Backmerge tag 'v4.7' into drm-next

Linux 4.7

As requested by Daniel Vetter as the conflicts were getting messy.

64 files changed, 1181 insertions, 666 deletions

diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 30defe6..821d86c 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -3851,7 +3851,7 @@ static void et131x_tx_timeout(struct net_device *netdev)
 	unsigned long flags;
 
 	/* If the device is closed, ignore the timeout */
-	if (~(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE))
+	if (!(adapter->flags & FMP_ADAPTER_INTERRUPT_IN_USE))
 		return;
 
 	/* Any nonrecoverable hardware error?
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index e0fb0f1..20760e1 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -509,8 +509,8 @@ static int au1000_mii_probe(struct net_device *dev)
 	 * on the current MAC's MII bus
 	 */
 	for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++)
-		if (mdiobus_get_phy(aup->mii_bus, aup->phy_addr)) {
-			phydev = mdiobus_get_phy(aup->mii_bus, aup->phy_addr);
+		if (mdiobus_get_phy(aup->mii_bus, phy_addr)) {
+			phydev = mdiobus_get_phy(aup->mii_bus, phy_addr);
 			if (!aup->phy_search_highest_addr)
 				/* break out with first one found */
 				break;
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index d02c424..8fc93c5 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -96,10 +96,6 @@ struct alx_priv {
 	unsigned int rx_ringsz;
 	unsigned int rxbuf_size;
 
-	struct page  *rx_page;
-	unsigned int rx_page_offset;
-	unsigned int rx_frag_size;
-
 	struct napi_struct napi;
 	struct alx_tx_queue txq;
 	struct alx_rx_queue rxq;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c98acdc..e708e36 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -70,35 +70,6 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry)
 	}
 }
 
-static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp)
-{
-	struct sk_buff *skb;
-	struct page *page;
-
-	if (alx->rx_frag_size > PAGE_SIZE)
-		return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
-
-	page = alx->rx_page;
-	if (!page) {
-		alx->rx_page = page = alloc_page(gfp);
-		if (unlikely(!page))
-			return NULL;
-		alx->rx_page_offset = 0;
-	}
-
-	skb = build_skb(page_address(page) + alx->rx_page_offset,
-			alx->rx_frag_size);
-	if (likely(skb)) {
-		alx->rx_page_offset += alx->rx_frag_size;
-		if (alx->rx_page_offset >= PAGE_SIZE)
-			alx->rx_page = NULL;
-		else
-			get_page(page);
-	}
-	return skb;
-}
-
-
 static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
@@ -115,9 +86,22 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = alx_alloc_skb(alx, gfp);
+		/*
+		 * When DMA RX address is set to something like
+		 * 0x....fc0, it will be very likely to cause DMA
+		 * RFD overflow issue.
+		 *
+		 * To work around it, we apply rx skb with 64 bytes
+		 * longer space, and offset the address whenever
+		 * 0x....fc0 is detected.
+		 */
+		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp);
 		if (!skb)
 			break;
+
+		if (((unsigned long)skb->data & 0xfff) == 0xfc0)
+			skb_reserve(skb, 64);
+
 		dma = dma_map_single(&alx->hw.pdev->dev,
 				     skb->data, alx->rxbuf_size,
 				     DMA_FROM_DEVICE);
@@ -153,7 +137,6 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 		alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur);
 	}
 
-
 	return count;
 }
 
@@ -622,11 +605,6 @@ static void alx_free_rings(struct alx_priv *alx)
 	kfree(alx->txq.bufs);
 	kfree(alx->rxq.bufs);
 
-	if (alx->rx_page) {
-		put_page(alx->rx_page);
-		alx->rx_page = NULL;
-	}
-
 	dma_free_coherent(&alx->hw.pdev->dev,
 			  alx->descmem.size,
 			  alx->descmem.virt,
@@ -681,7 +659,6 @@ static int alx_request_irq(struct alx_priv *alx)
 				  alx->dev->name, alx);
 		if (!err)
 			goto out;
-
 		/* fall back to legacy interrupt */
 		pci_disable_msi(alx->hw.pdev);
 	}
@@ -725,7 +702,6 @@ static int alx_init_sw(struct alx_priv *alx)
 	struct pci_dev *pdev = alx->hw.pdev;
 	struct alx_hw *hw = &alx->hw;
 	int err;
-	unsigned int head_size;
 
 	err = alx_identify_hw(alx);
 	if (err) {
@@ -741,12 +717,7 @@ static int alx_init_sw(struct alx_priv *alx)
 
