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

Pull networking fixes from David Miller:

 1) Fix two regressions in ipv6 route lookups, particularly wrt output
    interface specifications in the lookup key.  From David Ahern.

 2) Fix checks in ipv6 IPSEC tunnel pre-encap fragmentation, from
    Herbert Xu.

 3) Fix mis-advertisement of 1000BASE-T on bcm63xx_enet, from Simon
    Arlott.

 4) Some smsc phys misbehave with energy detect mode enabled, so add a
    DT property and disable it on such switches.  From Heiko Schocher.

 5) Fix TSO corruption on TX in mv643xx_eth, from Philipp Kirchhofer.

 6) Fix regression added by removal of openvswitch vport stats, from
    James Morse.

 7) Vendor Kconfig options should be bool, not tristate, from Andreas
    Schwab.

 8) Use non-_BH() net stats bump in tcp_xmit_probe_skb(), otherwise we
    barf during TCP REPAIR operations.

 9) Fix various bugs in openvswitch conntrack support, from Joe
    Stringer.

10) Fix NETLINK_LIST_MEMBERSHIPS locking, from David Herrmann.

11) Don't have VSOCK do sock_put() in interrupt context, from Jorgen
    Hansen.

12) Fix skb_realloc_headroom() failures properly in ISDN, from Karsten
    Keil.

13) Add some device IDs to qmi_wwan, from Bjorn Mork.

14) Fix ovs egress tunnel information when using lwtunnel devices, from
    Pravin B Shelar.

15) Add missing NETIF_F_FRAGLIST to macvtab feature list, from Jason
    Wang.

16) Fix incorrect handling of throw routes when the result of the throw
    cannot find a match, from Xin Long.

17) Protect ipv6 MTU calculations from wrap-around, from Hannes Frederic
    Sowa.

18) Fix failed autonegotiation on KSZ9031 micrel PHYs, from Nathan
    Sullivan.

19) Add missing memory barries in descriptor accesses or xgbe driver,
    from Thomas Lendacky.

20) Fix release conditon test in pppoe_release(), from Guillaume Nault.

21) Fix gianfar bugs wrt filter configuration, from Claudiu Manoil.

22) Fix violations of RX buffer alignment in sh_eth driver, from Sergei
    Shtylyov.

23) Fixing missing of_node_put() calls in various places around the
    networking, from Julia Lawall.

24) Fix incorrect leaf now walking in ipv4 routing tree, from Alexander
    Duyck.

25) RDS doesn't check pskb_pull()/pskb_trim() return values, from
    Sowmini Varadhan.

26) Fix VLAN configuration in mlx4 driver, from Jack Morgenstein.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
  ipv6: protect mtu calculation of wrap-around and infinite loop by rounding issues
  Revert "Merge branch 'ipv6-overflow-arith'"
  net/mlx4: Copy/set only sizeof struct mlx4_eqe bytes
  net/mlx4_en: Explicitly set no vlan tags in WQE ctrl segment when no vlan is present
  vhost: fix performance on LE hosts
  bpf: sample: define aarch64 specific registers
  amd-xgbe: Fix race between access of desc and desc index
  RDS-TCP: Recover correctly from pskb_pull()/pksb_trim() failure in rds_tcp_data_recv
  forcedeth: fix unilateral interrupt disabling in netpoll path
  openvswitch: Fix skb leak using IPv6 defrag
  ipv6: Export nf_ct_frag6_consume_orig()
  openvswitch: Fix double-free on ip_defrag() errors
  fib_trie: leaf_walk_rcu should not compute key if key is less than pn->key
  net: mv643xx_eth: add missing of_node_put
  ath6kl: add missing of_node_put
  net: phy: mdio: add missing of_node_put
  netdev/phy: add missing of_node_put
  net: netcp: add missing of_node_put
  net: thunderx: add missing of_node_put
  ipv6: gre: support SIT encapsulation
  ...

