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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 118 insertions, 29 deletions

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 4fdf0aa16978..7402ab12e46b 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -116,9 +116,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev);
 static void gfar_reset_task(struct work_struct *work);
 static void gfar_timeout(struct net_device *dev);
 static int gfar_close(struct net_device *dev);
-struct sk_buff *gfar_new_skb(struct net_device *dev);
-static void gfar_new_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp,
-			   struct sk_buff *skb);
+struct sk_buff *gfar_new_skb(struct net_device *dev, dma_addr_t *bufaddr);
 static int gfar_set_mac_address(struct net_device *dev);
 static int gfar_change_mtu(struct net_device *dev, int new_mtu);
 static irqreturn_t gfar_error(int irq, void *dev_id);
@@ -173,11 +171,14 @@ static void gfar_init_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp,
 static int gfar_init_bds(struct net_device *ndev)
 {
 	struct gfar_private *priv = netdev_priv(ndev);
+	struct gfar __iomem *regs = priv->gfargrp[0].regs;
 	struct gfar_priv_tx_q *tx_queue = NULL;
 	struct gfar_priv_rx_q *rx_queue = NULL;
 	struct txbd8 *txbdp;
 	struct rxbd8 *rxbdp;
+	u32 *rfbptr;
 	int i, j;
+	dma_addr_t bufaddr;
 
 	for (i = 0; i < priv->num_tx_queues; i++) {
 		tx_queue = priv->tx_queue[i];
@@ -201,6 +202,7 @@ static int gfar_init_bds(struct net_device *ndev)
 		txbdp->status |= TXBD_WRAP;
 	}
 
+	rfbptr = &regs->rfbptr0;
 	for (i = 0; i < priv->num_rx_queues; i++) {
 		rx_queue = priv->rx_queue[i];
 		rx_queue->cur_rx = rx_queue->rx_bd_base;
@@ -211,22 +213,22 @@ static int gfar_init_bds(struct net_device *ndev)
 			struct sk_buff *skb = rx_queue->rx_skbuff[j];
 
 			if (skb) {
-				gfar_init_rxbdp(rx_queue, rxbdp,
-						rxbdp->bufPtr);
+				bufaddr = rxbdp->bufPtr;
 			} else {
-				skb = gfar_new_skb(ndev);
+				skb = gfar_new_skb(ndev, &bufaddr);
 				if (!skb) {
 					netdev_err(ndev, "Can't allocate RX buffers\n");
 					return -ENOMEM;
 				}
 				rx_queue->rx_skbuff[j] = skb;
-
-				gfar_new_rxbdp(rx_queue, rxbdp, skb);
 			}
 
+			gfar_init_rxbdp(rx_queue, rxbdp, bufaddr);
 			rxbdp++;
 		}
 
+		rx_queue->rfbptr = rfbptr;
+		rfbptr += 2;
 	}
 
 	return 0;
@@ -336,6 +338,20 @@ static void gfar_init_tx_rx_base(struct gfar_private *priv)
 	}
 }
 
+static void gfar_init_rqprm(struct gfar_private *priv)
+{
+	struct gfar __iomem *regs = priv->gfargrp[0].regs;
+	u32 __iomem *baddr;
+	int i;
+
+	baddr = &regs->rqprm0;
+	for (i = 0; i < priv->num_rx_queues; i++) {
+		gfar_write(baddr, priv->rx_queue[i]->rx_ring_size |
+			   (DEFAULT_RX_LFC_THR << FBTHR_SHIFT));
+		baddr++;
+	}
+}
+
 static void gfar_rx_buff_size_config(struct gfar_private *priv)
 {
 	int frame_size = priv->ndev->mtu + ETH_HLEN + ETH_FCS_LEN;
@@ -396,6 +412,13 @@ static void gfar_mac_rx_config(struct gfar_private *priv)
 	if (priv->ndev->features & NETIF_F_HW_VLAN_CTAG_RX)
 		rctrl |= RCTRL_VLEX | RCTRL_PRSDEP_INIT;
 
