_tx_obj *txo, u32 status)
+{
+	switch (status) {
+	case LANCER_TX_COMP_LSO_ERR:
+		tx_stats(txo)->tx_tso_err++;
+		break;
+	case LANCER_TX_COMP_HSW_DROP_MAC_ERR:
+	case LANCER_TX_COMP_HSW_DROP_VLAN_ERR:
+		tx_stats(txo)->tx_spoof_check_err++;
+		break;
+	case LANCER_TX_COMP_QINQ_ERR:
+		tx_stats(txo)->tx_qinq_err++;
+		break;
+	case LANCER_TX_COMP_PARITY_ERR:
+		tx_stats(txo)->tx_internal_parity_err++;
+		break;
+	case LANCER_TX_COMP_DMA_ERR:
+		tx_stats(txo)->tx_dma_err++;
+		break;
+	}
+}
+
+static void be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
+			  int idx)
 {
 	struct be_eth_tx_compl *txcp;
-	int num_wrbs = 0, work_done;
+	int num_wrbs = 0, work_done = 0;
+	u32 compl_status;
+	u16 last_idx;
 
-	for (work_done = 0; work_done < budget; work_done++) {
-		txcp = be_tx_compl_get(&txo->cq);
-		if (!txcp)
-			break;
-		num_wrbs += be_tx_compl_process(adapter, txo,
-						AMAP_GET_BITS(struct
-							      amap_eth_tx_compl,
-							      wrb_index, txcp));
+	while ((txcp = be_tx_compl_get(&txo->cq))) {
+		last_idx = GET_TX_COMPL_BITS(wrb_index, txcp);
+		num_wrbs += be_tx_compl_process(adapter, txo, last_idx);
+		work_done++;
+
+		compl_status = GET_TX_COMPL_BITS(status, txcp);
+		if (compl_status) {
+			if (lancer_chip(adapter))
+				lancer_update_tx_err(txo, compl_status);
+			else
+				be_update_tx_err(txo, compl_status);
+		}
 	}
 
 	if (work_done) {
@@ -2474,7 +2511,6 @@ static bool be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
 		tx_stats(txo)->tx_compl += work_done;
 		u64_stats_update_end(&tx_stats(txo)->sync_compl);
 	}
-	return (work_done < budget); /* Done */
 }
 
 int be_poll(struct napi_struct *napi, int budget)
@@ -2483,17 +2519,12 @@ int be_poll(struct napi_struct *napi, int budget)
 	struct be_adapter *adapter = eqo->adapter;
 	int max_work = 0, work, i, num_evts;
 	struct be_rx_obj *rxo;
-	bool tx_done;
+	struct be_tx_obj *txo;
 
 	num_evts = events_get(eqo);
 
-	/* Process all TXQs serviced by this EQ */
-	for (i = eqo->idx; i < adapter->num_tx_qs; i += adapter->num_evt_qs) {
-		tx_done = be_process_tx(adapter, &adapter->tx_obj[i],
-					eqo->tx_budget, i);
-		if (!tx_done)
-			max_work = budget;
-	}
+	for_all_tx_queues_on_eq(adapter, eqo, txo, i)
+		be_process_tx(adapter, txo, i);
 
 	if (be_lock_napi(eqo)) {
 		/* This loop will iterate twice for EQ0 in which
@@ -2882,7 +2913,7 @@ static int be_rx_qs_create(struct be_adapter *adapter)
 
 	/* First time posting */
 	for_all_rx_queues(adapter, rxo, i)
-		be_post_rx_frags(rxo, GFP_KERNEL);
+		be_post_rx_frags(rxo, GFP_KERNEL, MAX_RX_POST);
 	return 0;
 }
 
@@ -3309,10 +3340,20 @@ static void BEx_get_resources(struct be_adapter *adapter,
 	 */
 	if (BE2_chip(adapter) || use_sriov ||  (adapter->port_num > 1) ||
 	    !be_physfn(adapter) || (be_is_mc(adapter) &&
-	    !(adapter->function_caps & BE_FUNCTION_CAPS_RSS)))
+	    !(adapter->function_caps & BE_FUNCTION_CAPS_RSS))) {
 		res->max_tx_qs = 1;
-	else
+	} else if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) {
+		struct be_resources super_nic_res = {0};
+
+		/* On a SuperNIC profile, the driver needs to use the
+		 * GET_PROFILE_CONFIG cmd to query the per-function TXQ limits
+		 */
+		be_cmd_get_profile_config(adapter, &super_nic_res, 0);
+		/* Some old versions of BE3 FW don't report max_tx_qs value */
+		res->max_tx_qs = super_nic_res.max_tx_qs ? : BE3_MAX_TX_QS;
+	} else {
 		res->max_tx_qs = BE3_MAX_TX_QS;
+	}
 
