Merge tag 'v4.2-rc7' into drm-next

Linux 4.2-rc7

Backmerge master for i915 fixes

93 files changed, 1276 insertions, 1414 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 317a49480475..a98dd4f1b0e3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -625,6 +625,23 @@ static void bond_set_dev_addr(struct net_device *bond_dev,
         call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
 }
 
+static struct slave *bond_get_old_active(struct bonding *bond,
+                                         struct slave *new_active)
+{
+        struct slave *slave;
+        struct list_head *iter;
+
+        bond_for_each_slave(bond, slave, iter) {
+                if (slave == new_active)
+                        continue;
+
+                if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
+                        return slave;
+        }
+
+        return NULL;
+}
+
 /* bond_do_fail_over_mac
  *
  * Perform special MAC address swapping for fail_over_mac settings
@@ -652,6 +669,9 @@ static void bond_do_fail_over_mac(struct bonding *bond,
                 if (!new_active)
                         return;
 
+                if (!old_active)
+                        old_active = bond_get_old_active(bond, new_active);
+
                 if (old_active) {
                         ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
                         ether_addr_copy(saddr.sa_data,
@@ -766,6 +786,7 @@ static bool bond_should_notify_peers(struct bonding *bond)
                    slave ? slave->dev->name : "NULL");
 
         if (!slave || !bond->send_peer_notif ||
+            !netif_carrier_ok(bond->dev) ||
             test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
                 return false;
 
@@ -1725,9 +1746,16 @@ err_free:
 
 err_undo_flags:
         /* Enslave of first slave has failed and we need to fix master's mac */
-        if (!bond_has_slaves(bond) &&
-            ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr))
-                eth_hw_addr_random(bond_dev);
+        if (!bond_has_slaves(bond)) {
+                if (ether_addr_equal_64bits(bond_dev->dev_addr,
+                                            slave_dev->dev_addr))
+                        eth_hw_addr_random(bond_dev);
+                if (bond_dev->type != ARPHRD_ETHER) {
+                        ether_setup(bond_dev);
+                        bond_dev->flags |= IFF_MASTER;
+                        bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+                }
+        }
 
         return res;
 }
@@ -1916,6 +1944,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
                 bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
                 netdev_info(bond_dev, "Destroying bond %s\n",
                             bond_dev->name);
+                bond_remove_proc_entry(bond);
                 unregister_netdevice(bond_dev);
         }
         return ret;
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index f4e40aa4d2a2..945c0955a967 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -577,10 +577,10 @@ static void at91_rx_overflow_err(struct net_device *dev)
 
         cf->can_id |= CAN_ERR_CRTL;
         cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
-        netif_receive_skb(skb);
 
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_receive_skb(skb);
 }
 
 /**
@@ -642,10 +642,10 @@ static void at91_read_msg(struct net_device *dev, unsigned int mb)
         }
 
         at91_read_mb(dev, mb, cf);
-        netif_receive_skb(skb);
 
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_receive_skb(skb);
 
         can_led_event(dev, CAN_LED_EVENT_RX);
 }
@@ -802,10 +802,10 @@ static int at91_poll_err(struct net_device *dev, int quota, u32 reg_sr)
                 return 0;
 
         at91_poll_err_frame(dev, cf, reg_sr);
-        netif_receive_skb(skb);
 
         dev->stats.rx_packets++;
         dev->stats.rx_bytes += cf->can_dlc;
+        netif_receive_skb(skb);
 
         return 1;
 }
@@ -1067,10 +1067,10 @@ static void at91_irq_err(struct net_device *dev)
                 return;
 
         at91_irq_err_state(dev, cf, new_state);
-        netif_rx(skb);
 
         dev->stats.rx_packets++;
         dev->stats.rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         priv->can.state = new_state;
 }
diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c
index 27ad312e7abf..57dadd52b428 100644
--- a/drivers/net/can/bfin_can.c
+++ b/drivers/net/can/bfin_can.c
@@ -424,10 +424,9 @@ static void bfin_can_rx(struct net_device *dev, u16 isrc)
                 cf->data[6 - i] = (6 - i) < cf->can_dlc ? (val >> 8) : 0;
         }
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 }
 
 static int bfin_can_err(struct net_device *dev, u16 isrc, u16 status)
@@ -508,10 +507,9 @@ static int bfin_can_err(struct net_device *dev, u16 isrc, u16 status)
 
         priv->can.state = state;
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index c11d44984036..70a8cbb29e75 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -504,10 +504,10 @@ static void cc770_rx(struct net_device *dev, unsigned int mo, u8 ctrl1)
                 for (i = 0; i < cf->can_dlc; i++)
                         cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
         }
-        netif_rx(skb);
 
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 }
 
 static int cc770_err(struct net_device *dev, u8 status)
@@ -584,10 +584,10 @@ static int cc770_err(struct net_device *dev, u8 status)
                 }
         }
 
-        netif_rx(skb);
 
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 6201c5a1a884..b1e8d729851c 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -577,10 +577,10 @@ static int flexcan_poll_bus_err(struct net_device *dev, u32 reg_esr)
                 return 0;
 
         do_bus_err(dev, cf, reg_esr);
-        netif_receive_skb(skb);
 
         dev->stats.rx_packets++;
         dev->stats.rx_bytes += cf->can_dlc;
+        netif_receive_skb(skb);
 
         return 1;
 }
@@ -622,10 +622,9 @@ static int flexcan_poll_state(struct net_device *dev, u32 reg_esr)
         if (unlikely(new_state == CAN_STATE_BUS_OFF))
                 can_bus_off(dev);
 
-        netif_receive_skb(skb);
-
         dev->stats.rx_packets++;
         dev->stats.rx_bytes += cf->can_dlc;
+        netif_receive_skb(skb);
 
         return 1;
 }
@@ -670,10 +669,10 @@ static int flexcan_read_frame(struct net_device *dev)
         }
 
         flexcan_read_fifo(dev, cf);
-        netif_receive_skb(skb);
 
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_receive_skb(skb);
 
         can_led_event(dev, CAN_LED_EVENT_RX);
 
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index e3d7e22a4fa0..db9538d4b358 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1216,11 +1216,12 @@ static int grcan_receive(struct net_device *dev, int budget)
                                 cf->data[i] = (u8)(slot[j] >> shift);
                         }
                 }
-                netif_receive_skb(skb);
 
                 /* Update statistics and read pointer */
                 stats->rx_packets++;
                 stats->rx_bytes += cf->can_dlc;
+                netif_receive_skb(skb);
+
                 rd = grcan_ring_add(rd, GRCAN_MSG_SIZE, dma->rx.size);
         }
 
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 32bd7f451aa4..7b92e911a616 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -377,10 +377,9 @@ static void sja1000_rx(struct net_device *dev)
         /* release receive buffer */
         sja1000_write_cmdreg(priv, CMD_RRB);
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         can_led_event(dev, CAN_LED_EVENT_RX);
 }
@@ -484,10 +483,9 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
                         can_bus_off(dev);
         }
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index a23a7af8eb9a..9a3f15cb7ef4 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -218,10 +218,10 @@ static void slc_bump(struct slcan *sl)
 
         memcpy(skb_put(skb, sizeof(struct can_frame)),
                &cf, sizeof(struct can_frame));
-        netif_rx_ni(skb);
 
         sl->dev->stats.rx_packets++;
         sl->dev->stats.rx_bytes += cf.can_dlc;
+        netif_rx_ni(skb);
 }
 
 /* parse tty input stream */
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index c1a95a34d62e..b7e83c212023 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1086,8 +1086,8 @@ static int mcp251x_can_probe(struct spi_device *spi)
         if (ret)
                 goto out_clk;
 
-        priv->power = devm_regulator_get(&spi->dev, "vdd");
-        priv->transceiver = devm_regulator_get(&spi->dev, "xceiver");
+        priv->power = devm_regulator_get_optional(&spi->dev, "vdd");
+        priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver");
         if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
             (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
                 ret = -EPROBE_DEFER;
@@ -1222,17 +1222,16 @@ static int __maybe_unused mcp251x_can_resume(struct device *dev)
         struct spi_device *spi = to_spi_device(dev);
         struct mcp251x_priv *priv = spi_get_drvdata(spi);
 
-        if (priv->after_suspend & AFTER_SUSPEND_POWER) {
+        if (priv->after_suspend & AFTER_SUSPEND_POWER)
                 mcp251x_power_enable(priv->power, 1);
+
+        if (priv->after_suspend & AFTER_SUSPEND_UP) {
+                mcp251x_power_enable(priv->transceiver, 1);
                 queue_work(priv->wq, &priv->restart_work);
         } else {
-                if (priv->after_suspend & AFTER_SUSPEND_UP) {
-                        mcp251x_power_enable(priv->transceiver, 1);
-                        queue_work(priv->wq, &priv->restart_work);
-                } else {
-                        priv->after_suspend = 0;
-                }
+                priv->after_suspend = 0;
         }
+
         priv->force_quit = 0;
         enable_irq(spi->irq);
         return 0;
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index e95a9e1a889f..cf345cbfe819 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -747,9 +747,9 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
                 }
         }
 
-        netif_rx(skb);
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 866bac0ae7e9..2d390384ef3b 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -324,10 +324,9 @@ static void ems_usb_rx_can_msg(struct ems_usb *dev, struct ems_cpc_msg *msg)
                         cf->data[i] = msg->msg.can_msg.msg[i];
         }
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 }
 
 static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg)
@@ -400,10 +399,9 @@ static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg)
                 stats->rx_errors++;
         }
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 }
 
 /*
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 411c1af92c62..0e5a4493ba4f 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -301,13 +301,12 @@ static void esd_usb2_rx_event(struct esd_usb2_net_priv *priv,
                         cf->data[7] = rxerr;
                 }
 
-                netif_rx(skb);
-
                 priv->bec.txerr = txerr;
                 priv->bec.rxerr = rxerr;
 
                 stats->rx_packets++;
                 stats->rx_bytes += cf->can_dlc;
+                netif_rx(skb);
         }
 }
 
@@ -347,10 +346,9 @@ static void esd_usb2_rx_can_msg(struct esd_usb2_net_priv *priv,
                                 cf->data[i] = msg->msg.rx.data[i];
                 }
 
-                netif_rx(skb);
-
                 stats->rx_packets++;
                 stats->rx_bytes += cf->can_dlc;
+                netif_rx(skb);
         }
 
         return;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 72427f21edff..6b94007ae052 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -526,9 +526,9 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
                 hwts->hwtstamp = timeval_to_ktime(tv);
         }
 
-        netif_rx(skb);
         mc->netdev->stats.rx_packets++;
         mc->netdev->stats.rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
@@ -659,12 +659,11 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
         hwts = skb_hwtstamps(skb);
         hwts->hwtstamp = timeval_to_ktime(tv);
 
-        /* push the skb */
-        netif_rx(skb);
-
         /* update statistics */
         mc->netdev->stats.rx_packets++;
         mc->netdev->stats.rx_bytes += cf->can_dlc;
+        /* push the skb */
+        netif_rx(skb);
 
         return 0;
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index dec51717635e..7d61b3279798 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -553,9 +553,9 @@ static int pcan_usb_pro_handle_canmsg(struct pcan_usb_pro_interface *usb_if,
         hwts = skb_hwtstamps(skb);
         hwts->hwtstamp = timeval_to_ktime(tv);
 
-        netif_rx(skb);
         netdev->stats.rx_packets++;
         netdev->stats.rx_bytes += can_frame->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
@@ -670,9 +670,9 @@ static int pcan_usb_pro_handle_error(struct pcan_usb_pro_interface *usb_if,
         peak_usb_get_ts_tv(&usb_if->time_ref, le32_to_cpu(er->ts32), &tv);
         hwts = skb_hwtstamps(skb);
         hwts->hwtstamp = timeval_to_ktime(tv);
-        netif_rx(skb);
         netdev->stats.rx_packets++;
         netdev->stats.rx_bytes += can_frame->can_dlc;
+        netif_rx(skb);
 
         return 0;
 }
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index dd52c7a4c80d..de95b1ccba3e 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -461,10 +461,9 @@ static void usb_8dev_rx_err_msg(struct usb_8dev_priv *priv,
         priv->bec.txerr = txerr;
         priv->bec.rxerr = rxerr;
 
-        netif_rx(skb);
-
         stats->rx_packets++;
         stats->rx_bytes += cf->can_dlc;
+        netif_rx(skb);
 }
 
 /* Read data and status frames */
@@ -494,10 +493,9 @@ static void usb_8dev_rx_can_msg(struct usb_8dev_priv *priv,
                 else
                         memcpy(cf->data, msg->data, cf->can_dlc);
 
-                netif_rx(skb);
-
                 stats->rx_packets++;
                 stats->rx_bytes += cf->can_dlc;
+                netif_rx(skb);
 
                 can_led_event(priv->netdev, CAN_LED_EVENT_RX);
         } else {
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 972982f8bea7..079897b3a955 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -696,9 +696,20 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds)
         }
 
         /* Include the pseudo-PHY address and the broadcast PHY address to
-         * divert reads towards our workaround
+         * divert reads towards our workaround. This is only required for
+         * 7445D0, since 7445E0 disconnects the internal switch pseudo-PHY such
+         * that we can use the regular SWITCH_MDIO master controller instead.
+         *
+         * By default, DSA initializes ds->phys_mii_mask to ds->phys_port_mask
+         * to have a 1:1 mapping between Port address and PHY address in order
+         * to utilize the slave_mii_bus instance to read from Port PHYs. This is
+         * not what we want here, so we initialize phys_mii_mask 0 to always
+         * utilize the "master" MDIO bus backed by the "mdio-unimac" driver.
          */
-        ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
+        if (of_machine_is_compatible("brcm,bcm7445d0"))
+                ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
+        else
+                ds->phys_mii_mask = 0;
 
         rev = reg_readl(priv, REG_SWITCH_REVISION);
         priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index fd8547c2b79d..561342466076 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1163,7 +1163,7 @@ int mv88e6xxx_leave_bridge(struct dsa_switch *ds, int port, u32 br_port_mask)
 
         newfid = __ffs(ps->fid_mask);
         ps->fid[port] = newfid;
-        ps->fid_mask &= (1 << newfid);
+        ps->fid_mask &= ~(1 << newfid);
         ps->bridge_mask[fid] &= ~(1 << port);
         ps->bridge_mask[newfid] = 1 << port;
 
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 2d1ce3c5d0dd..753887d02b46 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1763,16 +1763,9 @@ vortex_open(struct net_device *dev)
                         vp->rx_ring[i].addr = cpu_to_le32(pci_map_single(VORTEX_PCI(vp), skb->data, PKT_BUF_SZ, PCI_DMA_FROMDEVICE));
                 }
                 if (i != RX_RING_SIZE) {
-                        int j;
                         pr_emerg("%s: no memory for rx ring\n", dev->name);
-                        for (j = 0; j < i; j++) {
-                                if (vp->rx_skbuff[j]) {
-                                        dev_kfree_skb(vp->rx_skbuff[j]);
-                                        vp->rx_skbuff[j] = NULL;
-                                }
-                        }
                         retval = -ENOMEM;
-                        goto err_free_irq;
+                        goto err_free_skb;
                 }
                 /* Wrap the ring. */
                 vp->rx_ring[i-1].next = cpu_to_le32(vp->rx_ring_dma);
@@ -1782,7 +1775,13 @@ vortex_open(struct net_device *dev)
         if (!retval)
                 goto out;
 
-err_free_irq:
+err_free_skb:
+        for (i = 0; i < RX_RING_SIZE; i++) {
+                if (vp->rx_skbuff[i]) {
+                        dev_kfree_skb(vp->rx_skbuff[i]);
+                        vp->rx_skbuff[i] = NULL;
+                }
+        }
         free_irq(dev->irq, dev);
 err:
         if (vortex_debug > 1)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index a90d7364334f..f7fbdc9d1325 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -262,9 +262,9 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
         if (likely(skb)) {
                 (*pkts_compl)++;
                 (*bytes_compl) += skb->len;
+                dev_kfree_skb_any(skb);
         }
 
-        dev_kfree_skb_any(skb);
         tx_buf->first_bd = 0;
         tx_buf->skb = NULL;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 76b9052a961c..5907c821d131 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1718,6 +1718,22 @@ static int bnx2x_nvram_write(struct bnx2x *bp, u32 offset, u8 *data_buf,
                 offset += sizeof(u32);
                 data_buf += sizeof(u32);
                 written_so_far += sizeof(u32);
+
+                /* At end of each 4Kb page, release nvram lock to allow MFW
+                 * chance to take it for its own use.
+                 */
+                if ((cmd_flags & MCPR_NVM_COMMAND_LAST) &&
+                    (written_so_far < buf_size)) {
+                        DP(BNX2X_MSG_ETHTOOL | BNX2X_MSG_NVM,
+                           "Releasing NVM lock after offset 0x%x\n",
+                           (u32)(offset - sizeof(u32)));
+                        bnx2x_release_nvram_lock(bp);
+                        usleep_range(1000, 2000);
+                        rc = bnx2x_acquire_nvram_lock(bp);
+                        if (rc)
+                                return rc;
+                }
+
                 cmd_flags = 0;
         }
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 0612b19f6313..506047c38607 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -676,6 +676,7 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
                         if (!next_cmpl->valid)
                                 break;
                 }
+                packets++;
 
                 /* TODO: BNA_CQ_EF_LOCAL ? */
                 if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR |
@@ -692,7 +693,6 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
                 else
                         bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len);
 
-                packets++;
                 rcb->rxq->rx_packets++;
                 rcb->rxq->rx_bytes += totlen;
                 ccb->bytes_per_intr += totlen;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index caeb39561567..bf9eb2ecf960 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -104,6 +104,57 @@ static void *macb_rx_buffer(struct macb *bp, unsigned int index)
         return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
 }
 
+/* I/O accessors */
+static u32 hw_readl_native(struct macb *bp, int offset)
+{
+        return __raw_readl(bp->regs + offset);
+}
+
+static void hw_writel_native(struct macb *bp, int offset, u32 value)
+{
+        __raw_writel(value, bp->regs + offset);
+}
+
+static u32 hw_readl(struct macb *bp, int offset)
+{
+        return readl_relaxed(bp->regs + offset);
+}
+
+static void hw_writel(struct macb *bp, int offset, u32 value)
+{
+        writel_relaxed(value, bp->regs + offset);
+}
+
+/*
+ * Find the CPU endianness by using the loopback bit of NCR register. When the
+ * CPU is in big endian we need to program swaped mode for management
+ * descriptor access.
+ */
+static bool hw_is_native_io(void __iomem *addr)
+{
+        u32 value = MACB_BIT(LLB);
+
+        __raw_writel(value, addr + MACB_NCR);
+        value = __raw_readl(addr + MACB_NCR);
+
+        /* Write 0 back to disable everything */
+        __raw_writel(0, addr + MACB_NCR);
+
+        return value == MACB_BIT(LLB);
+}
+
+static bool hw_is_gem(void __iomem *addr, bool native_io)
+{
+        u32 id;
+
+        if (native_io)
+                id = __raw_readl(addr + MACB_MID);
+        else
+                id = readl_relaxed(addr + MACB_MID);
+
+        return MACB_BFEXT(IDNUM, id) >= 0x2;
+}
+
 static void macb_set_hwaddr(struct macb *bp)
 {
         u32 bottom;
@@ -160,7 +211,7 @@ static void macb_get_hwaddr(struct macb *bp)
                 }
         }
 
-        netdev_info(bp->dev, "invalid hw address, using random\n");
+        dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
         eth_hw_addr_random(bp->dev);
 }
 
@@ -252,7 +303,6 @@ static void macb_handle_link_change(struct net_device *dev)
         struct macb *bp = netdev_priv(dev);
         struct phy_device *phydev = bp->phy_dev;
         unsigned long flags;
-
         int status_change = 0;
 
         spin_lock_irqsave(&bp->lock, flags);
@@ -449,14 +499,14 @@ err_out:
 
 static void macb_update_stats(struct macb *bp)
 {
-        u32 __iomem *reg = bp->regs + MACB_PFR;
         u32 *p = &bp->hw_stats.macb.rx_pause_frames;
         u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+        int offset = MACB_PFR;
 
         WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
 
-        for(; p < end; p++, reg++)
-                *p += readl_relaxed(reg);
+        for(; p < end; p++, offset += 4)
+                *p += bp->macb_reg_readl(bp, offset);
 }
 
 static int macb_halt_tx(struct macb *bp)
@@ -1107,12 +1157,6 @@ static void macb_poll_controller(struct net_device *dev)
 }
 #endif
 
-static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
-                                                     unsigned int len)
-{
-        return (len + bp->max_tx_length - 1) / bp->max_tx_length;
-}
-
 static unsigned int macb_tx_map(struct macb *bp,
                                 struct macb_queue *queue,
                                 struct sk_buff *skb)
@@ -1263,11 +1307,11 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
          * socket buffer: skb fragments of jumbo frames may need to be
          * splitted into many buffer descriptors.
          */
-        count = macb_count_tx_descriptors(bp, skb_headlen(skb));
+        count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
         nr_frags = skb_shinfo(skb)->nr_frags;
         for (f = 0; f < nr_frags; f++) {
                 frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
-                count += macb_count_tx_descriptors(bp, frag_size);
+                count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
         }
 
         spin_lock_irqsave(&bp->lock, flags);
@@ -1603,7 +1647,6 @@ static u32 macb_dbw(struct macb *bp)
 static void macb_configure_dma(struct macb *bp)
 {
         u32 dmacfg;
-        u32 tmp, ncr;
 
         if (macb_is_gem(bp)) {
                 dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
@@ -1613,22 +1656,11 @@ static void macb_configure_dma(struct macb *bp)
                 dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
                 dmacfg &= ~GEM_BIT(ENDIA_PKT);
 
-                /* Find the CPU endianness by using the loopback bit of net_ctrl
-                 * register. save it first. When the CPU is in big endian we
-                 * need to program swaped mode for management descriptor access.
-                 */
-                ncr = macb_readl(bp, NCR);
-                __raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR);
-                tmp =  __raw_readl(bp->regs + MACB_NCR);
-
-                if (tmp == MACB_BIT(LLB))
+                if (bp->native_io)
                         dmacfg &= ~GEM_BIT(ENDIA_DESC);
                 else
                         dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */
 
-                /* Restore net_ctrl */
-                macb_writel(bp, NCR, ncr);
-
                 if (bp->dev->features & NETIF_F_HW_CSUM)
                         dmacfg |= GEM_BIT(TXCOEN);
                 else
@@ -1897,19 +1929,19 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu)
 
 static void gem_update_stats(struct macb *bp)
 {
-        int i;
+        unsigned int i;
         u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
 
         for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
                 u32 offset = gem_statistics[i].offset;
-                u64 val = readl_relaxed(bp->regs + offset);
+                u64 val = bp->macb_reg_readl(bp, offset);
 
                 bp->ethtool_stats[i] += val;
                 *p += val;
 
                 if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
                         /* Add GEM_OCTTXH, GEM_OCTRXH */
-                        val = readl_relaxed(bp->regs + offset + 4);
+                        val = bp->macb_reg_readl(bp, offset + 4);
                         bp->ethtool_stats[i] += ((u64)val) << 32;
                         *(++p) += val;
                 }
@@ -1976,7 +2008,7 @@ static int gem_get_sset_count(struct net_device *dev, int sset)
 
 static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 {
-        int i;
+        unsigned int i;
 
         switch (sset) {
         case ETH_SS_STATS:
@@ -2190,7 +2222,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co
         if (dt_conf)
                 bp->caps = dt_conf->caps;
 
-        if (macb_is_gem_hw(bp->regs)) {
+        if (hw_is_gem(bp->regs, bp->native_io)) {
                 bp->caps |= MACB_CAPS_MACB_IS_GEM;
 
                 dcfg = gem_readl(bp, DCFG1);
@@ -2201,10 +2233,11 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co
                         bp->caps |= MACB_CAPS_FIFO_MODE;
         }
 
-        netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
+        dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
 }
 
 static void macb_probe_queues(void __iomem *mem,
+                              bool native_io,
                               unsigned int *queue_mask,
                               unsigned int *num_queues)
 {
@@ -2219,7 +2252,7 @@ static void macb_probe_queues(void __iomem *mem,
          * we are early in the probe process and don't have the
          * MACB_CAPS_MACB_IS_GEM flag positioned
          */
-        if (!macb_is_gem_hw(mem))
+        if (!hw_is_gem(mem, native_io))
                 return;
 
         /* bit 0 is never set but queue 0 always exists */
@@ -2786,6 +2819,7 @@ static int macb_probe(struct platform_device *pdev)
         struct clk *pclk, *hclk, *tx_clk;
         unsigned int queue_mask, num_queues;
         struct macb_platform_data *pdata;
+        bool native_io;
         struct phy_device *phydev;
         struct net_device *dev;
         struct resource *regs;
@@ -2794,6 +2828,11 @@ static int macb_probe(struct platform_device *pdev)
         struct macb *bp;
         int err;
 
+        regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+        mem = devm_ioremap_resource(&pdev->dev, regs);
+        if (IS_ERR(mem))
+                return PTR_ERR(mem);
+
         if (np) {
                 const struct of_device_id *match;
 
@@ -2809,14 +2848,9 @@ static int macb_probe(struct platform_device *pdev)
         if (err)
                 return err;
 
