Merge branch 'dccp' of git://eden-feed.erg.abdn.ac.uk/net-next-2.6
diff --git a/drivers/net/cxgb4vf/adapter.h b/drivers/net/cxgb4vf/adapter.h
index 8ea0196..4766b41 100644
--- a/drivers/net/cxgb4vf/adapter.h
+++ b/drivers/net/cxgb4vf/adapter.h
@@ -60,7 +60,7 @@
 	 * MSI-X interrupt index usage.
 	 */
 	MSIX_FW		= 0,		/* MSI-X index for firmware Q */
-	MSIX_NIQFLINT	= 1,		/* MSI-X index base for Ingress Qs */
+	MSIX_IQFLINT	= 1,		/* MSI-X index base for Ingress Qs */
 	MSIX_EXTRAS	= 1,
 	MSIX_ENTRIES	= MAX_ETH_QSETS + MSIX_EXTRAS,
 
diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index c3449bb..9246d2f 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -280,9 +280,7 @@
 		const struct port_info *pi = netdev_priv(dev);
 		int qs, msi;
 
-		for (qs = 0, msi = MSIX_NIQFLINT;
-		     qs < pi->nqsets;
-		     qs++, msi++) {
+		for (qs = 0, msi = MSIX_IQFLINT; qs < pi->nqsets; qs++, msi++) {
 			snprintf(adapter->msix_info[msi].desc, namelen,
 				 "%s-%d", dev->name, qs);
 			adapter->msix_info[msi].desc[namelen] = 0;
@@ -309,7 +307,7 @@
 	/*
 	 * Ethernet queues.
 	 */
-	msi = MSIX_NIQFLINT;
+	msi = MSIX_IQFLINT;
 	for_each_ethrxq(s, rxq) {
 		err = request_irq(adapter->msix_info[msi].vec,
 				  t4vf_sge_intr_msix, 0,
@@ -337,7 +335,7 @@
 	int rxq, msi;
 
 	free_irq(adapter->msix_info[MSIX_FW].vec, &s->fw_evtq);
-	msi = MSIX_NIQFLINT;
+	msi = MSIX_IQFLINT;
 	for_each_ethrxq(s, rxq)
 		free_irq(adapter->msix_info[msi++].vec,
 			 &s->ethrxq[rxq].rspq);
@@ -527,7 +525,7 @@
 	 * brought up at which point lots of things get nailed down
 	 * permanently ...
 	 */
-	msix = MSIX_NIQFLINT;
+	msix = MSIX_IQFLINT;
 	for_each_port(adapter, pidx) {
 		struct net_device *dev = adapter->port[pidx];
 		struct port_info *pi = netdev_priv(dev);
@@ -1348,6 +1346,8 @@
 	u64 rx_csum;
 	u64 vlan_ex;
 	u64 vlan_ins;
+	u64 lro_pkts;
+	u64 lro_merged;
 };
 
 /*
@@ -1385,6 +1385,8 @@
 	"RxCsumGood        ",
 	"VLANextractions   ",
 	"VLANinsertions    ",
+	"GROPackets        ",
+	"GROMerged         ",
 };
 
 /*
@@ -1434,6 +1436,8 @@
 		stats->rx_csum += rxq->stats.rx_cso;
 		stats->vlan_ex += rxq->stats.vlan_ex;
 		stats->vlan_ins += txq->vlan_ins;
+		stats->lro_pkts += rxq->stats.lro_pkts;
+		stats->lro_merged += rxq->stats.lro_merged;
 	}
 }
 
@@ -1530,14 +1534,19 @@
 }
 
 /*
+ * TCP Segmentation Offload flags which we support.
+ */
+#define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+
+/*
  * Set TCP Segmentation Offloading feature capabilities.
  */
 static int cxgb4vf_set_tso(struct net_device *dev, u32 tso)
 {
 	if (tso)
-		dev->features |= NETIF_F_TSO | NETIF_F_TSO6;
+		dev->features |= TSO_FLAGS;
 	else
-		dev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+		dev->features &= ~TSO_FLAGS;
 	return 0;
 }
 
@@ -2028,7 +2037,7 @@
  * Tear down the /sys/kernel/debug/cxgb4vf sub-nodes created above.  We leave
  * it to our caller to tear down the directory (debugfs_root).
  */
-static void __devexit cleanup_debugfs(struct adapter *adapter)
+static void cleanup_debugfs(struct adapter *adapter)
 {
 	BUG_ON(adapter->debugfs_root == NULL);
 
@@ -2046,7 +2055,7 @@
  * adapter parameters we're going to be using and initialize basic adapter
  * hardware support.
  */
-static int adap_init0(struct adapter *adapter)
+static int __devinit adap_init0(struct adapter *adapter)
 {
 	struct vf_resources *vfres = &adapter->params.vfres;
 	struct sge_params *sge_params = &adapter->params.sge;
@@ -2470,7 +2479,6 @@
 		version_printed = 1;
 	}
 
-
 	/*
 	 * Initialize generic PCI device state.
 	 */
@@ -2607,7 +2615,7 @@
 		netif_carrier_off(netdev);
 		netdev->irq = pdev->irq;
 
-		netdev->features = (NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
+		netdev->features = (NETIF_F_SG | TSO_FLAGS |
 				    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 				    NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
 				    NETIF_F_GRO);
diff --git a/drivers/net/cxgb4vf/sge.c b/drivers/net/cxgb4vf/sge.c
index ecf0770..e0b3d1b 100644
--- a/drivers/net/cxgb4vf/sge.c
+++ b/drivers/net/cxgb4vf/sge.c
@@ -1568,6 +1568,9 @@
 	} else
 		skb_checksum_none_assert(skb);
 
+	/*
+	 * Deliver the packet to the stack.
+	 */
 	if (unlikely(pkt->vlan_ex)) {
 		struct vlan_group *grp = pi->vlan_grp;
 
@@ -2143,7 +2146,7 @@
 
 		/*
 		 * Calculate the size of the hardware free list ring plus
-		 * status page (which the SGE will place at the end of the
+		 * Status Page (which the SGE will place after the end of the
 		 * free list ring) in Egress Queue Units.
 		 */
 		flsz = (fl->size / FL_PER_EQ_UNIT +
@@ -2240,8 +2243,8 @@
 	struct port_info *pi = netdev_priv(dev);
 