21 files changed, 175 insertions, 80 deletions

diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 48ce83e..8d50314 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -847,21 +847,25 @@ static int emac_probe(struct platform_device *pdev)
 	if (ndev->irq == -ENXIO) {
 		netdev_err(ndev, "No irq resource\n");
 		ret = ndev->irq;
-		goto out;
+		goto out_iounmap;
 	}
 
 	db->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(db->clk)) {
 		ret = PTR_ERR(db->clk);
-		goto out;
+		goto out_iounmap;
 	}
 
-	clk_prepare_enable(db->clk);
+	ret = clk_prepare_enable(db->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "Error couldn't enable clock (%d)\n", ret);
+		goto out_iounmap;
+	}
 
 	ret = sunxi_sram_claim(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Error couldn't map SRAM to device\n");
-		goto out;
+		goto out_clk_disable_unprepare;
 	}
 
 	db->phy_node = of_parse_phandle(np, "phy", 0);
@@ -910,6 +914,10 @@ static int emac_probe(struct platform_device *pdev)
 
 out_release_sram:
 	sunxi_sram_release(&pdev->dev);
+out_clk_disable_unprepare:
+	clk_disable_unprepare(db->clk);
+out_iounmap:
+	iounmap(db->membase);
 out:
 	dev_err(db->dev, "not found (%d).\n", ret);
 
@@ -921,8 +929,12 @@ out:
 static int emac_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct emac_board_info *db = netdev_priv(ndev);
 
 	unregister_netdev(ndev);
+	sunxi_sram_release(&pdev->dev);
+	clk_disable_unprepare(db->clk);
+	iounmap(db->membase);
 	free_netdev(ndev);
 
 	dev_dbg(&pdev->dev, "released and freed device\n");
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index a4473d8..f672dba 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1595,7 +1595,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 				  packet->rdesc_count, 1);
 
 	/* Make sure ownership is written to the descriptor */
-	dma_wmb();
+	smp_wmb();
 
 	ring->cur = cur_index + 1;
 	if (!packet->skb->xmit_more ||
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index aae9d5e..dde0486 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1807,6 +1807,7 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 	struct netdev_queue *txq;
 	int processed = 0;
 	unsigned int tx_packets = 0, tx_bytes = 0;
+	unsigned int cur;
 
 	DBGPR("-->xgbe_tx_poll\n");
 
@@ -1814,10 +1815,15 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 	if (!ring)
 		return 0;
 
+	cur = ring->cur;
+
+	/* Be sure we get ring->cur before accessing descriptor data */
+	smp_rmb();
+
 	txq = netdev_get_tx_queue(netdev, channel->queue_index);
 
 	while ((processed < XGBE_TX_DESC_MAX_PROC) &&
-	       (ring->dirty != ring->cur)) {
+	       (ring->dirty != cur)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->dirty);
 		rdesc = rdata->rdesc;
 
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index a7f2cc3..4183c2a 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -2049,7 +2049,7 @@ static void swphy_poll_timer(unsigned long data)
 
 	for (i = 0; i < priv->num_ports; i++) {
 		struct bcm63xx_enetsw_port *port;
-		int val, j, up, advertise, lpa, lpa2, speed, duplex, media;
+		int val, j, up, advertise, lpa, speed, duplex, media;
 		int external_phy = bcm_enet_port_is_rgmii(i);
 		u8 override;
 
@@ -2092,22 +2092,27 @@ static void swphy_poll_timer(unsigned long data)
 		lpa = bcmenet_sw_mdio_read(priv, external_phy, port->phy_id,
 					   MII_LPA);
 