-        regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-        mem = devm_ioremap_resource(&pdev->dev, regs);
-        if (IS_ERR(mem)) {
-                err = PTR_ERR(mem);
-                goto err_disable_clocks;
-        }
+        native_io = hw_is_native_io(mem);
 
-        macb_probe_queues(mem, &queue_mask, &num_queues);
+        macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
         dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
         if (!dev) {
                 err = -ENOMEM;
@@ -2831,6 +2865,14 @@ static int macb_probe(struct platform_device *pdev)
         bp->pdev = pdev;
         bp->dev = dev;
         bp->regs = mem;
+        bp->native_io = native_io;
+        if (native_io) {
+                bp->macb_reg_readl = hw_readl_native;
+                bp->macb_reg_writel = hw_writel_native;
+        } else {
+                bp->macb_reg_readl = hw_readl;
+                bp->macb_reg_writel = hw_writel;
+        }
         bp->num_queues = num_queues;
         bp->queue_mask = queue_mask;
         if (macb_config)
@@ -2838,9 +2880,8 @@ static int macb_probe(struct platform_device *pdev)
         bp->pclk = pclk;
         bp->hclk = hclk;
         bp->tx_clk = tx_clk;
-        if (macb_config->jumbo_max_len) {
+        if (macb_config)
                 bp->jumbo_max_len = macb_config->jumbo_max_len;
-        }
 
         spin_lock_init(&bp->lock);
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d74655993d4b..1895b6b2addd 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -429,18 +429,12 @@
          | GEM_BF(name, value))
 
 /* Register access macros */
-#define macb_readl(port,reg)                            \
-        readl_relaxed((port)->regs + MACB_##reg)
-#define macb_writel(port,reg,value)                     \
-        writel_relaxed((value), (port)->regs + MACB_##reg)
-#define gem_readl(port, reg)                            \
-        readl_relaxed((port)->regs + GEM_##reg)
-#define gem_writel(port, reg, value)                    \
-        writel_relaxed((value), (port)->regs + GEM_##reg)
-#define queue_readl(queue, reg)                         \
-        readl_relaxed((queue)->bp->regs + (queue)->reg)
-#define queue_writel(queue, reg, value)                 \
-        writel_relaxed((value), (queue)->bp->regs + (queue)->reg)
+#define macb_readl(port, reg)           (port)->macb_reg_readl((port), MACB_##reg)
+#define macb_writel(port, reg, value)   (port)->macb_reg_writel((port), MACB_##reg, (value))
+#define gem_readl(port, reg)            (port)->macb_reg_readl((port), GEM_##reg)
+#define gem_writel(port, reg, value)    (port)->macb_reg_writel((port), GEM_##reg, (value))
+#define queue_readl(queue, reg)         (queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg)
+#define queue_writel(queue, reg, value) (queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value))
 
 /* Conditional GEM/MACB macros.  These perform the operation to the correct
  * register dependent on whether the device is a GEM or a MACB.  For registers
@@ -785,6 +779,11 @@ struct macb_queue {
 
 struct macb {
         void __iomem            *regs;
+        bool                    native_io;
+
+        /* hardware IO accessors */
+        u32     (*macb_reg_readl)(struct macb *bp, int offset);
+        void    (*macb_reg_writel)(struct macb *bp, int offset, u32 value);
 
         unsigned int            rx_tail;
         unsigned int            rx_prepared_head;
@@ -817,9 +816,9 @@ struct macb {
 
         struct mii_bus          *mii_bus;
         struct phy_device       *phy_dev;
-        unsigned int            link;
-        unsigned int            speed;
-        unsigned int            duplex;
+        int                     link;
+        int                     speed;
+        int                     duplex;
 
         u32                     caps;
         unsigned int            dma_burst_length;
@@ -843,9 +842,4 @@ static inline bool macb_is_gem(struct macb *bp)
         return !!(bp->caps & MACB_CAPS_MACB_IS_GEM);
 }
 
-static inline bool macb_is_gem_hw(void __iomem *addr)
-{
-        return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2);
-}
-
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index c4d6bbe9458d..02e23e6f1424 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -16,7 +16,6 @@ if NET_VENDOR_CAVIUM
 config THUNDER_NIC_PF
         tristate "Thunder Physical function driver"
         depends on 64BIT
-        default ARCH_THUNDER
         select THUNDER_NIC_BGX
         ---help---
           This driver supports Thunder's NIC physical function.
@@ -29,14 +28,12 @@ config THUNDER_NIC_PF
 config THUNDER_NIC_VF
         tristate "Thunder Virtual function driver"
         depends on 64BIT
-        default ARCH_THUNDER
         ---help---
           This driver supports Thunder's NIC virtual function
 
 config  THUNDER_NIC_BGX
         tristate "Thunder MAC interface driver (BGX)"
         depends on 64BIT
-        default ARCH_THUNDER
         ---help---
           This driver supports programming and controlling of MAC
           interface from NIC physical function driver.
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index dda8a02b7322..8aee250904ec 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -125,6 +125,15 @@
  */
 #define NICPF_CLK_PER_INT_TICK          2
 
+/* Time to wait before we decide that a SQ is stuck.
+ *
+ * Since both pkt rx and tx notifications are done with same CQ,
+ * when packets are being received at very high rate (eg: L2 forwarding)
+ * then freeing transmitted skbs will be delayed and watchdog
+ * will kick in, resetting interface. Hence keeping this value high.
+ */
+#define NICVF_TX_TIMEOUT                (50 * HZ)
+
 struct nicvf_cq_poll {
         u8      cq_idx;         /* Completion queue index */
         struct  napi_struct napi;
@@ -216,8 +225,9 @@ struct nicvf_drv_stats {
         /* Tx */
         u64 tx_frames_ok;
         u64 tx_drops;
-        u64 tx_busy;
         u64 tx_tso;
+        u64 txq_stop;
+        u64 txq_wake;
 };
 
 struct nicvf {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 16bd2d772db9..a4228e664567 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -66,9 +66,10 @@ static const struct nicvf_stat nicvf_drv_stats[] = {
         NICVF_DRV_STAT(rx_frames_jumbo),
         NICVF_DRV_STAT(rx_drops),
         NICVF_DRV_STAT(tx_frames_ok),
-        NICVF_DRV_STAT(tx_busy),
         NICVF_DRV_STAT(tx_tso),
         NICVF_DRV_STAT(tx_drops),
+        NICVF_DRV_STAT(txq_stop),
+        NICVF_DRV_STAT(txq_wake),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -126,6 +127,7 @@ static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl)
 
 static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 {
+        struct nicvf *nic = netdev_priv(netdev);
         int stats, qidx;
 
         if (sset != ETH_SS_STATS)
@@ -141,7 +143,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
                 data += ETH_GSTRING_LEN;
         }
 
-        for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+        for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
                 for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
                         sprintf(data, "rxq%d: %s", qidx,
                                 nicvf_queue_stats[stats].name);
@@ -149,7 +151,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
                 }
         }
 
-        for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+        for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
                 for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
                         sprintf(data, "txq%d: %s", qidx,
                                 nicvf_queue_stats[stats].name);
@@ -170,12 +172,14 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 
 static int nicvf_get_sset_count(struct net_device *netdev, int sset)
 {
+        struct nicvf *nic = netdev_priv(netdev);
+
         if (sset != ETH_SS_STATS)
                 return -EINVAL;
 
         return nicvf_n_hw_stats + nicvf_n_drv_stats +
                 (nicvf_n_queue_stats *
-                 (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+                 (nic->qs->rq_cnt + nic->qs->sq_cnt)) +
                 BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
 }
 
@@ -197,13 +201,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
                 *(data++) = ((u64 *)&nic->drv_stats)
                                 [nicvf_drv_stats[stat].index];
 
-        for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+        for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
                 for (stat = 0; stat < nicvf_n_queue_stats; stat++)
                         *(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
                                         [nicvf_queue_stats[stat].index];
         }
 
-        for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+        for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
                 for (stat = 0; stat < nicvf_n_queue_stats; stat++)
                         *(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
                                         [nicvf_queue_stats[stat].index];
@@ -543,6 +547,7 @@ static int nicvf_set_channels(struct net_device *dev,
 {
         struct nicvf *nic = netdev_priv(dev);
         int err = 0;
+        bool if_up = netif_running(dev);
 
         if (!channel->rx_count || !channel->tx_count)
                 return -EINVAL;
@@ -551,6 +556,9 @@ static int nicvf_set_channels(struct net_device *dev,
         if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
                 return -EINVAL;
 
+        if (if_up)
+                nicvf_stop(dev);
+
         nic->qs->rq_cnt = channel->rx_count;
         nic->qs->sq_cnt = channel->tx_count;
         nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
@@ -559,11 +567,9 @@ static int nicvf_set_channels(struct net_device *dev,
         if (err)
                 return err;
 
-        if (!netif_running(dev))
-                return err;
+        if (if_up)
+                nicvf_open(dev);
 
-        nicvf_stop(dev);
-        nicvf_open(dev);
         netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
                     nic->qs->sq_cnt, nic->qs->rq_cnt);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 8b119a035b7e..3b90afb8c293 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -234,7 +234,7 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
                                     nic->duplex == DUPLEX_FULL ?
                                 "Full duplex" : "Half duplex");
                         netif_carrier_on(nic->netdev);
-                        netif_tx_wake_all_queues(nic->netdev);
+                        netif_tx_start_all_queues(nic->netdev);
                 } else {
                         netdev_info(nic->netdev, "%s: Link is Down\n",
                                     nic->netdev->name);
@@ -425,6 +425,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
         if (skb) {
                 prefetch(skb);
                 dev_consume_skb_any(skb);
+                sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
         }
 }
 
@@ -476,12 +477,13 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
                                  struct napi_struct *napi, int budget)
 {
-        int processed_cqe, work_done = 0;
+        int processed_cqe, work_done = 0, tx_done = 0;
         int cqe_count, cqe_head;
         struct nicvf *nic = netdev_priv(netdev);
         struct queue_set *qs = nic->qs;
         struct cmp_queue *cq = &qs->cq[cq_idx];
         struct cqe_rx_t *cq_desc;
+        struct netdev_queue *txq;
 
         spin_lock_bh(&cq->lock);
 loop:
@@ -496,8 +498,8 @@ loop:
         cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
         cqe_head &= 0xFFFF;
 
-        netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
-                   __func__, cqe_count, cqe_head);
+        netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
+                   __func__, cq_idx, cqe_count, cqe_head);
         while (processed_cqe < cqe_count) {
                 /* Get the CQ descriptor */
                 cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -511,8 +513,8 @@ loop:
                         break;
                 }
 
-                netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
-                           cq_desc->cqe_type);
+                netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
+                           cq_idx, cq_desc->cqe_type);
                 switch (cq_desc->cqe_type) {
                 case CQE_TYPE_RX:
                         nicvf_rcv_pkt_handler(netdev, napi, cq,
@@ -522,6 +524,7 @@ loop:
                 case CQE_TYPE_SEND:
                         nicvf_snd_pkt_handler(netdev, cq,
                                               (void *)cq_desc, CQE_TYPE_SEND);
+                        tx_done++;
                 break;
                 case CQE_TYPE_INVALID:
                 case CQE_TYPE_RX_SPLIT:
@@ -532,8 +535,9 @@ loop:
                 }
                 processed_cqe++;
         }
-        netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
-                   __func__, processed_cqe, work_done, budget);
+        netdev_dbg(nic->netdev,
+                   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
+                   __func__, cq_idx, processed_cqe, work_done, budget);
 
         /* Ring doorbell to inform H/W to reuse processed CQEs */
         nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -543,6 +547,19 @@ loop:
                 goto loop;
 
 done:
+        /* Wakeup TXQ if its stopped earlier due to SQ full */
+        if (tx_done) {
+                txq = netdev_get_tx_queue(netdev, cq_idx);
+                if (netif_tx_queue_stopped(txq)) {
+                        netif_tx_start_queue(txq);
+                        nic->drv_stats.txq_wake++;
+                        if (netif_msg_tx_err(nic))
+                                netdev_warn(netdev,
+                                            "%s: Transmit queue wakeup SQ%d\n",
+                                            netdev->name, cq_idx);
+                }
+        }
+
         spin_unlock_bh(&cq->lock);
         return work_done;
 }
@@ -554,15 +571,10 @@ static int nicvf_poll(struct napi_struct *napi, int budget)
         struct net_device *netdev = napi->dev;
         struct nicvf *nic = netdev_priv(netdev);
         struct nicvf_cq_poll *cq;
-        struct netdev_queue *txq;
 
         cq = container_of(napi, struct nicvf_cq_poll, napi);
         work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
 
-        txq = netdev_get_tx_queue(netdev, cq->cq_idx);
-        if (netif_tx_queue_stopped(txq))
-                netif_tx_wake_queue(txq);
-
         if (work_done < budget) {
                 /* Slow packet rate, exit polling */
                 napi_complete(napi);
@@ -833,9 +845,9 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
                 return NETDEV_TX_OK;
         }
 
-        if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+        if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
                 netif_tx_stop_queue(txq);
-                nic->drv_stats.tx_busy++;
+                nic->drv_stats.txq_stop++;
                 if (netif_msg_tx_err(nic))
                         netdev_warn(netdev,
                                     "%s: Transmit ring full, stopping SQ%d\n",
@@ -859,7 +871,6 @@ int nicvf_stop(struct net_device *netdev)
         nicvf_send_msg_to_pf(nic, &mbx);
 
         netif_carrier_off(netdev);
-        netif_tx_disable(netdev);
 
         /* Disable RBDR & QS error interrupts */
         for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
@@ -894,6 +905,8 @@ int nicvf_stop(struct net_device *netdev)
                 kfree(cq_poll);
         }
 
+        netif_tx_disable(netdev);
+
         /* Free resources */
         nicvf_config_data_transfer(nic, false);
 
@@ -988,6 +1001,9 @@ int nicvf_open(struct net_device *netdev)
         for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
                 nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
+        nic->drv_stats.txq_stop = 0;
+        nic->drv_stats.txq_wake = 0;
+
         netif_carrier_on(netdev);
         netif_tx_start_all_queues(netdev);
 
@@ -1278,6 +1294,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
         netdev->hw_features = netdev->features;
 
         netdev->netdev_ops = &nicvf_netdev_ops;
+        netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
         INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
@@ -1318,11 +1335,17 @@ static void nicvf_remove(struct pci_dev *pdev)
         pci_disable_device(pdev);
 }
 
+static void nicvf_shutdown(struct pci_dev *pdev)
+{
+        nicvf_remove(pdev);
+}
+
 static struct pci_driver nicvf_driver = {
         .name = DRV_NAME,
         .id_table = nicvf_id_table,
         .probe = nicvf_probe,
         .remove = nicvf_remove,
+        .shutdown = nicvf_shutdown,
 };
 
 static int __init nicvf_init_module(void)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d69d228d11a0..ca4240aa6d15 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -103,9 +103,11 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 
         /* Allocate a new page */
         if (!nic->rb_page) {
-                nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+                nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+                                           order);
                 if (!nic->rb_page) {
-                        netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+                        netdev_err(nic->netdev,
+                                   "Failed to allocate new rcv buffer\n");
                         return -ENOMEM;
                 }
                 nic->rb_page_offset = 0;
@@ -382,7 +384,8 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
                 return;
 
         if (sq->tso_hdrs)
-                dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+                dma_free_coherent(&nic->pdev->dev,
+                                  sq->dmem.q_len * TSO_HEADER_SIZE,
                                   sq->tso_hdrs, sq->tso_hdrs_phys);
 
         kfree(sq->skbuff);
@@ -863,10 +866,11 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq,
                         continue;
                 }
                 skb = (struct sk_buff *)sq->skbuff[sq->head];
+                if (skb)
+                        dev_kfree_skb_any(skb);
                 atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
                 atomic64_add(hdr->tot_len,
                              (atomic64_t *)&netdev->stats.tx_bytes);
-                dev_kfree_skb_any(skb);
                 nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
         }
 }
@@ -992,7 +996,7 @@ static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
 
         memset(gather, 0, SND_QUEUE_DESC_SIZE);
         gather->subdesc_type = SQ_DESC_TYPE_GATHER;
-        gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+        gather->ld_type = NIC_SEND_LD_TYPE_E_LDD;
         gather->size = size;
         gather->addr = data;
 }
@@ -1048,7 +1052,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
                 }
                 nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
                                          seg_subdescs - 1, skb, seg_len);
-                sq->skbuff[hdr_qentry] = 0;
+                sq->skbuff[hdr_qentry] = (u64)NULL;
                 qentry = nicvf_get_nxt_sqentry(sq, qentry);
 
                 desc_cnt += seg_subdescs;
@@ -1062,6 +1066,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
         /* Inform HW to xmit all TSO segments */
         nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
                               skb_get_queue_mapping(skb), desc_cnt);
+        nic->drv_stats.tx_tso++;
         return 1;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 8341bdf755d1..f0937b7bfe9f 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -62,7 +62,7 @@
 #define SND_QUEUE_CNT           8
 #define CMP_QUEUE_CNT           8 /* Max of RCV and SND qcount */
 
-#define SND_QSIZE               SND_QUEUE_SIZE4
+#define SND_QSIZE               SND_QUEUE_SIZE2
 #define SND_QUEUE_LEN           (1ULL << (SND_QSIZE + 10))
 #define MAX_SND_QUEUE_LEN       (1ULL << (SND_QUEUE_SIZE6 + 10))
 #define SND_QUEUE_THRESH        2ULL
@@ -70,7 +70,10 @@
 /* Since timestamp not enabled, otherwise 2 */
 #define MAX_CQE_PER_PKT_XMIT            1
 
-#define CMP_QSIZE               CMP_QUEUE_SIZE4
+/* Keep CQ and SQ sizes same, if timestamping
+ * is enabled this equation will change.
+ */
+#define CMP_QSIZE               CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN           (1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH    0
 #define CMP_QUEUE_TIMER_THRESH  220 /* 10usec */
@@ -87,7 +90,12 @@
 
 #define MAX_CQES_FOR_TX         ((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
                                  MAX_CQE_PER_PKT_XMIT)
-#define RQ_CQ_DROP              ((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+/* Calculate number of CQEs to reserve for all SQEs.
+ * Its 1/256th level of CQ size.
+ * '+ 1' to account for pipelining
+ */
+#define RQ_CQ_DROP              ((256 / (CMP_QUEUE_LEN / \
+                                 (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1)
 
 /* Descriptor size in bytes */
 #define SND_QUEUE_DESC_SIZE     16
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 633ec05dfe05..b961a89dc626 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -673,7 +673,10 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
         bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
         bgx_flush_dmac_addrs(bgx, lmacid);
 
-        if (lmac->phydev)
+        if ((bgx->lmac_type != BGX_MODE_XFI) &&
+            (bgx->lmac_type != BGX_MODE_XLAUI) &&
+            (bgx->lmac_type != BGX_MODE_40G_KR) &&
+            (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev)
                 phy_disconnect(lmac->phydev);
 
         lmac->phydev = NULL;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index a11485fbb33f..c3c7db41819d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2332,10 +2332,11 @@ int t4_setup_debugfs(struct adapter *adap)
                                         EXT_MEM1_SIZE_G(size));
                 }
         } else {
-                if (i & EXT_MEM_ENABLE_F)
+                if (i & EXT_MEM_ENABLE_F) {
                         size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A);
                         add_debugfs_mem(adap, "mc", MEM_MC,
                                         EXT_MEM_SIZE_G(size));
+                }
         }
 
         de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap,
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 2716e6f30d9a..00e3a6b6b822 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -620,6 +620,11 @@ enum be_if_flags {
                                          BE_IF_FLAGS_VLAN_PROMISCUOUS |\
                                          BE_IF_FLAGS_MCAST_PROMISCUOUS)
 
+#define BE_IF_EN_FLAGS  (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\
+                        BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED)
+
+#define BE_IF_ALL_FILT_FLAGS    (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS)
+
 /* An RX interface is an object with one or more MAC addresses and
  * filtering capabilities. */
 struct be_cmd_req_if_create {
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 6f642426308c..c28e3bfdccd7 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -273,6 +273,10 @@ static int be_mac_addr_set(struct net_device *netdev, void *p)
         if (ether_addr_equal(addr->sa_data, netdev->dev_addr))
                 return 0;
 
+        /* if device is not running, copy MAC to netdev->dev_addr */
+        if (!netif_running(netdev))
+                goto done;
+
         /* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT
          * privilege or if PF did not provision the new MAC address.
          * On BE3, this cmd will always fail if the VF doesn't have the
@@ -307,9 +311,9 @@ static int be_mac_addr_set(struct net_device *netdev, void *p)
                 status = -EPERM;
                 goto err;
         }
-
-        memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
-        dev_info(dev, "MAC address changed to %pM\n", mac);
+done:
+        ether_addr_copy(netdev->dev_addr, addr->sa_data);
+        dev_info(dev, "MAC address changed to %pM\n", addr->sa_data);
         return 0;
 err:
         dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data);
@@ -2447,10 +2451,24 @@ static void be_eq_clean(struct be_eq_obj *eqo)
         be_eq_notify(eqo->adapter, eqo->q.id, false, true, num, 0);
 }
 
-static void be_rx_cq_clean(struct be_rx_obj *rxo)
+/* Free posted rx buffers that were not used */
+static void be_rxq_clean(struct be_rx_obj *rxo)
 {
-        struct be_rx_page_info *page_info;
         struct be_queue_info *rxq = &rxo->q;
+        struct be_rx_page_info *page_info;
+
+        while (atomic_read(&rxq->used) > 0) {
+                page_info = get_rx_page_info(rxo);
+                put_page(page_info->page);
+                memset(page_info, 0, sizeof(*page_info));
+        }
+        BUG_ON(atomic_read(&rxq->used));
+        rxq->tail = 0;
+        rxq->head = 0;
+}
+
+static void be_rx_cq_clean(struct be_rx_obj *rxo)
+{
         struct be_queue_info *rx_cq = &rxo->cq;
         struct be_rx_compl_info *rxcp;
         struct be_adapter *adapter = rxo->adapter;
@@ -2487,16 +2505,6 @@ static void be_rx_cq_clean(struct be_rx_obj *rxo)
 
         /* After cleanup, leave the CQ in unarmed state */
         be_cq_notify(adapter, rx_cq->id, false, 0);
-
-        /* Then free posted rx buffers that were not used */
-        while (atomic_read(&rxq->used) > 0) {
-                page_info = get_rx_page_info(rxo);
-                put_page(page_info->page);
-                memset(page_info, 0, sizeof(*page_info));
-        }
-        BUG_ON(atomic_read(&rxq->used));
-        rxq->tail = 0;
-        rxq->head = 0;
 }
 
 static void be_tx_compl_clean(struct be_adapter *adapter)
@@ -2576,8 +2584,8 @@ static void be_evt_queues_destroy(struct be_adapter *adapter)
                         be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ);
                         napi_hash_del(&eqo->napi);
                         netif_napi_del(&eqo->napi);
+                        free_cpumask_var(eqo->affinity_mask);
                 }
-                free_cpumask_var(eqo->affinity_mask);
                 be_queue_free(adapter, &eqo->q);
         }
 }
@@ -2594,13 +2602,7 @@ static int be_evt_queues_create(struct be_adapter *adapter)
 
         for_all_evt_queues(adapter, eqo, i) {
                 int numa_node = dev_to_node(&adapter->pdev->dev);
-                if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
-                        return -ENOMEM;
-                cpumask_set_cpu(cpumask_local_spread(i, numa_node),
-                                eqo->affinity_mask);
-                netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
-                               BE_NAPI_WEIGHT);
-                napi_hash_add(&eqo->napi);
+
                 aic = &adapter->aic_obj[i];
                 eqo->adapter = adapter;
                 eqo->idx = i;
@@ -2616,6 +2618,14 @@ static int be_evt_queues_create(struct be_adapter *adapter)
                 rc = be_cmd_eq_create(adapter, eqo);
                 if (rc)
                         return rc;
+
+                if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
+                        return -ENOMEM;
+                cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+                                eqo->affinity_mask);
+                netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
+                               BE_NAPI_WEIGHT);
+                napi_hash_add(&eqo->napi);
         }
         return 0;
 }
@@ -3354,13 +3364,54 @@ static void be_rx_qs_destroy(struct be_adapter *adapter)
         for_all_rx_queues(adapter, rxo, i) {
                 q = &rxo->q;
                 if (q->created) {
+                        /* If RXQs are destroyed while in an "out of buffer"
+                         * state, there is a possibility of an HW stall on
+                         * Lancer. So, post 64 buffers to each queue to relieve
+                         * the "out of buffer" condition.
+                         * Make sure there's space in the RXQ before posting.
+                         */
+                        if (lancer_chip(adapter)) {
+                                be_rx_cq_clean(rxo);
+                                if (atomic_read(&q->used) == 0)
+                                        be_post_rx_frags(rxo, GFP_KERNEL,
+                                                         MAX_RX_POST);
+                        }
+
                         be_cmd_rxq_destroy(adapter, q);
                         be_rx_cq_clean(rxo);
+                        be_rxq_clean(rxo);
                 }
                 be_queue_free(adapter, q);
         }
 }
 