 	/*
-	 * Calculate the size of the hardware TX Queue (including the
-	 * status age on the end) in units of TX Descriptors.
+	 * Calculate the size of the hardware TX Queue (including the Status
+	 * Page on the end of the TX Queue) in units of TX Descriptors.
 	 */
 	nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc);
 
diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c
index e306c20..f7d7f97 100644
--- a/drivers/net/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/cxgb4vf/t4vf_hw.c
@@ -1276,7 +1276,7 @@
  */
 int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 {
-	struct fw_cmd_hdr *cmd_hdr = (struct fw_cmd_hdr *)rpl;
+	const struct fw_cmd_hdr *cmd_hdr = (const struct fw_cmd_hdr *)rpl;
 	u8 opcode = FW_CMD_OP_GET(be32_to_cpu(cmd_hdr->hi));
 
 	switch (opcode) {
@@ -1284,7 +1284,8 @@
 		/*
 		 * Link/module state change message.
 		 */
-		const struct fw_port_cmd *port_cmd = (void *)rpl;
+		const struct fw_port_cmd *port_cmd =
+			(const struct fw_port_cmd *)rpl;
 		u32 word;
 		int action, port_id, link_ok, speed, fc, pidx;
 
diff --git a/drivers/net/sh_eth.c b/drivers/net/sh_eth.c
index 50259df..b12660d 100644
--- a/drivers/net/sh_eth.c
+++ b/drivers/net/sh_eth.c
@@ -45,9 +45,9 @@
 	u32 ioaddr = ndev->base_addr;
 
 	if (mdp->duplex) /* Full */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) | ECMR_DM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) | ECMR_DM, ioaddr + ECMR);
 	else		/* Half */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) & ~ECMR_DM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) & ~ECMR_DM, ioaddr + ECMR);
 }
 
 static void sh_eth_set_rate(struct net_device *ndev)
@@ -57,10 +57,10 @@
 
 	switch (mdp->speed) {
 	case 10: /* 10BASE */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) & ~ECMR_RTM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) & ~ECMR_RTM, ioaddr + ECMR);
 		break;
 	case 100:/* 100BASE */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) | ECMR_RTM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) | ECMR_RTM, ioaddr + ECMR);
 		break;
 	default:
 		break;
@@ -96,9 +96,9 @@
 	u32 ioaddr = ndev->base_addr;
 
 	if (mdp->duplex) /* Full */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) | ECMR_DM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) | ECMR_DM, ioaddr + ECMR);
 	else		/* Half */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) & ~ECMR_DM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) & ~ECMR_DM, ioaddr + ECMR);
 }
 
 static void sh_eth_set_rate(struct net_device *ndev)
@@ -108,10 +108,10 @@
 
 	switch (mdp->speed) {
 	case 10: /* 10BASE */
-		ctrl_outl(0, ioaddr + RTRATE);
+		writel(0, ioaddr + RTRATE);
 		break;
 	case 100:/* 100BASE */
-		ctrl_outl(1, ioaddr + RTRATE);
+		writel(1, ioaddr + RTRATE);
 		break;
 	default:
 		break;
@@ -143,7 +143,7 @@
 static void sh_eth_chip_reset(struct net_device *ndev)
 {
 	/* reset device */
-	ctrl_outl(ARSTR_ARSTR, ARSTR);
+	writel(ARSTR_ARSTR, ARSTR);
 	mdelay(1);
 }
 
@@ -152,10 +152,10 @@
 	u32 ioaddr = ndev->base_addr;
 	int cnt = 100;
 
-	ctrl_outl(EDSR_ENALL, ioaddr + EDSR);
-	ctrl_outl(ctrl_inl(ioaddr + EDMR) | EDMR_SRST, ioaddr + EDMR);
+	writel(EDSR_ENALL, ioaddr + EDSR);
+	writel(readl(ioaddr + EDMR) | EDMR_SRST, ioaddr + EDMR);
 	while (cnt > 0) {
-		if (!(ctrl_inl(ioaddr + EDMR) & 0x3))
+		if (!(readl(ioaddr + EDMR) & 0x3))
 			break;
 		mdelay(1);
 		cnt--;
@@ -164,14 +164,14 @@
 		printk(KERN_ERR "Device reset fail\n");
 
 	/* Table Init */
-	ctrl_outl(0x0, ioaddr + TDLAR);
-	ctrl_outl(0x0, ioaddr + TDFAR);
-	ctrl_outl(0x0, ioaddr + TDFXR);
-	ctrl_outl(0x0, ioaddr + TDFFR);
-	ctrl_outl(0x0, ioaddr + RDLAR);
-	ctrl_outl(0x0, ioaddr + RDFAR);
-	ctrl_outl(0x0, ioaddr + RDFXR);
-	ctrl_outl(0x0, ioaddr + RDFFR);
+	writel(0x0, ioaddr + TDLAR);
+	writel(0x0, ioaddr + TDFAR);
+	writel(0x0, ioaddr + TDFXR);
+	writel(0x0, ioaddr + TDFFR);
+	writel(0x0, ioaddr + RDLAR);
+	writel(0x0, ioaddr + RDFAR);
+	writel(0x0, ioaddr + RDFXR);
+	writel(0x0, ioaddr + RDFFR);
 }
 
 static void sh_eth_set_duplex(struct net_device *ndev)
@@ -180,9 +180,9 @@
 	u32 ioaddr = ndev->base_addr;
 
 	if (mdp->duplex) /* Full */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) | ECMR_DM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) | ECMR_DM, ioaddr + ECMR);
 	else		/* Half */
-		ctrl_outl(ctrl_inl(ioaddr + ECMR) & ~ECMR_DM, ioaddr + ECMR);
+		writel(readl(ioaddr + ECMR) & ~ECMR_DM, ioaddr + ECMR);
 }
 
 static void sh_eth_set_rate(struct net_device *ndev)
@@ -192,13 +192,13 @@
 
 	switch (mdp->speed) {
 	case 10: /* 10BASE */
-		ctrl_outl(GECMR_10, ioaddr + GECMR);
+		writel(GECMR_10, ioaddr + GECMR);
 		break;
 	case 100:/* 100BASE */
-		ctrl_outl(GECMR_100, ioaddr + GECMR);
+		writel(GECMR_100, ioaddr + GECMR);
 		break;
 	case 1000: /* 1000BASE */
-		ctrl_outl(GECMR_1000, ioaddr + GECMR);
+		writel(GECMR_1000, ioaddr + GECMR);
 		break;
 	default:
 		break;
@@ -283,9 +283,9 @@
 {
 	u32 ioaddr = ndev->base_addr;
 
-	ctrl_outl(ctrl_inl(ioaddr + EDMR) | EDMR_SRST, ioaddr + EDMR);
+	writel(readl(ioaddr + EDMR) | EDMR_SRST, ioaddr + EDMR);
 	mdelay(3);
-	ctrl_outl(ctrl_inl(ioaddr + EDMR) & ~EDMR_SRST, ioaddr + EDMR);
+	writel(readl(ioaddr + EDMR) & ~EDMR_SRST, ioaddr + EDMR);
 }
 #endif
 
@@ -336,10 +336,10 @@
 {
 	u32 ioaddr = ndev->base_addr;
 
-	ctrl_outl((ndev->dev_addr[0] << 24) | (ndev->dev_addr[1] << 16) |
+	writel((ndev->dev_addr[0] << 24) | (ndev->dev_addr[1] << 16) |
 		  (ndev->dev_addr[2] << 8) | (ndev->dev_addr[3]),
 		  ioaddr + MAHR);
-	ctrl_outl((ndev->dev_addr[4] << 8) | (ndev->dev_addr[5]),
+	writel((ndev->dev_addr[4] << 8) | (ndev->dev_addr[5]),
 		  ioaddr + MALR);
 }
 