-		lpa2 = bcmenet_sw_mdio_read(priv, external_phy, port->phy_id,
-					    MII_STAT1000);
-
 		/* figure out media and duplex from advertise and LPA values */
 		media = mii_nway_result(lpa & advertise);
 		duplex = (media & ADVERTISE_FULL) ? 1 : 0;
-		if (lpa2 & LPA_1000FULL)
-			duplex = 1;
-
-		if (lpa2 & (LPA_1000FULL | LPA_1000HALF))
-			speed = 1000;
-		else {
-			if (media & (ADVERTISE_100FULL | ADVERTISE_100HALF))
-				speed = 100;
-			else
-				speed = 10;
+
+		if (media & (ADVERTISE_100FULL | ADVERTISE_100HALF))
+			speed = 100;
+		else
+			speed = 10;
+
+		if (val & BMSR_ESTATEN) {
+			advertise = bcmenet_sw_mdio_read(priv, external_phy,
+						port->phy_id, MII_CTRL1000);
+
+			lpa = bcmenet_sw_mdio_read(priv, external_phy,
+						port->phy_id, MII_STAT1000);
+
+			if (advertise & (ADVERTISE_1000FULL | ADVERTISE_1000HALF)
+					&& lpa & (LPA_1000FULL | LPA_1000HALF)) {
+				speed = 1000;
+				duplex = (lpa & LPA_1000FULL);
+			}
 		}
 
 		dev_info(&priv->pdev->dev,
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 9b35d14..8fb84e6 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -3,7 +3,7 @@
 #
 
 config NET_VENDOR_CAVIUM
-	tristate "Cavium ethernet drivers"
+	bool "Cavium ethernet drivers"
 	depends on PCI
 	default y
 	---help---
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index b3a5947..c561fdc 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -22,7 +22,6 @@
 
 struct nicpf {
 	struct pci_dev		*pdev;
-	u8			rev_id;
 	u8			node;
 	unsigned int		flags;
 	u8			num_vf_en;      /* No of VF enabled */
@@ -44,6 +43,7 @@ struct nicpf {
 	u8			duplex[MAX_LMAC];
 	u32			speed[MAX_LMAC];
 	u16			cpi_base[MAX_NUM_VFS_SUPPORTED];
+	u16			rssi_base[MAX_NUM_VFS_SUPPORTED];
 	u16			rss_ind_tbl_size;
 	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
 
@@ -54,6 +54,11 @@ struct nicpf {
 	bool			irq_allocated[NIC_PF_MSIX_VECTORS];
 };
 
+static inline bool pass1_silicon(struct nicpf *nic)
+{
+	return nic->pdev->revision < 8;
+}
+
 /* Supported devices */
 static const struct pci_device_id nic_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) },
@@ -117,7 +122,7 @@ static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx)
 	 * when PF writes to MBOX(1), in next revisions when
 	 * PF writes to MBOX(0)
 	 */
-	if (nic->rev_id == 0) {
+	if (pass1_silicon(nic)) {
 		/* see the comment for nic_reg_write()/nic_reg_read()
 		 * functions above
 		 */
@@ -305,9 +310,6 @@ static void nic_init_hw(struct nicpf *nic)
 {
 	int i;
 
-	/* Reset NIC, in case the driver is repeatedly inserted and removed */
-	nic_reg_write(nic, NIC_PF_SOFT_RESET, 1);
-
 	/* Enable NIC HW block */
 	nic_reg_write(nic, NIC_PF_CFG, 0x3);
 
@@ -395,8 +397,18 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg)
 			padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */
 
 		/* Leave RSS_SIZE as '0' to disable RSS */
-		nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3),
-			      (vnic << 24) | (padd << 16) | (rssi_base + rssi));
+		if (pass1_silicon(nic)) {
+			nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3),
+				      (vnic << 24) | (padd << 16) |
+				      (rssi_base + rssi));
+		} else {
+			/* Set MPI_ALG to '0' to disable MCAM parsing */
+			nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3),
+				      (padd << 16));
+			/* MPI index is same as CPI if MPI_ALG is not enabled */
+			nic_reg_write(nic, NIC_PF_MPI_0_2047_CFG | (cpi << 3),
+				      (vnic << 24) | (rssi_base + rssi));
+		}
 
 		if ((rssi + 1) >= cfg->rq_cnt)
 			continue;
@@ -409,6 +421,7 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg)
 			rssi = ((cpi - cpi_base) & 0x38) >> 3;
 	}
 	nic->cpi_base[cfg->vf_id] = cpi_base;
+	nic->rssi_base[cfg->vf_id] = rssi_base;
 }
 