+static void be_disable_if_filters(struct be_adapter *adapter)
+{
+        be_cmd_pmac_del(adapter, adapter->if_handle,
+                        adapter->pmac_id[0], 0);
+
+        be_clear_uc_list(adapter);
+
+        /* The IFACE flags are enabled in the open path and cleared
+         * in the close path. When a VF gets detached from the host and
+         * assigned to a VM the following happens:
+         *      - VF's IFACE flags get cleared in the detach path
+         *      - IFACE create is issued by the VF in the attach path
+         * Due to a bug in the BE3/Skyhawk-R FW
+         * (Lancer FW doesn't have the bug), the IFACE capability flags
+         * specified along with the IFACE create cmd issued by a VF are not
+         * honoured by FW.  As a consequence, if a *new* driver
+         * (that enables/disables IFACE flags in open/close)
+         * is loaded in the host and an *old* driver is * used by a VM/VF,
+         * the IFACE gets created *without* the needed flags.
+         * To avoid this, disable RX-filter flags only for Lancer.
+         */
+        if (lancer_chip(adapter)) {
+                be_cmd_rx_filter(adapter, BE_IF_ALL_FILT_FLAGS, OFF);
+                adapter->if_flags &= ~BE_IF_ALL_FILT_FLAGS;
+        }
+}
+
 static int be_close(struct net_device *netdev)
 {
         struct be_adapter *adapter = netdev_priv(netdev);
@@ -3373,6 +3424,8 @@ static int be_close(struct net_device *netdev)
         if (!(adapter->flags & BE_FLAGS_SETUP_DONE))
                 return 0;
 
+        be_disable_if_filters(adapter);
+
         be_roce_dev_close(adapter);
 
         if (adapter->flags & BE_FLAGS_NAPI_ENABLED) {
@@ -3392,7 +3445,6 @@ static int be_close(struct net_device *netdev)
         be_tx_compl_clean(adapter);
 
         be_rx_qs_destroy(adapter);
-        be_clear_uc_list(adapter);
 
         for_all_evt_queues(adapter, eqo, i) {
                 if (msix_enabled(adapter))
@@ -3477,6 +3529,31 @@ static int be_rx_qs_create(struct be_adapter *adapter)
         return 0;
 }
 
+static int be_enable_if_filters(struct be_adapter *adapter)
+{
+        int status;
+
+        status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON);
+        if (status)
+                return status;
+
+        /* For BE3 VFs, the PF programs the initial MAC address */
+        if (!(BEx_chip(adapter) && be_virtfn(adapter))) {
+                status = be_cmd_pmac_add(adapter, adapter->netdev->dev_addr,
+                                         adapter->if_handle,
+                                         &adapter->pmac_id[0], 0);
+                if (status)
+                        return status;
+        }
+
+        if (adapter->vlans_added)
+                be_vid_config(adapter);
+
+        be_set_rx_mode(adapter->netdev);
+
+        return 0;
+}
+
 static int be_open(struct net_device *netdev)
 {
         struct be_adapter *adapter = netdev_priv(netdev);
@@ -3490,6 +3567,10 @@ static int be_open(struct net_device *netdev)
         if (status)
                 goto err;
 
+        status = be_enable_if_filters(adapter);
+        if (status)
+                goto err;
+
         status = be_irq_register(adapter);
         if (status)
                 goto err;
@@ -3686,16 +3767,6 @@ static void be_cancel_err_detection(struct be_adapter *adapter)
         }
 }
 
-static void be_mac_clear(struct be_adapter *adapter)
-{
-        if (adapter->pmac_id) {
-                be_cmd_pmac_del(adapter, adapter->if_handle,
-                                adapter->pmac_id[0], 0);
-                kfree(adapter->pmac_id);
-                adapter->pmac_id = NULL;
-        }
-}
-
 #ifdef CONFIG_BE2NET_VXLAN
 static void be_disable_vxlan_offloads(struct be_adapter *adapter)
 {
@@ -3770,8 +3841,8 @@ static int be_clear(struct be_adapter *adapter)
 #ifdef CONFIG_BE2NET_VXLAN
         be_disable_vxlan_offloads(adapter);
 #endif
-        /* delete the primary mac along with the uc-mac list */
-        be_mac_clear(adapter);
+        kfree(adapter->pmac_id);
+        adapter->pmac_id = NULL;
 
         be_cmd_if_destroy(adapter, adapter->if_handle,  0);
 
@@ -3782,25 +3853,11 @@ static int be_clear(struct be_adapter *adapter)
         return 0;
 }
 
-static int be_if_create(struct be_adapter *adapter, u32 *if_handle,
-                        u32 cap_flags, u32 vf)
-{
-        u32 en_flags;
-
-        en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-                   BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |
-                   BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS;
-
-        en_flags &= cap_flags;
-
-        return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf);
-}
-
 static int be_vfs_if_create(struct be_adapter *adapter)
 {
         struct be_resources res = {0};
+        u32 cap_flags, en_flags, vf;
         struct be_vf_cfg *vf_cfg;
-        u32 cap_flags, vf;
         int status;
 
         /* If a FW profile exists, then cap_flags are updated */
@@ -3821,8 +3878,12 @@ static int be_vfs_if_create(struct be_adapter *adapter)
                         }
                 }
 
-                status = be_if_create(adapter, &vf_cfg->if_handle,
-                                      cap_flags, vf + 1);
+                en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
+                                        BE_IF_FLAGS_BROADCAST |
+                                        BE_IF_FLAGS_MULTICAST |
+                                        BE_IF_FLAGS_PASS_L3L4_ERRORS);
+                status = be_cmd_if_create(adapter, cap_flags, en_flags,
+                                          &vf_cfg->if_handle, vf + 1);
                 if (status)
                         return status;
         }
@@ -4194,15 +4255,8 @@ static int be_mac_setup(struct be_adapter *adapter)
 
                 memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
                 memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
-        } else {
-                /* Maybe the HW was reset; dev_addr must be re-programmed */
-                memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN);
         }
 
-        /* For BE3-R VFs, the PF programs the initial MAC address */
-        if (!(BEx_chip(adapter) && be_virtfn(adapter)))
-                be_cmd_pmac_add(adapter, mac, adapter->if_handle,
-                                &adapter->pmac_id[0], 0);
         return 0;
 }
 
@@ -4342,6 +4396,7 @@ static int be_func_init(struct be_adapter *adapter)
 static int be_setup(struct be_adapter *adapter)
 {
         struct device *dev = &adapter->pdev->dev;
+        u32 en_flags;
         int status;
 
         status = be_func_init(adapter);
@@ -4364,8 +4419,11 @@ static int be_setup(struct be_adapter *adapter)
         if (status)
                 goto err;
 
-        status = be_if_create(adapter, &adapter->if_handle,
-                              be_if_cap_flags(adapter), 0);
+        /* will enable all the needed filter flags in be_open() */
+        en_flags = BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS;
+        en_flags = en_flags & be_if_cap_flags(adapter);
+        status = be_cmd_if_create(adapter, be_if_cap_flags(adapter), en_flags,
+                                  &adapter->if_handle, 0);
         if (status)
                 goto err;
 
@@ -4391,11 +4449,6 @@ static int be_setup(struct be_adapter *adapter)
                 dev_err(dev, "Please upgrade firmware to version >= 4.0\n");
         }
 
-        if (adapter->vlans_added)
-                be_vid_config(adapter);
-
-        be_set_rx_mode(adapter->netdev);
-
         status = be_cmd_set_flow_control(adapter, adapter->tx_fc,
                                          adapter->rx_fc);
         if (status)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 1eee73cccdf5..99d33e2d35e6 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -562,6 +562,7 @@ struct fec_enet_private {
 };
 
 void fec_ptp_init(struct platform_device *pdev);
+void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 42e20e5385ac..271bb5862346 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3142,8 +3142,8 @@ static int fec_enet_init(struct net_device *ndev)
                         fep->bufdesc_size;
 
         /* Allocate memory for buffer descriptors. */
-        cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
-                                      GFP_KERNEL);
+        cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
+                                       GFP_KERNEL);
         if (!cbd_base) {
                 return -ENOMEM;
         }
@@ -3431,6 +3431,12 @@ fec_probe(struct platform_device *pdev)
                 fep->reg_phy = NULL;
         }
 
+        pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
+        pm_runtime_use_autosuspend(&pdev->dev);
+        pm_runtime_get_noresume(&pdev->dev);
+        pm_runtime_set_active(&pdev->dev);
+        pm_runtime_enable(&pdev->dev);
+
         fec_reset_phy(pdev);
 
         if (fep->bufdesc_ex)
@@ -3465,8 +3471,6 @@ fec_probe(struct platform_device *pdev)
         netif_carrier_off(ndev);
         fec_enet_clk_enable(ndev, false);
         pinctrl_pm_select_sleep_state(&pdev->dev);
-        pm_runtime_set_active(&pdev->dev);
-        pm_runtime_enable(&pdev->dev);
 
         ret = register_netdev(ndev);
         if (ret)
@@ -3481,8 +3485,6 @@ fec_probe(struct platform_device *pdev)
         fep->rx_copybreak = COPYBREAK_DEFAULT;
         INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
 
-        pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
-        pm_runtime_use_autosuspend(&pdev->dev);
         pm_runtime_mark_last_busy(&pdev->dev);
         pm_runtime_put_autosuspend(&pdev->dev);
 
@@ -3493,6 +3495,7 @@ failed_register:
 failed_mii_init:
 failed_irq:
 failed_init:
+        fec_ptp_stop(pdev);
         if (fep->reg_phy)
                 regulator_disable(fep->reg_phy);
 failed_regulator:
@@ -3514,14 +3517,12 @@ fec_drv_remove(struct platform_device *pdev)
         struct net_device *ndev = platform_get_drvdata(pdev);
         struct fec_enet_private *fep = netdev_priv(ndev);
 
-        cancel_delayed_work_sync(&fep->time_keep);
         cancel_work_sync(&fep->tx_timeout_work);
+        fec_ptp_stop(pdev);
         unregister_netdev(ndev);
         fec_enet_mii_remove(fep);
         if (fep->reg_phy)
                 regulator_disable(fep->reg_phy);
-        if (fep->ptp_clock)
-                ptp_clock_unregister(fep->ptp_clock);
         of_node_put(fep->phy_node);
         free_netdev(ndev);
 
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index a15663ad7f5e..f457a23d0bfb 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -604,6 +604,16 @@ void fec_ptp_init(struct platform_device *pdev)
         schedule_delayed_work(&fep->time_keep, HZ);
 }
 
+void fec_ptp_stop(struct platform_device *pdev)
+{
+        struct net_device *ndev = platform_get_drvdata(pdev);
+        struct fec_enet_private *fep = netdev_priv(ndev);
+
+        cancel_delayed_work_sync(&fep->time_keep);
+        if (fep->ptp_clock)
+                ptp_clock_unregister(fep->ptp_clock);
+}
+
 /**
  * fec_ptp_check_pps_event
  * @fep: the fec_enet_private structure handle
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 56316db6c5a6..cf8e54652df9 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -586,7 +586,8 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
         frag = skb_shinfo(skb)->frags;
         while (nr_frags) {
                 CBDC_SC(bdp,
-                        BD_ENET_TX_STATS | BD_ENET_TX_LAST | BD_ENET_TX_TC);
+                        BD_ENET_TX_STATS | BD_ENET_TX_INTR | BD_ENET_TX_LAST |
+                        BD_ENET_TX_TC);
                 CBDS_SC(bdp, BD_ENET_TX_READY);
 
                 if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0)
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index b34214e2df5f..016743e355de 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -110,7 +110,7 @@ static int do_pd_setup(struct fs_enet_private *fep)
 }
 
 #define FEC_NAPI_RX_EVENT_MSK   (FEC_ENET_RXF | FEC_ENET_RXB)
-#define FEC_NAPI_TX_EVENT_MSK   (FEC_ENET_TXF | FEC_ENET_TXB)
+#define FEC_NAPI_TX_EVENT_MSK   (FEC_ENET_TXF)
 #define FEC_RX_EVENT            (FEC_ENET_RXF)
 #define FEC_TX_EVENT            (FEC_ENET_TXF)
 #define FEC_ERR_EVENT_MSK       (FEC_ENET_HBERR | FEC_ENET_BABR | \
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ff875028fdff..2b7610f341b0 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -565,22 +565,6 @@ static void gfar_ints_enable(struct gfar_private *priv)
         }
 }
 
-static void lock_tx_qs(struct gfar_private *priv)
-{
-        int i;
-
-        for (i = 0; i < priv->num_tx_queues; i++)
-                spin_lock(&priv->tx_queue[i]->txlock);
-}
-
-static void unlock_tx_qs(struct gfar_private *priv)
-{
-        int i;
-
-        for (i = 0; i < priv->num_tx_queues; i++)
-                spin_unlock(&priv->tx_queue[i]->txlock);
-}
-
 static int gfar_alloc_tx_queues(struct gfar_private *priv)
 {
         int i;
@@ -1376,7 +1360,6 @@ static int gfar_probe(struct platform_device *ofdev)
         priv->dev = &ofdev->dev;
         SET_NETDEV_DEV(dev, &ofdev->dev);
 
-        spin_lock_init(&priv->bflock);
         INIT_WORK(&priv->reset_task, gfar_reset_task);
 
         platform_set_drvdata(ofdev, priv);
@@ -1470,9 +1453,8 @@ static int gfar_probe(struct platform_device *ofdev)
                 goto register_fail;
         }
 
-        device_init_wakeup(&dev->dev,
-                           priv->device_flags &
-                           FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+        device_set_wakeup_capable(&dev->dev, priv->device_flags &
+                                  FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
         /* fill out IRQ number and name fields */
         for (i = 0; i < priv->num_grps; i++) {
@@ -1540,48 +1522,37 @@ static int gfar_suspend(struct device *dev)
         struct gfar_private *priv = dev_get_drvdata(dev);
         struct net_device *ndev = priv->ndev;
         struct gfar __iomem *regs = priv->gfargrp[0].regs;
-        unsigned long flags;
         u32 tempval;
-
         int magic_packet = priv->wol_en &&
                            (priv->device_flags &
                             FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
+        if (!netif_running(ndev))
+                return 0;
+
+        disable_napi(priv);
+        netif_tx_lock(ndev);
         netif_device_detach(ndev);
+        netif_tx_unlock(ndev);
 
-        if (netif_running(ndev)) {
+        gfar_halt(priv);
 
-                local_irq_save(flags);
-                lock_tx_qs(priv);
+        if (magic_packet) {
+                /* Enable interrupt on Magic Packet */
+                gfar_write(&regs->imask, IMASK_MAG);
 
-                gfar_halt_nodisable(priv);
+                /* Enable Magic Packet mode */
+                tempval = gfar_read(&regs->maccfg2);
+                tempval |= MACCFG2_MPEN;
+                gfar_write(&regs->maccfg2, tempval);
 
-                /* Disable Tx, and Rx if wake-on-LAN is disabled. */
+                /* re-enable the Rx block */
                 tempval = gfar_read(&regs->maccfg1);
-
-                tempval &= ~MACCFG1_TX_EN;
-
-                if (!magic_packet)
-                        tempval &= ~MACCFG1_RX_EN;
-
+                tempval |= MACCFG1_RX_EN;
                 gfar_write(&regs->maccfg1, tempval);
 
-                unlock_tx_qs(priv);
-                local_irq_restore(flags);
-
-                disable_napi(priv);
-
-                if (magic_packet) {
-                        /* Enable interrupt on Magic Packet */
-                        gfar_write(&regs->imask, IMASK_MAG);
-
-                        /* Enable Magic Packet mode */
-                        tempval = gfar_read(&regs->maccfg2);
-                        tempval |= MACCFG2_MPEN;
-                        gfar_write(&regs->maccfg2, tempval);
-                } else {
-                        phy_stop(priv->phydev);
-                }
+        } else {
+                phy_stop(priv->phydev);
         }
 
         return 0;
@@ -1592,37 +1563,26 @@ static int gfar_resume(struct device *dev)
         struct gfar_private *priv = dev_get_drvdata(dev);
         struct net_device *ndev = priv->ndev;
         struct gfar __iomem *regs = priv->gfargrp[0].regs;
-        unsigned long flags;
         u32 tempval;
         int magic_packet = priv->wol_en &&
                            (priv->device_flags &
                             FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
-        if (!netif_running(ndev)) {
-                netif_device_attach(ndev);
+        if (!netif_running(ndev))
                 return 0;
-        }
 
-        if (!magic_packet && priv->phydev)
+        if (magic_packet) {
+                /* Disable Magic Packet mode */
+                tempval = gfar_read(&regs->maccfg2);
+                tempval &= ~MACCFG2_MPEN;
+                gfar_write(&regs->maccfg2, tempval);
+        } else {
                 phy_start(priv->phydev);
-
-        /* Disable Magic Packet mode, in case something
-         * else woke us up.
-         */
-        local_irq_save(flags);
-        lock_tx_qs(priv);
-
-        tempval = gfar_read(&regs->maccfg2);
-        tempval &= ~MACCFG2_MPEN;
-        gfar_write(&regs->maccfg2, tempval);
+        }
 
         gfar_start(priv);
 
-        unlock_tx_qs(priv);
-        local_irq_restore(flags);
-
         netif_device_attach(ndev);
-
         enable_napi(priv);
 
         return 0;
@@ -2045,7 +2005,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
                 /* Install our interrupt handlers for Error,
                  * Transmit, and Receive
                  */
-                err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
+                err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
+                                  IRQF_NO_SUSPEND,
                                   gfar_irq(grp, ER)->name, grp);
                 if (err < 0) {
                         netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2068,7 +2029,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
                         goto rx_irq_fail;
                 }
         } else {
-                err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
+                err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
+                                  IRQF_NO_SUSPEND,
                                   gfar_irq(grp, TX)->name, grp);
                 if (err < 0) {
                         netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2169,8 +2131,6 @@ static int gfar_enet_open(struct net_device *dev)
         if (err)
                 return err;
 
-        device_set_wakeup_enable(&dev->dev, priv->wol_en);
-
         return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index daa1d37de642..5545e4103368 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -1145,9 +1145,6 @@ struct gfar_private {
         int oldduplex;
         int oldlink;
 
-        /* Bitfield update lock */
-        spinlock_t bflock;
-
         uint32_t msg_enable;
 
         struct work_struct reset_task;
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index fda12fb32ec7..5b90fcf96265 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -653,7 +653,6 @@ static void gfar_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
         struct gfar_private *priv = netdev_priv(dev);
-        unsigned long flags;
 
         if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) &&
             wol->wolopts != 0)
@@ -664,9 +663,7 @@ static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
         device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC);
 
-        spin_lock_irqsave(&priv->bflock, flags);
-        priv->wol_en =  !!device_may_wakeup(&dev->dev);
-        spin_unlock_irqrestore(&priv->bflock, flags);
+        priv->wol_en = !!device_may_wakeup(&dev->dev);
 
         return 0;
 }
@@ -903,27 +900,6 @@ static int gfar_check_filer_hardware(struct gfar_private *priv)
         return 0;
 }
 
-static int gfar_comp_asc(const void *a, const void *b)
-{
-        return memcmp(a, b, 4);
-}
-
-static int gfar_comp_desc(const void *a, const void *b)
-{
-        return -memcmp(a, b, 4);
-}
-
-static void gfar_swap(void *a, void *b, int size)
-{
-        u32 *_a = a;
-        u32 *_b = b;
-
-        swap(_a[0], _b[0]);
-        swap(_a[1], _b[1]);
-        swap(_a[2], _b[2]);
-        swap(_a[3], _b[3]);
-}
-
 /* Write a mask to filer cache */
 static void gfar_set_mask(u32 mask, struct filer_table *tab)
 {
@@ -1273,310 +1249,6 @@ static int gfar_convert_to_filer(struct ethtool_rx_flow_spec *rule,
         return 0;
 }
 
-/* Copy size filer entries */
-static void gfar_copy_filer_entries(struct gfar_filer_entry dst[0],
-                                    struct gfar_filer_entry src[0], s32 size)
-{
-        while (size > 0) {
-                size--;
-                dst[size].ctrl = src[size].ctrl;
-                dst[size].prop = src[size].prop;
-        }
-}
-
-/* Delete the contents of the filer-table between start and end
- * and collapse them
- */
-static int gfar_trim_filer_entries(u32 begin, u32 end, struct filer_table *tab)
-{
-        int length;
-
-        if (end > MAX_FILER_CACHE_IDX || end < begin)
-                return -EINVAL;
-
-        end++;
-        length = end - begin;
-
-        /* Copy */
-        while (end < tab->index) {
-                tab->fe[begin].ctrl = tab->fe[end].ctrl;
-                tab->fe[begin++].prop = tab->fe[end++].prop;
-
-        }
-        /* Fill up with don't cares */
-        while (begin < tab->index) {
-                tab->fe[begin].ctrl = 0x60;
-                tab->fe[begin].prop = 0xFFFFFFFF;
-                begin++;
-        }
-
-        tab->index -= length;
-        return 0;
-}
-
-/* Make space on the wanted location */
-static int gfar_expand_filer_entries(u32 begin, u32 length,
-                                     struct filer_table *tab)
-{
-        if (length == 0 || length + tab->index > MAX_FILER_CACHE_IDX ||
-            begin > MAX_FILER_CACHE_IDX)
-                return -EINVAL;
-
-        gfar_copy_filer_entries(&(tab->fe[begin + length]), &(tab->fe[begin]),
-                                tab->index - length + 1);
-
-        tab->index += length;
-        return 0;
-}
-
-static int gfar_get_next_cluster_start(int start, struct filer_table *tab)
-{
-        for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1);
-             start++) {
-                if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) ==
-                    (RQFCR_AND | RQFCR_CLE))
-                        return start;
-        }
-        return -1;
-}
-
-static int gfar_get_next_cluster_end(int start, struct filer_table *tab)
-{
-        for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1);
-             start++) {
-                if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) ==
-                    (RQFCR_CLE))
-                        return start;
-        }
-        return -1;
-}
-
-/* Uses hardwares clustering option to reduce
- * the number of filer table entries
- */
-static void gfar_cluster_filer(struct filer_table *tab)
-{
-        s32 i = -1, j, iend, jend;
-
-        while ((i = gfar_get_next_cluster_start(++i, tab)) != -1) {
-                j = i;
-                while ((j = gfar_get_next_cluster_start(++j, tab)) != -1) {
-                        /* The cluster entries self and the previous one
-                         * (a mask) must be identical!
-                         */
-                        if (tab->fe[i].ctrl != tab->fe[j].ctrl)
-                                break;
-                        if (tab->fe[i].prop != tab->fe[j].prop)
-                                break;
-                        if (tab->fe[i - 1].ctrl != tab->fe[j - 1].ctrl)
-                                break;
-                        if (tab->fe[i - 1].prop != tab->fe[j - 1].prop)
-                                break;
-                        iend = gfar_get_next_cluster_end(i, tab);
-                        jend = gfar_get_next_cluster_end(j, tab);
-                        if (jend == -1 || iend == -1)
-                                break;
-
-                        /* First we make some free space, where our cluster
-                         * element should be. Then we copy it there and finally
-                         * delete in from its old location.
-                         */
-                        if (gfar_expand_filer_entries(iend, (jend - j), tab) ==
-                            -EINVAL)
-                                break;
-
-                        gfar_copy_filer_entries(&(tab->fe[iend + 1]),
-                                                &(tab->fe[jend + 1]), jend - j);
-
-                        if (gfar_trim_filer_entries(jend - 1,
-                                                    jend + (jend - j),
-                                                    tab) == -EINVAL)
-                                return;
-
-                        /* Mask out cluster bit */
-                        tab->fe[iend].ctrl &= ~(RQFCR_CLE);
-                }
-        }
-}
-
-/* Swaps the masked bits of a1<>a2 and b1<>b2 */
-static void gfar_swap_bits(struct gfar_filer_entry *a1,
-                           struct gfar_filer_entry *a2,
-                           struct gfar_filer_entry *b1,
-                           struct gfar_filer_entry *b2, u32 mask)
-{
-        u32 temp[4];
-        temp[0] = a1->ctrl & mask;
-        temp[1] = a2->ctrl & mask;
-        temp[2] = b1->ctrl & mask;
-        temp[3] = b2->ctrl & mask;
-
-        a1->ctrl &= ~mask;
-        a2->ctrl &= ~mask;
-        b1->ctrl &= ~mask;
-        b2->ctrl &= ~mask;
-
-        a1->ctrl |= temp[1];
-        a2->ctrl |= temp[0];
-        b1->ctrl |= temp[3];
-        b2->ctrl |= temp[2];
-}
-
-/* Generate a list consisting of masks values with their start and
- * end of validity and block as indicator for parts belonging
- * together (glued by ANDs) in mask_table
- */
-static u32 gfar_generate_mask_table(struct gfar_mask_entry *mask_table,
-                                    struct filer_table *tab)
-{
-        u32 i, and_index = 0, block_index = 1;
-
-        for (i = 0; i < tab->index; i++) {
-
-                /* LSByte of control = 0 sets a mask */
-                if (!(tab->fe[i].ctrl & 0xF)) {
-                        mask_table[and_index].mask = tab->fe[i].prop;
-                        mask_table[and_index].start = i;
-                        mask_table[and_index].block = block_index;
-                        if (and_index >= 1)
-                                mask_table[and_index - 1].end = i - 1;
-                        and_index++;
-                }
-                /* cluster starts and ends will be separated because they should
-                 * hold their position
-                 */
-                if (tab->fe[i].ctrl & RQFCR_CLE)
-                        block_index++;
-                /* A not set AND indicates the end of a depended block */
-                if (!(tab->fe[i].ctrl & RQFCR_AND))
-                        block_index++;
-        }
-
-        mask_table[and_index - 1].end = i - 1;
-
-        return and_index;
-}
-
-/* Sorts the entries of mask_table by the values of the masks.
- * Important: The 0xFF80 flags of the first and last entry of a
- * block must hold their position (which queue, CLusterEnable, ReJEct,
- * AND)
- */
-static void gfar_sort_mask_table(struct gfar_mask_entry *mask_table,
-                                 struct filer_table *temp_table, u32 and_index)
-{
-        /* Pointer to compare function (_asc or _desc) */
-        int (*gfar_comp)(const void *, const void *);
-
-        u32 i, size = 0, start = 0, prev = 1;
-        u32 old_first, old_last, new_first, new_last;
-
-        gfar_comp = &gfar_comp_desc;
-
-        for (i = 0; i < and_index; i++) {
-                if (prev != mask_table[i].block) {
-                        old_first = mask_table[start].start + 1;
-                        old_last = mask_table[i - 1].end;
-                        sort(mask_table + start, size,
-                             sizeof(struct gfar_mask_entry),
-                             gfar_comp, &gfar_swap);
-
-                        /* Toggle order for every block. This makes the
-                         * thing more efficient!
-                         */
-                        if (gfar_comp == gfar_comp_desc)
-                                gfar_comp = &gfar_comp_asc;
-                        else
-                                gfar_comp = &gfar_comp_desc;
-
-                        new_first = mask_table[start].start + 1;
-                        new_last = mask_table[i - 1].end;
-
-                        gfar_swap_bits(&temp_table->fe[new_first],
-                                       &temp_table->fe[old_first],
-                                       &temp_table->fe[new_last],
-                                       &temp_table->fe[old_last],
-                                       RQFCR_QUEUE | RQFCR_CLE |
-                                       RQFCR_RJE | RQFCR_AND);
-
-                        start = i;
-                        size = 0;
-                }
-                size++;
-                prev = mask_table[i].block;
-        }
-}
-
-/* Reduces the number of masks needed in the filer table to save entries
- * This is done by sorting the masks of a depended block. A depended block is
- * identified by gluing ANDs or CLE. The sorting order toggles after every
- * block. Of course entries in scope of a mask must change their location with
- * it.
- */
-static int gfar_optimize_filer_masks(struct filer_table *tab)
-{
-        struct filer_table *temp_table;
-        struct gfar_mask_entry *mask_table;
-
-        u32 and_index = 0, previous_mask = 0, i = 0, j = 0, size = 0;
-        s32 ret = 0;
-
-        /* We need a copy of the filer table because
-         * we want to change its order
-         */
-        temp_table = kmemdup(tab, sizeof(*temp_table), GFP_KERNEL);
-        if (temp_table == NULL)
-                return -ENOMEM;
-
-        mask_table = kcalloc(MAX_FILER_CACHE_IDX / 2 + 1,
-                             sizeof(struct gfar_mask_entry), GFP_KERNEL);
-
-        if (mask_table == NULL) {
-                ret = -ENOMEM;
-                goto end;
-        }
-
-        and_index = gfar_generate_mask_table(mask_table, tab);
-
-        gfar_sort_mask_table(mask_table, temp_table, and_index);
-
-        /* Now we can copy the data from our duplicated filer table to
-         * the real one in the order the mask table says
-         */
-        for (i = 0; i < and_index; i++) {
-                size = mask_table[i].end - mask_table[i].start + 1;
-                gfar_copy_filer_entries(&(tab->fe[j]),
-                                &(temp_table->fe[mask_table[i].start]), size);
-                j += size;
-        }
-
-        /* And finally we just have to check for duplicated masks and drop the
-         * second ones
-         */
-        for (i = 0; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) {
-                if (tab->fe[i].ctrl == 0x80) {
-                        previous_mask = i++;
-                        break;
-                }
-        }
-        for (; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) {
-                if (tab->fe[i].ctrl == 0x80) {
-                        if (tab->fe[i].prop == tab->fe[previous_mask].prop) {
-                                /* Two identical ones found!
-                                 * So drop the second one!
-                                 */
-                                gfar_trim_filer_entries(i, i, tab);
-                        } else
-                                /* Not identical! */
-                                previous_mask = i;
-                }
-        }
-
-        kfree(mask_table);
-end:    kfree(temp_table);
-        return ret;
-}
-
 /* Write the bit-pattern from software's buffer to hardware registers */
 static int gfar_write_filer_table(struct gfar_private *priv,
                                   struct filer_table *tab)
@@ -1586,11 +1258,10 @@ static int gfar_write_filer_table(struct gfar_private *priv,
                 return -EBUSY;
 