@@ -358,12 +358,12 @@
 	if (mac[0] || mac[1] || mac[2] || mac[3] || mac[4] || mac[5]) {
 		memcpy(ndev->dev_addr, mac, 6);
 	} else {
-		ndev->dev_addr[0] = (ctrl_inl(ioaddr + MAHR) >> 24);
-		ndev->dev_addr[1] = (ctrl_inl(ioaddr + MAHR) >> 16) & 0xFF;
-		ndev->dev_addr[2] = (ctrl_inl(ioaddr + MAHR) >> 8) & 0xFF;
-		ndev->dev_addr[3] = (ctrl_inl(ioaddr + MAHR) & 0xFF);
-		ndev->dev_addr[4] = (ctrl_inl(ioaddr + MALR) >> 8) & 0xFF;
-		ndev->dev_addr[5] = (ctrl_inl(ioaddr + MALR) & 0xFF);
+		ndev->dev_addr[0] = (readl(ioaddr + MAHR) >> 24);
+		ndev->dev_addr[1] = (readl(ioaddr + MAHR) >> 16) & 0xFF;
+		ndev->dev_addr[2] = (readl(ioaddr + MAHR) >> 8) & 0xFF;
+		ndev->dev_addr[3] = (readl(ioaddr + MAHR) & 0xFF);
+		ndev->dev_addr[4] = (readl(ioaddr + MALR) >> 8) & 0xFF;
+		ndev->dev_addr[5] = (readl(ioaddr + MALR) & 0xFF);
 	}
 }
 
@@ -379,19 +379,19 @@
 /* PHY bit set */
 static void bb_set(u32 addr, u32 msk)
 {
-	ctrl_outl(ctrl_inl(addr) | msk, addr);
+	writel(readl(addr) | msk, addr);
 }
 
 /* PHY bit clear */
 static void bb_clr(u32 addr, u32 msk)
 {
-	ctrl_outl((ctrl_inl(addr) & ~msk), addr);
+	writel((readl(addr) & ~msk), addr);
 }
 
 /* PHY bit read */
 static int bb_read(u32 addr, u32 msk)
 {
-	return (ctrl_inl(addr) & msk) != 0;
+	return (readl(addr) & msk) != 0;
 }
 
 /* Data I/O pin control */
@@ -506,9 +506,9 @@
 		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
 		/* Rx descriptor address set */
 		if (i == 0) {
-			ctrl_outl(mdp->rx_desc_dma, ioaddr + RDLAR);
+			writel(mdp->rx_desc_dma, ioaddr + RDLAR);
 #if defined(CONFIG_CPU_SUBTYPE_SH7763)
-			ctrl_outl(mdp->rx_desc_dma, ioaddr + RDFAR);
+			writel(mdp->rx_desc_dma, ioaddr + RDFAR);
 #endif
 		}
 	}
@@ -528,9 +528,9 @@
 		txdesc->buffer_length = 0;
 		if (i == 0) {
 			/* Tx descriptor address set */
-			ctrl_outl(mdp->tx_desc_dma, ioaddr + TDLAR);
+			writel(mdp->tx_desc_dma, ioaddr + TDLAR);
 #if defined(CONFIG_CPU_SUBTYPE_SH7763)
-			ctrl_outl(mdp->tx_desc_dma, ioaddr + TDFAR);
+			writel(mdp->tx_desc_dma, ioaddr + TDFAR);
 #endif
 		}
 	}
@@ -623,71 +623,71 @@
 	/* Descriptor format */
 	sh_eth_ring_format(ndev);
 	if (mdp->cd->rpadir)
-		ctrl_outl(mdp->cd->rpadir_value, ioaddr + RPADIR);
+		writel(mdp->cd->rpadir_value, ioaddr + RPADIR);
 
 	/* all sh_eth int mask */
-	ctrl_outl(0, ioaddr + EESIPR);
+	writel(0, ioaddr + EESIPR);
 
 #if defined(__LITTLE_ENDIAN__)
 	if (mdp->cd->hw_swap)
-		ctrl_outl(EDMR_EL, ioaddr + EDMR);
+		writel(EDMR_EL, ioaddr + EDMR);
 	else
 #endif
-		ctrl_outl(0, ioaddr + EDMR);
+		writel(0, ioaddr + EDMR);
 
 	/* FIFO size set */
-	ctrl_outl(mdp->cd->fdr_value, ioaddr + FDR);
-	ctrl_outl(0, ioaddr + TFTR);
+	writel(mdp->cd->fdr_value, ioaddr + FDR);
+	writel(0, ioaddr + TFTR);
 
 	/* Frame recv control */
-	ctrl_outl(mdp->cd->rmcr_value, ioaddr + RMCR);
+	writel(mdp->cd->rmcr_value, ioaddr + RMCR);
 
 	rx_int_var = mdp->rx_int_var = DESC_I_RINT8 | DESC_I_RINT5;
 	tx_int_var = mdp->tx_int_var = DESC_I_TINT2;
-	ctrl_outl(rx_int_var | tx_int_var, ioaddr + TRSCER);
+	writel(rx_int_var | tx_int_var, ioaddr + TRSCER);
 
 	if (mdp->cd->bculr)
-		ctrl_outl(0x800, ioaddr + BCULR);	/* Burst sycle set */
+		writel(0x800, ioaddr + BCULR);	/* Burst sycle set */
 
-	ctrl_outl(mdp->cd->fcftr_value, ioaddr + FCFTR);
+	writel(mdp->cd->fcftr_value, ioaddr + FCFTR);
 
 	if (!mdp->cd->no_trimd)
-		ctrl_outl(0, ioaddr + TRIMD);
+		writel(0, ioaddr + TRIMD);
 
 	/* Recv frame limit set register */
-	ctrl_outl(RFLR_VALUE, ioaddr + RFLR);
+	writel(RFLR_VALUE, ioaddr + RFLR);
 
-	ctrl_outl(ctrl_inl(ioaddr + EESR), ioaddr + EESR);
-	ctrl_outl(mdp->cd->eesipr_value, ioaddr + EESIPR);
+	writel(readl(ioaddr + EESR), ioaddr + EESR);
+	writel(mdp->cd->eesipr_value, ioaddr + EESIPR);
 
 	/* PAUSE Prohibition */
-	val = (ctrl_inl(ioaddr + ECMR) & ECMR_DM) |
+	val = (readl(ioaddr + ECMR) & ECMR_DM) |
 		ECMR_ZPF | (mdp->duplex ? ECMR_DM : 0) | ECMR_TE | ECMR_RE;
 
-	ctrl_outl(val, ioaddr + ECMR);
+	writel(val, ioaddr + ECMR);
 
 	if (mdp->cd->set_rate)
 		mdp->cd->set_rate(ndev);
 