 /* Responsds to VF with its RSS indirection table size */
@@ -434,10 +447,9 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
 {
 	u8  qset, idx = 0;
 	u64 cpi_cfg, cpi_base, rssi_base, rssi;
+	u64 idx_addr;
 
-	cpi_base = nic->cpi_base[cfg->vf_id];
-	cpi_cfg = nic_reg_read(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3));
-	rssi_base = (cpi_cfg & 0x0FFF) + cfg->tbl_offset;
+	rssi_base = nic->rssi_base[cfg->vf_id] + cfg->tbl_offset;
 
 	rssi = rssi_base;
 	qset = cfg->vf_id;
@@ -454,9 +466,15 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
 		idx++;
 	}
 
+	cpi_base = nic->cpi_base[cfg->vf_id];
+	if (pass1_silicon(nic))
+		idx_addr = NIC_PF_CPI_0_2047_CFG;
+	else
+		idx_addr = NIC_PF_MPI_0_2047_CFG;
+	cpi_cfg = nic_reg_read(nic, idx_addr | (cpi_base << 3));
 	cpi_cfg &= ~(0xFULL << 20);
 	cpi_cfg |= (cfg->hash_bits << 20);
-	nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3), cpi_cfg);
+	nic_reg_write(nic, idx_addr | (cpi_base << 3), cpi_cfg);
 }
 
 /* 4 level transmit side scheduler configutation
@@ -1001,8 +1019,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_release_regions;
 	}
 
-	pci_read_config_byte(pdev, PCI_REVISION_ID, &nic->rev_id);
-
 	nic->node = nic_get_node_id(pdev);
 
 	nic_set_lmac_vf_mapping(nic);
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index 58197bb..dd536be 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -85,7 +85,11 @@
 #define   NIC_PF_ECC3_DBE_INT_W1S		(0x2708)
 #define   NIC_PF_ECC3_DBE_ENA_W1C		(0x2710)
 #define   NIC_PF_ECC3_DBE_ENA_W1S		(0x2718)
+#define   NIC_PF_MCAM_0_191_ENA			(0x100000)
+#define   NIC_PF_MCAM_0_191_M_0_5_DATA		(0x110000)
+#define   NIC_PF_MCAM_CTRL			(0x120000)
 #define   NIC_PF_CPI_0_2047_CFG			(0x200000)
+#define   NIC_PF_MPI_0_2047_CFG			(0x210000)
 #define   NIC_PF_RSSI_0_4097_RQ			(0x220000)
 #define   NIC_PF_LMAC_0_7_CFG			(0x240000)
 #define   NIC_PF_LMAC_0_7_SW_XOFF		(0x242000)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index b63e579..a937772 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -29,7 +29,7 @@
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
 			 PCI_DEVICE_ID_THUNDER_NIC_VF,
-			 PCI_VENDOR_ID_CAVIUM, 0xA11E) },
+			 PCI_VENDOR_ID_CAVIUM, 0xA134) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
 			 PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF,
 			 PCI_VENDOR_ID_CAVIUM, 0xA11E) },
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 574c492..180aa9f 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -977,8 +977,10 @@ static int bgx_init_of_phy(struct bgx *bgx)
 		SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev);
 		bgx->lmac[lmac].lmacid = lmac;
 		lmac++;
-		if (lmac == MAX_LMAC_PER_BGX)
+		if (lmac == MAX_LMAC_PER_BGX) {
+			of_node_put(np_child);
 			break;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 710715f..ce38d26 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -341,7 +341,7 @@ static void gfar_rx_offload_en(struct gfar_private *priv)
 	if (priv->ndev->features & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX))
 		priv->uses_rxfcb = 1;
 