         /* Fill regular entries */
-        for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop);
-             i++)
+        for (; i < MAX_FILER_IDX && (tab->fe[i].ctrl | tab->fe[i].prop); i++)
                 gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop);
         /* Fill the rest with fall-troughs */
-        for (; i < MAX_FILER_IDX - 1; i++)
+        for (; i < MAX_FILER_IDX; i++)
                 gfar_write_filer(priv, i, 0x60, 0xFFFFFFFF);
         /* Last entry must be default accept
          * because that's what people expect
@@ -1624,7 +1295,6 @@ static int gfar_process_filer_changes(struct gfar_private *priv)
 {
         struct ethtool_flow_spec_container *j;
         struct filer_table *tab;
-        s32 i = 0;
         s32 ret = 0;
 
         /* So index is set to zero, too! */
@@ -1649,17 +1319,6 @@ static int gfar_process_filer_changes(struct gfar_private *priv)
                 }
         }
 
-        i = tab->index;
-
-        /* Optimizations to save entries */
-        gfar_cluster_filer(tab);
-        gfar_optimize_filer_masks(tab);
-
-        pr_debug("\tSummary:\n"
-                 "\tData on hardware: %d\n"
-                 "\tCompression rate: %d%%\n",
-                 tab->index, 100 - (100 * tab->index) / i);
-
         /* Write everything to hardware */
         ret = gfar_write_filer_table(priv, tab);
         if (ret == -EBUSY) {
@@ -1725,13 +1384,14 @@ static int gfar_add_cls(struct gfar_private *priv,
         }
 
 process:
+        priv->rx_list.count++;
         ret = gfar_process_filer_changes(priv);
         if (ret)
                 goto clean_list;
-        priv->rx_list.count++;
         return ret;
 
 clean_list:
+        priv->rx_list.count--;
         list_del(&temp->list);
 clean_mem:
         kfree(temp);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 370e20ed224c..62e48bc0cb23 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1462,7 +1462,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                      struct mvneta_rx_queue *rxq)
 {
         struct net_device *dev = pp->dev;
-        int rx_done, rx_filled;
+        int rx_done;
         u32 rcvd_pkts = 0;
         u32 rcvd_bytes = 0;
 
@@ -1473,7 +1473,6 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                 rx_todo = rx_done;
 
         rx_done = 0;
-        rx_filled = 0;
 
         /* Fairness NAPI loop */
         while (rx_done < rx_todo) {
@@ -1484,7 +1483,6 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                 int rx_bytes, err;
 
                 rx_done++;
-                rx_filled++;
                 rx_status = rx_desc->status;
                 rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
                 data = (unsigned char *)rx_desc->buf_cookie;
@@ -1524,6 +1522,14 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                         continue;
                 }
 
+                /* Refill processing */
+                err = mvneta_rx_refill(pp, rx_desc);
+                if (err) {
+                        netdev_err(dev, "Linux processing - Can't refill\n");
+                        rxq->missed++;
+                        goto err_drop_frame;
+                }
+
                 skb = build_skb(data, pp->frag_size > PAGE_SIZE ? 0 : pp->frag_size);
                 if (!skb)
                         goto err_drop_frame;
@@ -1543,14 +1549,6 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                 mvneta_rx_csum(pp, rx_status, skb);
 
                 napi_gro_receive(&pp->napi, skb);
-
-                /* Refill processing */
-                err = mvneta_rx_refill(pp, rx_desc);
-                if (err) {
-                        netdev_err(dev, "Linux processing - Can't refill\n");
-                        rxq->missed++;
-                        rx_filled--;
-                }
         }
 
         if (rcvd_pkts) {
@@ -1563,7 +1561,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
         }
 
         /* Update rxq management counters */
-        mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled);
+        mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
 
         return rx_done;
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 3e8b1bfb1f2e..d9884fd15b45 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -27,6 +27,8 @@
 #include <linux/of_address.h>
 #include <linux/phy.h>
 #include <linux/clk.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
 #include <uapi/linux/ppp_defs.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
@@ -299,6 +301,7 @@
 
 /* Coalescing */
 #define MVPP2_TXDONE_COAL_PKTS_THRESH   15
+#define MVPP2_TXDONE_HRTIMER_PERIOD_NS  1000000UL
 #define MVPP2_RX_COAL_PKTS              32
 #define MVPP2_RX_COAL_USEC              100
 
@@ -660,6 +663,14 @@ struct mvpp2_pcpu_stats {
         u64     tx_bytes;
 };
 
+/* Per-CPU port control */
+struct mvpp2_port_pcpu {
+        struct hrtimer tx_done_timer;
+        bool timer_scheduled;
+        /* Tasklet for egress finalization */
+        struct tasklet_struct tx_done_tasklet;
+};
+
 struct mvpp2_port {
         u8 id;
 
@@ -679,6 +690,9 @@ struct mvpp2_port {
         u32 pending_cause_rx;
         struct napi_struct napi;
 
+        /* Per-CPU port control */
+        struct mvpp2_port_pcpu __percpu *pcpu;
+
         /* Flags */
         unsigned long flags;
 
@@ -776,6 +790,9 @@ struct mvpp2_txq_pcpu {
         /* Array of transmitted skb */
         struct sk_buff **tx_skb;
 
+        /* Array of transmitted buffers' physical addresses */
+        dma_addr_t *tx_buffs;
+
         /* Index of last TX DMA descriptor that was inserted */
         int txq_put_index;
 
@@ -913,8 +930,6 @@ struct mvpp2_bm_pool {
         /* Occupied buffers indicator */
         atomic_t in_use;
         int in_use_thresh;
-
-        spinlock_t lock;
 };
 
 struct mvpp2_buff_hdr {
@@ -963,9 +978,13 @@ static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
 }
 
 static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
-                              struct sk_buff *skb)
+                              struct sk_buff *skb,
+                              struct mvpp2_tx_desc *tx_desc)
 {
         txq_pcpu->tx_skb[txq_pcpu->txq_put_index] = skb;
+        if (skb)
+                txq_pcpu->tx_buffs[txq_pcpu->txq_put_index] =
+                                                         tx_desc->buf_phys_addr;
         txq_pcpu->txq_put_index++;
         if (txq_pcpu->txq_put_index == txq_pcpu->size)
                 txq_pcpu->txq_put_index = 0;
@@ -3376,7 +3395,6 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev,
         bm_pool->pkt_size = 0;
         bm_pool->buf_num = 0;
         atomic_set(&bm_pool->in_use, 0);
-        spin_lock_init(&bm_pool->lock);
 
         return 0;
 }
@@ -3647,7 +3665,6 @@ static struct mvpp2_bm_pool *
 mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type,
                   int pkt_size)
 {
-        unsigned long flags = 0;
         struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool];
         int num;
 
@@ -3656,8 +3673,6 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type,
                 return NULL;
         }
 
-        spin_lock_irqsave(&new_pool->lock, flags);
-
         if (new_pool->type == MVPP2_BM_FREE)
                 new_pool->type = type;
 
@@ -3686,8 +3701,6 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type,
                 if (num != pkts_num) {
                         WARN(1, "pool %d: %d of %d allocated\n",
                              new_pool->id, num, pkts_num);
-                        /* We need to undo the bufs_add() allocations */
-                        spin_unlock_irqrestore(&new_pool->lock, flags);
                         return NULL;
                 }
         }
@@ -3695,15 +3708,12 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type,
         mvpp2_bm_pool_bufsize_set(port->priv, new_pool,
                                   MVPP2_RX_BUF_SIZE(new_pool->pkt_size));
 
-        spin_unlock_irqrestore(&new_pool->lock, flags);
-
         return new_pool;
 }
 
 /* Initialize pools for swf */
 static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port)
 {
-        unsigned long flags = 0;
         int rxq;
 
         if (!port->pool_long) {
@@ -3714,9 +3724,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port)
                 if (!port->pool_long)
                         return -ENOMEM;
 
-                spin_lock_irqsave(&port->pool_long->lock, flags);
                 port->pool_long->port_map |= (1 << port->id);
-                spin_unlock_irqrestore(&port->pool_long->lock, flags);
 
                 for (rxq = 0; rxq < rxq_number; rxq++)
                         mvpp2_rxq_long_pool_set(port, rxq, port->pool_long->id);
@@ -3730,9 +3738,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port)
                 if (!port->pool_short)
                         return -ENOMEM;
 
-                spin_lock_irqsave(&port->pool_short->lock, flags);
                 port->pool_short->port_map |= (1 << port->id);
-                spin_unlock_irqrestore(&port->pool_short->lock, flags);
 
                 for (rxq = 0; rxq < rxq_number; rxq++)
                         mvpp2_rxq_short_pool_set(port, rxq,
@@ -3806,7 +3812,6 @@ static void mvpp2_interrupts_unmask(void *arg)
 
         mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id),
                     (MVPP2_CAUSE_MISC_SUM_MASK |
-                     MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK |
                      MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
 }
 
@@ -4382,23 +4387,6 @@ static void mvpp2_rx_time_coal_set(struct mvpp2_port *port,
         rxq->time_coal = usec;
 }
 
-/* Set threshold for TX_DONE pkts coalescing */
-static void mvpp2_tx_done_pkts_coal_set(void *arg)
-{
-        struct mvpp2_port *port = arg;
-        int queue;
-        u32 val;
-
-        for (queue = 0; queue < txq_number; queue++) {
-                struct mvpp2_tx_queue *txq = port->txqs[queue];
-
-                val = (txq->done_pkts_coal << MVPP2_TRANSMITTED_THRESH_OFFSET) &
-                       MVPP2_TRANSMITTED_THRESH_MASK;
-                mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-                mvpp2_write(port->priv, MVPP2_TXQ_THRESH_REG, val);
-        }
-}
-
 /* Free Tx queue skbuffs */
 static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
                                 struct mvpp2_tx_queue *txq,
@@ -4407,8 +4395,8 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
         int i;
 
         for (i = 0; i < num; i++) {
-                struct mvpp2_tx_desc *tx_desc = txq->descs +
-                                                        txq_pcpu->txq_get_index;
+                dma_addr_t buf_phys_addr =
+                                    txq_pcpu->tx_buffs[txq_pcpu->txq_get_index];
                 struct sk_buff *skb = txq_pcpu->tx_skb[txq_pcpu->txq_get_index];
 
                 mvpp2_txq_inc_get(txq_pcpu);
@@ -4416,8 +4404,8 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
                 if (!skb)
                         continue;
 
-                dma_unmap_single(port->dev->dev.parent, tx_desc->buf_phys_addr,
-                                 tx_desc->data_size, DMA_TO_DEVICE);
+                dma_unmap_single(port->dev->dev.parent, buf_phys_addr,
+                                 skb_headlen(skb), DMA_TO_DEVICE);
                 dev_kfree_skb_any(skb);
         }
 }
@@ -4433,7 +4421,7 @@ static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port,
 static inline struct mvpp2_tx_queue *mvpp2_get_tx_queue(struct mvpp2_port *port,
                                                         u32 cause)
 {
-        int queue = fls(cause >> 16) - 1;
+        int queue = fls(cause) - 1;
 
         return port->txqs[queue];
 }
@@ -4460,6 +4448,29 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq,
                         netif_tx_wake_queue(nq);
 }
 
+static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause)
+{
+        struct mvpp2_tx_queue *txq;
+        struct mvpp2_txq_pcpu *txq_pcpu;
+        unsigned int tx_todo = 0;
+
+        while (cause) {
+                txq = mvpp2_get_tx_queue(port, cause);
+                if (!txq)
+                        break;
+
+                txq_pcpu = this_cpu_ptr(txq->pcpu);
+
+                if (txq_pcpu->count) {
+                        mvpp2_txq_done(port, txq, txq_pcpu);
+                        tx_todo += txq_pcpu->count;
+                }
+
+                cause &= ~(1 << txq->log_id);
+        }
+        return tx_todo;
+}
+
 /* Rx/Tx queue initialization/cleanup methods */
 
 /* Allocate and initialize descriptors for aggr TXQ */
@@ -4649,12 +4660,13 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
                 txq_pcpu->tx_skb = kmalloc(txq_pcpu->size *
                                            sizeof(*txq_pcpu->tx_skb),
                                            GFP_KERNEL);
-                if (!txq_pcpu->tx_skb) {
-                        dma_free_coherent(port->dev->dev.parent,
-                                          txq->size * MVPP2_DESC_ALIGNED_SIZE,
-                                          txq->descs, txq->descs_phys);
-                        return -ENOMEM;
-                }
+                if (!txq_pcpu->tx_skb)
+                        goto error;
+
+                txq_pcpu->tx_buffs = kmalloc(txq_pcpu->size *
+                                             sizeof(dma_addr_t), GFP_KERNEL);
+                if (!txq_pcpu->tx_buffs)
+                        goto error;
 
                 txq_pcpu->count = 0;
                 txq_pcpu->reserved_num = 0;
@@ -4663,6 +4675,19 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
         }
 
         return 0;
+
+error:
+        for_each_present_cpu(cpu) {
+                txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
+                kfree(txq_pcpu->tx_skb);
+                kfree(txq_pcpu->tx_buffs);
+        }
+
+        dma_free_coherent(port->dev->dev.parent,
+                          txq->size * MVPP2_DESC_ALIGNED_SIZE,
+                          txq->descs, txq->descs_phys);
+
+        return -ENOMEM;
 }
 
 /* Free allocated TXQ resources */
@@ -4675,6 +4700,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
         for_each_present_cpu(cpu) {
                 txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
                 kfree(txq_pcpu->tx_skb);
+                kfree(txq_pcpu->tx_buffs);
         }
 
         if (txq->descs)
@@ -4805,7 +4831,6 @@ static int mvpp2_setup_txqs(struct mvpp2_port *port)
                         goto err_cleanup;
         }
 
-        on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1);
         on_each_cpu(mvpp2_txq_sent_counter_clear, port, 1);
         return 0;
 
@@ -4887,6 +4912,49 @@ static void mvpp2_link_event(struct net_device *dev)
         }
 }
 
+static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu)
+{
+        ktime_t interval;
+
+        if (!port_pcpu->timer_scheduled) {
+                port_pcpu->timer_scheduled = true;
+                interval = ktime_set(0, MVPP2_TXDONE_HRTIMER_PERIOD_NS);
+                hrtimer_start(&port_pcpu->tx_done_timer, interval,
+                              HRTIMER_MODE_REL_PINNED);
+        }
+}
+
+static void mvpp2_tx_proc_cb(unsigned long data)
+{
+        struct net_device *dev = (struct net_device *)data;
+        struct mvpp2_port *port = netdev_priv(dev);
+        struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
+        unsigned int tx_todo, cause;
+
+        if (!netif_running(dev))
+                return;
+        port_pcpu->timer_scheduled = false;
+
+        /* Process all the Tx queues */
+        cause = (1 << txq_number) - 1;
+        tx_todo = mvpp2_tx_done(port, cause);
+
+        /* Set the timer in case not all the packets were processed */
+        if (tx_todo)
+                mvpp2_timer_set(port_pcpu);
+}
+
+static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
+{
+        struct mvpp2_port_pcpu *port_pcpu = container_of(timer,
+                                                         struct mvpp2_port_pcpu,
+                                                         tx_done_timer);
+
+        tasklet_schedule(&port_pcpu->tx_done_tasklet);
+
+        return HRTIMER_NORESTART;
+}
+
 /* Main RX/TX processing routines */
 
 /* Display more error info */
@@ -5144,11 +5212,11 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb,
                 if (i == (skb_shinfo(skb)->nr_frags - 1)) {
                         /* Last descriptor */
                         tx_desc->command = MVPP2_TXD_L_DESC;
-                        mvpp2_txq_inc_put(txq_pcpu, skb);
+                        mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
                 } else {
                         /* Descriptor in the middle: Not First, Not Last */
                         tx_desc->command = 0;
-                        mvpp2_txq_inc_put(txq_pcpu, NULL);
+                        mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
                 }
         }
 
@@ -5214,12 +5282,12 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev)
                 /* First and Last descriptor */
                 tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC;
                 tx_desc->command = tx_cmd;
-                mvpp2_txq_inc_put(txq_pcpu, skb);
+                mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
         } else {
                 /* First but not Last */
                 tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE;
                 tx_desc->command = tx_cmd;
-                mvpp2_txq_inc_put(txq_pcpu, NULL);
+                mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
 
                 /* Continue with other skb fragments */
                 if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
@@ -5255,6 +5323,17 @@ out:
                 dev_kfree_skb_any(skb);
         }
 
+        /* Finalize TX processing */
+        if (txq_pcpu->count >= txq->done_pkts_coal)
+                mvpp2_txq_done(port, txq, txq_pcpu);
+
+        /* Set the timer in case not all frags were processed */
+        if (txq_pcpu->count <= frags && txq_pcpu->count > 0) {
+                struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
+
+                mvpp2_timer_set(port_pcpu);
+        }
+
         return NETDEV_TX_OK;
 }
 
@@ -5268,10 +5347,11 @@ static inline void mvpp2_cause_error(struct net_device *dev, int cause)
                 netdev_err(dev, "tx fifo underrun error\n");
 }
 
-static void mvpp2_txq_done_percpu(void *arg)
+static int mvpp2_poll(struct napi_struct *napi, int budget)
 {
-        struct mvpp2_port *port = arg;
-        u32 cause_rx_tx, cause_tx, cause_misc;
+        u32 cause_rx_tx, cause_rx, cause_misc;
+        int rx_done = 0;
+        struct mvpp2_port *port = netdev_priv(napi->dev);
 
         /* Rx/Tx cause register
          *
@@ -5285,7 +5365,7 @@ static void mvpp2_txq_done_percpu(void *arg)
          */
         cause_rx_tx = mvpp2_read(port->priv,
                                  MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
-        cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
+        cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
         cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK;
 
         if (cause_misc) {
@@ -5297,26 +5377,6 @@ static void mvpp2_txq_done_percpu(void *arg)
                             cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
         }
 
-        /* Release TX descriptors */
-        if (cause_tx) {
-                struct mvpp2_tx_queue *txq = mvpp2_get_tx_queue(port, cause_tx);
-                struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu);
-
-                if (txq_pcpu->count)
-                        mvpp2_txq_done(port, txq, txq_pcpu);
-        }
-}
-
-static int mvpp2_poll(struct napi_struct *napi, int budget)
-{
-        u32 cause_rx_tx, cause_rx;
-        int rx_done = 0;
-        struct mvpp2_port *port = netdev_priv(napi->dev);
-
-        on_each_cpu(mvpp2_txq_done_percpu, port, 1);
-
-        cause_rx_tx = mvpp2_read(port->priv,
-                                 MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
         cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK;
 
         /* Process RX packets */
@@ -5561,6 +5621,8 @@ err_cleanup_rxqs:
 static int mvpp2_stop(struct net_device *dev)
 {
         struct mvpp2_port *port = netdev_priv(dev);
+        struct mvpp2_port_pcpu *port_pcpu;
+        int cpu;
 
         mvpp2_stop_dev(port);
         mvpp2_phy_disconnect(port);
@@ -5569,6 +5631,13 @@ static int mvpp2_stop(struct net_device *dev)
         on_each_cpu(mvpp2_interrupts_mask, port, 1);
 
         free_irq(port->irq, port);
+        for_each_present_cpu(cpu) {
+                port_pcpu = per_cpu_ptr(port->pcpu, cpu);
+
+                hrtimer_cancel(&port_pcpu->tx_done_timer);
+                port_pcpu->timer_scheduled = false;
+                tasklet_kill(&port_pcpu->tx_done_tasklet);
+        }
         mvpp2_cleanup_rxqs(port);
         mvpp2_cleanup_txqs(port);
 
@@ -5784,7 +5853,6 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev,
                 txq->done_pkts_coal = c->tx_max_coalesced_frames;
         }
 
-        on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1);
         return 0;
 }
 
@@ -6035,6 +6103,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 {
         struct device_node *phy_node;
         struct mvpp2_port *port;
+        struct mvpp2_port_pcpu *port_pcpu;
         struct net_device *dev;
         struct resource *res;
         const char *dt_mac_addr;
@@ -6044,7 +6113,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
         int features;
         int phy_mode;
         int priv_common_regs_num = 2;
-        int err, i;
+        int err, i, cpu;
 
         dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number,
                                  rxq_number);
@@ -6135,6 +6204,24 @@ static int mvpp2_port_probe(struct platform_device *pdev,
         }
         mvpp2_port_power_up(port);
 