 	/* E-MAC Status Register clear */
-	ctrl_outl(mdp->cd->ecsr_value, ioaddr + ECSR);
+	writel(mdp->cd->ecsr_value, ioaddr + ECSR);
 
 	/* E-MAC Interrupt Enable register */
-	ctrl_outl(mdp->cd->ecsipr_value, ioaddr + ECSIPR);
+	writel(mdp->cd->ecsipr_value, ioaddr + ECSIPR);
 
 	/* Set MAC address */
 	update_mac_address(ndev);
 
 	/* mask reset */
 	if (mdp->cd->apr)
-		ctrl_outl(APR_AP, ioaddr + APR);
+		writel(APR_AP, ioaddr + APR);
 	if (mdp->cd->mpr)
-		ctrl_outl(MPR_MP, ioaddr + MPR);
+		writel(MPR_MP, ioaddr + MPR);
 	if (mdp->cd->tpauser)
-		ctrl_outl(TPAUSER_UNLIMITED, ioaddr + TPAUSER);
+		writel(TPAUSER_UNLIMITED, ioaddr + TPAUSER);
 
 	/* Setting the Rx mode will start the Rx process. */
-	ctrl_outl(EDRRR_R, ioaddr + EDRRR);
+	writel(EDRRR_R, ioaddr + EDRRR);
 
 	netif_start_queue(ndev);
 
@@ -811,8 +811,8 @@
 
 	/* Restart Rx engine if stopped. */
 	/* If we don't need to check status, don't. -KDU */
-	if (!(ctrl_inl(ndev->base_addr + EDRRR) & EDRRR_R))
-		ctrl_outl(EDRRR_R, ndev->base_addr + EDRRR);
+	if (!(readl(ndev->base_addr + EDRRR) & EDRRR_R))
+		writel(EDRRR_R, ndev->base_addr + EDRRR);
 
 	return 0;
 }
@@ -827,8 +827,8 @@
 	u32 mask;
 
 	if (intr_status & EESR_ECI) {
-		felic_stat = ctrl_inl(ioaddr + ECSR);
-		ctrl_outl(felic_stat, ioaddr + ECSR);	/* clear int */
+		felic_stat = readl(ioaddr + ECSR);
+		writel(felic_stat, ioaddr + ECSR);	/* clear int */
 		if (felic_stat & ECSR_ICD)
 			mdp->stats.tx_carrier_errors++;
 		if (felic_stat & ECSR_LCHNG) {
@@ -839,25 +839,25 @@
 				else
 					link_stat = PHY_ST_LINK;
 			} else {
-				link_stat = (ctrl_inl(ioaddr + PSR));
+				link_stat = (readl(ioaddr + PSR));
 				if (mdp->ether_link_active_low)
 					link_stat = ~link_stat;
 			}
 			if (!(link_stat & PHY_ST_LINK)) {
 				/* Link Down : disable tx and rx */
-				ctrl_outl(ctrl_inl(ioaddr + ECMR) &
+				writel(readl(ioaddr + ECMR) &
 					  ~(ECMR_RE | ECMR_TE), ioaddr + ECMR);
 			} else {
 				/* Link Up */
-				ctrl_outl(ctrl_inl(ioaddr + EESIPR) &
+				writel(readl(ioaddr + EESIPR) &
 					  ~DMAC_M_ECI, ioaddr + EESIPR);
 				/*clear int */
-				ctrl_outl(ctrl_inl(ioaddr + ECSR),
+				writel(readl(ioaddr + ECSR),
 					  ioaddr + ECSR);
-				ctrl_outl(ctrl_inl(ioaddr + EESIPR) |
+				writel(readl(ioaddr + EESIPR) |
 					  DMAC_M_ECI, ioaddr + EESIPR);
 				/* enable tx and rx */
-				ctrl_outl(ctrl_inl(ioaddr + ECMR) |
+				writel(readl(ioaddr + ECMR) |
 					  (ECMR_RE | ECMR_TE), ioaddr + ECMR);
 			}
 		}
@@ -888,8 +888,8 @@
 		/* Receive Descriptor Empty int */
 		mdp->stats.rx_over_errors++;
 
-		if (ctrl_inl(ioaddr + EDRRR) ^ EDRRR_R)
-			ctrl_outl(EDRRR_R, ioaddr + EDRRR);
+		if (readl(ioaddr + EDRRR) ^ EDRRR_R)
+			writel(EDRRR_R, ioaddr + EDRRR);
 		dev_err(&ndev->dev, "Receive Descriptor Empty\n");
 	}
 	if (intr_status & EESR_RFE) {
@@ -903,7 +903,7 @@
 		mask &= ~EESR_ADE;
 	if (intr_status & mask) {
 		/* Tx error */
-		u32 edtrr = ctrl_inl(ndev->base_addr + EDTRR);
+		u32 edtrr = readl(ndev->base_addr + EDTRR);
 		/* dmesg */
 		dev_err(&ndev->dev, "TX error. status=%8.8x cur_tx=%8.8x ",
 				intr_status, mdp->cur_tx);
@@ -915,7 +915,7 @@
 		/* SH7712 BUG */
 		if (edtrr ^ EDTRR_TRNS) {
 			/* tx dma start */
-			ctrl_outl(EDTRR_TRNS, ndev->base_addr + EDTRR);
+			writel(EDTRR_TRNS, ndev->base_addr + EDTRR);
 		}
 		/* wakeup */
 		netif_wake_queue(ndev);
@@ -934,12 +934,12 @@
 	spin_lock(&mdp->lock);
 
 	/* Get interrpt stat */
-	intr_status = ctrl_inl(ioaddr + EESR);
+	intr_status = readl(ioaddr + EESR);
 	/* Clear interrupt */
 	if (intr_status & (EESR_FRC | EESR_RMAF | EESR_RRF |
 			EESR_RTLF | EESR_RTSF | EESR_PRE | EESR_CERF |
 			cd->tx_check | cd->eesr_err_check)) {
-		ctrl_outl(intr_status, ioaddr + EESR);
+		writel(intr_status, ioaddr + EESR);
 		ret = IRQ_HANDLED;
 	} else
 		goto other_irq;
@@ -1000,7 +1000,7 @@
 				mdp->cd->set_rate(ndev);
 		}
 		if (mdp->link == PHY_DOWN) {
-			ctrl_outl((ctrl_inl(ioaddr + ECMR) & ~ECMR_TXF)
+			writel((readl(ioaddr + ECMR) & ~ECMR_TXF)
 					| ECMR_DM, ioaddr + ECMR);
 			new_state = 1;
 			mdp->link = phydev->link;
@@ -1125,7 +1125,7 @@
 
 	/* worning message out. */
 	printk(KERN_WARNING "%s: transmit timed out, status %8.8x,"
-	       " resetting...\n", ndev->name, (int)ctrl_inl(ioaddr + EESR));
+	       " resetting...\n", ndev->name, (int)readl(ioaddr + EESR));
 