 	hw->smb_timer = 400;
 	hw->mtu = alx->dev->mtu;
-
 	alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu);
-	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	alx->rx_frag_size = roundup_pow_of_two(head_size);
-
 	alx->tx_ringsz = 256;
 	alx->rx_ringsz = 512;
 	hw->imt = 200;
@@ -848,7 +819,6 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 {
 	struct alx_priv *alx = netdev_priv(netdev);
 	int max_frame = ALX_MAX_FRAME_LEN(mtu);
-	unsigned int head_size;
 
 	if ((max_frame < ALX_MIN_FRAME_SIZE) ||
 	    (max_frame > ALX_MAX_FRAME_SIZE))
@@ -860,9 +830,6 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 	netdev->mtu = mtu;
 	alx->hw.mtu = mtu;
 	alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE);
-	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	alx->rx_frag_size = roundup_pow_of_two(head_size);
 	netdev_update_features(netdev);
 	if (netif_running(netdev))
 		alx_reinit(alx);
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 08a23e6..1a3555d 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -259,6 +259,7 @@ static void nb8800_receive(struct net_device *dev, unsigned int i,
 		if (err) {
 			netdev_err(dev, "rx buffer allocation failed\n");
 			dev->stats.rx_dropped++;
+			dev_kfree_skb(skb);
 			return;
 		}
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 543bf38..bfa26a2 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -392,7 +392,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		else
 			p = (char *)priv;
 		p += s->stat_offset;
-		data[i] = *(u32 *)p;
+		data[i] = *(unsigned long *)p;
 	}
 }
 
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index ee5f431..25bbae5 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -231,7 +231,7 @@ err_dma:
 	dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb),
 			 DMA_TO_DEVICE);
 
-	while (i > 0) {
+	while (i-- > 0) {
 		int index = (ring->end + i) % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[index];
 		u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1);
@@ -267,15 +267,16 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 	while (ring->start != ring->end) {
 		int slot_idx = ring->start % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[slot_idx];
-		u32 ctl1;
+		u32 ctl0, ctl1;
 		int len;
 
 		if (slot_idx == empty_slot)
 			break;
 
+		ctl0 = le32_to_cpu(ring->cpu_base[slot_idx].ctl0);
 		ctl1 = le32_to_cpu(ring->cpu_base[slot_idx].ctl1);
 		len = ctl1 & BGMAC_DESC_CTL1_LEN;
-		if (ctl1 & BGMAC_DESC_CTL0_SOF)
+		if (ctl0 & BGMAC_DESC_CTL0_SOF)
 			/* Unmap no longer used buffer */
 			dma_unmap_single(dma_dev, slot->dma_addr, len,
 					 DMA_TO_DEVICE);
@@ -1312,7 +1313,8 @@ static int bgmac_open(struct net_device *net_dev)
 
 	phy_start(bgmac->phy_dev);
 
-	netif_carrier_on(net_dev);
+	netif_start_queue(net_dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a38cb04..1b0ae4a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1591,7 +1591,7 @@ static int bnxt_get_module_eeprom(struct net_device *dev,
 {
 	struct bnxt *bp = netdev_priv(dev);
 	u16  start = eeprom->offset, length = eeprom->len;
-	int rc;
+	int rc = 0;
 
 	memset(data, 0, eeprom->len);
 
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8de79ae..0e7e7da 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2821,7 +2821,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		if (!g) {
 			netif_info(lio, tx_err, lio->netdev,
 				   "Transmit scatter gather: glist null!\n");
-			goto lio_xmit_failed;
+			goto lio_xmit_dma_failed;
 		}
 
 		cmdsetup.s.gather = 1;
@@ -2892,7 +2892,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 	else
 		status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more);
 	if (status == IQ_SEND_FAILED)
-		goto lio_xmit_failed;
+		goto lio_xmit_dma_failed;
 
 	netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n");
 
@@ -2906,12 +2906,13 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	return NETDEV_TX_OK;
 
+lio_xmit_dma_failed:
+	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
+			 ndata.datasize, DMA_TO_DEVICE);
 lio_xmit_failed:
 	stats->tx_dropped++;
 	netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n",
 		   iq_no, stats->tx_dropped);
-	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
-			 ndata.datasize, DMA_TO_DEVICE);
 	recv_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 95f17f8..16ed203 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -499,6 +499,7 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
 	u32 rr_quantum;
 	u8 sq_idx = sq->sq_num;
 	u8 pqs_vnic;
+	int svf;
 
 	if (sq->sqs_mode)
 		pqs_vnic = nic->pqs_vf[vnic];
@@ -511,10 +512,19 @@ static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic,
 	/* 24 bytes for FCS, IPG and preamble */
 	rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
 