+        port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
+        if (!port->pcpu) {
+                err = -ENOMEM;
+                goto err_free_txq_pcpu;
+        }
+
+        for_each_present_cpu(cpu) {
+                port_pcpu = per_cpu_ptr(port->pcpu, cpu);
+
+                hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
+                             HRTIMER_MODE_REL_PINNED);
+                port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
+                port_pcpu->timer_scheduled = false;
+
+                tasklet_init(&port_pcpu->tx_done_tasklet, mvpp2_tx_proc_cb,
+                             (unsigned long)dev);
+        }
+
         netif_napi_add(dev, &port->napi, mvpp2_poll, NAPI_POLL_WEIGHT);
         features = NETIF_F_SG | NETIF_F_IP_CSUM;
         dev->features = features | NETIF_F_RXCSUM;
@@ -6144,7 +6231,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
         err = register_netdev(dev);
         if (err < 0) {
                 dev_err(&pdev->dev, "failed to register netdev\n");
-                goto err_free_txq_pcpu;
+                goto err_free_port_pcpu;
         }
         netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
 
@@ -6153,6 +6240,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
         priv->port_list[id] = port;
         return 0;
 
+err_free_port_pcpu:
+        free_percpu(port->pcpu);
 err_free_txq_pcpu:
         for (i = 0; i < txq_number; i++)
                 free_percpu(port->txqs[i]->pcpu);
@@ -6171,6 +6260,7 @@ static void mvpp2_port_remove(struct mvpp2_port *port)
         int i;
 
         unregister_netdev(port->dev);
+        free_percpu(port->pcpu);
         free_percpu(port->stats);
         for (i = 0; i < txq_number; i++)
                 free_percpu(port->txqs[i]->pcpu);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 82040137d7d9..0a3202047569 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -686,6 +686,7 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 {
         struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
         struct mlx4_cmd_context *context;
+        long ret_wait;
         int err = 0;
 
         down(&cmd->event_sem);
@@ -711,8 +712,20 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
         if (err)
                 goto out_reset;
 
-        if (!wait_for_completion_timeout(&context->done,
-                                         msecs_to_jiffies(timeout))) {
+        if (op == MLX4_CMD_SENSE_PORT) {
+                ret_wait =
+                        wait_for_completion_interruptible_timeout(&context->done,
+                                                                  msecs_to_jiffies(timeout));
+                if (ret_wait < 0) {
+                        context->fw_status = 0;
+                        context->out_param = 0;
+                        context->result = 0;
+                }
+        } else {
+                ret_wait = (long)wait_for_completion_timeout(&context->done,
+                                                             msecs_to_jiffies(timeout));
+        }
+        if (!ret_wait) {
                 mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
                           op);
                 if (op == MLX4_CMD_NOP) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 7a4f20bb7fcb..9c145dddd717 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -246,7 +246,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 
 static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
 {
-        BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
         return ring->prod == ring->cons;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index aae13adfb492..8e81e53c370e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -601,7 +601,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
                                                         continue;
                                                 mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
                                                          __func__, i, port);
-                                                s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+                                                s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
                                                 if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
                                                         eqe->event.port_change.port =
                                                                 cpu_to_be32(
@@ -640,7 +640,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
                                                         continue;
                                                 if (i == mlx4_master_func_num(dev))
                                                         continue;
-                                                s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+                                                s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
                                                 if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
                                                         eqe->event.port_change.port =
                                                                 cpu_to_be32(
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12fbfcb44d8a..29c2a017a450 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2273,6 +2273,11 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
                 } else if (err == -ENOENT) {
                         err = 0;
                         continue;
+                } else if (mlx4_is_slave(dev) && err == -EINVAL) {
+                        priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev);
+                        mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n",
+                                  MLX4_SINK_COUNTER_INDEX(dev));
+                        err = 0;
                 } else {
                         mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
                                  __func__, port + 1, err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index afad529838de..06e3e1e54c35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -391,6 +391,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
         /* disable cmdif checksum */
         MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0);
 
+        MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12);
+
         err = set_caps(dev, set_ctx, set_sz);
 
 query_ex:
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index 33669c29b341..753ea8bad953 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1415,7 +1415,7 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter)
         if (fw->size & 0xF) {
                 addr = dest + size;
                 for (i = 0; i < (fw->size & 0xF); i++)
-                        data[i] = temp[size + i];
+                        data[i] = ((u8 *)temp)[size + i];
                 for (; i < 16; i++)
                         data[i] = 0;
                 ret = qlcnic_ms_mem_write128(adapter, addr,
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3df51faf18ae..f790f61ea78a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4875,10 +4875,12 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
         case RTL_GIGA_MAC_VER_46:
         case RTL_GIGA_MAC_VER_47:
         case RTL_GIGA_MAC_VER_48:
+                RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
+                break;
         case RTL_GIGA_MAC_VER_49:
         case RTL_GIGA_MAC_VER_50:
         case RTL_GIGA_MAC_VER_51:
-                RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
+                RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
                 break;
         default:
                 RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index fd9745714d90..78849dd4ef8e 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -228,9 +228,7 @@ static void ravb_ring_format(struct net_device *ndev, int q)
         struct ravb_desc *desc = NULL;
         int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q];
         int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q];
-        struct sk_buff *skb;
         dma_addr_t dma_addr;
-        void *buffer;
         int i;
 
         priv->cur_rx[q] = 0;
@@ -241,41 +239,28 @@ static void ravb_ring_format(struct net_device *ndev, int q)
         memset(priv->rx_ring[q], 0, rx_ring_size);
         /* Build RX ring buffer */
         for (i = 0; i < priv->num_rx_ring[q]; i++) {
-                priv->rx_skb[q][i] = NULL;
-                skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1);
-                if (!skb)
-                        break;
-                ravb_set_buffer_align(skb);
                 /* RX descriptor */
                 rx_desc = &priv->rx_ring[q][i];
                 /* The size of the buffer should be on 16-byte boundary. */
                 rx_desc->ds_cc = cpu_to_le16(ALIGN(PKT_BUF_SZ, 16));
-                dma_addr = dma_map_single(&ndev->dev, skb->data,
+                dma_addr = dma_map_single(&ndev->dev, priv->rx_skb[q][i]->data,
                                           ALIGN(PKT_BUF_SZ, 16),
                                           DMA_FROM_DEVICE);
-                if (dma_mapping_error(&ndev->dev, dma_addr)) {
-                        dev_kfree_skb(skb);
-                        break;
-                }
-                priv->rx_skb[q][i] = skb;
+                /* We just set the data size to 0 for a failed mapping which
+                 * should prevent DMA from happening...
+                 */
+                if (dma_mapping_error(&ndev->dev, dma_addr))
+                        rx_desc->ds_cc = cpu_to_le16(0);
                 rx_desc->dptr = cpu_to_le32(dma_addr);
                 rx_desc->die_dt = DT_FEMPTY;
         }
         rx_desc = &priv->rx_ring[q][i];
         rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
         rx_desc->die_dt = DT_LINKFIX; /* type */
-        priv->dirty_rx[q] = (u32)(i - priv->num_rx_ring[q]);
 
         memset(priv->tx_ring[q], 0, tx_ring_size);
         /* Build TX ring buffer */
         for (i = 0; i < priv->num_tx_ring[q]; i++) {
-                priv->tx_skb[q][i] = NULL;
-                priv->tx_buffers[q][i] = NULL;
-                buffer = kmalloc(PKT_BUF_SZ + RAVB_ALIGN - 1, GFP_KERNEL);
-                if (!buffer)
-                        break;
-                /* Aligned TX buffer */
-                priv->tx_buffers[q][i] = buffer;
                 tx_desc = &priv->tx_ring[q][i];
                 tx_desc->die_dt = DT_EEMPTY;
         }
@@ -298,7 +283,10 @@ static void ravb_ring_format(struct net_device *ndev, int q)
 static int ravb_ring_init(struct net_device *ndev, int q)
 {
         struct ravb_private *priv = netdev_priv(ndev);
+        struct sk_buff *skb;
         int ring_size;
+        void *buffer;
+        int i;
 
         /* Allocate RX and TX skb rings */
         priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -308,12 +296,28 @@ static int ravb_ring_init(struct net_device *ndev, int q)
         if (!priv->rx_skb[q] || !priv->tx_skb[q])
                 goto error;
 
+        for (i = 0; i < priv->num_rx_ring[q]; i++) {
+                skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1);
+                if (!skb)
+                        goto error;
+                ravb_set_buffer_align(skb);
+                priv->rx_skb[q][i] = skb;
+        }
+
         /* Allocate rings for the aligned buffers */
         priv->tx_buffers[q] = kcalloc(priv->num_tx_ring[q],
                                       sizeof(*priv->tx_buffers[q]), GFP_KERNEL);
         if (!priv->tx_buffers[q])
                 goto error;
 
+        for (i = 0; i < priv->num_tx_ring[q]; i++) {
+                buffer = kmalloc(PKT_BUF_SZ + RAVB_ALIGN - 1, GFP_KERNEL);
+                if (!buffer)
+                        goto error;
+                /* Aligned TX buffer */
+                priv->tx_buffers[q][i] = buffer;
+        }
+
         /* Allocate all RX descriptors. */
         ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1);
         priv->rx_ring[q] = dma_alloc_coherent(NULL, ring_size,
@@ -524,6 +528,10 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
                 if (--boguscnt < 0)
                         break;
 
+                /* We use 0-byte descriptors to mark the DMA mapping errors */
+                if (!pkt_len)
+                        continue;
+
                 if (desc_status & MSC_MC)
                         stats->multicast++;
 
@@ -543,10 +551,9 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
 
                         skb = priv->rx_skb[q][entry];
                         priv->rx_skb[q][entry] = NULL;
-                        dma_sync_single_for_cpu(&ndev->dev,
-                                                le32_to_cpu(desc->dptr),
-                                                ALIGN(PKT_BUF_SZ, 16),
-                                                DMA_FROM_DEVICE);
+                        dma_unmap_single(&ndev->dev, le32_to_cpu(desc->dptr),
+                                         ALIGN(PKT_BUF_SZ, 16),
+                                         DMA_FROM_DEVICE);
                         get_ts &= (q == RAVB_NC) ?
                                         RAVB_RXTSTAMP_TYPE_V2_L2_EVENT :
                                         ~RAVB_RXTSTAMP_TYPE_V2_L2_EVENT;
@@ -584,17 +591,15 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
                         if (!skb)
                                 break;  /* Better luck next round. */
                         ravb_set_buffer_align(skb);
-                        dma_unmap_single(&ndev->dev, le32_to_cpu(desc->dptr),
-                                         ALIGN(PKT_BUF_SZ, 16),
-                                         DMA_FROM_DEVICE);
                         dma_addr = dma_map_single(&ndev->dev, skb->data,
                                                   le16_to_cpu(desc->ds_cc),
                                                   DMA_FROM_DEVICE);
                         skb_checksum_none_assert(skb);
-                        if (dma_mapping_error(&ndev->dev, dma_addr)) {
-                                dev_kfree_skb_any(skb);
-                                break;
-                        }
+                        /* We just set the data size to 0 for a failed mapping
+                         * which should prevent DMA  from happening...
+                         */
+                        if (dma_mapping_error(&ndev->dev, dma_addr))
+                                desc->ds_cc = cpu_to_le16(0);
                         desc->dptr = cpu_to_le32(dma_addr);
                         priv->rx_skb[q][entry] = skb;
                 }
@@ -1279,7 +1284,6 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
         u32 dma_addr;
         void *buffer;
         u32 entry;
-        u32 tccr;
 
         spin_lock_irqsave(&priv->lock, flags);
         if (priv->cur_tx[q] - priv->dirty_tx[q] >= priv->num_tx_ring[q]) {
@@ -1328,9 +1332,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
         dma_wmb();
         desc->die_dt = DT_FSINGLE;
 
-        tccr = ravb_read(ndev, TCCR);
-        if (!(tccr & (TCCR_TSRQ0 << q)))
-                ravb_write(ndev, tccr | (TCCR_TSRQ0 << q), TCCR);
+        ravb_write(ndev, ravb_read(ndev, TCCR) | (TCCR_TSRQ0 << q), TCCR);
 
         priv->cur_tx[q]++;
         if (priv->cur_tx[q] - priv->dirty_tx[q] >= priv->num_tx_ring[q] &&
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 2d8578cade03..2e7f9a2834be 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -4821,6 +4821,7 @@ static void rocker_remove_ports(const struct rocker *rocker)
                 rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE,
                                    ROCKER_OP_FLAG_REMOVE);
                 unregister_netdev(rocker_port->dev);
+                free_netdev(rocker_port->dev);
         }
         kfree(rocker->ports);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 7e3129e7f143..f0e4bb4e3ec5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -42,7 +42,7 @@
 #define NSS_COMMON_CLK_DIV_MASK                 0x7f
 
 #define NSS_COMMON_CLK_SRC_CTRL                 0x14
-#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x)       (1 << x)
+#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x)       (x)
 /* Mode is coded on 1 bit but is different depending on the MAC ID:
  * MAC0: QSGMII=0 RGMII=1
  * MAC1: QSGMII=0 SGMII=0 RGMII=1
@@ -291,7 +291,7 @@ static void *ipq806x_gmac_setup(struct platform_device *pdev)
 
         /* Configure the clock src according to the mode */
         regmap_read(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, &val);
-        val &= ~NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
+        val &= ~(1 << NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id));
         switch (gmac->phy_mode) {
         case PHY_INTERFACE_MODE_RGMII:
                 val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) <<
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 50f7a7a26821..864b476f7fd5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2843,7 +2843,7 @@ int stmmac_dvr_probe(struct device *device,
         if (res->mac)
                 memcpy(priv->dev->dev_addr, res->mac, ETH_ALEN);
 
-        dev_set_drvdata(device, priv);
+        dev_set_drvdata(device, priv->dev);
 
         /* Verify driver arguments */
         stmmac_verify_args();
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index f3918c7e7eeb..bcdc8955c719 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -413,3 +413,7 @@ static int stmmac_pltfr_resume(struct device *dev)
 SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend,
                                        stmmac_pltfr_resume);
 EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 0c5842aeb807..ab6051a43134 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6658,10 +6658,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
                 struct sk_buff *skb_new;
 
                 skb_new = skb_realloc_headroom(skb, len);
-                if (!skb_new) {
-                        rp->tx_errors++;
+                if (!skb_new)
                         goto out_drop;
-                }
                 kfree_skb(skb);
                 skb = skb_new;
         } else
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f335bf119ab5..d155bf2573cd 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -793,9 +793,7 @@ static irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id)
 static int cpsw_poll(struct napi_struct *napi, int budget)
 {
         struct cpsw_priv        *priv = napi_to_priv(napi);
-        int                     num_tx, num_rx;
-
-        num_tx = cpdma_chan_process(priv->txch, 128);
+        int                     num_rx;
 
         num_rx = cpdma_chan_process(priv->rxch, budget);
         if (num_rx < budget) {
@@ -810,9 +808,8 @@ static int cpsw_poll(struct napi_struct *napi, int budget)
                 }
         }
 
-        if (num_rx || num_tx)
-                cpsw_dbg(priv, intr, "poll %d rx, %d tx pkts\n",
-                         num_rx, num_tx);
+        if (num_rx)
+                cpsw_dbg(priv, intr, "poll %d rx pkts\n", num_rx);
 
         return num_rx;
 }
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index bbacf5cccec2..bb1bb72121c0 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -85,7 +85,6 @@ struct netcp_intf {
         struct list_head        rxhook_list_head;
         unsigned int            rx_queue_id;
         void                    *rx_fdq[KNAV_DMA_FDQ_PER_CHAN];
-        u32                     rx_buffer_sizes[KNAV_DMA_FDQ_PER_CHAN];
         struct napi_struct      rx_napi;
         struct napi_struct      tx_napi;
 
@@ -223,6 +222,7 @@ void *netcp_device_find_module(struct netcp_device *netcp_device,
 
 /* SGMII functions */
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port);
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set);
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port);
 int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface);
 
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 5ec4ed3f6c8d..4755838c6137 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -34,6 +34,7 @@
 #define NETCP_SOP_OFFSET        (NET_IP_ALIGN + NET_SKB_PAD)
 #define NETCP_NAPI_WEIGHT       64
 #define NETCP_TX_TIMEOUT        (5 * HZ)
+#define NETCP_PACKET_SIZE       (ETH_FRAME_LEN + ETH_FCS_LEN)
 #define NETCP_MIN_PACKET_SIZE   ETH_ZLEN
 #define NETCP_MAX_MCAST_ADDR    16
 
@@ -804,30 +805,28 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
         if (likely(fdq == 0)) {
                 unsigned int primary_buf_len;
                 /* Allocate a primary receive queue entry */
-                buf_len = netcp->rx_buffer_sizes[0] + NETCP_SOP_OFFSET;
+                buf_len = NETCP_PACKET_SIZE + NETCP_SOP_OFFSET;
                 primary_buf_len = SKB_DATA_ALIGN(buf_len) +
                                 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-                if (primary_buf_len <= PAGE_SIZE) {
-                        bufptr = netdev_alloc_frag(primary_buf_len);
-                        pad[1] = primary_buf_len;
-                } else {
-                        bufptr = kmalloc(primary_buf_len, GFP_ATOMIC |
-                                         GFP_DMA32 | __GFP_COLD);
-                        pad[1] = 0;
-                }
+                bufptr = netdev_alloc_frag(primary_buf_len);
+                pad[1] = primary_buf_len;
 
                 if (unlikely(!bufptr)) {
-                        dev_warn_ratelimited(netcp->ndev_dev, "Primary RX buffer alloc failed\n");
+                        dev_warn_ratelimited(netcp->ndev_dev,
+                                             "Primary RX buffer alloc failed\n");
                         goto fail;
                 }
                 dma = dma_map_single(netcp->dev, bufptr, buf_len,
                                      DMA_TO_DEVICE);
+                if (unlikely(dma_mapping_error(netcp->dev, dma)))
+                        goto fail;
+
                 pad[0] = (u32)bufptr;
 
         } else {
                 /* Allocate a secondary receive queue entry */
-                page = alloc_page(GFP_ATOMIC | GFP_DMA32 | __GFP_COLD);
+                page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD);
                 if (unlikely(!page)) {
                         dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n");
                         goto fail;
@@ -1010,7 +1009,7 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp)
 
         /* Map the linear buffer */
         dma_addr = dma_map_single(dev, skb->data, pkt_len, DMA_TO_DEVICE);
-        if (unlikely(!dma_addr)) {
+        if (unlikely(dma_mapping_error(dev, dma_addr))) {
                 dev_err(netcp->ndev_dev, "Failed to map skb buffer\n");
                 return NULL;
         }
@@ -1546,8 +1545,8 @@ static int netcp_setup_navigator_resources(struct net_device *ndev)
         knav_queue_disable_notify(netcp->rx_queue);
 
         /* open Rx FDQs */
-        for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN &&
-             netcp->rx_queue_depths[i] && netcp->rx_buffer_sizes[i]; ++i) {
+        for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_queue_depths[i];
+             ++i) {
                 snprintf(name, sizeof(name), "rx-fdq-%s-%d", ndev->name, i);
                 netcp->rx_fdq[i] = knav_queue_open(name, KNAV_QUEUE_GP, 0);
                 if (IS_ERR_OR_NULL(netcp->rx_fdq[i])) {
@@ -1617,11 +1616,11 @@ static int netcp_ndo_open(struct net_device *ndev)
         }
         mutex_unlock(&netcp_modules_lock);
 
-        netcp_rxpool_refill(netcp);
         napi_enable(&netcp->rx_napi);
         napi_enable(&netcp->tx_napi);
         knav_queue_enable_notify(netcp->tx_compl_q);
         knav_queue_enable_notify(netcp->rx_queue);
+        netcp_rxpool_refill(netcp);
         netif_tx_wake_all_queues(ndev);
         dev_dbg(netcp->ndev_dev, "netcp device %s opened\n", ndev->name);
         return 0;
@@ -1941,14 +1940,6 @@ static int netcp_create_interface(struct netcp_device *netcp_device,
                 netcp->rx_queue_depths[0] = 128;
         }
 
-        ret = of_property_read_u32_array(node_interface, "rx-buffer-size",
-                                         netcp->rx_buffer_sizes,
-                                         KNAV_DMA_FDQ_PER_CHAN);
-        if (ret) {
-                dev_err(dev, "missing \"rx-buffer-size\" parameter\n");
-                netcp->rx_buffer_sizes[0] = 1536;
-        }
-
         ret = of_property_read_u32_array(node_interface, "rx-pool", temp, 2);
         if (ret < 0) {
                 dev_err(dev, "missing \"rx-pool\" parameter\n");
@@ -2112,6 +2103,7 @@ probe_quit:
 static int netcp_remove(struct platform_device *pdev)
 {
         struct netcp_device *netcp_device = platform_get_drvdata(pdev);
+        struct netcp_intf *netcp_intf, *netcp_tmp;
         struct netcp_inst_modpriv *inst_modpriv, *tmp;
         struct netcp_module *module;
 
@@ -2123,10 +2115,17 @@ static int netcp_remove(struct platform_device *pdev)
                 list_del(&inst_modpriv->inst_list);
                 kfree(inst_modpriv);
         }
-        WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n",
-             pdev->name);
 
-        devm_kfree(&pdev->dev, netcp_device);
+        /* now that all modules are removed, clean up the interfaces */
+        list_for_each_entry_safe(netcp_intf, netcp_tmp,
+                                 &netcp_device->interface_head,
+                                 interface_list) {
+                netcp_delete_interface(netcp_device, netcp_intf->ndev);
+        }
+
+        WARN(!list_empty(&netcp_device->interface_head),
+             "%s interface list not empty!\n", pdev->name);
+
         pm_runtime_put_sync(&pdev->dev);
         pm_runtime_disable(&pdev->dev);
         platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 9b7e0a34c98b..1974a8ae764a 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -1901,11 +1901,28 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave,
         writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control));
 }
 
+static void gbe_sgmii_rtreset(struct gbe_priv *priv,
+                              struct gbe_slave *slave, bool set)
+{
+        void __iomem *sgmii_port_regs;
+
+        if (SLAVE_LINK_IS_XGMII(slave))
+                return;
+
+        if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
+                sgmii_port_regs = priv->sgmii_port34_regs;
+        else
+                sgmii_port_regs = priv->sgmii_port_regs;
+
+        netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+}
+
 static void gbe_slave_stop(struct gbe_intf *intf)
 {
         struct gbe_priv *gbe_dev = intf->gbe_dev;
         struct gbe_slave *slave = intf->slave;
 
+        gbe_sgmii_rtreset(gbe_dev, slave, true);
         gbe_port_reset(slave);
         /* Disable forwarding */
         cpsw_ale_control_set(gbe_dev->ale, slave->port_num,
@@ -1947,6 +1964,7 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf)
 
         gbe_sgmii_config(priv, slave);
         gbe_port_reset(slave);
+        gbe_sgmii_rtreset(priv, slave, false);
         gbe_port_config(priv, slave, priv->rx_packet_max);
         gbe_set_slave_mac(slave, gbe_intf);
         /* enable forwarding */
@@ -2490,10 +2508,9 @@ static void free_secondary_ports(struct gbe_priv *gbe_dev)
 {
         struct gbe_slave *slave;
 
-        for (;;) {
+        while (!list_empty(&gbe_dev->secondary_slaves)) {
                 slave = first_sec_slave(gbe_dev);
-                if (!slave)
-                        break;
+
                 if (slave->phy)
                         phy_disconnect(slave->phy);
                 list_del(&slave->slave_list);
@@ -2839,14 +2856,13 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
                                       &gbe_dev->dma_chan_name);
         if (ret < 0) {
                 dev_err(dev, "missing \"tx-channel\" parameter\n");
-                ret = -ENODEV;
-                goto quit;
+                return -EINVAL;
         }
 
         if (!strcmp(node->name, "gbe")) {
                 ret = get_gbe_resource_version(gbe_dev, node);
                 if (ret)
-                        goto quit;
+                        return ret;
 
                 dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version);
 
@@ -2857,22 +2873,20 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
                 else
                         ret = -ENODEV;
 
-                if (ret)
-                        goto quit;
         } else if (!strcmp(node->name, "xgbe")) {
                 ret = set_xgbe_ethss10_priv(gbe_dev, node);
                 if (ret)
-                        goto quit;
+                        return ret;
                 ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs,
                                              gbe_dev->ss_regs);
-                if (ret)
-                        goto quit;
         } else {
                 dev_err(dev, "unknown GBE node(%s)\n", node->name);
                 ret = -ENODEV;
-                goto quit;
         }
 
+        if (ret)
+                return ret;
+
         interfaces = of_get_child_by_name(node, "interfaces");
         if (!interfaces)
                 dev_err(dev, "could not find interfaces\n");
@@ -2880,11 +2894,11 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
         ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
                                 gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
         if (ret)
-                goto quit;
+                return ret;
 
         ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
         if (ret)
-                goto quit;
+                return ret;
 
         /* Create network interfaces */
         INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
@@ -2899,6 +2913,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
                 if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
                         break;
         }
+        of_node_put(interfaces);
 
         if (!gbe_dev->num_slaves)
                 dev_warn(dev, "No network interface configured\n");
@@ -2911,9 +2926,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
         of_node_put(secondary_ports);
 
         if (!gbe_dev->num_slaves) {
-                dev_err(dev, "No network interface or secondary ports configured\n");
+                dev_err(dev,
+                        "No network interface or secondary ports configured\n");
                 ret = -ENODEV;
-                goto quit;
+                goto free_sec_ports;
         }
 
         memset(&ale_params, 0, sizeof(ale_params));
@@ -2927,7 +2943,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
         if (!gbe_dev->ale) {
                 dev_err(gbe_dev->dev, "error initializing ale engine\n");
                 ret = -ENODEV;
-                goto quit;
+                goto free_sec_ports;
         } else {
                 dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
         }
@@ -2943,14 +2959,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
         *inst_priv = gbe_dev;
         return 0;
 