 	/* tx_errors count up */
 	mdp->stats.tx_errors++;
@@ -1196,8 +1196,8 @@
 
 	mdp->cur_tx++;
 
-	if (!(ctrl_inl(ndev->base_addr + EDTRR) & EDTRR_TRNS))
-		ctrl_outl(EDTRR_TRNS, ndev->base_addr + EDTRR);
+	if (!(readl(ndev->base_addr + EDTRR) & EDTRR_TRNS))
+		writel(EDTRR_TRNS, ndev->base_addr + EDTRR);
 
 	return NETDEV_TX_OK;
 }
@@ -1212,11 +1212,11 @@
 	netif_stop_queue(ndev);
 
 	/* Disable interrupts by clearing the interrupt mask. */
-	ctrl_outl(0x0000, ioaddr + EESIPR);
+	writel(0x0000, ioaddr + EESIPR);
 
 	/* Stop the chip's Tx and Rx processes. */
-	ctrl_outl(0, ioaddr + EDTRR);
-	ctrl_outl(0, ioaddr + EDRRR);
+	writel(0, ioaddr + EDTRR);
+	writel(0, ioaddr + EDRRR);
 
 	/* PHY Disconnect */
 	if (mdp->phydev) {
@@ -1251,20 +1251,20 @@
 
 	pm_runtime_get_sync(&mdp->pdev->dev);
 
-	mdp->stats.tx_dropped += ctrl_inl(ioaddr + TROCR);
-	ctrl_outl(0, ioaddr + TROCR);	/* (write clear) */
-	mdp->stats.collisions += ctrl_inl(ioaddr + CDCR);
-	ctrl_outl(0, ioaddr + CDCR);	/* (write clear) */
-	mdp->stats.tx_carrier_errors += ctrl_inl(ioaddr + LCCR);
-	ctrl_outl(0, ioaddr + LCCR);	/* (write clear) */
+	mdp->stats.tx_dropped += readl(ioaddr + TROCR);
+	writel(0, ioaddr + TROCR);	/* (write clear) */
+	mdp->stats.collisions += readl(ioaddr + CDCR);
+	writel(0, ioaddr + CDCR);	/* (write clear) */
+	mdp->stats.tx_carrier_errors += readl(ioaddr + LCCR);
+	writel(0, ioaddr + LCCR);	/* (write clear) */
 #if defined(CONFIG_CPU_SUBTYPE_SH7763)
-	mdp->stats.tx_carrier_errors += ctrl_inl(ioaddr + CERCR);/* CERCR */
-	ctrl_outl(0, ioaddr + CERCR);	/* (write clear) */
-	mdp->stats.tx_carrier_errors += ctrl_inl(ioaddr + CEECR);/* CEECR */
-	ctrl_outl(0, ioaddr + CEECR);	/* (write clear) */
+	mdp->stats.tx_carrier_errors += readl(ioaddr + CERCR);/* CERCR */
+	writel(0, ioaddr + CERCR);	/* (write clear) */
+	mdp->stats.tx_carrier_errors += readl(ioaddr + CEECR);/* CEECR */
+	writel(0, ioaddr + CEECR);	/* (write clear) */
 #else
-	mdp->stats.tx_carrier_errors += ctrl_inl(ioaddr + CNDCR);
-	ctrl_outl(0, ioaddr + CNDCR);	/* (write clear) */
+	mdp->stats.tx_carrier_errors += readl(ioaddr + CNDCR);
+	writel(0, ioaddr + CNDCR);	/* (write clear) */
 #endif
 	pm_runtime_put_sync(&mdp->pdev->dev);
 
@@ -1295,11 +1295,11 @@
 
 	if (ndev->flags & IFF_PROMISC) {
 		/* Set promiscuous. */
-		ctrl_outl((ctrl_inl(ioaddr + ECMR) & ~ECMR_MCT) | ECMR_PRM,
+		writel((readl(ioaddr + ECMR) & ~ECMR_MCT) | ECMR_PRM,
 			  ioaddr + ECMR);
 	} else {
 		/* Normal, unicast/broadcast-only mode. */
-		ctrl_outl((ctrl_inl(ioaddr + ECMR) & ~ECMR_PRM) | ECMR_MCT,
+		writel((readl(ioaddr + ECMR) & ~ECMR_PRM) | ECMR_MCT,
 			  ioaddr + ECMR);
 	}
 }
@@ -1307,30 +1307,30 @@
 /* SuperH's TSU register init function */
 static void sh_eth_tsu_init(u32 ioaddr)
 {
-	ctrl_outl(0, ioaddr + TSU_FWEN0);	/* Disable forward(0->1) */
-	ctrl_outl(0, ioaddr + TSU_FWEN1);	/* Disable forward(1->0) */
-	ctrl_outl(0, ioaddr + TSU_FCM);	/* forward fifo 3k-3k */
-	ctrl_outl(0xc, ioaddr + TSU_BSYSL0);
-	ctrl_outl(0xc, ioaddr + TSU_BSYSL1);
-	ctrl_outl(0, ioaddr + TSU_PRISL0);
-	ctrl_outl(0, ioaddr + TSU_PRISL1);
-	ctrl_outl(0, ioaddr + TSU_FWSL0);
-	ctrl_outl(0, ioaddr + TSU_FWSL1);
-	ctrl_outl(TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, ioaddr + TSU_FWSLC);
+	writel(0, ioaddr + TSU_FWEN0);	/* Disable forward(0->1) */
+	writel(0, ioaddr + TSU_FWEN1);	/* Disable forward(1->0) */
+	writel(0, ioaddr + TSU_FCM);	/* forward fifo 3k-3k */
+	writel(0xc, ioaddr + TSU_BSYSL0);
+	writel(0xc, ioaddr + TSU_BSYSL1);
+	writel(0, ioaddr + TSU_PRISL0);
+	writel(0, ioaddr + TSU_PRISL1);
+	writel(0, ioaddr + TSU_FWSL0);
+	writel(0, ioaddr + TSU_FWSL1);
+	writel(TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, ioaddr + TSU_FWSLC);
 #if defined(CONFIG_CPU_SUBTYPE_SH7763)
-	ctrl_outl(0, ioaddr + TSU_QTAG0);	/* Disable QTAG(0->1) */
-	ctrl_outl(0, ioaddr + TSU_QTAG1);	/* Disable QTAG(1->0) */
+	writel(0, ioaddr + TSU_QTAG0);	/* Disable QTAG(0->1) */
+	writel(0, ioaddr + TSU_QTAG1);	/* Disable QTAG(1->0) */
 #else
-	ctrl_outl(0, ioaddr + TSU_QTAGM0);	/* Disable QTAG(0->1) */
-	ctrl_outl(0, ioaddr + TSU_QTAGM1);	/* Disable QTAG(1->0) */
+	writel(0, ioaddr + TSU_QTAGM0);	/* Disable QTAG(0->1) */
+	writel(0, ioaddr + TSU_QTAGM1);	/* Disable QTAG(1->0) */
 #endif
-	ctrl_outl(0, ioaddr + TSU_FWSR);	/* all interrupt status clear */
-	ctrl_outl(0, ioaddr + TSU_FWINMK);	/* Disable all interrupt */
-	ctrl_outl(0, ioaddr + TSU_TEN);	/* Disable all CAM entry */
-	ctrl_outl(0, ioaddr + TSU_POST1);	/* Disable CAM entry [ 0- 7] */
-	ctrl_outl(0, ioaddr + TSU_POST2);	/* Disable CAM entry [ 8-15] */
-	ctrl_outl(0, ioaddr + TSU_POST3);	/* Disable CAM entry [16-23] */
-	ctrl_outl(0, ioaddr + TSU_POST4);	/* Disable CAM entry [24-31] */
+	writel(0, ioaddr + TSU_FWSR);	/* all interrupt status clear */
+	writel(0, ioaddr + TSU_FWINMK);	/* Disable all interrupt */
+	writel(0, ioaddr + TSU_TEN);	/* Disable all CAM entry */
+	writel(0, ioaddr + TSU_POST1);	/* Disable CAM entry [ 0- 7] */
+	writel(0, ioaddr + TSU_POST2);	/* Disable CAM entry [ 8-15] */
+	writel(0, ioaddr + TSU_POST3);	/* Disable CAM entry [16-23] */
+	writel(0, ioaddr + TSU_POST4);	/* Disable CAM entry [24-31] */
 }
 #endif /* SH_ETH_HAS_TSU */
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 578debb..fccb11f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -592,8 +592,7 @@
 	struct rps_map __rcu		*rps_map;
 	struct rps_dev_flow_table __rcu	*rps_flow_table;
 	struct kobject			kobj;
-	struct netdev_rx_queue		*first;
-	atomic_t			count;
+	struct net_device		*dev;
 } ____cacheline_aligned_in_smp;
 #endif /* CONFIG_RPS */
 