-	if (priv->hwts_rx_en)
+	if (priv->hwts_rx_en || priv->rx_filer_enable)
 		priv->uses_rxfcb = 1;
 }
 
@@ -351,7 +351,7 @@ static void gfar_mac_rx_config(struct gfar_private *priv)
 	u32 rctrl = 0;
 
 	if (priv->rx_filer_enable) {
-		rctrl |= RCTRL_FILREN;
+		rctrl |= RCTRL_FILREN | RCTRL_PRSDEP_INIT;
 		/* Program the RIR0 reg with the required distribution */
 		if (priv->poll_mode == GFAR_SQ_POLLING)
 			gfar_write(&regs->rir0, DEFAULT_2RXQ_RIR0);
@@ -3462,11 +3462,9 @@ static irqreturn_t gfar_error(int irq, void *grp_id)
 		netif_dbg(priv, tx_err, dev, "Transmit Error\n");
 	}
 	if (events & IEVENT_BSY) {
-		dev->stats.rx_errors++;
+		dev->stats.rx_over_errors++;
 		atomic64_inc(&priv->extra_stats.rx_bsy);
 
-		gfar_receive(irq, grp_id);
-
 		netif_dbg(priv, rx_err, dev, "busy error (rstat: %x)\n",
 			  gfar_read(&regs->rstat));
 	}
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 6bdc891..a33e4a8 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -676,14 +676,14 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	u32 fcr = 0x0, fpr = FPR_FILER_MASK;
 
 	if (ethflow & RXH_L2DA) {
-		fcr = RQFCR_PID_DAH |RQFCR_CMP_NOMATCH |
+		fcr = RQFCR_PID_DAH | RQFCR_CMP_NOMATCH |
 		      RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0;
 		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
 		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 
-		fcr = RQFCR_PID_DAL | RQFCR_AND | RQFCR_CMP_NOMATCH |
+		fcr = RQFCR_PID_DAL | RQFCR_CMP_NOMATCH |
 		      RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0;
 		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
 		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index e972b5e..13a5d4c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1344,6 +1344,12 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 			data[i++] = (i40e_gstrings_veb_stats[j].sizeof_stat ==
 				     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 		}
+		for (j = 0; j < I40E_MAX_TRAFFIC_CLASS; j++) {
+			data[i++] = veb->tc_stats.tc_tx_packets[j];
+			data[i++] = veb->tc_stats.tc_tx_bytes[j];
+			data[i++] = veb->tc_stats.tc_rx_packets[j];
+			data[i++] = veb->tc_stats.tc_rx_bytes[j];
+		}
 	}
 	for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) {
 		p = (char *)pf + i40e_gstrings_stats[j].stat_offset;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dd44faf..3dd26cd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7911,6 +7911,7 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	if (pf->hw.func_caps.vmdq) {
 		pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
 		pf->flags |= I40E_FLAG_VMDQ_ENABLED;
+		pf->num_vmdq_qps = i40e_default_queues_per_vmdq(pf);
 	}
 
 #ifdef I40E_FCOE
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 960169e..dfb6d5f 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -759,11 +759,23 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq,
 
 	desc->l4i_chk = 0;
 	desc->byte_cnt = length;
-	desc->buf_ptr = dma_map_single(dev->dev.parent, data,
-				       length, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(dev->dev.parent, desc->buf_ptr))) {
-		WARN(1, "dma_map_single failed!\n");
-		return -ENOMEM;
+
+	if (length <= 8 && (uintptr_t)data & 0x7) {
+		/* Copy unaligned small data fragment to TSO header data area */
+		memcpy(txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE,
+		       data, length);
+		desc->buf_ptr = txq->tso_hdrs_dma
+			+ txq->tx_curr_desc * TSO_HEADER_SIZE;
+	} else {
+		/* Alignment is okay, map buffer and hand off to hardware */
+		txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE;
+		desc->buf_ptr = dma_map_single(dev->dev.parent, data,
+			length, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(dev->dev.parent,
+					       desc->buf_ptr))) {
+			WARN(1, "dma_map_single failed!\n");
+			return -ENOMEM;
+		}
 	}
 