 	if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
 	    !use_sriov && be_physfn(adapter))
@@ -3362,7 +3403,7 @@ static int be_get_sriov_config(struct be_adapter *adapter)
 
 	if (!be_max_vfs(adapter)) {
 		if (num_vfs)
-			dev_warn(dev, "device doesn't support SRIOV\n");
+			dev_warn(dev, "SRIOV is disabled. Ignoring num_vfs\n");
 		adapter->num_vfs = 0;
 		return 0;
 	}
@@ -3413,16 +3454,16 @@ static int be_get_resources(struct be_adapter *adapter)
 		if (be_roce_supported(adapter))
 			res.max_evt_qs /= 2;
 		adapter->res = res;
-
-		dev_info(dev, "Max: txqs %d, rxqs %d, rss %d, eqs %d, vfs %d\n",
-			 be_max_txqs(adapter), be_max_rxqs(adapter),
-			 be_max_rss(adapter), be_max_eqs(adapter),
-			 be_max_vfs(adapter));
-		dev_info(dev, "Max: uc-macs %d, mc-macs %d, vlans %d\n",
-			 be_max_uc(adapter), be_max_mc(adapter),
-			 be_max_vlans(adapter));
 	}
 
+	dev_info(dev, "Max: txqs %d, rxqs %d, rss %d, eqs %d, vfs %d\n",
+		 be_max_txqs(adapter), be_max_rxqs(adapter),
+		 be_max_rss(adapter), be_max_eqs(adapter),
+		 be_max_vfs(adapter));
+	dev_info(dev, "Max: uc-macs %d, mc-macs %d, vlans %d\n",
+		 be_max_uc(adapter), be_max_mc(adapter),
+		 be_max_vlans(adapter));
+
 	return 0;
 }
 
@@ -3633,9 +3674,10 @@ static int be_setup(struct be_adapter *adapter)
 		goto err;
 
 	be_cmd_get_fw_ver(adapter);
+	dev_info(dev, "FW version is %s\n", adapter->fw_ver);
 
 	if (BE2_chip(adapter) && fw_major_num(adapter->fw_ver) < 4) {
-		dev_err(dev, "Firmware on card is old(%s), IRQs may not work.",
+		dev_err(dev, "Firmware on card is old(%s), IRQs may not work",
 			adapter->fw_ver);
 		dev_err(dev, "Please upgrade firmware to version >= 4.0\n");
 	}
@@ -3683,8 +3725,6 @@ static void be_netpoll(struct net_device *netdev)
 		be_eq_notify(eqo->adapter, eqo->q.id, false, true, 0);
 		napi_schedule(&eqo->napi);
 	}
-
-	return;
 }
 #endif
 
@@ -4052,6 +4092,7 @@ static int lancer_fw_download(struct be_adapter *adapter,
 {
 #define LANCER_FW_DOWNLOAD_CHUNK      (32 * 1024)
 #define LANCER_FW_DOWNLOAD_LOCATION   "/prg"
+	struct device *dev = &adapter->pdev->dev;
 	struct be_dma_mem flash_cmd;
 	const u8 *data_ptr = NULL;
 	u8 *dest_image_ptr = NULL;
@@ -4064,21 +4105,16 @@ static int lancer_fw_download(struct be_adapter *adapter,
 	u8 change_status;
 
 	if (!IS_ALIGNED(fw->size, sizeof(u32))) {
-		dev_err(&adapter->pdev->dev,
-			"FW Image not properly aligned. "
-			"Length must be 4 byte aligned.\n");
-		status = -EINVAL;
-		goto lancer_fw_exit;
+		dev_err(dev, "FW image size should be multiple of 4\n");
+		return -EINVAL;
 	}
 
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
-	flash_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, flash_cmd.size,
+	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size,
 					  &flash_cmd.dma, GFP_KERNEL);
-	if (!flash_cmd.va) {
-		status = -ENOMEM;
-		goto lancer_fw_exit;
-	}
+	if (!flash_cmd.va)
+		return -ENOMEM;
 
 	dest_image_ptr = flash_cmd.va +
 				sizeof(struct lancer_cmd_req_write_object);
@@ -4113,35 +4149,27 @@ static int lancer_fw_download(struct be_adapter *adapter,
 						 &add_status);
 	}
 