-	tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	if (!sq->sqs_mode) {
+		tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	} else {
+		for (svf = 0; svf < MAX_SQS_PER_VF; svf++) {
+			if (nic->vf_sqs[pqs_vnic][svf] == vnic)
+				break;
+		}
+		tl4 = (MAX_LMAC_PER_BGX * NIC_TL4_PER_LMAC);
+		tl4 += (lmac * NIC_TL4_PER_LMAC * MAX_SQS_PER_VF);
+		tl4 += (svf * NIC_TL4_PER_LMAC);
+		tl4 += (bgx * NIC_TL4_PER_BGX);
+	}
 	tl4 += sq_idx;
-	if (sq->sqs_mode)
-		tl4 += vnic * 8;
 
 	tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3);
 	nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 |
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 3ed2198..63a39ac 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -551,7 +551,9 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 	}
 
 	/* Clear rcvflt bit (latching high) and read it back */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT)
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
 	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
 		dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
 		if (bgx->use_training) {
@@ -570,13 +572,6 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	/* Wait for MAC RX to be ready */
-	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
-			 SMU_RX_CTL_STATUS, true)) {
-		dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
-		return -1;
-	}
-
 	/* Wait for BGX RX to be idle */
 	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
 		dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
@@ -589,29 +584,30 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 		return -1;
 	}
 
-	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
-		dev_err(&bgx->pdev->dev, "Receive fault\n");
-		return -1;
-	}
-
-	/* Receive link is latching low. Force it high and verify it */
-	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
-	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
-			 SPU_STATUS1_RCV_LNK, false)) {
-		dev_err(&bgx->pdev->dev, "SPU receive link down\n");
-		return -1;
-	}
-
+	/* Clear receive packet disable */
 	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
 	cfg &= ~SPU_MISC_CTL_RX_DIS;
 	bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
-	return 0;
+
+	/* Check for MAC RX faults */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_CTL);
+	/* 0 - Link is okay, 1 - Local fault, 2 - Remote fault */
+	cfg &= SMU_RX_CTL_STATUS;
+	if (!cfg)
+		return 0;
+
+	/* Rx local/remote fault seen.
+	 * Do lmac reinit to see if condition recovers
+	 */
+	bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type);
+
+	return -1;
 }
 
 static void bgx_poll_for_link(struct work_struct *work)
 {
 	struct lmac *lmac;
-	u64 link;
+	u64 spu_link, smu_link;
 
 	lmac = container_of(work, struct lmac, dwork.work);
 
@@ -621,8 +617,11 @@ static void bgx_poll_for_link(struct work_struct *work)
 	bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
 		     SPU_STATUS1_RCV_LNK, false);
 
-	link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
-	if (link & SPU_STATUS1_RCV_LNK) {
+	spu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+	smu_link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SMUX_RX_CTL);
+
+	if ((spu_link & SPU_STATUS1_RCV_LNK) &&
+	    !(smu_link & SMU_RX_CTL_STATUS)) {
 		lmac->link_up = 1;
 		if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
 			lmac->last_speed = 40000;
@@ -636,9 +635,15 @@ static void bgx_poll_for_link(struct work_struct *work)
 	}
 
 	if (lmac->last_link != lmac->link_up) {
+		if (lmac->link_up) {
+			if (bgx_xaui_check_link(lmac)) {
+				/* Errors, clear link_up state */
+				lmac->link_up = 0;
+				lmac->last_speed = SPEED_UNKNOWN;
+				lmac->last_duplex = DUPLEX_UNKNOWN;
+			}
+		}
 		lmac->last_link = lmac->link_up;
-		if (lmac->link_up)
-			bgx_xaui_check_link(lmac);
 	}
 
 	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
@@ -710,7 +715,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 {
 	struct lmac *lmac;
-	u64 cmrx_cfg;
+	u64 cfg;
 
 	lmac = &bgx->lmac[lmacid];
 	if (lmac->check_link) {
@@ -719,9 +724,33 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 		destroy_workqueue(lmac->check_link);
 	}
 