+	/* Clear the LFC bit */
+	gfar_write(&regs->rctrl, rctrl);
+	/* Init flow control threshold values */
+	gfar_init_rqprm(priv);
+	gfar_write(&regs->ptv, DEFAULT_LFC_PTVVAL);
+	rctrl |= RCTRL_LFC;
+
 	/* Init rctrl based on our settings */
 	gfar_write(&regs->rctrl, rctrl);
 }
@@ -1687,6 +1710,9 @@ static int init_phy(struct net_device *dev)
 	priv->phydev->supported &= (GFAR_SUPPORTED | gigabit_support);
 	priv->phydev->advertising = priv->phydev->supported;
 
+	/* Add support for flow control, but don't advertise it by default */
+	priv->phydev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause);
+
 	return 0;
 }
 
@@ -2290,6 +2316,8 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 						   0,
 						   frag_len,
 						   DMA_TO_DEVICE);
+			if (unlikely(dma_mapping_error(priv->dev, bufaddr)))
+				goto dma_map_err;
 
 			/* set the TxBD length and buffer pointer */
 			txbdp->bufPtr = bufaddr;
@@ -2339,8 +2367,12 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		fcb->ptp = 1;
 	}
 
-	txbdp_start->bufPtr = dma_map_single(priv->dev, skb->data,
-					     skb_headlen(skb), DMA_TO_DEVICE);
+	bufaddr = dma_map_single(priv->dev, skb->data, skb_headlen(skb),
+				 DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(priv->dev, bufaddr)))
+		goto dma_map_err;
+
+	txbdp_start->bufPtr = bufaddr;
 
 	/* If time stamping is requested one additional TxBD must be set up. The
 	 * first TxBD points to the FCB and must have a data length of
@@ -2406,6 +2438,25 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	spin_unlock_irqrestore(&tx_queue->txlock, flags);
 
 	return NETDEV_TX_OK;
+
+dma_map_err:
+	txbdp = next_txbd(txbdp_start, base, tx_queue->tx_ring_size);
+	if (do_tstamp)
+		txbdp = next_txbd(txbdp, base, tx_queue->tx_ring_size);
+	for (i = 0; i < nr_frags; i++) {
+		lstatus = txbdp->lstatus;
+		if (!(lstatus & BD_LFLAG(TXBD_READY)))
+			break;
+
+		txbdp->lstatus = lstatus & ~BD_LFLAG(TXBD_READY);
+		bufaddr = txbdp->bufPtr;
+		dma_unmap_page(priv->dev, bufaddr, txbdp->length,
+			       DMA_TO_DEVICE);
+		txbdp = next_txbd(txbdp, base, tx_queue->tx_ring_size);
+	}
+	gfar_wmb();
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
 }
 
 /* Stops the kernel queue, and halts the controller */
@@ -2606,18 +2657,6 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 	netdev_tx_completed_queue(txq, howmany, bytes_sent);
 }
 
-static void gfar_new_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp,
-			   struct sk_buff *skb)
-{
-	struct net_device *dev = rx_queue->dev;
-	struct gfar_private *priv = netdev_priv(dev);
-	dma_addr_t buf;
-
-	buf = dma_map_single(priv->dev, skb->data,
-			     priv->rx_buffer_size, DMA_FROM_DEVICE);
-	gfar_init_rxbdp(rx_queue, bdp, buf);
-}
-
 static struct sk_buff *gfar_alloc_skb(struct net_device *dev)
 {
 	struct gfar_private *priv = netdev_priv(dev);
@@ -2632,9 +2671,25 @@ static struct sk_buff *gfar_alloc_skb(struct net_device *dev)
 	return skb;
 }
 