-	dma_free_coherent(&adapter->pdev->dev, flash_cmd.size, flash_cmd.va,
-			  flash_cmd.dma);
+	dma_free_coherent(dev, flash_cmd.size, flash_cmd.va, flash_cmd.dma);
 	if (status) {
-		dev_err(&adapter->pdev->dev,
-			"Firmware load error. "
-			"Status code: 0x%x Additional Status: 0x%x\n",
-			status, add_status);
-		goto lancer_fw_exit;
+		dev_err(dev, "Firmware load error\n");
+		return be_cmd_status(status);
 	}
 
+	dev_info(dev, "Firmware flashed successfully\n");
+
 	if (change_status == LANCER_FW_RESET_NEEDED) {
-		dev_info(&adapter->pdev->dev,
-			 "Resetting adapter to activate new FW\n");
+		dev_info(dev, "Resetting adapter to activate new FW\n");
 		status = lancer_physdev_ctrl(adapter,
 					     PHYSDEV_CONTROL_FW_RESET_MASK);
 		if (status) {
-			dev_err(&adapter->pdev->dev,
-				"Adapter busy for FW reset.\n"
-				"New FW will not be active.\n");
-			goto lancer_fw_exit;
+			dev_err(dev, "Adapter busy, could not reset FW\n");
+			dev_err(dev, "Reboot server to activate new FW\n");
 		}
 	} else if (change_status != LANCER_NO_RESET_NEEDED) {
-		dev_err(&adapter->pdev->dev,
-			"System reboot required for new FW to be active\n");
+		dev_info(dev, "Reboot server to activate new FW\n");
 	}
 
-	dev_info(&adapter->pdev->dev, "Firmware flashed successfully\n");
-lancer_fw_exit:
-	return status;
+	return 0;
 }
 
 #define UFI_TYPE2		2
@@ -4374,7 +4402,6 @@ static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
 	return;
 err:
 	be_disable_vxlan_offloads(adapter);
-	return;
 }
 
 static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
@@ -4506,6 +4533,7 @@ static int be_map_pci_bars(struct be_adapter *adapter)
 	return 0;
 
 pci_map_err:
+	dev_err(&adapter->pdev->dev, "Error in mapping PCI BARs\n");
 	be_unmap_pci_bars(adapter);
 	return -ENOMEM;
 }
@@ -4713,7 +4741,6 @@ static void be_func_recovery_task(struct work_struct *work)
 	be_detect_error(adapter);
 
 	if (adapter->hw_error && lancer_chip(adapter)) {
-
 		rtnl_lock();
 		netif_device_detach(adapter->netdev);
 		rtnl_unlock();
@@ -4750,7 +4777,7 @@ static void be_worker(struct work_struct *work)
 	if (!adapter->stats_cmd_sent) {
 		if (lancer_chip(adapter))
 			lancer_cmd_get_pport_stats(adapter,
-						&adapter->stats_cmd);
+						   &adapter->stats_cmd);
 		else
 			be_cmd_get_stats(adapter, &adapter->stats_cmd);
 	}
@@ -4764,7 +4791,7 @@ static void be_worker(struct work_struct *work)
 		 * allocation failures.
 		 */
 		if (rxo->rx_post_starved)
-			be_post_rx_frags(rxo, GFP_KERNEL);
+			be_post_rx_frags(rxo, GFP_KERNEL, MAX_RX_POST);
 	}
 
 	be_eqd_update(adapter);
@@ -4822,6 +4849,8 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
 	struct net_device *netdev;
 	char port_name;
 
+	dev_info(&pdev->dev, "%s version is %s\n", DRV_NAME, DRV_VER);
+
 	status = pci_enable_device(pdev);
 	if (status)
 		goto do_none;
@@ -4853,11 +4882,9 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
 		}
 	}
 
-	if (be_physfn(adapter)) {
-		status = pci_enable_pcie_error_reporting(pdev);
-		if (!status)
-			dev_info(&pdev->dev, "PCIe error reporting enabled\n");
-	}
+	status = pci_enable_pcie_error_reporting(pdev);
+	if (!status)
+		dev_info(&pdev->dev, "PCIe error reporting enabled\n");
 
 	status = be_ctrl_init(adapter);
 	if (status)
@@ -4897,7 +4924,8 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
 
 	INIT_DELAYED_WORK(&adapter->work, be_worker);
 	INIT_DELAYED_WORK(&adapter->func_recovery_work, be_func_recovery_task);
-	adapter->rx_fc = adapter->tx_fc = true;
+	adapter->rx_fc = true;
+	adapter->tx_fc = true;
 
 	status = be_setup(adapter);
 	if (status)