-	cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
-	cmrx_cfg &= ~(1 << 15);
-	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+	/* Disable packet reception */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_RX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Give chance for Rx/Tx FIFO to get drained */
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_RX_FIFO_LEN, (u64)0x1FFF, true);
+	bgx_poll_reg(bgx, lmacid, BGX_CMRX_TX_FIFO_LEN, (u64)0x3FFF, true);
+
+	/* Disable packet transmission */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_PKT_TX_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	/* Disable serdes lanes */
+        if (!lmac->is_sgmii)
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+        else
+                bgx_reg_modify(bgx, lmacid,
+                               BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_PWR_DN);
+
+	/* Disable LMAC */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
 	if ((bgx->lmac_type != BGX_MODE_XFI) &&
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 149e179..42010d2 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -41,6 +41,7 @@
 #define BGX_CMRX_RX_STAT10		0xC0
 #define BGX_CMRX_RX_BP_DROP		0xC8
 #define BGX_CMRX_RX_DMAC_CTL		0x0E8
+#define BGX_CMRX_RX_FIFO_LEN		0x108
 #define BGX_CMR_RX_DMACX_CAM		0x200
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(x << 49)
@@ -50,6 +51,7 @@
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
 #define BGX_CMR_RX_LMACS		0x468
+#define BGX_CMRX_TX_FIFO_LEN		0x518
 #define BGX_CMRX_TX_STAT0		0x600
 #define BGX_CMRX_TX_STAT1		0x608
 #define BGX_CMRX_TX_STAT2		0x610
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index c4b262c..2accab3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x0E
-#define T4FW_VERSION_MICRO 0x04
+#define T4FW_VERSION_MINOR 0x0F
+#define T4FW_VERSION_MICRO 0x25
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x0E
-#define T5FW_VERSION_MICRO 0x04
+#define T5FW_VERSION_MINOR 0x0F
+#define T5FW_VERSION_MICRO 0x25
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x0E
-#define T6FW_VERSION_MICRO 0x04
+#define T6FW_VERSION_MINOR 0x0F
+#define T6FW_VERSION_MICRO 0x25
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 4edb98c..4466a11 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -860,6 +860,11 @@ static netdev_tx_t ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int entry;
 	void *dest;
 
+	if (skb_put_padto(skb, ETHOC_ZLEN)) {
+		dev->stats.tx_errors++;
+		goto out_no_free;
+	}
+
 	if (unlikely(skb->len > ETHOC_BUFSIZ)) {
 		dev->stats.tx_errors++;
 		goto out;
@@ -894,6 +899,7 @@ static netdev_tx_t ethoc_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 out:
 	dev_kfree_skb(skb);
+out_no_free:
 	return NETDEV_TX_OK;
 }
 
@@ -1086,7 +1092,7 @@ static int ethoc_probe(struct platform_device *pdev)
 	if (!priv->iobase) {
 		dev_err(&pdev->dev, "cannot remap I/O memory space\n");
 		ret = -ENXIO;
-		goto error;
+		goto free;
 	}
 
 	if (netdev->mem_end) {
@@ -1095,7 +1101,7 @@ static int ethoc_probe(struct platform_device *pdev)
 		if (!priv->membase) {
 			dev_err(&pdev->dev, "cannot remap memory space\n");
 			ret = -ENXIO;
-			goto error;
+			goto free;
 		}
 	} else {
 		/* Allocate buffer memory */
@@ -1106,7 +1112,7 @@ static int ethoc_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "cannot allocate %dB buffer\n",
 				buffer_size);
 			ret = -ENOMEM;
-			goto error;
+			goto free;
 		}
 		netdev->mem_end = netdev->mem_start + buffer_size;
 		priv->dma_alloc = buffer_size;
@@ -1120,7 +1126,7 @@ static int ethoc_probe(struct platform_device *pdev)
 		128, (netdev->mem_end - netdev->mem_start + 1) / ETHOC_BUFSIZ);
 	if (num_bd < 4) {
 		ret = -ENODEV;
-		goto error;
+		goto free;
 	}
 	priv->num_bd = num_bd;
 	/* num_tx must be a power of two */
@@ -1133,7 +1139,7 @@ static int ethoc_probe(struct platform_device *pdev)
 	priv->vma = devm_kzalloc(&pdev->dev, num_bd*sizeof(void *), GFP_KERNEL);
 	if (!priv->vma) {
 		ret = -ENOMEM;
-		goto error;
+		goto free;
 	}
 
 	/* Allow the platform setup code to pass in a MAC address. */
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 06f0317..9b7a3f5 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -285,6 +285,7 @@ static void nps_enet_hw_reset(struct net_device *ndev)
 	ge_rst_value |= NPS_ENET_ENABLE << RST_GMAC_0_SHIFT;
 	nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value);
 	usleep_range(10, 20);
+	ge_rst_value = 0;
 	nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst_value);
 