-quit:
-        if (gbe_dev->hw_stats)
-                devm_kfree(dev, gbe_dev->hw_stats);
-        cpsw_ale_destroy(gbe_dev->ale);
-        if (gbe_dev->ss_regs)
-                devm_iounmap(dev, gbe_dev->ss_regs);
-        of_node_put(interfaces);
-        devm_kfree(dev, gbe_dev);
+free_sec_ports:
+        free_secondary_ports(gbe_dev);
         return ret;
 }
 
@@ -3023,12 +3033,9 @@ static int gbe_remove(struct netcp_device *netcp_device, void *inst_priv)
         free_secondary_ports(gbe_dev);
 
         if (!list_empty(&gbe_dev->gbe_intf_head))
-                dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n");
+                dev_alert(gbe_dev->dev,
+                          "unreleased ethss interfaces present\n");
 
-        devm_kfree(gbe_dev->dev, gbe_dev->hw_stats);
-        devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs);
-        memset(gbe_dev, 0x00, sizeof(*gbe_dev));
-        devm_kfree(gbe_dev->dev, gbe_dev);
         return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c
index dbeb14266e2f..5d8419f658d0 100644
--- a/drivers/net/ethernet/ti/netcp_sgmii.c
+++ b/drivers/net/ethernet/ti/netcp_sgmii.c
@@ -18,6 +18,9 @@
 
 #include "netcp.h"
 
+#define SGMII_SRESET_RESET              BIT(0)
+#define SGMII_SRESET_RTRESET            BIT(1)
+
 #define SGMII_REG_STATUS_LOCK           BIT(4)
 #define SGMII_REG_STATUS_LINK           BIT(0)
 #define SGMII_REG_STATUS_AUTONEG        BIT(2)
@@ -51,12 +54,35 @@ static void sgmii_write_reg_bit(void __iomem *base, int reg, u32 val)
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port)
 {
         /* Soft reset */
-        sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1);
-        while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0)
+        sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port),
+                            SGMII_SRESET_RESET);
+
+        while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) &
+                SGMII_SRESET_RESET) != 0x0)
                 ;
+
         return 0;
 }
 
+/* port is 0 based */
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set)
+{
+        u32 reg;
+        bool oldval;
+
+        /* Initiate a soft reset */
+        reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port));
+        oldval = (reg & SGMII_SRESET_RTRESET) != 0x0;
+        if (set)
+                reg |= SGMII_SRESET_RTRESET;
+        else
+                reg &= ~SGMII_SRESET_RTRESET;
+        sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg);
+        wmb();
+
+        return oldval;
+}
+
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port)
 {
         u32 status = 0, link = 0;
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 2ffbf13471d0..216bfd350169 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -728,11 +728,12 @@ static int mkiss_open(struct tty_struct *tty)
         dev->type = ARPHRD_AX25;
 
         /* Perform the low-level AX25 initialization. */
-        if ((err = ax_open(ax->dev))) {
+        err = ax_open(ax->dev);
+        if (err)
                 goto out_free_netdev;
-        }
 
-        if (register_netdev(dev))
+        err = register_netdev(dev);
+        if (err)
                 goto out_free_buffers;
 
         /* after register_netdev() - because else printk smashes the kernel */
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 953a97492fab..9542b7bac61a 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -67,8 +67,6 @@ struct ipvl_dev {
         struct ipvl_port        *port;
         struct net_device       *phy_dev;
         struct list_head        addrs;
-        int                     ipv4cnt;
-        int                     ipv6cnt;
         struct ipvl_pcpu_stats  __percpu *pcpu_stats;
         DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
         netdev_features_t       sfeatures;
@@ -106,6 +104,11 @@ static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
         return rcu_dereference(d->rx_handler_data);
 }
 
+static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d)
+{
+        return rcu_dereference_bh(d->rx_handler_data);
+}
+
 static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
 {
         return rtnl_dereference(d->rx_handler_data);
@@ -124,5 +127,5 @@ struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
 bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6);
 struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,
                                         const void *iaddr, bool is_v6);
-void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync);
+void ipvlan_ht_addr_del(struct ipvl_addr *addr);
 #endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 8afbedad620d..207f62e8de9a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -85,11 +85,9 @@ void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr)
                 hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]);
 }
 
-void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync)
+void ipvlan_ht_addr_del(struct ipvl_addr *addr)
 {
         hlist_del_init_rcu(&addr->hlnode);
-        if (sync)
-                synchronize_rcu();
 }
 
 struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
@@ -531,7 +529,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 {
         struct ipvl_dev *ipvlan = netdev_priv(dev);
-        struct ipvl_port *port = ipvlan_port_get_rcu(ipvlan->phy_dev);
+        struct ipvl_port *port = ipvlan_port_get_rcu_bh(ipvlan->phy_dev);
 
         if (!port)
                 goto out;
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 1acc283160d9..20b58bdecf75 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -153,10 +153,9 @@ static int ipvlan_open(struct net_device *dev)
         else
                 dev->flags &= ~IFF_NOARP;
 
-        if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
-                list_for_each_entry(addr, &ipvlan->addrs, anode)
-                        ipvlan_ht_addr_add(ipvlan, addr);
-        }
+        list_for_each_entry(addr, &ipvlan->addrs, anode)
+                ipvlan_ht_addr_add(ipvlan, addr);
+
         return dev_uc_add(phy_dev, phy_dev->dev_addr);
 }
 
@@ -171,10 +170,9 @@ static int ipvlan_stop(struct net_device *dev)
 
         dev_uc_del(phy_dev, phy_dev->dev_addr);
 
-        if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
-                list_for_each_entry(addr, &ipvlan->addrs, anode)
-                        ipvlan_ht_addr_del(addr, !dev->dismantle);
-        }
+        list_for_each_entry(addr, &ipvlan->addrs, anode)
+                ipvlan_ht_addr_del(addr);
+
         return 0;
 }
 
@@ -471,8 +469,6 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev,
         ipvlan->port = port;
         ipvlan->sfeatures = IPVLAN_FEATURES;
         INIT_LIST_HEAD(&ipvlan->addrs);
-        ipvlan->ipv4cnt = 0;
-        ipvlan->ipv6cnt = 0;
 
         /* TODO Probably put random address here to be presented to the
          * world but keep using the physical-dev address for the outgoing
@@ -508,12 +504,12 @@ static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
         struct ipvl_dev *ipvlan = netdev_priv(dev);
         struct ipvl_addr *addr, *next;
 
-        if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
-                list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
-                        ipvlan_ht_addr_del(addr, !dev->dismantle);
-                        list_del(&addr->anode);
-                }
+        list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
+                ipvlan_ht_addr_del(addr);
+                list_del(&addr->anode);
+                kfree_rcu(addr, rcu);
         }
+
         list_del_rcu(&ipvlan->pnode);
         unregister_netdevice_queue(dev, head);
         netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
@@ -627,7 +623,7 @@ static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
         memcpy(&addr->ip6addr, ip6_addr, sizeof(struct in6_addr));
         addr->atype = IPVL_IPV6;
         list_add_tail(&addr->anode, &ipvlan->addrs);
-        ipvlan->ipv6cnt++;
+
         /* If the interface is not up, the address will be added to the hash
          * list by ipvlan_open.
          */
@@ -645,10 +641,8 @@ static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
         if (!addr)
                 return;
 
-        ipvlan_ht_addr_del(addr, true);
+        ipvlan_ht_addr_del(addr);
         list_del(&addr->anode);
-        ipvlan->ipv6cnt--;
-        WARN_ON(ipvlan->ipv6cnt < 0);
         kfree_rcu(addr, rcu);
 
         return;
@@ -661,6 +655,10 @@ static int ipvlan_addr6_event(struct notifier_block *unused,
         struct net_device *dev = (struct net_device *)if6->idev->dev;
         struct ipvl_dev *ipvlan = netdev_priv(dev);
 
+        /* FIXME IPv6 autoconf calls us from bh without RTNL */
+        if (in_softirq())
+                return NOTIFY_DONE;
+
         if (!netif_is_ipvlan(dev))
                 return NOTIFY_DONE;
 
@@ -699,7 +697,7 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
         memcpy(&addr->ip4addr, ip4_addr, sizeof(struct in_addr));
         addr->atype = IPVL_IPV4;
         list_add_tail(&addr->anode, &ipvlan->addrs);
-        ipvlan->ipv4cnt++;
+
         /* If the interface is not up, the address will be added to the hash
          * list by ipvlan_open.
          */
@@ -717,10 +715,8 @@ static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
         if (!addr)
                 return;
 
-        ipvlan_ht_addr_del(addr, true);
+        ipvlan_ht_addr_del(addr);
         list_del(&addr->anode);
-        ipvlan->ipv4cnt--;
-        WARN_ON(ipvlan->ipv4cnt < 0);
         kfree_rcu(addr, rcu);
 
         return;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 3b933bb5a8d5..edd77342773a 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -719,6 +719,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
         struct virtio_net_hdr vnet_hdr = { 0 };
         int vnet_hdr_len = 0;
         int copylen = 0;
+        int depth;
         bool zerocopy = false;
         size_t linear;
         ssize_t n;
@@ -804,6 +805,12 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
         skb_probe_transport_header(skb, ETH_HLEN);
 
+        /* Move network header to the right position for VLAN tagged packets */
+        if ((skb->protocol == htons(ETH_P_8021Q) ||
+             skb->protocol == htons(ETH_P_8021AD)) &&
+            __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+                skb_set_network_header(skb, depth);
+
         rcu_read_lock();
         vlan = rcu_dereference(q->vlan);
         /* copy skb_ubuf_info for callback when skb has no error */
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 3cc316cb7e6b..d8757bf9ad75 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -102,6 +102,12 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data,
 
         netdev_dbg(ndev, "%s: %d byte payload received\n", __func__, len);
 
+        if (len < 0) {
+                ndev->stats.rx_errors++;
+                ndev->stats.rx_length_errors++;
+                goto enqueue_again;
+        }
+
         skb_put(skb, len);
         skb->protocol = eth_type_trans(skb, ndev);
         skb->ip_summed = CHECKSUM_NONE;
@@ -121,6 +127,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data,
                 return;
         }
 
+enqueue_again:
         rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN);
         if (rc) {
                 dev_kfree_skb(skb);
@@ -184,7 +191,7 @@ static int ntb_netdev_open(struct net_device *ndev)
 
                 rc = ntb_transport_rx_enqueue(dev->qp, skb, skb->data,
                                               ndev->mtu + ETH_HLEN);
-                if (rc == -EINVAL) {
+                if (rc) {
                         dev_kfree_skb(skb);
                         goto err;
                 }
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index c7a12e2e07b7..8a3bf5469892 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -164,7 +164,7 @@ static int dp83867_config_init(struct phy_device *phydev)
                         return ret;
         }
 
-        if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) ||
+        if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) &&
             (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) {
                 val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL,
                                             DP83867_DEVADDR, phydev->addr);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 095ef3fe369a..46a14cbb0215 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -421,6 +421,8 @@ static int mdio_bus_match(struct device *dev, struct device_driver *drv)
 {
         struct phy_device *phydev = to_phy_device(dev);
         struct phy_driver *phydrv = to_phy_driver(drv);
+        const int num_ids = ARRAY_SIZE(phydev->c45_ids.device_ids);
+        int i;
 
         if (of_driver_match_device(dev, drv))
                 return 1;
@@ -428,8 +430,21 @@ static int mdio_bus_match(struct device *dev, struct device_driver *drv)
         if (phydrv->match_phy_device)
                 return phydrv->match_phy_device(phydev);
 
-        return (phydrv->phy_id & phydrv->phy_id_mask) ==
-                (phydev->phy_id & phydrv->phy_id_mask);
+        if (phydev->is_c45) {
+                for (i = 1; i < num_ids; i++) {
+                        if (!(phydev->c45_ids.devices_in_package & (1 << i)))
+                                continue;
+
+                        if ((phydrv->phy_id & phydrv->phy_id_mask) ==
+                            (phydev->c45_ids.device_ids[i] &
+                             phydrv->phy_id_mask))
+                                return 1;
+                }
+                return 0;
+        } else {
+                return (phydrv->phy_id & phydrv->phy_id_mask) ==
+                        (phydev->phy_id & phydrv->phy_id_mask);
+        }
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f603f362504b..9d43460ce3c7 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -757,6 +757,7 @@ static const struct usb_device_id products[] = {
         {QMI_FIXED_INTF(0x1199, 0x901c, 8)},    /* Sierra Wireless EM7700 */
         {QMI_FIXED_INTF(0x1199, 0x901f, 8)},    /* Sierra Wireless EM7355 */
         {QMI_FIXED_INTF(0x1199, 0x9041, 8)},    /* Sierra Wireless MC7305/MC7355 */
+        {QMI_FIXED_INTF(0x1199, 0x9041, 10)},   /* Sierra Wireless MC7305/MC7355 */
         {QMI_FIXED_INTF(0x1199, 0x9051, 8)},    /* Netgear AirCard 340U */
         {QMI_FIXED_INTF(0x1199, 0x9053, 8)},    /* Sierra Wireless Modem */
         {QMI_FIXED_INTF(0x1199, 0x9054, 8)},    /* Sierra Wireless Modem */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 7f6419ebb5e1..ad8cbc6c9ee7 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -27,7 +27,7 @@
 #include <linux/usb/cdc.h>
 
 /* Version Information */
-#define DRIVER_VERSION "v1.08.0 (2015/01/13)"
+#define DRIVER_VERSION "v1.08.1 (2015/07/28)"
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
 #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters"
 #define MODULENAME "r8152"
@@ -1902,11 +1902,10 @@ static void rtl_drop_queued_tx(struct r8152 *tp)
 static void rtl8152_tx_timeout(struct net_device *netdev)
 {
         struct r8152 *tp = netdev_priv(netdev);
-        int i;
 
         netif_warn(tp, tx_err, netdev, "Tx timeout\n");
-        for (i = 0; i < RTL8152_MAX_TX; i++)
-                usb_unlink_urb(tp->tx_info[i].urb);
+
+        usb_queue_reset_device(tp->intf);
 }
 
 static void rtl8152_set_rx_mode(struct net_device *netdev)
@@ -2075,7 +2074,6 @@ static int rtl_start_rx(struct r8152 *tp)
 {
         int i, ret = 0;
 
-        napi_disable(&tp->napi);
         INIT_LIST_HEAD(&tp->rx_done);
         for (i = 0; i < RTL8152_MAX_RX; i++) {
                 INIT_LIST_HEAD(&tp->rx_info[i].list);
@@ -2083,7 +2081,6 @@ static int rtl_start_rx(struct r8152 *tp)
                 if (ret)
                         break;
         }
-        napi_enable(&tp->napi);
 
         if (ret && ++i < RTL8152_MAX_RX) {
                 struct list_head rx_queue;
@@ -2166,6 +2163,7 @@ static int rtl8153_enable(struct r8152 *tp)
         if (test_bit(RTL8152_UNPLUG, &tp->flags))
                 return -ENODEV;
 
+        usb_disable_lpm(tp->udev);
         set_tx_qlen(tp);
         rtl_set_eee_plus(tp);
         r8153_set_rx_early_timeout(tp);
@@ -2337,11 +2335,61 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts)
                 device_set_wakeup_enable(&tp->udev->dev, false);
 }
 
+static void r8153_u1u2en(struct r8152 *tp, bool enable)
+{
+        u8 u1u2[8];
+
+        if (enable)
+                memset(u1u2, 0xff, sizeof(u1u2));
+        else
+                memset(u1u2, 0x00, sizeof(u1u2));
+
+        usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
+}
+
+static void r8153_u2p3en(struct r8152 *tp, bool enable)
+{
+        u32 ocp_data;
+
+        ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
+        if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04)
+                ocp_data |= U2P3_ENABLE;
+        else
+                ocp_data &= ~U2P3_ENABLE;
+        ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
+}
+
+static void r8153_power_cut_en(struct r8152 *tp, bool enable)
+{
+        u32 ocp_data;
+
+        ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
+        if (enable)
+                ocp_data |= PWR_EN | PHASE2_EN;
+        else
+                ocp_data &= ~(PWR_EN | PHASE2_EN);
+        ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
+
+        ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
+        ocp_data &= ~PCUT_STATUS;
+        ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
+}
+
+static bool rtl_can_wakeup(struct r8152 *tp)
+{
+        struct usb_device *udev = tp->udev;
+
+        return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP);
+}
+
 static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 {
         if (enable) {
                 u32 ocp_data;
 
+                r8153_u1u2en(tp, false);
+                r8153_u2p3en(tp, false);
+
                 __rtl_set_wol(tp, WAKE_ANY);
 
                 ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2353,6 +2401,8 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
                 ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
         } else {
                 __rtl_set_wol(tp, tp->saved_wolopts);
+                r8153_u2p3en(tp, true);
+                r8153_u1u2en(tp, true);
         }
 }
 
@@ -2599,46 +2649,6 @@ static void r8153_hw_phy_cfg(struct r8152 *tp)
         set_bit(PHY_RESET, &tp->flags);
 }
 
-static void r8153_u1u2en(struct r8152 *tp, bool enable)
-{
-        u8 u1u2[8];
-
-        if (enable)
-                memset(u1u2, 0xff, sizeof(u1u2));
-        else
-                memset(u1u2, 0x00, sizeof(u1u2));
-
-        usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
-}
-
-static void r8153_u2p3en(struct r8152 *tp, bool enable)
-{
-        u32 ocp_data;
-
-        ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
-        if (enable)
-                ocp_data |= U2P3_ENABLE;
-        else
-                ocp_data &= ~U2P3_ENABLE;
-        ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
-}
-
-static void r8153_power_cut_en(struct r8152 *tp, bool enable)
-{
-        u32 ocp_data;
-
-        ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
-        if (enable)
-                ocp_data |= PWR_EN | PHASE2_EN;
-        else
-                ocp_data &= ~(PWR_EN | PHASE2_EN);
-        ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
-
-        ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
-        ocp_data &= ~PCUT_STATUS;
-        ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
-}
-
 static void r8153_first_init(struct r8152 *tp)
 {
         u32 ocp_data;
@@ -2781,6 +2791,7 @@ static void rtl8153_disable(struct r8152 *tp)
         r8153_disable_aldps(tp);
         rtl_disable(tp);
         r8153_enable_aldps(tp);
+        usb_enable_lpm(tp->udev);
 }
 
 static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
@@ -2901,9 +2912,13 @@ static void rtl8153_up(struct r8152 *tp)
         if (test_bit(RTL8152_UNPLUG, &tp->flags))
                 return;
 
+        r8153_u1u2en(tp, false);
         r8153_disable_aldps(tp);
         r8153_first_init(tp);
         r8153_enable_aldps(tp);
+        r8153_u2p3en(tp, true);
+        r8153_u1u2en(tp, true);
+        usb_enable_lpm(tp->udev);
 }
 
 static void rtl8153_down(struct r8152 *tp)
@@ -2914,6 +2929,7 @@ static void rtl8153_down(struct r8152 *tp)
         }
 
         r8153_u1u2en(tp, false);
+        r8153_u2p3en(tp, false);
         r8153_power_cut_en(tp, false);
         r8153_disable_aldps(tp);
         r8153_enter_oob(tp);
@@ -2932,8 +2948,10 @@ static void set_carrier(struct r8152 *tp)
                 if (!netif_carrier_ok(netdev)) {
                         tp->rtl_ops.enable(tp);
                         set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+                        napi_disable(&tp->napi);
                         netif_carrier_on(netdev);
                         rtl_start_rx(tp);
+                        napi_enable(&tp->napi);
                 }
         } else {
                 if (netif_carrier_ok(netdev)) {
@@ -3252,6 +3270,7 @@ static void r8153_init(struct r8152 *tp)
                 msleep(20);
         }
 
+        usb_disable_lpm(tp->udev);
         r8153_u2p3en(tp, false);
 
         if (tp->version == RTL_VER_04) {
@@ -3319,6 +3338,59 @@ static void r8153_init(struct r8152 *tp)
         r8153_enable_aldps(tp);
         r8152b_enable_fc(tp);
         rtl_tally_reset(tp);
+        r8153_u2p3en(tp, true);
+}
+
+static int rtl8152_pre_reset(struct usb_interface *intf)
+{
+        struct r8152 *tp = usb_get_intfdata(intf);
+        struct net_device *netdev;
+
+        if (!tp)
+                return 0;
+
+        netdev = tp->netdev;
+        if (!netif_running(netdev))
+                return 0;
+
+        napi_disable(&tp->napi);
+        clear_bit(WORK_ENABLE, &tp->flags);
+        usb_kill_urb(tp->intr_urb);
+        cancel_delayed_work_sync(&tp->schedule);
+        if (netif_carrier_ok(netdev)) {
+                netif_stop_queue(netdev);
+                mutex_lock(&tp->control);
+                tp->rtl_ops.disable(tp);
+                mutex_unlock(&tp->control);
+        }
+
+        return 0;
+}
+
+static int rtl8152_post_reset(struct usb_interface *intf)
+{
+        struct r8152 *tp = usb_get_intfdata(intf);
+        struct net_device *netdev;
+
+        if (!tp)
+                return 0;
+
+        netdev = tp->netdev;
+        if (!netif_running(netdev))
+                return 0;
+
+        set_bit(WORK_ENABLE, &tp->flags);
+        if (netif_carrier_ok(netdev)) {
+                mutex_lock(&tp->control);
+                tp->rtl_ops.enable(tp);
+                rtl8152_set_rx_mode(netdev);
+                mutex_unlock(&tp->control);
+                netif_wake_queue(netdev);
+        }
+
+        napi_enable(&tp->napi);
+
+        return 0;
 }
 
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
@@ -3374,9 +3446,11 @@ static int rtl8152_resume(struct usb_interface *intf)
                 if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
                         rtl_runtime_suspend_enable(tp, false);
                         clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+                        napi_disable(&tp->napi);
                         set_bit(WORK_ENABLE, &tp->flags);
                         if (netif_carrier_ok(tp->netdev))
                                 rtl_start_rx(tp);
+                        napi_enable(&tp->napi);
                 } else {
                         tp->rtl_ops.up(tp);
                         rtl8152_set_speed(tp, AUTONEG_ENABLE,
@@ -3403,12 +3477,15 @@ static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
         if (usb_autopm_get_interface(tp->intf) < 0)
                 return;
 
-        mutex_lock(&tp->control);
-
-        wol->supported = WAKE_ANY;
-        wol->wolopts = __rtl_get_wol(tp);
-
-        mutex_unlock(&tp->control);
+        if (!rtl_can_wakeup(tp)) {
+                wol->supported = 0;
+                wol->wolopts = 0;
+        } else {
+                mutex_lock(&tp->control);
+                wol->supported = WAKE_ANY;
+                wol->wolopts = __rtl_get_wol(tp);
+                mutex_unlock(&tp->control);
+        }
 
         usb_autopm_put_interface(tp->intf);
 }
@@ -3418,6 +3495,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
         struct r8152 *tp = netdev_priv(dev);
         int ret;
 
+        if (!rtl_can_wakeup(tp))
+                return -EOPNOTSUPP;
+
         ret = usb_autopm_get_interface(tp->intf);
         if (ret < 0)
                 goto out_set_wol;
@@ -4059,6 +4139,9 @@ static int rtl8152_probe(struct usb_interface *intf,
                 goto out1;
         }
 
+        if (!rtl_can_wakeup(tp))
+                __rtl_set_wol(tp, 0);
+
         tp->saved_wolopts = __rtl_get_wol(tp);
         if (tp->saved_wolopts)
                 device_set_wakeup_enable(&udev->dev, true);
@@ -4132,6 +4215,8 @@ static struct usb_driver rtl8152_driver = {
         .suspend =      rtl8152_suspend,
         .resume =       rtl8152_resume,
         .reset_resume = rtl8152_resume,
+        .pre_reset =    rtl8152_pre_reset,
+        .post_reset =   rtl8152_post_reset,
         .supports_autosuspend = 1,
         .disable_hub_initiated_lpm = 1,
 };
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 63c7810e1545..237f8e5e493d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1756,9 +1756,9 @@ static int virtnet_probe(struct virtio_device *vdev)
         /* Do we support "hardware" checksums? */
         if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
                 /* This opens up the world of extra features. */
-                dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+                dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG;
                 if (csum)
-                        dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+                        dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 
                 if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
                         dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
@@ -1828,7 +1828,8 @@ static int virtnet_probe(struct virtio_device *vdev)
         else
                 vi->hdr_len = sizeof(struct virtio_net_hdr);
 