-struct sk_buff *gfar_new_skb(struct net_device *dev)
+struct sk_buff *gfar_new_skb(struct net_device *dev, dma_addr_t *bufaddr)
 {
-	return gfar_alloc_skb(dev);
+	struct gfar_private *priv = netdev_priv(dev);
+	struct sk_buff *skb;
+	dma_addr_t addr;
+
+	skb = gfar_alloc_skb(dev);
+	if (!skb)
+		return NULL;
+
+	addr = dma_map_single(priv->dev, skb->data,
+			      priv->rx_buffer_size, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(priv->dev, addr))) {
+		dev_kfree_skb_any(skb);
+		return NULL;
+	}
+
+	*bufaddr = addr;
+	return skb;
 }
 
 static inline void count_errors(unsigned short status, struct net_device *dev)
@@ -2805,11 +2860,12 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit)
 
 	while (!((bdp->status & RXBD_EMPTY) || (--rx_work_limit < 0))) {
 		struct sk_buff *newskb;
+		dma_addr_t bufaddr;
 
 		rmb();
 
 		/* Add another skb for the future */
-		newskb = gfar_new_skb(dev);
+		newskb = gfar_new_skb(dev, &bufaddr);
 
 		skb = rx_queue->rx_skbuff[rx_queue->skb_currx];
 
@@ -2825,9 +2881,10 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit)
 			     bdp->status & RXBD_ERR)) {
 			count_errors(bdp->status, dev);
 
-			if (unlikely(!newskb))
+			if (unlikely(!newskb)) {
 				newskb = skb;
-			else if (skb)
+				bufaddr = bdp->bufPtr;
+			} else if (skb)
 				dev_kfree_skb(skb);
 		} else {
 			/* Increment the number of packets */
@@ -2854,7 +2911,11 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit)
 		rx_queue->rx_skbuff[rx_queue->skb_currx] = newskb;
 
 		/* Setup the new bdp */
-		gfar_new_rxbdp(rx_queue, bdp, newskb);
+		gfar_init_rxbdp(rx_queue, bdp, bufaddr);
+
+		/* Update Last Free RxBD pointer for LFC */
+		if (unlikely(rx_queue->rfbptr && priv->tx_actual_en))
+			gfar_write(rx_queue->rfbptr, (u32)bdp);
 
 		/* Update to the next pointer */
 		bdp = next_bd(bdp, base, rx_queue->rx_ring_size);
@@ -3370,7 +3431,11 @@ static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv)
 		if (phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = mii_advertise_flowctrl(phydev->advertising);
+		lcl_adv = 0;
+		if (phydev->advertising & ADVERTISED_Pause)
+			lcl_adv |= ADVERTISE_PAUSE_CAP;
+		if (phydev->advertising & ADVERTISED_Asym_Pause)
+			lcl_adv |= ADVERTISE_PAUSE_ASYM;
 
 		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 		if (flowctrl & FLOW_CTRL_TX)
@@ -3386,6 +3451,9 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 {
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
 	struct phy_device *phydev = priv->phydev;
+	struct gfar_priv_rx_q *rx_queue = NULL;
+	int i;
+	struct rxbd8 *bdp;
 
 	if (unlikely(test_bit(GFAR_RESETTING, &priv->state)))
 		return;
@@ -3394,6 +3462,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
+		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))
@@ -3438,6 +3507,26 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		tempval1 &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW);
 		tempval1 |= gfar_get_flowctrl_cfg(priv);
 
+		/* Turn last free buffer recording on */
+		if ((tempval1 & MACCFG1_TX_FLOW) && !tx_flow_oldval) {
+			for (i = 0; i < priv->num_rx_queues; i++) {
+				rx_queue = priv->rx_queue[i];
+				bdp = rx_queue->cur_rx;
+				/* skip to previous bd */
+				bdp = skip_bd(bdp, rx_queue->rx_ring_size - 1,
+					      rx_queue->rx_bd_base,
+					      rx_queue->rx_ring_size);
+
+				if (rx_queue->rfbptr)
+					gfar_write(rx_queue->rfbptr, (u32)bdp);
+			}
+
+			priv->tx_actual_en = 1;
+		}
+
+		if (unlikely(!(tempval1 & MACCFG1_TX_FLOW) && tx_flow_oldval))
+			priv->tx_actual_en = 0;
+
 		gfar_write(&regs->maccfg1, tempval1);
 		gfar_write(&regs->maccfg2, tempval);
 		gfar_write(&regs->ecntrl, ecntrl);