 	/* Tx fifo reset sequence */
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 864cb21..88f3c85 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -75,6 +75,7 @@
 #include <linux/uaccess.h>
 #include <asm/firmware.h>
 #include <linux/seq_file.h>
+#include <linux/workqueue.h>
 
 #include "ibmvnic.h"
 
@@ -89,6 +90,7 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
 static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
 static int ibmvnic_remove(struct vio_dev *);
 static void release_sub_crqs(struct ibmvnic_adapter *);
+static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *);
 static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
 static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
 static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
@@ -469,7 +471,8 @@ static int ibmvnic_open(struct net_device *netdev)
 	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP;
 	ibmvnic_send_crq(adapter, &crq);
 
-	netif_start_queue(netdev);
+	netif_tx_start_all_queues(netdev);
+
 	return 0;
 
 bounce_map_failed:
@@ -519,7 +522,7 @@ static int ibmvnic_close(struct net_device *netdev)
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_disable(&adapter->napi[i]);
 
-	netif_stop_queue(netdev);
+	netif_tx_stop_all_queues(netdev);
 
 	if (adapter->bounce_buffer) {
 		if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
@@ -1212,12 +1215,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 		goto reg_failed;
 	}
 
-	scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
-	if (scrq->irq == NO_IRQ) {
-		dev_err(dev, "Error mapping irq\n");
-		goto map_irq_failed;
-	}
-
 	scrq->adapter = adapter;
 	scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
 	scrq->cur = 0;
@@ -1230,12 +1227,6 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 
 	return scrq;
 
-map_irq_failed:
-	do {
-		rc = plpar_hcall_norets(H_FREE_SUB_CRQ,
-					adapter->vdev->unit_address,
-					scrq->crq_num);
-	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
 reg_failed:
 	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
 			 DMA_BIDIRECTIONAL);
@@ -1256,6 +1247,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter)
 			if (adapter->tx_scrq[i]) {
 				free_irq(adapter->tx_scrq[i]->irq,
 					 adapter->tx_scrq[i]);
+				irq_dispose_mapping(adapter->tx_scrq[i]->irq);
 				release_sub_crq_queue(adapter,
 						      adapter->tx_scrq[i]);
 			}
@@ -1267,6 +1259,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter)
 			if (adapter->rx_scrq[i]) {
 				free_irq(adapter->rx_scrq[i]->irq,
 					 adapter->rx_scrq[i]);
+				irq_dispose_mapping(adapter->rx_scrq[i]->irq);
 				release_sub_crq_queue(adapter,
 						      adapter->rx_scrq[i]);
 			}
@@ -1276,6 +1269,29 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter)
 	adapter->requested_caps = 0;
 }
 
+static void release_sub_crqs_no_irqs(struct ibmvnic_adapter *adapter)
+{
+	int i;
+
+	if (adapter->tx_scrq) {
+		for (i = 0; i < adapter->req_tx_queues; i++)
+			if (adapter->tx_scrq[i])
+				release_sub_crq_queue(adapter,
+						      adapter->tx_scrq[i]);
+		adapter->tx_scrq = NULL;
+	}
+
+	if (adapter->rx_scrq) {
+		for (i = 0; i < adapter->req_rx_queues; i++)
+			if (adapter->rx_scrq[i])
+				release_sub_crq_queue(adapter,
+						      adapter->rx_scrq[i]);
+		adapter->rx_scrq = NULL;
+	}
+
+	adapter->requested_caps = 0;
+}
+
 static int disable_scrq_irq(struct ibmvnic_adapter *adapter,
 			    struct ibmvnic_sub_crq_queue *scrq)
 {
@@ -1395,6 +1411,66 @@ static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance)
 	return IRQ_HANDLED;
 }
 