@@ -2239,6 +2238,8 @@
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
+int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev);
+
 static inline int net_gso_ok(int features, int gso_type)
 {
 	int feature = gso_type << NETIF_F_GSO_SHIFT;
@@ -2254,10 +2255,7 @@
 static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
 {
 	if (skb_is_gso(skb)) {
-		int features = dev->features;
-
-		if (skb->protocol == htons(ETH_P_8021Q) || skb->vlan_tci)
-			features &= dev->vlan_features;
+		int features = netif_get_vlan_features(skb, dev);
 
 		return (!skb_gso_ok(skb, features) ||
 			unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
diff --git a/include/net/flow.h b/include/net/flow.h
index 0ac3fb5..7196e68 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -67,6 +67,7 @@
 		} dnports;
 
 		__be32		spi;
+		__be32		gre_key;
 
 		struct {
 			__u8	type;
@@ -78,6 +79,7 @@
 #define fl_icmp_code	uli_u.icmpt.code
 #define fl_ipsec_spi	uli_u.spi
 #define fl_mh_type	uli_u.mht.type
+#define fl_gre_key	uli_u.gre_key
 	__u32           secid;	/* used by xfrm; see secid.txt */
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index bcfb6b2..54b2832 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -805,6 +805,9 @@
 	case IPPROTO_MH:
 		port = htons(fl->fl_mh_type);
 		break;
+	case IPPROTO_GRE:
+		port = htonl(fl->fl_gre_key) >> 16;
+		break;
 	default:
 		port = 0;	/*XXX*/
 	}
@@ -826,6 +829,9 @@
 	case IPPROTO_ICMPV6:
 		port = htons(fl->fl_icmp_code);
 		break;
+	case IPPROTO_GRE:
+		port = htonl(fl->fl_gre_key) & 0xffff;
+		break;
 	default:
 		port = 0;	/*XXX*/
 	}
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 52077ca..55d2135 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -334,6 +334,12 @@
 	vlandev->features &= ~dev->vlan_features;
 	vlandev->features |= dev->features & dev->vlan_features;
 	vlandev->gso_max_size = dev->gso_max_size;
+
+	if (dev->features & NETIF_F_HW_VLAN_TX)
+		vlandev->hard_header_len = dev->hard_header_len;
+	else
+		vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
+
 #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
 	vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
 #endif
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index db01b31..4625ba6 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -45,8 +45,6 @@
  *	@real_dev: underlying netdevice
  *	@real_dev_addr: address of underlying netdevice
  *	@dent: proc dir entry
- *	@cnt_inc_headroom_on_tx: statistic - number of skb expansions on TX
- *	@cnt_encap_on_xmit: statistic - number of skb encapsulations on TX
  *	@vlan_rx_stats: ptr to percpu rx stats
  */
 struct vlan_dev_info {
@@ -62,8 +60,6 @@
 	unsigned char				real_dev_addr[ETH_ALEN];
 
 	struct proc_dir_entry			*dent;
-	unsigned long				cnt_inc_headroom_on_tx;
-	unsigned long				cnt_encap_on_xmit;
 	struct vlan_rx_stats __percpu		*vlan_rx_stats;
 };
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 14e3d1f..f3c9552 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -274,9 +274,6 @@
 	u16 vlan_tci = 0;
 	int rc;
 
-	if (WARN_ON(skb_headroom(skb) < dev->hard_header_len))
-		return -ENOSPC;
-
 	if (!(vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR)) {
 		vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
 
@@ -326,24 +323,12 @@
 	 */
 	if (veth->h_vlan_proto != htons(ETH_P_8021Q) ||
 	    vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR) {
-		unsigned int orig_headroom = skb_headroom(skb);
 		u16 vlan_tci;
-
-		vlan_dev_info(dev)->cnt_encap_on_xmit++;
-
 		vlan_tci = vlan_dev_info(dev)->vlan_id;
 		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
-		skb = __vlan_put_tag(skb, vlan_tci);
-		if (!skb) {
-			txq->tx_dropped++;
-			return NETDEV_TX_OK;
-		}
-
-		if (orig_headroom < VLAN_HLEN)
-			vlan_dev_info(dev)->cnt_inc_headroom_on_tx++;
+		skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
 	}
 
-
 	skb_set_dev(skb, vlan_dev_info(dev)->real_dev);
 	len = skb->len;
 	ret = dev_queue_xmit(skb);
@@ -357,32 +342,6 @@
 	return ret;
 }
 
-static netdev_tx_t vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb,
-						    struct net_device *dev)
-{
-	int i = skb_get_queue_mapping(skb);
-	struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
-	u16 vlan_tci;
-	unsigned int len;
-	int ret;
-
-	vlan_tci = vlan_dev_info(dev)->vlan_id;
-	vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
-	skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
-
-	skb->dev = vlan_dev_info(dev)->real_dev;
-	len = skb->len;
-	ret = dev_queue_xmit(skb);
-
-	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
-		txq->tx_packets++;
-		txq->tx_bytes += len;
-	} else
-		txq->tx_dropped++;
-
-	return ret;
-}
-
 static u16 vlan_dev_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
 	struct net_device *rdev = vlan_dev_info(dev)->real_dev;
@@ -719,8 +678,7 @@
 	.parse	 = eth_header_parse,
 };
 