 	cmd_sts = BUFFER_OWNED_BY_DMA;
@@ -779,7 +791,8 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq,
 }
 
 static inline void
-txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length)
+txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length,
+		u32 *first_cmd_sts, bool first_desc)
 {
 	struct mv643xx_eth_private *mp = txq_to_mp(txq);
 	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
@@ -788,6 +801,7 @@ txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length)
 	int ret;
 	u32 cmd_csum = 0;
 	u16 l4i_chk = 0;
+	u32 cmd_sts;
 
 	tx_index = txq->tx_curr_desc;
 	desc = &txq->tx_desc_area[tx_index];
@@ -803,9 +817,17 @@ txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length)
 	desc->byte_cnt = hdr_len;
 	desc->buf_ptr = txq->tso_hdrs_dma +
 			txq->tx_curr_desc * TSO_HEADER_SIZE;
-	desc->cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA  | TX_FIRST_DESC |
+	cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA  | TX_FIRST_DESC |
 				   GEN_CRC;
 
+	/* Defer updating the first command descriptor until all
+	 * following descriptors have been written.
+	 */
+	if (first_desc)
+		*first_cmd_sts = cmd_sts;
+	else
+		desc->cmd_sts = cmd_sts;
+
 	txq->tx_curr_desc++;
 	if (txq->tx_curr_desc == txq->tx_ring_size)
 		txq->tx_curr_desc = 0;
@@ -819,6 +841,8 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
 	int desc_count = 0;
 	struct tso_t tso;
 	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	struct tx_desc *first_tx_desc;
+	u32 first_cmd_sts = 0;
 
 	/* Count needed descriptors */
 	if ((txq->tx_desc_count + tso_count_descs(skb)) >= txq->tx_ring_size) {
@@ -826,11 +850,14 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
 		return -EBUSY;
 	}
 
+	first_tx_desc = &txq->tx_desc_area[txq->tx_curr_desc];
+
 	/* Initialize the TSO handler, and prepare the first payload */
 	tso_start(skb, &tso);
 
 	total_len = skb->len - hdr_len;
 	while (total_len > 0) {
+		bool first_desc = (desc_count == 0);
 		char *hdr;
 
 		data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
@@ -840,7 +867,8 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
 		/* prepare packet headers: MAC + IP + TCP */
 		hdr = txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE;
 		tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
-		txq_put_hdr_tso(skb, txq, data_left);
+		txq_put_hdr_tso(skb, txq, data_left, &first_cmd_sts,
+				first_desc);
 
 		while (data_left > 0) {
 			int size;
@@ -860,6 +888,10 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
 	__skb_queue_tail(&txq->tx_skb, skb);
 	skb_tx_timestamp(skb);
 
+	/* ensure all other descriptors are written before first cmd_sts */
+	wmb();
+	first_tx_desc->cmd_sts = first_cmd_sts;
+
 	/* clear TX_END status */
 	mp->work_tx_end &= ~(1 << txq->index);
 
@@ -2785,8 +2817,10 @@ static int mv643xx_eth_shared_of_probe(struct platform_device *pdev)
 
 	for_each_available_child_of_node(np, pnp) {
 		ret = mv643xx_eth_shared_of_add_port(pdev, pnp);
-		if (ret)
+		if (ret) {
+			of_node_put(pnp);
 			return ret;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0a32020..2177e56 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2398,7 +2398,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			}
 		}
 
-		memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size);
+		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
 		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
 		INIT_WORK(&priv->mfunc.master.comm_work,
 			  mlx4_master_comm_channel);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 494e776..4421bf5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -964,6 +964,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 			tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN;
 		else if (vlan_proto == ETH_P_8021Q)
 			tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN;
+		else
+			tx_desc->ctrl.ins_vlan = 0;
 
 		tx_desc->ctrl.fence_size = real_size;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index c344884..603d1c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -196,7 +196,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 		return;
 	}
 