+static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
+{
+	struct device *dev = &adapter->vdev->dev;
+	struct ibmvnic_sub_crq_queue *scrq;
+	int i = 0, j = 0;
+	int rc = 0;
+
+	for (i = 0; i < adapter->req_tx_queues; i++) {
+		scrq = adapter->tx_scrq[i];
+		scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
+
+		if (scrq->irq == NO_IRQ) {
+			rc = -EINVAL;
+			dev_err(dev, "Error mapping irq\n");
+			goto req_tx_irq_failed;
+		}
+
+		rc = request_irq(scrq->irq, ibmvnic_interrupt_tx,
+				 0, "ibmvnic_tx", scrq);
+
+		if (rc) {
+			dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n",
+				scrq->irq, rc);
+			irq_dispose_mapping(scrq->irq);
+			goto req_rx_irq_failed;
+		}
+	}
+
+	for (i = 0; i < adapter->req_rx_queues; i++) {
+		scrq = adapter->rx_scrq[i];
+		scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
+		if (scrq->irq == NO_IRQ) {
+			rc = -EINVAL;
+			dev_err(dev, "Error mapping irq\n");
+			goto req_rx_irq_failed;
+		}
+		rc = request_irq(scrq->irq, ibmvnic_interrupt_rx,
+				 0, "ibmvnic_rx", scrq);
+		if (rc) {
+			dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n",
+				scrq->irq, rc);
+			irq_dispose_mapping(scrq->irq);
+			goto req_rx_irq_failed;
+		}
+	}
+	return rc;
+
+req_rx_irq_failed:
+	for (j = 0; j < i; j++)
+		free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
+		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+	i = adapter->req_tx_queues;
+req_tx_irq_failed:
+	for (j = 0; j < i; j++)
+		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
+		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+	release_sub_crqs_no_irqs(adapter);
+	return rc;
+}
+
 static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 {
 	struct device *dev = &adapter->vdev->dev;
@@ -1403,8 +1479,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	union ibmvnic_crq crq;
 	int total_queues;
 	int more = 0;
-	int i, j;
-	int rc;
+	int i;
 
 	if (!retry) {
 		/* Sub-CRQ entries are 32 byte long */
@@ -1483,13 +1558,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	for (i = 0; i < adapter->req_tx_queues; i++) {
 		adapter->tx_scrq[i] = allqueues[i];
 		adapter->tx_scrq[i]->pool_index = i;
-		rc = request_irq(adapter->tx_scrq[i]->irq, ibmvnic_interrupt_tx,
-				 0, "ibmvnic_tx", adapter->tx_scrq[i]);
-		if (rc) {
-			dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n",
-				adapter->tx_scrq[i]->irq, rc);
-			goto req_tx_irq_failed;
-		}
 	}
 
 	adapter->rx_scrq = kcalloc(adapter->req_rx_queues,
@@ -1500,13 +1568,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	for (i = 0; i < adapter->req_rx_queues; i++) {
 		adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues];
 		adapter->rx_scrq[i]->scrq_num = i;
-		rc = request_irq(adapter->rx_scrq[i]->irq, ibmvnic_interrupt_rx,
-				 0, "ibmvnic_rx", adapter->rx_scrq[i]);
-		if (rc) {
-			dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n",
-				adapter->rx_scrq[i]->irq, rc);
-			goto req_rx_irq_failed;
-		}
 	}
 
 	memset(&crq, 0, sizeof(crq));
@@ -1559,15 +1620,6 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 
 	return;
 
-req_rx_irq_failed:
-	for (j = 0; j < i; j++)
-		free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
-	i = adapter->req_tx_queues;
-req_tx_irq_failed:
-	for (j = 0; j < i; j++)
-		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
-	kfree(adapter->rx_scrq);
-	adapter->rx_scrq = NULL;
 rx_failed:
 	kfree(adapter->tx_scrq);
 	adapter->tx_scrq = NULL;
@@ -2121,7 +2173,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 				  struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff;
+	struct ibmvnic_error_buff *error_buff, *tmp;
 	unsigned long flags;
 	bool found = false;
 	int i;
@@ -2133,7 +2185,7 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 	}
 
 	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry(error_buff, &adapter->errors, list)
+	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
 		if (error_buff->error_id == crq->request_error_rsp.error_id) {
 			found = true;
 			list_del(&error_buff->list);
@@ -2348,9 +2400,9 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 			 *req_value,
 			 (long int)be32_to_cpu(crq->request_capability_rsp.
 					       number), name);
-		release_sub_crqs(adapter);
+		release_sub_crqs_no_irqs(adapter);
 		*req_value = be32_to_cpu(crq->request_capability_rsp.number);
-		complete(&adapter->init_done);
+		init_sub_crqs(adapter, 1);
 		return;
 	default:
 		dev_err(dev, "Error %d in request cap rsp\n",
@@ -2659,7 +2711,7 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 
 out:
 	if (atomic_read(&adapter->running_cap_queries) == 0)
-		complete(&adapter->init_done);
+		init_sub_crqs(adapter, 0);
 		/* We're done querying the capabilities, initialize sub-crqs */
 }
 