-static const struct net_device_ops vlan_netdev_ops, vlan_netdev_accel_ops,
-		    vlan_netdev_ops_sq, vlan_netdev_accel_ops_sq;
+static const struct net_device_ops vlan_netdev_ops, vlan_netdev_ops_sq;
 
 static int vlan_dev_init(struct net_device *dev)
 {
@@ -755,19 +713,16 @@
 	if (real_dev->features & NETIF_F_HW_VLAN_TX) {
 		dev->header_ops      = real_dev->header_ops;
 		dev->hard_header_len = real_dev->hard_header_len;
-		if (real_dev->netdev_ops->ndo_select_queue)
-			dev->netdev_ops = &vlan_netdev_accel_ops_sq;
-		else
-			dev->netdev_ops = &vlan_netdev_accel_ops;
 	} else {
 		dev->header_ops      = &vlan_header_ops;
 		dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN;
-		if (real_dev->netdev_ops->ndo_select_queue)
-			dev->netdev_ops = &vlan_netdev_ops_sq;
-		else
-			dev->netdev_ops = &vlan_netdev_ops;
 	}
 
+	if (real_dev->netdev_ops->ndo_select_queue)
+		dev->netdev_ops = &vlan_netdev_ops_sq;
+	else
+		dev->netdev_ops = &vlan_netdev_ops;
+
 	if (is_vlan_dev(real_dev))
 		subclass = 1;
 
@@ -908,30 +863,6 @@
 #endif
 };
 
-static const struct net_device_ops vlan_netdev_accel_ops = {
-	.ndo_change_mtu		= vlan_dev_change_mtu,
-	.ndo_init		= vlan_dev_init,
-	.ndo_uninit		= vlan_dev_uninit,
-	.ndo_open		= vlan_dev_open,
-	.ndo_stop		= vlan_dev_stop,
-	.ndo_start_xmit =  vlan_dev_hwaccel_hard_start_xmit,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_mac_address	= vlan_dev_set_mac_address,
-	.ndo_set_rx_mode	= vlan_dev_set_rx_mode,
-	.ndo_set_multicast_list	= vlan_dev_set_rx_mode,
-	.ndo_change_rx_flags	= vlan_dev_change_rx_flags,
-	.ndo_do_ioctl		= vlan_dev_ioctl,
-	.ndo_neigh_setup	= vlan_dev_neigh_setup,
-	.ndo_get_stats64	= vlan_dev_get_stats64,
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
-	.ndo_fcoe_ddp_setup	= vlan_dev_fcoe_ddp_setup,
-	.ndo_fcoe_ddp_done	= vlan_dev_fcoe_ddp_done,
-	.ndo_fcoe_enable	= vlan_dev_fcoe_enable,
-	.ndo_fcoe_disable	= vlan_dev_fcoe_disable,
-	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
-#endif
-};
-
 static const struct net_device_ops vlan_netdev_ops_sq = {
 	.ndo_select_queue	= vlan_dev_select_queue,
 	.ndo_change_mtu		= vlan_dev_change_mtu,
@@ -957,31 +888,6 @@
 #endif
 };
 
-static const struct net_device_ops vlan_netdev_accel_ops_sq = {
-	.ndo_select_queue	= vlan_dev_select_queue,
-	.ndo_change_mtu		= vlan_dev_change_mtu,
-	.ndo_init		= vlan_dev_init,
-	.ndo_uninit		= vlan_dev_uninit,
-	.ndo_open		= vlan_dev_open,
-	.ndo_stop		= vlan_dev_stop,
-	.ndo_start_xmit =  vlan_dev_hwaccel_hard_start_xmit,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_set_mac_address	= vlan_dev_set_mac_address,
-	.ndo_set_rx_mode	= vlan_dev_set_rx_mode,
-	.ndo_set_multicast_list	= vlan_dev_set_rx_mode,
-	.ndo_change_rx_flags	= vlan_dev_change_rx_flags,
-	.ndo_do_ioctl		= vlan_dev_ioctl,
-	.ndo_neigh_setup	= vlan_dev_neigh_setup,
-	.ndo_get_stats64	= vlan_dev_get_stats64,
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
-	.ndo_fcoe_ddp_setup	= vlan_dev_fcoe_ddp_setup,
-	.ndo_fcoe_ddp_done	= vlan_dev_fcoe_ddp_done,
-	.ndo_fcoe_enable	= vlan_dev_fcoe_enable,
-	.ndo_fcoe_disable	= vlan_dev_fcoe_disable,
-	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
-#endif
-};
-
 void vlan_setup(struct net_device *dev)
 {
 	ether_setup(dev);
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index 80e280f..d1314cf 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -280,7 +280,6 @@
 	const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
 	struct rtnl_link_stats64 temp;
 	const struct rtnl_link_stats64 *stats;
-	static const char fmt[] = "%30s %12lu\n";
 	static const char fmt64[] = "%30s %12llu\n";
 	int i;
 
@@ -299,10 +298,6 @@
 	seq_puts(seq, "\n");
 	seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
 	seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
-	seq_printf(seq, fmt, "total headroom inc",
-		   dev_info->cnt_inc_headroom_on_tx);
-	seq_printf(seq, fmt, "total encap on xmit",
-		   dev_info->cnt_encap_on_xmit);
 	seq_printf(seq, "Device: %s", dev_info->real_dev->name);
 	/* now show all PRIORITY mappings relating to this VLAN */
 	seq_printf(seq, "\nINGRESS priority mappings: "
diff --git a/net/core/dev.c b/net/core/dev.c
index 5968c82..8725d16 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1794,16 +1794,18 @@
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_type *ptype;
 	__be16 type = skb->protocol;
+	int vlan_depth = ETH_HLEN;
 	int err;
 
-	if (type == htons(ETH_P_8021Q)) {
-		struct vlan_ethhdr *veh;
+	while (type == htons(ETH_P_8021Q)) {
+		struct vlan_hdr *vh;
 
-		if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+		if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
 			return ERR_PTR(-EINVAL);
 
-		veh = (struct vlan_ethhdr *)skb->data;
-		type = veh->h_vlan_encapsulated_proto;
+		vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+		type = vh->h_vlan_encapsulated_proto;
+		vlan_depth += VLAN_HLEN;
 	}
 
 	skb_reset_mac_header(skb);
@@ -1966,6 +1968,22 @@
 	}
 }
 
+int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev)
+{
+	__be16 protocol = skb->protocol;
+
+	if (protocol == htons(ETH_P_8021Q)) {
+		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+		protocol = veh->h_vlan_encapsulated_proto;
+	} else if (!skb->vlan_tci)
+		return dev->features;
+
+	if (protocol != htons(ETH_P_8021Q))
+		return dev->features & dev->vlan_features;
+	else
+		return 0;
+}
+
 /*
  * Returns true if either:
  *	1. skb has frag_list and the device doesn't support FRAGLIST, or
@@ -1976,15 +1994,20 @@
 static inline int skb_needs_linearize(struct sk_buff *skb,
 				      struct net_device *dev)
 {
-	int features = dev->features;
+	if (skb_is_nonlinear(skb)) {
+		int features = dev->features;
 