-        if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT))
+        if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) ||
+            virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
                 vi->any_header_sg = true;
 
         if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 7193b7304fdd..848ea6a399f2 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -589,7 +589,8 @@ static int cosa_probe(int base, int irq, int dma)
                 chan->netdev->base_addr = chan->cosa->datareg;
                 chan->netdev->irq = chan->cosa->irq;
                 chan->netdev->dma = chan->cosa->dma;
-                if (register_hdlc_device(chan->netdev)) {
+                err = register_hdlc_device(chan->netdev);
+                if (err) {
                         netdev_warn(chan->netdev,
                                     "register_hdlc_device() failed\n");
                         free_netdev(chan->netdev);
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 5e15e8e10ed3..a31a6804dc34 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -279,6 +279,7 @@ static void ath9k_hw_read_revisions(struct ath_hw *ah)
                 return;
         case AR9300_DEVID_QCA956X:
                 ah->hw_version.macVersion = AR_SREV_VERSION_9561;
+                return;
         }
 
         val = REG_READ(ah, AR_SREV) & AR_SREV_ID;
diff --git a/drivers/net/wireless/b43/tables_nphy.c b/drivers/net/wireless/b43/tables_nphy.c
index 25d1cbd34306..b2f0d245bcf3 100644
--- a/drivers/net/wireless/b43/tables_nphy.c
+++ b/drivers/net/wireless/b43/tables_nphy.c
@@ -3728,7 +3728,7 @@ const u32 *b43_nphy_get_tx_gain_table(struct b43_wldev *dev)
                 switch (phy->rev) {
                 case 6:
                 case 5:
-                        if (sprom->fem.ghz5.extpa_gain == 3)
+                        if (sprom->fem.ghz2.extpa_gain == 3)
                                 return b43_ntab_tx_gain_epa_rev3_hi_pwr_2g;
                         /* fall through */
                 case 4:
diff --git a/drivers/net/wireless/iwlwifi/iwl-fh.h b/drivers/net/wireless/iwlwifi/iwl-fh.h
index d56064861a9c..d45dc021cda2 100644
--- a/drivers/net/wireless/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/iwlwifi/iwl-fh.h
@@ -438,6 +438,12 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(unsigned int chnl)
 #define RX_QUEUE_MASK                         255
 #define RX_QUEUE_SIZE_LOG                     8
 
+/*
+ * RX related structures and functions
+ */
+#define RX_FREE_BUFFERS 64
+#define RX_LOW_WATERMARK 8
+
 /**
  * struct iwl_rb_status - reserve buffer status
  *      host memory mapped FH registers
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 80fefe7d7b8c..3b8e85e51002 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -540,13 +540,11 @@ static void iwl_set_hw_address_family_8000(struct device *dev,
                 hw_addr = (const u8 *)(mac_override +
                                  MAC_ADDRESS_OVERRIDE_FAMILY_8000);
 
-                /* The byte order is little endian 16 bit, meaning 214365 */
-                data->hw_addr[0] = hw_addr[1];
-                data->hw_addr[1] = hw_addr[0];
-                data->hw_addr[2] = hw_addr[3];
-                data->hw_addr[3] = hw_addr[2];
-                data->hw_addr[4] = hw_addr[5];
-                data->hw_addr[5] = hw_addr[4];
+                /*
+                 * Store the MAC address from MAO section.
+                 * No byte swapping is required in MAO section
+                 */
+                memcpy(data->hw_addr, hw_addr, ETH_ALEN);
 
                 /*
                  * Force the use of the OTP MAC address in case of reserved MAC
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 5e4cbdb44c60..737774a01c74 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -660,7 +660,8 @@ struct iwl_scan_config {
  * iwl_umac_scan_flags
  *@IWL_UMAC_SCAN_FLAG_PREEMPTIVE: scan process triggered by this scan request
  *      can be preempted by other scan requests with higher priority.
- *      The low priority scan is aborted.
+ *      The low priority scan will be resumed when the higher proirity scan is
+ *      completed.
  *@IWL_UMAC_SCAN_FLAG_START_NOTIF: notification will be sent to the driver
  *      when scan starts.
  */
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 5de144968723..5514ad6d4e54 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -1023,7 +1023,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm,
         cmd->scan_priority =
                 iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6);
 
-        if (iwl_mvm_scan_total_iterations(params) == 0)
+        if (iwl_mvm_scan_total_iterations(params) == 1)
                 cmd->ooc_priority =
                         iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6);
         else
@@ -1109,6 +1109,9 @@ static int iwl_mvm_scan_umac(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
         cmd->uid = cpu_to_le32(uid);
         cmd->general_flags = cpu_to_le32(iwl_mvm_scan_umac_flags(mvm, params));
 
+        if (type == IWL_MVM_SCAN_SCHED)
+                cmd->flags = cpu_to_le32(IWL_UMAC_SCAN_FLAG_PREEMPTIVE);
+
         if (iwl_mvm_scan_use_ebs(mvm, vif, n_iterations))
                 cmd->channel_flags = IWL_SCAN_CHANNEL_FLAG_EBS |
                                      IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index d68dc697a4a0..26f076e82149 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -1401,6 +1401,7 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
         bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
         u8 sta_id;
         int ret;
+        static const u8 __maybe_unused zero_addr[ETH_ALEN] = {0};
 
         lockdep_assert_held(&mvm->mutex);
 
@@ -1467,7 +1468,7 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 end:
         IWL_DEBUG_WEP(mvm, "key: cipher=%x len=%d idx=%d sta=%pM ret=%d\n",
                       keyconf->cipher, keyconf->keylen, keyconf->keyidx,
-                      sta->addr, ret);
+                      sta ? sta->addr : zero_addr, ret);
         return ret;
 }
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/time-event.c b/drivers/net/wireless/iwlwifi/mvm/time-event.c
index d24b6a83e68c..e472729e5f14 100644
--- a/drivers/net/wireless/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/iwlwifi/mvm/time-event.c
@@ -86,7 +86,7 @@ void iwl_mvm_te_clear_data(struct iwl_mvm *mvm,
 {
         lockdep_assert_held(&mvm->time_event_lock);
 
-        if (te_data->id == TE_MAX)
+        if (!te_data->vif)
                 return;
 
         list_del(&te_data->list);
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 7ba7a118ff5c..89116864d2a0 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -252,7 +252,7 @@ void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd,
 
         if (info->band == IEEE80211_BAND_2GHZ &&
             !iwl_mvm_bt_coex_is_shared_ant_avail(mvm))
-                rate_flags = BIT(mvm->cfg->non_shared_ant) << RATE_MCS_ANT_POS;
+                rate_flags = mvm->cfg->non_shared_ant << RATE_MCS_ANT_POS;
         else
                 rate_flags =
                         BIT(mvm->mgmt_last_antenna_idx) << RATE_MCS_ANT_POS;
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 2ed1e4d2774d..9f65c1cff1b1 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -368,12 +368,14 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 /* 3165 Series */
         {IWL_PCI_DEVICE(0x3165, 0x4010, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3165, 0x4012, iwl3165_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x3166, 0x4212, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3165, 0x4410, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3165, 0x4510, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3165, 0x4110, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3166, 0x4310, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3166, 0x4210, iwl3165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x3165, 0x8010, iwl3165_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x3165, 0x8110, iwl3165_2ac_cfg)},
 
 /* 7265 Series */
         {IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)},
@@ -426,9 +428,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
         {IWL_PCI_DEVICE(0x24F4, 0x1130, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F4, 0x1030, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xC010, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0xC110, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xD010, iwl8260_2ac_cfg)},
-        {IWL_PCI_DEVICE(0x24F4, 0xC030, iwl8260_2ac_cfg)},
-        {IWL_PCI_DEVICE(0x24F4, 0xD030, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xC050, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xD050, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x8010, iwl8260_2ac_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h
index 31f72a61cc3f..376b84e54ad7 100644
--- a/drivers/net/wireless/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/iwlwifi/pcie/internal.h
@@ -44,15 +44,6 @@
 #include "iwl-io.h"
 #include "iwl-op-mode.h"
 
-/*
- * RX related structures and functions
- */
-#define RX_NUM_QUEUES 1
-#define RX_POST_REQ_ALLOC 2
-#define RX_CLAIM_REQ_ALLOC 8
-#define RX_POOL_SIZE ((RX_CLAIM_REQ_ALLOC - RX_POST_REQ_ALLOC) * RX_NUM_QUEUES)
-#define RX_LOW_WATERMARK 8
-
 struct iwl_host_cmd;
 
 /*This file includes the declaration that are internal to the
@@ -86,29 +77,29 @@ struct isr_statistics {
  * struct iwl_rxq - Rx queue
  * @bd: driver's pointer to buffer of receive buffer descriptors (rbd)
  * @bd_dma: bus address of buffer of receive buffer descriptors (rbd)
+ * @pool:
+ * @queue:
  * @read: Shared index to newest available Rx buffer
  * @write: Shared index to oldest written Rx packet
  * @free_count: Number of pre-allocated buffers in rx_free
- * @used_count: Number of RBDs handled to allocator to use for allocation
  * @write_actual:
- * @rx_free: list of RBDs with allocated RB ready for use
- * @rx_used: list of RBDs with no RB attached
+ * @rx_free: list of free SKBs for use
+ * @rx_used: List of Rx buffers with no SKB
  * @need_update: flag to indicate we need to update read/write index
  * @rb_stts: driver's pointer to receive buffer status
  * @rb_stts_dma: bus address of receive buffer status
  * @lock:
- * @pool: initial pool of iwl_rx_mem_buffer for the queue
- * @queue: actual rx queue
  *
  * NOTE:  rx_free and rx_used are used as a FIFO for iwl_rx_mem_buffers
  */
 struct iwl_rxq {
         __le32 *bd;
         dma_addr_t bd_dma;
+        struct iwl_rx_mem_buffer pool[RX_QUEUE_SIZE + RX_FREE_BUFFERS];
+        struct iwl_rx_mem_buffer *queue[RX_QUEUE_SIZE];
         u32 read;
         u32 write;
         u32 free_count;
-        u32 used_count;
         u32 write_actual;
         struct list_head rx_free;
         struct list_head rx_used;
@@ -116,32 +107,6 @@ struct iwl_rxq {
         struct iwl_rb_status *rb_stts;
         dma_addr_t rb_stts_dma;
         spinlock_t lock;
-        struct iwl_rx_mem_buffer pool[RX_QUEUE_SIZE];
-        struct iwl_rx_mem_buffer *queue[RX_QUEUE_SIZE];
-};
-
-/**
- * struct iwl_rb_allocator - Rx allocator
- * @pool: initial pool of allocator
- * @req_pending: number of requests the allcator had not processed yet
- * @req_ready: number of requests honored and ready for claiming
- * @rbd_allocated: RBDs with pages allocated and ready to be handled to
- *      the queue. This is a list of &struct iwl_rx_mem_buffer
- * @rbd_empty: RBDs with no page attached for allocator use. This is a list
- *      of &struct iwl_rx_mem_buffer
- * @lock: protects the rbd_allocated and rbd_empty lists
- * @alloc_wq: work queue for background calls
- * @rx_alloc: work struct for background calls
- */
-struct iwl_rb_allocator {
-        struct iwl_rx_mem_buffer pool[RX_POOL_SIZE];
-        atomic_t req_pending;
-        atomic_t req_ready;
-        struct list_head rbd_allocated;
-        struct list_head rbd_empty;
-        spinlock_t lock;
-        struct workqueue_struct *alloc_wq;
-        struct work_struct rx_alloc;
 };
 
 struct iwl_dma_ptr {
@@ -285,7 +250,7 @@ iwl_pcie_get_scratchbuf_dma(struct iwl_txq *txq, int idx)
 /**
  * struct iwl_trans_pcie - PCIe transport specific data
  * @rxq: all the RX queue data
- * @rba: allocator for RX replenishing
+ * @rx_replenish: work that will be called when buffers need to be allocated
  * @drv - pointer to iwl_drv
  * @trans: pointer to the generic transport area
  * @scd_base_addr: scheduler sram base address in SRAM
@@ -308,7 +273,7 @@ iwl_pcie_get_scratchbuf_dma(struct iwl_txq *txq, int idx)
  */
 struct iwl_trans_pcie {
         struct iwl_rxq rxq;
-        struct iwl_rb_allocator rba;
+        struct work_struct rx_replenish;
         struct iwl_trans *trans;
         struct iwl_drv *drv;
 
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index a3fbaa0ef5e0..adad8d0fae7f 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -1,7 +1,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -74,29 +74,16 @@
  * resets the Rx queue buffers with new memory.
  *
  * The management in the driver is as follows:
- * + A list of pre-allocated RBDs is stored in iwl->rxq->rx_free.
- *   When the interrupt handler is called, the request is processed.
- *   The page is either stolen - transferred to the upper layer
- *   or reused - added immediately to the iwl->rxq->rx_free list.
- * + When the page is stolen - the driver updates the matching queue's used
- *   count, detaches the RBD and transfers it to the queue used list.
- *   When there are two used RBDs - they are transferred to the allocator empty
- *   list. Work is then scheduled for the allocator to start allocating
- *   eight buffers.
- *   When there are another 6 used RBDs - they are transferred to the allocator
- *   empty list and the driver tries to claim the pre-allocated buffers and
- *   add them to iwl->rxq->rx_free. If it fails - it continues to claim them
- *   until ready.
- *   When there are 8+ buffers in the free list - either from allocation or from
- *   8 reused unstolen pages - restock is called to update the FW and indexes.
- * + In order to make sure the allocator always has RBDs to use for allocation
- *   the allocator has initial pool in the size of num_queues*(8-2) - the
- *   maximum missing RBDs per allocation request (request posted with 2
- *    empty RBDs, there is no guarantee when the other 6 RBDs are supplied).
- *   The queues supplies the recycle of the rest of the RBDs.
+ * + A list of pre-allocated SKBs is stored in iwl->rxq->rx_free.  When
+ *   iwl->rxq->free_count drops to or below RX_LOW_WATERMARK, work is scheduled
+ *   to replenish the iwl->rxq->rx_free.
+ * + In iwl_pcie_rx_replenish (scheduled) if 'processed' != 'read' then the
+ *   iwl->rxq is replenished and the READ INDEX is updated (updating the
+ *   'processed' and 'read' driver indexes as well)
  * + A received packet is processed and handed to the kernel network stack,
  *   detached from the iwl->rxq.  The driver 'processed' index is updated.
- * + If there are no allocated buffers in iwl->rxq->rx_free,
+ * + The Host/Firmware iwl->rxq is replenished at irq thread time from the
+ *   rx_free list. If there are no allocated buffers in iwl->rxq->rx_free,
  *   the READ INDEX is not incremented and iwl->status(RX_STALLED) is set.
  *   If there were enough free buffers and RX_STALLED is set it is cleared.
  *
@@ -105,32 +92,18 @@
  *
  * iwl_rxq_alloc()            Allocates rx_free
  * iwl_pcie_rx_replenish()    Replenishes rx_free list from rx_used, and calls
- *                            iwl_pcie_rxq_restock.
- *                            Used only during initialization.
+ *                            iwl_pcie_rxq_restock
  * iwl_pcie_rxq_restock()     Moves available buffers from rx_free into Rx
  *                            queue, updates firmware pointers, and updates
- *                            the WRITE index.
- * iwl_pcie_rx_allocator()     Background work for allocating pages.
+ *                            the WRITE index.  If insufficient rx_free buffers
+ *                            are available, schedules iwl_pcie_rx_replenish
  *
  * -- enable interrupts --
  * ISR - iwl_rx()             Detach iwl_rx_mem_buffers from pool up to the
  *                            READ INDEX, detaching the SKB from the pool.
  *                            Moves the packet buffer from queue to rx_used.
- *                            Posts and claims requests to the allocator.
  *                            Calls iwl_pcie_rxq_restock to refill any empty
  *                            slots.
- *
- * RBD life-cycle:
- *
- * Init:
- * rxq.pool -> rxq.rx_used -> rxq.rx_free -> rxq.queue
- *
- * Regular Receive interrupt:
- * Page Stolen:
- * rxq.queue -> rxq.rx_used -> allocator.rbd_empty ->
- * allocator.rbd_allocated -> rxq.rx_free -> rxq.queue
- * Page not Stolen:
- * rxq.queue -> rxq.rx_free -> rxq.queue
  * ...
  *
  */
@@ -267,6 +240,10 @@ static void iwl_pcie_rxq_restock(struct iwl_trans *trans)
                 rxq->free_count--;
         }
         spin_unlock(&rxq->lock);
+        /* If the pre-allocated buffer pool is dropping low, schedule to
+         * refill it */
+        if (rxq->free_count <= RX_LOW_WATERMARK)
+                schedule_work(&trans_pcie->rx_replenish);
 
         /* If we've added more space for the firmware to place data, tell it.
          * Increment device's write pointer in multiples of 8. */
@@ -278,44 +255,6 @@ static void iwl_pcie_rxq_restock(struct iwl_trans *trans)
 }
 
 /*
- * iwl_pcie_rx_alloc_page - allocates and returns a page.
- *
- */
-static struct page *iwl_pcie_rx_alloc_page(struct iwl_trans *trans)
-{
-        struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-        struct iwl_rxq *rxq = &trans_pcie->rxq;
-        struct page *page;
-        gfp_t gfp_mask = GFP_KERNEL;
-
-        if (rxq->free_count > RX_LOW_WATERMARK)
-                gfp_mask |= __GFP_NOWARN;
-
-        if (trans_pcie->rx_page_order > 0)
-                gfp_mask |= __GFP_COMP;
-
-        /* Alloc a new receive buffer */
-        page = alloc_pages(gfp_mask, trans_pcie->rx_page_order);
-        if (!page) {
-                if (net_ratelimit())
-                        IWL_DEBUG_INFO(trans, "alloc_pages failed, order: %d\n",
-                                       trans_pcie->rx_page_order);
-                /* Issue an error if the hardware has consumed more than half
-                 * of its free buffer list and we don't have enough
-                 * pre-allocated buffers.
-`                */
-                if (rxq->free_count <= RX_LOW_WATERMARK &&
-                    iwl_rxq_space(rxq) > (RX_QUEUE_SIZE / 2) &&
-                    net_ratelimit())
-                        IWL_CRIT(trans,
-                                 "Failed to alloc_pages with GFP_KERNEL. Only %u free buffers remaining.\n",
-                                 rxq->free_count);
-                return NULL;
-        }
-        return page;
-}
-
-/*
  * iwl_pcie_rxq_alloc_rbs - allocate a page for each used RBD
  *
  * A used RBD is an Rx buffer that has been given to the stack. To use it again
@@ -324,12 +263,13 @@ static struct page *iwl_pcie_rx_alloc_page(struct iwl_trans *trans)
  * iwl_pcie_rxq_restock. The latter function will update the HW to use the newly
  * allocated buffers.
  */
-static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans)
+static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority)
 {
         struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
         struct iwl_rxq *rxq = &trans_pcie->rxq;
         struct iwl_rx_mem_buffer *rxb;
         struct page *page;
+        gfp_t gfp_mask = priority;
 
         while (1) {
                 spin_lock(&rxq->lock);
@@ -339,10 +279,32 @@ static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans)
                 }
                 spin_unlock(&rxq->lock);
 
+                if (rxq->free_count > RX_LOW_WATERMARK)
+                        gfp_mask |= __GFP_NOWARN;
+
+                if (trans_pcie->rx_page_order > 0)
+                        gfp_mask |= __GFP_COMP;
+
                 /* Alloc a new receive buffer */
-                page = iwl_pcie_rx_alloc_page(trans);
-                if (!page)
+                page = alloc_pages(gfp_mask, trans_pcie->rx_page_order);
+                if (!page) {
+                        if (net_ratelimit())
+                                IWL_DEBUG_INFO(trans, "alloc_pages failed, "
+                                           "order: %d\n",
+                                           trans_pcie->rx_page_order);
+
+                        if ((rxq->free_count <= RX_LOW_WATERMARK) &&
+                            net_ratelimit())
+                                IWL_CRIT(trans, "Failed to alloc_pages with %s."
+                                         "Only %u free buffers remaining.\n",
+                                         priority == GFP_ATOMIC ?
+                                         "GFP_ATOMIC" : "GFP_KERNEL",
+                                         rxq->free_count);
+                        /* We don't reschedule replenish work here -- we will
+                         * call the restock method and if it still needs
+                         * more buffers it will schedule replenish */
                         return;
+                }
 
                 spin_lock(&rxq->lock);
 
@@ -393,7 +355,7 @@ static void iwl_pcie_rxq_free_rbs(struct iwl_trans *trans)
 
         lockdep_assert_held(&rxq->lock);
 
-        for (i = 0; i < RX_QUEUE_SIZE; i++) {
+        for (i = 0; i < RX_FREE_BUFFERS + RX_QUEUE_SIZE; i++) {
                 if (!rxq->pool[i].page)
                         continue;
                 dma_unmap_page(trans->dev, rxq->pool[i].page_dma,
@@ -410,144 +372,32 @@ static void iwl_pcie_rxq_free_rbs(struct iwl_trans *trans)
  * When moving to rx_free an page is allocated for the slot.
  *
  * Also restock the Rx queue via iwl_pcie_rxq_restock.
- * This is called only during initialization
+ * This is called as a scheduled work item (except for during initialization)
  */
-static void iwl_pcie_rx_replenish(struct iwl_trans *trans)
+static void iwl_pcie_rx_replenish(struct iwl_trans *trans, gfp_t gfp)
 {
-        iwl_pcie_rxq_alloc_rbs(trans);
+        iwl_pcie_rxq_alloc_rbs(trans, gfp);
 
         iwl_pcie_rxq_restock(trans);
 }
 
-/*
- * iwl_pcie_rx_allocator - Allocates pages in the background for RX queues
- *
- * Allocates for each received request 8 pages
- * Called as a scheduled work item.
- */
-static void iwl_pcie_rx_allocator(struct iwl_trans *trans)
-{
-        struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
-
-        while (atomic_read(&rba->req_pending)) {
-                int i;
-                struct list_head local_empty;
-                struct list_head local_allocated;
-
-                INIT_LIST_HEAD(&local_allocated);
-                spin_lock(&rba->lock);
-                /* swap out the entire rba->rbd_empty to a local list */
-                list_replace_init(&rba->rbd_empty, &local_empty);
-                spin_unlock(&rba->lock);
-
-                for (i = 0; i < RX_CLAIM_REQ_ALLOC;) {
-                        struct iwl_rx_mem_buffer *rxb;
-                        struct page *page;
-
-                        /* List should never be empty - each reused RBD is
-                         * returned to the list, and initial pool covers any
-                         * possible gap between the time the page is allocated
-                         * to the time the RBD is added.
-                         */
-                        BUG_ON(list_empty(&local_empty));
-                        /* Get the first rxb from the rbd list */
-                        rxb = list_first_entry(&local_empty,
-                                               struct iwl_rx_mem_buffer, list);
-                        BUG_ON(rxb->page);
-
-                        /* Alloc a new receive buffer */
-                        page = iwl_pcie_rx_alloc_page(trans);
-                        if (!page)
-                                continue;
-                        rxb->page = page;
-
-                        /* Get physical address of the RB */
-                        rxb->page_dma = dma_map_page(trans->dev, page, 0,
-                                        PAGE_SIZE << trans_pcie->rx_page_order,
-                                        DMA_FROM_DEVICE);
-                        if (dma_mapping_error(trans->dev, rxb->page_dma)) {
-                                rxb->page = NULL;
-                                __free_pages(page, trans_pcie->rx_page_order);
-                                continue;
-                        }
-                        /* dma address must be no more than 36 bits */
-                        BUG_ON(rxb->page_dma & ~DMA_BIT_MASK(36));
-                        /* and also 256 byte aligned! */
-                        BUG_ON(rxb->page_dma & DMA_BIT_MASK(8));
-
-                        /* move the allocated entry to the out list */
-                        list_move(&rxb->list, &local_allocated);
-                        i++;
-                }
-
-                spin_lock(&rba->lock);
-                /* add the allocated rbds to the allocator allocated list */
-                list_splice_tail(&local_allocated, &rba->rbd_allocated);
-                /* add the unused rbds back to the allocator empty list */
-                list_splice_tail(&local_empty, &rba->rbd_empty);
-                spin_unlock(&rba->lock);
-
-                atomic_dec(&rba->req_pending);
-                atomic_inc(&rba->req_ready);
-        }
-}
-
-/*
- * iwl_pcie_rx_allocator_get - Returns the pre-allocated pages
-.*
-.* Called by queue when the queue posted allocation request and
- * has freed 8 RBDs in order to restock itself.
- */
-static int iwl_pcie_rx_allocator_get(struct iwl_trans *trans,
-                                     struct iwl_rx_mem_buffer
-                                     *out[RX_CLAIM_REQ_ALLOC])
-{
-        struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
-        int i;
-
-        if (atomic_dec_return(&rba->req_ready) < 0) {
-                atomic_inc(&rba->req_ready);
-                IWL_DEBUG_RX(trans,
-                             "Allocation request not ready, pending requests = %d\n",
-                             atomic_read(&rba->req_pending));
-                return -ENOMEM;
-        }
-
-        spin_lock(&rba->lock);
-        for (i = 0; i < RX_CLAIM_REQ_ALLOC; i++) {
-                /* Get next free Rx buffer, remove it from free list */
-                out[i] = list_first_entry(&rba->rbd_allocated,
-                               struct iwl_rx_mem_buffer, list);
-                list_del(&out[i]->list);
-        }
-        spin_unlock(&rba->lock);
-
-        return 0;
-}
-
-static void iwl_pcie_rx_allocator_work(struct work_struct *data)
+static void iwl_pcie_rx_replenish_work(struct work_struct *data)
 {
-        struct iwl_rb_allocator *rba_p =
-                container_of(data, struct iwl_rb_allocator, rx_alloc);
         struct iwl_trans_pcie *trans_pcie =
-                container_of(rba_p, struct iwl_trans_pcie, rba);
+            container_of(data, struct iwl_trans_pcie, rx_replenish);
 