@@ -3141,14 +3193,14 @@ static void handle_request_ras_comp_num_rsp(union ibmvnic_crq *crq,
 
 static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 {
-	struct ibmvnic_inflight_cmd *inflight_cmd;
+	struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
 	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff;
+	struct ibmvnic_error_buff *error_buff, *tmp2;
 	unsigned long flags;
 	unsigned long flags2;
 
 	spin_lock_irqsave(&adapter->inflight_lock, flags);
-	list_for_each_entry(inflight_cmd, &adapter->inflight, list) {
+	list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) {
 		switch (inflight_cmd->crq.generic.cmd) {
 		case LOGIN:
 			dma_unmap_single(dev, adapter->login_buf_token,
@@ -3165,8 +3217,8 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 			break;
 		case REQUEST_ERROR_INFO:
 			spin_lock_irqsave(&adapter->error_list_lock, flags2);
-			list_for_each_entry(error_buff, &adapter->errors,
-					    list) {
+			list_for_each_entry_safe(error_buff, tmp2,
+						 &adapter->errors, list) {
 				dma_unmap_single(dev, error_buff->dma,
 						 error_buff->len,
 						 DMA_FROM_DEVICE);
@@ -3202,8 +3254,8 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			dev_info(dev, "Partner initialized\n");
 			/* Send back a response */
 			rc = ibmvnic_send_crq_init_complete(adapter);
-			if (rc == 0)
-				send_version_xchg(adapter);
+			if (!rc)
+				schedule_work(&adapter->vnic_crq_init);
 			else
 				dev_err(dev, "Can't send initrsp rc=%ld\n", rc);
 			break;
@@ -3555,8 +3607,63 @@ static const struct file_operations ibmvnic_dump_ops = {
 	.release        = single_release,
 };
 
+static void handle_crq_init_rsp(struct work_struct *work)
+{
+	struct ibmvnic_adapter *adapter = container_of(work,
+						       struct ibmvnic_adapter,
+						       vnic_crq_init);
+	struct device *dev = &adapter->vdev->dev;
+	struct net_device *netdev = adapter->netdev;
+	unsigned long timeout = msecs_to_jiffies(30000);
+	int rc;
+
+	send_version_xchg(adapter);
+	reinit_completion(&adapter->init_done);
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
+		dev_err(dev, "Passive init timeout\n");
+		goto task_failed;
+	}
+
+	do {
+		if (adapter->renegotiate) {
+			adapter->renegotiate = false;
+			release_sub_crqs_no_irqs(adapter);
+			send_cap_queries(adapter);
+
+			reinit_completion(&adapter->init_done);
+			if (!wait_for_completion_timeout(&adapter->init_done,
+							 timeout)) {
+				dev_err(dev, "Passive init timeout\n");
+				goto task_failed;
+			}
+		}
+	} while (adapter->renegotiate);
+	rc = init_sub_crq_irqs(adapter);
+
+	if (rc)
+		goto task_failed;
+
+	netdev->real_num_tx_queues = adapter->req_tx_queues;
+
+	rc = register_netdev(netdev);
+	if (rc) {
+		dev_err(dev,
+			"failed to register netdev rc=%d\n", rc);
+		goto register_failed;
+	}
+	dev_info(dev, "ibmvnic registered\n");
+
+	return;
+
+register_failed:
+	release_sub_crqs(adapter);
+task_failed:
+	dev_err(dev, "Passive initialization was not successful\n");
+}
+
 static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 {
+	unsigned long timeout = msecs_to_jiffies(30000);
 	struct ibmvnic_adapter *adapter;
 	struct net_device *netdev;
 	unsigned char *mac_addr_p;
@@ -3593,6 +3700,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	netdev->ethtool_ops = &ibmvnic_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
+	INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
+
 	spin_lock_init(&adapter->stats_lock);
 
 	rc = ibmvnic_init_crq_queue(adapter);
@@ -3635,30 +3744,26 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	ibmvnic_send_crq_init(adapter);
 
 	init_completion(&adapter->init_done);
-	wait_for_completion(&adapter->init_done);
+	if (!wait_for_completion_timeout(&adapter->init_done, timeout))
+		return 0;
 
 	do {
-		adapter->renegotiate = false;
-
-		init_sub_crqs(adapter, 0);
-		reinit_completion(&adapter->init_done);
-		wait_for_completion(&adapter->init_done);
-
 		if (adapter->renegotiate) {
-			release_sub_crqs(adapter);
+			adapter->renegotiate = false;
+			release_sub_crqs_no_irqs(adapter);
 			send_cap_queries(adapter);
 
 			reinit_completion(&adapter->init_done);
-			wait_for_completion(&adapter->init_done);
+			if (!wait_for_completion_timeout(&adapter->init_done,
+							 timeout))
+				return 0;
 		}
 	} while (adapter->renegotiate);
 