-	memcpy(s_eqe, eqe, dev->caps.eqe_size - 1);
+	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
 	s_eqe->slave_id = slave;
 	/* ensure all information is written before setting the ownersip bit */
 	dma_wmb();
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index a41bb5e..75e88f4 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -4076,6 +4076,8 @@ static void nv_do_nic_poll(unsigned long data)
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
 	u32 mask = 0;
+	unsigned long flags;
+	unsigned int irq = 0;
 
 	/*
 	 * First disable irq(s) and then
@@ -4085,25 +4087,27 @@ static void nv_do_nic_poll(unsigned long data)
 
 	if (!using_multi_irqs(dev)) {
 		if (np->msi_flags & NV_MSI_X_ENABLED)
-			disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector);
+			irq = np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector;
 		else
-			disable_irq_lockdep(np->pci_dev->irq);
+			irq = np->pci_dev->irq;
 		mask = np->irqmask;
 	} else {
 		if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) {
-			disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector);
+			irq = np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector;
 			mask |= NVREG_IRQ_RX_ALL;
 		}
 		if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) {
-			disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector);
+			irq = np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector;
 			mask |= NVREG_IRQ_TX_ALL;
 		}
 		if (np->nic_poll_irq & NVREG_IRQ_OTHER) {
-			disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector);
+			irq = np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector;
 			mask |= NVREG_IRQ_OTHER;
 		}
 	}
-	/* disable_irq() contains synchronize_irq, thus no irq handler can run now */
+
+	disable_irq_nosync_lockdep_irqsave(irq, &flags);
+	synchronize_irq(irq);
 
 	if (np->recover_error) {
 		np->recover_error = 0;
@@ -4156,28 +4160,22 @@ static void nv_do_nic_poll(unsigned long data)
 			nv_nic_irq_optimized(0, dev);
 		else
 			nv_nic_irq(0, dev);
-		if (np->msi_flags & NV_MSI_X_ENABLED)
-			enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector);
-		else
-			enable_irq_lockdep(np->pci_dev->irq);
 	} else {
 		if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) {
 			np->nic_poll_irq &= ~NVREG_IRQ_RX_ALL;
 			nv_nic_irq_rx(0, dev);
-			enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector);
 		}
 		if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) {
 			np->nic_poll_irq &= ~NVREG_IRQ_TX_ALL;
 			nv_nic_irq_tx(0, dev);
-			enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector);
 		}
 		if (np->nic_poll_irq & NVREG_IRQ_OTHER) {
 			np->nic_poll_irq &= ~NVREG_IRQ_OTHER;
 			nv_nic_irq_other(0, dev);
-			enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector);
 		}
 	}
 
+	enable_irq_lockdep_irqrestore(irq, &flags);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 257ea71..a484d8b 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1127,7 +1127,7 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	struct sh_eth_txdesc *txdesc = NULL;
 	int rx_ringsize = sizeof(*rxdesc) * mdp->num_rx_ring;
 	int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring;
-	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1;
+	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1;
 	dma_addr_t dma_addr;
 
 	mdp->cur_rx = 0;
@@ -1148,8 +1148,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 
 		/* RX descriptor */
 		rxdesc = &mdp->rx_ring[i];
-		/* The size of the buffer is a multiple of 16 bytes. */
-		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
+		/* The size of the buffer is a multiple of 32 bytes. */
+		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32);
 		dma_addr = dma_map_single(&ndev->dev, skb->data,
 					  rxdesc->buffer_length,
 					  DMA_FROM_DEVICE);
@@ -1450,7 +1450,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 	struct sk_buff *skb;
 	u16 pkt_len = 0;
 	u32 desc_status;
-	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1;
+	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1;
 	dma_addr_t dma_addr;
 