-        iwl_pcie_rx_allocator(trans_pcie->trans);
+        iwl_pcie_rx_replenish(trans_pcie->trans, GFP_KERNEL);
 }
 
 static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
 {
         struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
         struct iwl_rxq *rxq = &trans_pcie->rxq;
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
         struct device *dev = trans->dev;
 
         memset(&trans_pcie->rxq, 0, sizeof(trans_pcie->rxq));
 
         spin_lock_init(&rxq->lock);
-        spin_lock_init(&rba->lock);
 
         if (WARN_ON(rxq->bd || rxq->rb_stts))
                 return -EINVAL;
@@ -637,49 +487,15 @@ static void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
         INIT_LIST_HEAD(&rxq->rx_free);
         INIT_LIST_HEAD(&rxq->rx_used);
         rxq->free_count = 0;
-        rxq->used_count = 0;
 
-        for (i = 0; i < RX_QUEUE_SIZE; i++)
+        for (i = 0; i < RX_FREE_BUFFERS + RX_QUEUE_SIZE; i++)
                 list_add(&rxq->pool[i].list, &rxq->rx_used);
 }
 
-static void iwl_pcie_rx_init_rba(struct iwl_rb_allocator *rba)
-{
-        int i;
-
-        lockdep_assert_held(&rba->lock);
-
-        INIT_LIST_HEAD(&rba->rbd_allocated);
-        INIT_LIST_HEAD(&rba->rbd_empty);
-
-        for (i = 0; i < RX_POOL_SIZE; i++)
-                list_add(&rba->pool[i].list, &rba->rbd_empty);
-}
-
-static void iwl_pcie_rx_free_rba(struct iwl_trans *trans)
-{
-        struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
-        int i;
-
-        lockdep_assert_held(&rba->lock);
-
-        for (i = 0; i < RX_POOL_SIZE; i++) {
-                if (!rba->pool[i].page)
-                        continue;
-                dma_unmap_page(trans->dev, rba->pool[i].page_dma,
-                               PAGE_SIZE << trans_pcie->rx_page_order,
-                               DMA_FROM_DEVICE);
-                __free_pages(rba->pool[i].page, trans_pcie->rx_page_order);
-                rba->pool[i].page = NULL;
-        }
-}
-
 int iwl_pcie_rx_init(struct iwl_trans *trans)
 {
         struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
         struct iwl_rxq *rxq = &trans_pcie->rxq;
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
         int i, err;
 
         if (!rxq->bd) {
@@ -687,21 +503,11 @@ int iwl_pcie_rx_init(struct iwl_trans *trans)
                 if (err)
                         return err;
         }
-        if (!rba->alloc_wq)
-                rba->alloc_wq = alloc_workqueue("rb_allocator",
-                                                WQ_HIGHPRI | WQ_UNBOUND, 1);
-        INIT_WORK(&rba->rx_alloc, iwl_pcie_rx_allocator_work);
-
-        spin_lock(&rba->lock);
-        atomic_set(&rba->req_pending, 0);
-        atomic_set(&rba->req_ready, 0);
-        /* free all first - we might be reconfigured for a different size */
-        iwl_pcie_rx_free_rba(trans);
-        iwl_pcie_rx_init_rba(rba);
-        spin_unlock(&rba->lock);
 
         spin_lock(&rxq->lock);
 
+        INIT_WORK(&trans_pcie->rx_replenish, iwl_pcie_rx_replenish_work);
+
         /* free all first - we might be reconfigured for a different size */
         iwl_pcie_rxq_free_rbs(trans);
         iwl_pcie_rx_init_rxb_lists(rxq);
@@ -716,7 +522,7 @@ int iwl_pcie_rx_init(struct iwl_trans *trans)
         memset(rxq->rb_stts, 0, sizeof(*rxq->rb_stts));
         spin_unlock(&rxq->lock);
 
-        iwl_pcie_rx_replenish(trans);
+        iwl_pcie_rx_replenish(trans, GFP_KERNEL);
 
         iwl_pcie_rx_hw_init(trans, rxq);
 
@@ -731,7 +537,6 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
 {
         struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
         struct iwl_rxq *rxq = &trans_pcie->rxq;
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
 
         /*if rxq->bd is NULL, it means that nothing has been allocated,
          * exit now */
@@ -740,15 +545,7 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
                 return;
         }
 
-        cancel_work_sync(&rba->rx_alloc);
-        if (rba->alloc_wq) {
-                destroy_workqueue(rba->alloc_wq);
-                rba->alloc_wq = NULL;
-        }
-
-        spin_lock(&rba->lock);
-        iwl_pcie_rx_free_rba(trans);
-        spin_unlock(&rba->lock);
+        cancel_work_sync(&trans_pcie->rx_replenish);
 
         spin_lock(&rxq->lock);
         iwl_pcie_rxq_free_rbs(trans);
@@ -769,43 +566,6 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
         rxq->rb_stts = NULL;
 }
 
-/*
- * iwl_pcie_rx_reuse_rbd - Recycle used RBDs
- *
- * Called when a RBD can be reused. The RBD is transferred to the allocator.
- * When there are 2 empty RBDs - a request for allocation is posted
- */
-static void iwl_pcie_rx_reuse_rbd(struct iwl_trans *trans,
-                                  struct iwl_rx_mem_buffer *rxb,
-                                  struct iwl_rxq *rxq)
-{
-        struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-        struct iwl_rb_allocator *rba = &trans_pcie->rba;
-
-        /* Count the used RBDs */
-        rxq->used_count++;
-
-        /* Move the RBD to the used list, will be moved to allocator in batches
-         * before claiming or posting a request*/
-        list_add_tail(&rxb->list, &rxq->rx_used);
-
-        /* If we have RX_POST_REQ_ALLOC new released rx buffers -
-         * issue a request for allocator. Modulo RX_CLAIM_REQ_ALLOC is
-         * used for the case we failed to claim RX_CLAIM_REQ_ALLOC,
-         * after but we still need to post another request.
-         */
-        if ((rxq->used_count % RX_CLAIM_REQ_ALLOC) == RX_POST_REQ_ALLOC) {
-                /* Move the 2 RBDs to the allocator ownership.
-                 Allocator has another 6 from pool for the request completion*/
-                spin_lock(&rba->lock);
-                list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
-                spin_unlock(&rba->lock);
-
-                atomic_inc(&rba->req_pending);
-                queue_work(rba->alloc_wq, &rba->rx_alloc);
-        }
-}
-
 static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
                                 struct iwl_rx_mem_buffer *rxb)
 {
@@ -928,13 +688,13 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
                          */
                         __free_pages(rxb->page, trans_pcie->rx_page_order);
                         rxb->page = NULL;
-                        iwl_pcie_rx_reuse_rbd(trans, rxb, rxq);
+                        list_add_tail(&rxb->list, &rxq->rx_used);
                 } else {
                         list_add_tail(&rxb->list, &rxq->rx_free);
                         rxq->free_count++;
                 }
         } else
-                iwl_pcie_rx_reuse_rbd(trans, rxb, rxq);
+                list_add_tail(&rxb->list, &rxq->rx_used);
 }
 
 /*
@@ -944,7 +704,10 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans)
 {
         struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
         struct iwl_rxq *rxq = &trans_pcie->rxq;
-        u32 r, i, j;
+        u32 r, i;
+        u8 fill_rx = 0;
+        u32 count = 8;
+        int total_empty;
 
 restart:
         spin_lock(&rxq->lock);
@@ -957,6 +720,14 @@ restart:
         if (i == r)
                 IWL_DEBUG_RX(trans, "HW = SW = %d\n", r);
 
+        /* calculate total frames need to be restock after handling RX */
+        total_empty = r - rxq->write_actual;
+        if (total_empty < 0)
+                total_empty += RX_QUEUE_SIZE;
+
+        if (total_empty > (RX_QUEUE_SIZE / 2))
+                fill_rx = 1;
+
         while (i != r) {
                 struct iwl_rx_mem_buffer *rxb;
 
@@ -968,48 +739,29 @@ restart:
                 iwl_pcie_rx_handle_rb(trans, rxb);
 
                 i = (i + 1) & RX_QUEUE_MASK;
-
-                /* If we have RX_CLAIM_REQ_ALLOC released rx buffers -
-                 * try to claim the pre-allocated buffers from the allocator */
-                if (rxq->used_count >= RX_CLAIM_REQ_ALLOC) {
-                        struct iwl_rb_allocator *rba = &trans_pcie->rba;
-                        struct iwl_rx_mem_buffer *out[RX_CLAIM_REQ_ALLOC];
-
-                        /* Add the remaining 6 empty RBDs for allocator use */
-                        spin_lock(&rba->lock);
-                        list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
-                        spin_unlock(&rba->lock);
-
-                        /* If not ready - continue, will try to reclaim later.
-                        * No need to reschedule work - allocator exits only on
-                        * success */
-                        if (!iwl_pcie_rx_allocator_get(trans, out)) {
-                                /* If success - then RX_CLAIM_REQ_ALLOC
-                                 * buffers were retrieved and should be added
-                                 * to free list */
-                                rxq->used_count -= RX_CLAIM_REQ_ALLOC;
-                                for (j = 0; j < RX_CLAIM_REQ_ALLOC; j++) {
-                                        list_add_tail(&out[j]->list,
-                                                      &rxq->rx_free);
-                                        rxq->free_count++;
-                                }
+                /* If there are a lot of unused frames,
+                 * restock the Rx queue so ucode wont assert. */
+                if (fill_rx) {
+                        count++;
+                        if (count >= 8) {
+                                rxq->read = i;
+                                spin_unlock(&rxq->lock);
+                                iwl_pcie_rx_replenish(trans, GFP_ATOMIC);
+                                count = 0;
+                                goto restart;
                         }
                 }
-                /* handle restock for two cases:
-                * - we just pulled buffers from the allocator
-                * - we have 8+ unstolen pages accumulated */
-                if (rxq->free_count >=  RX_CLAIM_REQ_ALLOC) {
-                        rxq->read = i;
-                        spin_unlock(&rxq->lock);
-                        iwl_pcie_rxq_restock(trans);
-                        goto restart;
-                }
         }
 
         /* Backtrack one entry */
         rxq->read = i;
         spin_unlock(&rxq->lock);
 
+        if (fill_rx)
+                iwl_pcie_rx_replenish(trans, GFP_ATOMIC);
+        else
+                iwl_pcie_rxq_restock(trans);
+
         if (trans_pcie->napi.poll)
                 napi_gro_flush(&trans_pcie->napi, false);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 43ae658af6ec..9e144e71da0b 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -182,7 +182,7 @@ static void iwl_trans_pcie_write_shr(struct iwl_trans *trans, u32 reg, u32 val)
 
 static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)
 {
-        if (!trans->cfg->apmg_not_supported)
+        if (trans->cfg->apmg_not_supported)
                 return;
 
         if (vaux && pci_pme_capable(to_pci_dev(trans->dev), PCI_D3cold))
@@ -478,10 +478,16 @@ static void iwl_pcie_apm_stop(struct iwl_trans *trans, bool op_mode_leave)
                 if (trans->cfg->device_family == IWL_DEVICE_FAMILY_7000)
                         iwl_set_bits_prph(trans, APMG_PCIDEV_STT_REG,
                                           APMG_PCIDEV_STT_VAL_WAKE_ME);
-                else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
+                else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) {
+                        iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+                                    CSR_RESET_LINK_PWR_MGMT_DISABLED);
                         iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
                                     CSR_HW_IF_CONFIG_REG_PREPARE |
                                     CSR_HW_IF_CONFIG_REG_ENABLE_PME);
+                        mdelay(1);
+                        iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+                                      CSR_RESET_LINK_PWR_MGMT_DISABLED);
+                }
                 mdelay(5);
         }
 
@@ -575,6 +581,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
         if (ret >= 0)
                 return 0;
 
+        iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+                    CSR_RESET_LINK_PWR_MGMT_DISABLED);
+        msleep(1);
+
         for (iter = 0; iter < 10; iter++) {
                 /* If HW is not ready, prepare the conditions to check again */
                 iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
@@ -582,8 +592,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 
                 do {
                         ret = iwl_pcie_set_hw_ready(trans);
-                        if (ret >= 0)
-                                return 0;
+                        if (ret >= 0) {
+                                ret = 0;
+                                goto out;
+                        }
 
                         usleep_range(200, 1000);
                         t += 200;
@@ -593,6 +605,10 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 
         IWL_ERR(trans, "Couldn't prepare the card\n");
 
+out:
+        iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+                      CSR_RESET_LINK_PWR_MGMT_DISABLED);
+
         return ret;
 }
 
@@ -2459,7 +2475,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
         struct iwl_trans_pcie *trans_pcie;
         struct iwl_trans *trans;
         u16 pci_cmd;
-        int err;
+        int ret;
 
         trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
                                 &pdev->dev, cfg, &trans_ops_pcie, 0);
@@ -2474,8 +2490,8 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
         spin_lock_init(&trans_pcie->ref_lock);
         init_waitqueue_head(&trans_pcie->ucode_write_waitq);
 
-        err = pci_enable_device(pdev);
-        if (err)
+        ret = pci_enable_device(pdev);
+        if (ret)
                 goto out_no_pci;
 
         if (!cfg->base_params->pcie_l1_allowed) {
@@ -2491,23 +2507,23 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
         pci_set_master(pdev);
 
-        err = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
-        if (!err)
-                err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(36));
-        if (err) {
-                err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-                if (!err)
-                        err = pci_set_consistent_dma_mask(pdev,
+        ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
+        if (!ret)
+                ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(36));
+        if (ret) {
+                ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+                if (!ret)
+                        ret = pci_set_consistent_dma_mask(pdev,
                                                           DMA_BIT_MASK(32));
                 /* both attempts failed: */
-                if (err) {
+                if (ret) {
                         dev_err(&pdev->dev, "No suitable DMA available\n");
                         goto out_pci_disable_device;
                 }
         }
 
-        err = pci_request_regions(pdev, DRV_NAME);
-        if (err) {
+        ret = pci_request_regions(pdev, DRV_NAME);
+        if (ret) {
                 dev_err(&pdev->dev, "pci_request_regions failed\n");
                 goto out_pci_disable_device;
         }
@@ -2515,7 +2531,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
         trans_pcie->hw_base = pci_ioremap_bar(pdev, 0);
         if (!trans_pcie->hw_base) {
                 dev_err(&pdev->dev, "pci_ioremap_bar failed\n");
-                err = -ENODEV;
+                ret = -ENODEV;
                 goto out_pci_release_regions;
         }
 
@@ -2527,9 +2543,9 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
         trans_pcie->pci_dev = pdev;
         iwl_disable_interrupts(trans);
 
-        err = pci_enable_msi(pdev);
-        if (err) {
-                dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", err);
+        ret = pci_enable_msi(pdev);
+        if (ret) {
+                dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", ret);
                 /* enable rfkill interrupt: hw bug w/a */
                 pci_read_config_word(pdev, PCI_COMMAND, &pci_cmd);
                 if (pci_cmd & PCI_COMMAND_INTX_DISABLE) {
@@ -2547,11 +2563,16 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
          */
         if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) {
                 unsigned long flags;
-                int ret;
 
                 trans->hw_rev = (trans->hw_rev & 0xfff0) |
                                 (CSR_HW_REV_STEP(trans->hw_rev << 2) << 2);
 
+                ret = iwl_pcie_prepare_card_hw(trans);
+                if (ret) {
+                        IWL_WARN(trans, "Exit HW not ready\n");
+                        goto out_pci_disable_msi;
+                }
+
                 /*
                  * in-order to recognize C step driver should read chip version
                  * id located at the AUX bus MISC address space.
@@ -2591,13 +2612,14 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
         /* Initialize the wait queue for commands */
         init_waitqueue_head(&trans_pcie->wait_command_queue);
 
-        if (iwl_pcie_alloc_ict(trans))
+        ret = iwl_pcie_alloc_ict(trans);
+        if (ret)
                 goto out_pci_disable_msi;
 
-        err = request_threaded_irq(pdev->irq, iwl_pcie_isr,
+        ret = request_threaded_irq(pdev->irq, iwl_pcie_isr,
                                    iwl_pcie_irq_handler,
                                    IRQF_SHARED, DRV_NAME, trans);
-        if (err) {
+        if (ret) {
                 IWL_ERR(trans, "Error allocating IRQ %d\n", pdev->irq);
                 goto out_free_ict;
         }
@@ -2617,5 +2639,5 @@ out_pci_disable_device:
         pci_disable_device(pdev);
 out_no_pci:
         iwl_trans_free(trans);
-        return ERR_PTR(err);
+        return ERR_PTR(ret);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index 2b86c2135de3..607acb53c847 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -1875,8 +1875,19 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
         /* start timer if queue currently empty */
         if (q->read_ptr == q->write_ptr) {
-                if (txq->wd_timeout)
-                        mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
+                if (txq->wd_timeout) {
+                        /*
+                         * If the TXQ is active, then set the timer, if not,
+                         * set the timer in remainder so that the timer will
+                         * be armed with the right value when the station will
+                         * wake up.
+                         */
+                        if (!txq->frozen)
+                                mod_timer(&txq->stuck_timer,
+                                          jiffies + txq->wd_timeout);
+                        else
+                                txq->frozen_expiry_remainder = txq->wd_timeout;
+                }
                 IWL_DEBUG_RPM(trans, "Q: %d first tx - take ref\n", q->id);
                 iwl_trans_pcie_ref(trans);
         }
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
index b6cc9ff47fc2..1c6788aecc62 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
@@ -172,6 +172,7 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
                 (struct rsi_91x_sdiodev *)adapter->rsi_dev;
         u32 len;
         u32 num_blocks;
+        const u8 *fw;
         const struct firmware *fw_entry = NULL;
         u32 block_size = dev->tx_blk_size;
         int status = 0;
@@ -200,6 +201,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
                 return status;
         }
 
+        /* Copy firmware into DMA-accessible memory */
+        fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
+        if (!fw)
+                return -ENOMEM;
         len = fw_entry->size;
 
         if (len % 4)
@@ -210,7 +215,8 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
         rsi_dbg(INIT_ZONE, "%s: Instruction size:%d\n", __func__, len);
         rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks);
 
-        status = rsi_copy_to_card(common, fw_entry->data, len, num_blocks);
+        status = rsi_copy_to_card(common, fw, len, num_blocks);
+        kfree(fw);
         release_firmware(fw_entry);
         return status;
 }
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
index 1106ce76707e..30c2cf7fa93b 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
@@ -146,7 +146,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
                 return status;
         }
 
+        /* Copy firmware into DMA-accessible memory */
         fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
+        if (!fw)
+                return -ENOMEM;
         len = fw_entry->size;
 
         if (len % 4)
@@ -158,6 +161,7 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
         rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks);
 
         status = rsi_copy_to_card(common, fw, len, num_blocks);
+        kfree(fw);
         release_firmware(fw_entry);
         return status;
 }
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index 3b3a88b53b11..585d0883c7e5 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -1015,9 +1015,12 @@ static void send_beacon_frame(struct ieee80211_hw *hw,
 {
         struct rtl_priv *rtlpriv = rtl_priv(hw);
         struct sk_buff *skb = ieee80211_beacon_get(hw, vif);
+        struct rtl_tcb_desc tcb_desc;
 
-        if (skb)
-                rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, NULL);
+        if (skb) {
+                memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc));
+                rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, &tcb_desc);
+        }
 }
 
 static void rtl_op_bss_info_changed(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
index 1017f02d7bf7..7bf88d9dcdc3 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
@@ -385,6 +385,7 @@ module_param_named(debug, rtl8723be_mod_params.debug, int, 0444);
 module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444);
 module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog,
                    bool, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 1a83e190fc15..28577a31549d 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -61,6 +61,12 @@ void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
 void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
 {
         atomic_dec(&queue->inflight_packets);
+
+        /* Wake the dealloc thread _after_ decrementing inflight_packets so
+         * that if kthread_stop() has already been called, the dealloc thread
+         * does not wait forever with nothing to wake it.
+         */
+        wake_up(&queue->dealloc_wq);
 }
 
 int xenvif_schedulable(struct xenvif *vif)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 880d0d63e872..3f44b522b831 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -810,23 +810,17 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
 static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue,
                                                         struct sk_buff *skb,
                                                         struct xen_netif_tx_request *txp,
-                                                        struct gnttab_map_grant_ref *gop)
+                                                        struct gnttab_map_grant_ref *gop,
+                                                        unsigned int frag_overflow,
+                                                        struct sk_buff *nskb)
 {
         struct skb_shared_info *shinfo = skb_shinfo(skb);
         skb_frag_t *frags = shinfo->frags;
         u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
         int start;
         pending_ring_idx_t index;
-        unsigned int nr_slots, frag_overflow = 0;
+        unsigned int nr_slots;
 
-        /* At this point shinfo->nr_frags is in fact the number of
-         * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
-         */
-        if (shinfo->nr_frags > MAX_SKB_FRAGS) {
-                frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;
-                BUG_ON(frag_overflow > MAX_SKB_FRAGS);
-                shinfo->nr_frags = MAX_SKB_FRAGS;
-        }
         nr_slots = shinfo->nr_frags;
 
         /* Skip first skb fragment if it is on same page as header fragment. */
@@ -841,13 +835,6 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *que
         }
 
         if (frag_overflow) {
-                struct sk_buff *nskb = xenvif_alloc_skb(0);
-                if (unlikely(nskb == NULL)) {
-                        if (net_ratelimit())
-                                netdev_err(queue->vif->dev,
-                                           "Can't allocate the frag_list skb.\n");
-                        return NULL;
-                }
 
                 shinfo = skb_shinfo(nskb);
                 frags = shinfo->frags;
@@ -1175,9 +1162,10 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
                                      unsigned *copy_ops,
                                      unsigned *map_ops)
 {
-        struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop;
-        struct sk_buff *skb;
+        struct gnttab_map_grant_ref *gop = queue->tx_map_ops;
+        struct sk_buff *skb, *nskb;
         int ret;
+        unsigned int frag_overflow;
 
         while (skb_queue_len(&queue->tx_queue) < budget) {
                 struct xen_netif_tx_request txreq;
@@ -1265,6 +1253,29 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
                         break;
                 }
 
+                skb_shinfo(skb)->nr_frags = ret;
+                if (data_len < txreq.size)
+                        skb_shinfo(skb)->nr_frags++;
+                /* At this point shinfo->nr_frags is in fact the number of
+                 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
+                 */
+                frag_overflow = 0;
+                nskb = NULL;
+                if (skb_shinfo(skb)->nr_frags > MAX_SKB_FRAGS) {
+                        frag_overflow = skb_shinfo(skb)->nr_frags - MAX_SKB_FRAGS;
+                        BUG_ON(frag_overflow > MAX_SKB_FRAGS);
+                        skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS;
+                        nskb = xenvif_alloc_skb(0);
+                        if (unlikely(nskb == NULL)) {
+                                kfree_skb(skb);
+                                xenvif_tx_err(queue, &txreq, idx);
+                                if (net_ratelimit())
+                                        netdev_err(queue->vif->dev,
+                                                   "Can't allocate the frag_list skb.\n");
+                                break;
+                        }
+                }
+
                 if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
                         struct xen_netif_extra_info *gso;
                         gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
@@ -1272,6 +1283,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
                         if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
                                 /* Failure in xenvif_set_skb_gso is fatal. */
                                 kfree_skb(skb);
+                                kfree_skb(nskb);
                                 break;
                         }
                 }
@@ -1294,9 +1306,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
                 (*copy_ops)++;
 
-                skb_shinfo(skb)->nr_frags = ret;
                 if (data_len < txreq.size) {
-                        skb_shinfo(skb)->nr_frags++;
                         frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
                                              pending_idx);
                         xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop);
@@ -1310,13 +1320,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
                 queue->pending_cons++;
 
-                request_gop = xenvif_get_requests(queue, skb, txfrags, gop);
-                if (request_gop == NULL) {
-                        kfree_skb(skb);
-                        xenvif_tx_err(queue, &txreq, idx);
-                        break;
-                }
-                gop = request_gop;
+                gop = xenvif_get_requests(queue, skb, txfrags, gop,
+                                          frag_overflow, nskb);
 
                 __skb_queue_tail(&queue->tx_queue, skb);
 
@@ -1536,7 +1541,6 @@ void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success)
                 smp_wmb();
                 queue->dealloc_prod++;
         } while (ubuf);
-        wake_up(&queue->dealloc_wq);
         spin_unlock_irqrestore(&queue->callback_lock, flags);
 
         if (likely(zerocopy_success))
@@ -1566,13 +1570,13 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
                 smp_rmb();
 
                 while (dc != dp) {
-                        BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
+                        BUG_ON(gop - queue->tx_unmap_ops >= MAX_PENDING_REQS);
                         pending_idx =
                                 queue->dealloc_ring[pending_index(dc++)];
 
-                        pending_idx_release[gop-queue->tx_unmap_ops] =
+                        pending_idx_release[gop - queue->tx_unmap_ops] =
                                 pending_idx;
-                        queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
+                        queue->pages_to_unmap[gop - queue->tx_unmap_ops] =
                                 queue->mmap_pages[pending_idx];
                         gnttab_set_unmap_op(gop,
                                             idx_to_kaddr(queue, pending_idx),