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

Conflicts:
	drivers/net/ethernet/cavium/Kconfig

The cavium conflict was overlapping dependency
changes.

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

19 files changed, 349 insertions, 528 deletions

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 1637de6caf46..a2bb1f0934d5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -264,9 +264,9 @@ 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 6f909077b919..aeb7ce64452e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1723,6 +1723,22 @@ 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/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 358442087878..9b35d142f47a 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
 	select PHYLIB
 	select MDIO_OCTEON
 	---help---
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index ce075d11fb3f..6700dcc9960e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2778,10 +2778,11 @@ 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 36d835bd5f3c..7d178bdb112e 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 d86bc5d52246..15cc3a1f12ff 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);
@@ -2452,10 +2456,24 @@ 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;
@@ -2492,16 +2510,6 @@ 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)
@@ -2581,8 +2589,8 @@ 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);
 	}
 }
@@ -2599,13 +2607,7 @@ 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;
@@ -2621,6 +2623,14 @@ 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;
 }
@@ -3359,13 +3369,54 @@ 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);
@@ -3378,6 +3429,8 @@ 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) {
@@ -3397,7 +3450,6 @@ 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))
@@ -3482,6 +3534,31 @@ 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);
@@ -3495,6 +3572,10 @@ 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;
@@ -3685,16 +3766,6 @@ 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)
 {
@@ -3769,8 +3840,8 @@ 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);
 
@@ -3781,25 +3852,11 @@ 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 */
@@ -3820,8 +3877,12 @@ 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;
 	}
@@ -4193,15 +4254,8 @@ 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;
 }
 
@@ -4341,6 +4395,7 @@ 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);
@@ -4363,8 +4418,11 @@ 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;
 
@@ -4390,11 +4448,6 @@ 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_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d8e07bb7e601..787da8e54e99 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3438,6 +3438,7 @@ fec_probe(struct platform_device *pdev)
 
 	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);
 
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_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 555e461b0cfe..6bdc89179b72 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -902,27 +902,6 @@ 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)
 {
@@ -1272,310 +1251,6 @@ 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)
@@ -1585,11 +1260,10 @@ 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
@@ -1623,7 +1297,6 @@ 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! */
@@ -1648,17 +1321,6 @@ 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) {
@@ -1724,13 +1386,14 @@ 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/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/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 603a8b0908ee..03aabdd79abe 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/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/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index af050759eb44..cf9c0b241d07 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -4927,6 +4927,7 @@ 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 333489f0fd24..9d89bdbf029f 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
@@ -308,7 +308,7 @@ static int ipq806x_gmac_probe(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/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index a8a730641bbb..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;
 
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 29ae672917b7..1a5aca55ea9f 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
 
@@ -815,30 +816,28 @@ 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;
@@ -1021,7 +1020,7 @@ 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;
 	}
@@ -1557,8 +1556,8 @@ 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])) {
@@ -1952,14 +1951,6 @@ 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");