 	boguscnt = min(boguscnt, *quota);
@@ -1506,7 +1506,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
 			dma_unmap_single(&ndev->dev, rxdesc->addr,
-					 ALIGN(mdp->rx_buf_sz, 16),
+					 ALIGN(mdp->rx_buf_sz, 32),
 					 DMA_FROM_DEVICE);
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
@@ -1524,8 +1524,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 	for (; mdp->cur_rx - mdp->dirty_rx > 0; mdp->dirty_rx++) {
 		entry = mdp->dirty_rx % mdp->num_rx_ring;
 		rxdesc = &mdp->rx_ring[entry];
-		/* The size of the buffer is 16 byte boundary. */
-		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
+		/* The size of the buffer is 32 byte boundary. */
+		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32);
 
 		if (mdp->rx_skbuff[entry] == NULL) {
 			skb = netdev_alloc_skb(ndev, skbuff_size);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 8fc90f1..874fb29 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/of_device.h>
 #include <linux/if_vlan.h>
@@ -365,6 +366,7 @@ struct cpsw_priv {
 	spinlock_t			lock;
 	struct platform_device		*pdev;
 	struct net_device		*ndev;
+	struct device_node		*phy_node;
 	struct napi_struct		napi_rx;
 	struct napi_struct		napi_tx;
 	struct device			*dev;
@@ -1145,7 +1147,11 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 		cpsw_ale_add_mcast(priv->ale, priv->ndev->broadcast,
 				   1 << slave_port, 0, 0, ALE_MCAST_FWD_2);
 
-	slave->phy = phy_connect(priv->ndev, slave->data->phy_id,
+	if (priv->phy_node)
+		slave->phy = of_phy_connect(priv->ndev, priv->phy_node,
+				 &cpsw_adjust_link, 0, slave->data->phy_if);
+	else
+		slave->phy = phy_connect(priv->ndev, slave->data->phy_id,
 				 &cpsw_adjust_link, slave->data->phy_if);
 	if (IS_ERR(slave->phy)) {
 		dev_err(priv->dev, "phy %s not found on slave %d\n",
@@ -1934,11 +1940,12 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv,
 	slave->port_vlan = data->dual_emac_res_vlan;
 }
 
-static int cpsw_probe_dt(struct cpsw_platform_data *data,
+static int cpsw_probe_dt(struct cpsw_priv *priv,
 			 struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *slave_node;
+	struct cpsw_platform_data *data = &priv->data;
 	int i = 0, ret;
 	u32 prop;
 
@@ -2029,6 +2036,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		if (strcmp(slave_node->name, "slave"))
 			continue;
 
+		priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0);
 		parp = of_get_property(slave_node, "phy_id", &lenp);
 		if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) {
 			dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i);
@@ -2044,7 +2052,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		}
 		snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
 			 PHY_ID_FMT, mdio->name, phyid);
-
 		slave_data->phy_if = of_get_phy_mode(slave_node);
 		if (slave_data->phy_if < 0) {
 			dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n",
@@ -2240,7 +2247,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(&pdev->dev);
 
-	if (cpsw_probe_dt(&priv->data, pdev)) {
+	if (cpsw_probe_dt(priv, pdev)) {
 		dev_err(&pdev->dev, "cpsw: platform data missing\n");
 		ret = -ENODEV;
 		goto clean_runtime_disable_ret;
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 6bff8d8..4e70e75 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -2637,8 +2637,10 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev,
 			mac_phy_link = true;
 
 		slave->open = true;
-		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
+		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) {
+			of_node_put(port);
 			break;
+		}
 	}
 
 	/* of_phy_connect() is needed only for MAC-PHY interface */
@@ -3137,8 +3139,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 			continue;
 		}
 		gbe_dev->num_slaves++;
-		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
+		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) {
+			of_node_put(interface);
 			break;
+		}
 	}
 	of_node_put(interfaces);