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

Conflicts:
	net/ipv6/xfrm6_output.c
	net/openvswitch/flow_netlink.c
	net/openvswitch/vport-gre.c
	net/openvswitch/vport-vxlan.c
	net/openvswitch/vport.c
	net/openvswitch/vport.h

The openvswitch conflicts were overlapping changes.  One was
the egress tunnel info fix in 'net' and the other was the
vport ->send() op simplification in 'net-next'.

The xfrm6_output.c conflicts was also a simplification
overlapping a bug fix.

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 98 insertions, 33 deletions

diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 48ce83e443c2..8d50314ac3eb 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 45512242baea..112f1bc8bcee 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();
+	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 49f796aaad4f..cff8940e1694 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1811,6 +1811,7 @@ 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");
 
@@ -1818,10 +1819,11 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 	if (!ring)
 		return 0;
 
+	cur = ring->cur;
 	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 95af75d35bc5..8b1929e9f698 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -2048,7 +2048,7 @@ 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;
 
@@ -2091,22 +2091,27 @@ 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 9b35d142f47a..8fb84e69c30e 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/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 8fd26fdd7705..3f385ffe420f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1406,6 +1406,12 @@ 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 3e595adfb0bf..b825f978d441 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8154,6 +8154,7 @@ 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 603d29df5832..6bf725921e79 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);
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 55d2d8577d07..040fbc1e5508 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -31,6 +31,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/gpio.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>
@@ -366,6 +367,7 @@ 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;
@@ -1146,7 +1148,11 @@ 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",
@@ -2245,7 +2252,7 @@ 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;