-	if (skb->protocol == htons(ETH_P_8021Q) || vlan_tx_tag_present(skb))
-		features &= dev->vlan_features;
+		if (vlan_tx_tag_present(skb))
+			features &= dev->vlan_features;
 
-	return skb_is_nonlinear(skb) &&
-	       ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) ||
-		(skb_shinfo(skb)->nr_frags && (!(features & NETIF_F_SG) ||
-					      illegal_highdma(dev, skb))));
+		return (skb_has_frag_list(skb) &&
+			!(features & NETIF_F_FRAGLIST)) ||
+			(skb_shinfo(skb)->nr_frags &&
+			(!(features & NETIF_F_SG) ||
+			illegal_highdma(dev, skb)));
+	}
+
+	return 0;
 }
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
@@ -5028,12 +5051,8 @@
 	}
 	dev->_rx = rx;
 
-	/*
-	 * Set a pointer to first element in the array which holds the
-	 * reference count.
-	 */
 	for (i = 0; i < count; i++)
-		rx[i].first = rx;
+		rx[i].dev = dev;
 #endif
 	return 0;
 }
@@ -5109,14 +5128,6 @@
 
 	dev->iflink = -1;
 
-	ret = netif_alloc_rx_queues(dev);
-	if (ret)
-		goto out;
-
-	ret = netif_alloc_netdev_queues(dev);
-	if (ret)
-		goto out;
-
 	netdev_init_queues(dev);
 
 	/* Init, if this function is available */
@@ -5576,10 +5587,14 @@
 
 	dev->num_tx_queues = queue_count;
 	dev->real_num_tx_queues = queue_count;
+	if (netif_alloc_netdev_queues(dev))
+		goto free_pcpu;
 
 #ifdef CONFIG_RPS
 	dev->num_rx_queues = queue_count;
 	dev->real_num_rx_queues = queue_count;
+	if (netif_alloc_rx_queues(dev))
+		goto free_pcpu;
 #endif
 
 	dev->gso_max_size = GSO_MAX_SIZE;
@@ -5596,6 +5611,11 @@
 
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
+	kfree(dev->_tx);
+#ifdef CONFIG_RPS
+	kfree(dev->_rx);
+#endif
+
 free_p:
 	kfree(p);
 	return NULL;
@@ -5617,6 +5637,9 @@
 	release_net(dev_net(dev));
 
 	kfree(dev->_tx);
+#ifdef CONFIG_RPS
+	kfree(dev->_rx);
+#endif
 
 	kfree(rcu_dereference_raw(dev->ingress_queue));
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a5ff5a8..3ba526b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -706,7 +706,6 @@
 static void rx_queue_release(struct kobject *kobj)
 {
 	struct netdev_rx_queue *queue = to_rx_queue(kobj);
-	struct netdev_rx_queue *first = queue->first;
 	struct rps_map *map;
 	struct rps_dev_flow_table *flow_table;
 
@@ -719,8 +718,7 @@
 	if (flow_table)
 		call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
 
-	if (atomic_dec_and_test(&first->count))
-		kfree(first);
+	dev_put(queue->dev);
 }
 
 static struct kobj_type rx_queue_ktype = {
@@ -732,7 +730,6 @@
 static int rx_queue_add_kobject(struct net_device *net, int index)
 {
 	struct netdev_rx_queue *queue = net->_rx + index;
-	struct netdev_rx_queue *first = queue->first;
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
@@ -745,7 +742,7 @@
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	atomic_inc(&first->count);
+	dev_hold(queue->dev);
 
 	return error;
 }
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 0f0e0f0..a1bf2f4 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -163,6 +163,16 @@
 	}
 }
 
+#define for_each_pmc_rcu(in_dev, pmc)				\
+	for (pmc = rcu_dereference(in_dev->mc_list);		\
+	     pmc != NULL;					\
+	     pmc = rcu_dereference(pmc->next_rcu))
+
+#define for_each_pmc_rtnl(in_dev, pmc)				\
+	for (pmc = rtnl_dereference(in_dev->mc_list);		\
+	     pmc != NULL;					\
+	     pmc = rtnl_dereference(pmc->next_rcu))
+
 #ifdef CONFIG_IP_MULTICAST
 
 /*
@@ -502,16 +512,6 @@
 	return skb;
 }
 
-#define for_each_pmc_rcu(in_dev, pmc)				\
-	for (pmc = rcu_dereference(in_dev->mc_list);		\
-	     pmc != NULL;					\
-	     pmc = rcu_dereference(pmc->next_rcu))
-
-#define for_each_pmc_rtnl(in_dev, pmc)				\
-	for (pmc = rtnl_dereference(in_dev->mc_list);		\
-	     pmc != NULL;					\
-	     pmc = rtnl_dereference(pmc->next_rcu))
-
 static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc)
 {
 	struct sk_buff *skb = NULL;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index cab2057..aace653 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -779,9 +779,9 @@
 					.tos = RT_TOS(tos)
 				}
 			},
-			.proto = IPPROTO_GRE
-		}
-;
+			.proto = IPPROTO_GRE,
+			.fl_gre_key = tunnel->parms.o_key
+		};
 		if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
 			dev->stats.tx_carrier_errors++;
 			goto tx_error;
@@ -958,7 +958,8 @@
 					.tos = RT_TOS(iph->tos)
 				}
 			},
-			.proto = IPPROTO_GRE
+			.proto = IPPROTO_GRE,
+			.fl_gre_key = tunnel->parms.o_key
 		};
 		struct rtable *rt;
 
@@ -1223,7 +1224,8 @@
 					.tos = RT_TOS(t->parms.iph.tos)
 				}
 			},
-			.proto = IPPROTO_GRE
+			.proto = IPPROTO_GRE,
+			.fl_gre_key = t->parms.o_key
 		};
 		struct rtable *rt;
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index dd1fd8c..4a8c533 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/inetdevice.h>
+#include <linux/if_tunnel.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
@@ -154,6 +155,20 @@
 				fl->fl_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
 			}
 			break;
+
+		case IPPROTO_GRE:
+			if (pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags = (__be16 *)xprth;
+				__be32 *gre_hdr = (__be32 *)xprth;
+
+				if (greflags[0] & GRE_KEY) {
+					if (greflags[0] & GRE_CSUM)
+						gre_hdr++;
+					fl->fl_gre_key = gre_hdr[1];
+				}
+			}
+			break;
+
 		default:
 			fl->fl_ipsec_spi = 0;
 			break;