-	/* if init_sub_crqs is partially successful, retry */
-	while (!adapter->tx_scrq || !adapter->rx_scrq) {
-		init_sub_crqs(adapter, 1);
-
-		reinit_completion(&adapter->init_done);
-		wait_for_completion(&adapter->init_done);
+	rc = init_sub_crq_irqs(adapter);
+	if (rc) {
+		dev_err(&dev->dev, "failed to initialize sub crq irqs\n");
+		goto free_debugfs;
 	}
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
@@ -3666,12 +3771,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	rc = register_netdev(netdev);
 	if (rc) {
 		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
-		goto free_debugfs;
+		goto free_sub_crqs;
 	}
 	dev_info(&dev->dev, "ibmvnic registered\n");
 
 	return 0;
 
+free_sub_crqs:
+	release_sub_crqs(adapter);
 free_debugfs:
 	if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
 		debugfs_remove_recursive(adapter->debugfs_dir);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 0b66a50..e82898f 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1045,4 +1045,6 @@ struct ibmvnic_adapter {
 	u64 opt_rxba_entries_per_subcrq;
 	__be64 tx_rx_desc_req;
 	u8 map_id;
+
+	struct work_struct vnic_crq_init;
 };
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 75e6089..2b2e2f8 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2789,7 +2789,7 @@ static void e1000e_vlan_filter_enable(struct e1000_adapter *adapter)
 }
 
 /**
- * e1000e_vlan_strip_enable - helper to disable HW VLAN stripping
+ * e1000e_vlan_strip_disable - helper to disable HW VLAN stripping
  * @adapter: board private structure to initialize
  **/
 static void e1000e_vlan_strip_disable(struct e1000_adapter *adapter)
@@ -6915,6 +6915,14 @@ static netdev_features_t e1000_fix_features(struct net_device *netdev,
 	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
 		features &= ~NETIF_F_RXFCS;
 
+	/* Since there is no support for separate Rx/Tx vlan accel
+	 * enable/disable make sure Tx flag is always in same state as Rx.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	else
+		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
 	return features;
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5ea2200..501f15d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1344,6 +1344,13 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 	if (!vsi || !macaddr)
 		return NULL;
 
+	/* Do not allow broadcast filter to be added since broadcast filter
+	 * is added as part of add VSI for any newly created VSI except
+	 * FDIR VSI
+	 */
+	if (is_broadcast_ether_addr(macaddr))
+		return NULL;
+
 	f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev);
 	if (!f) {
 		f = kzalloc(sizeof(*f), GFP_ATOMIC);
@@ -2151,18 +2158,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 					 aq_ret, pf->hw.aq.asq_last_status);
 			}
 		}
-		aq_ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw,
-						   vsi->seid,
-						   cur_promisc, NULL);
-		if (aq_ret) {
-			retval = i40e_aq_rc_to_posix(aq_ret,
-						     pf->hw.aq.asq_last_status);
-			dev_info(&pf->pdev->dev,
-				 "set brdcast promisc failed, err %s, aq_err %s\n",
-				 i40e_stat_str(&pf->hw, aq_ret),
-				 i40e_aq_str(&pf->hw,
-					     pf->hw.aq.asq_last_status));
-		}
 	}
 out:
 	/* if something went wrong then set the changed flag so we try again */
@@ -7726,10 +7721,11 @@ static int i40e_init_msix(struct i40e_pf *pf)
  * i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector
  * @vsi: the VSI being configured
  * @v_idx: index of the vector in the vsi struct
+ * @cpu: cpu to be used on affinity_mask
  *
  * We allocate one q_vector.  If allocation fails we return -ENOMEM.
  **/
-static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
+static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu)
 {
 	struct i40e_q_vector *q_vector;
 
@@ -7740,7 +7736,8 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
 
 	q_vector->vsi = vsi;
 	q_vector->v_idx = v_idx;
-	cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
+	cpumask_set_cpu(cpu, &q_vector->affinity_mask);
+
 	if (vsi->netdev)
 		netif_napi_add(vsi->netdev, &q_vector->napi,
 			       i40e_napi_poll, NAPI_POLL_WEIGHT);
@@ -7764,8 +7761,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
 static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
-	int v_idx, num_q_vectors;
-	int err;
+	int err, v_idx, num_q_vectors, current_cpu;
 
 	/* if not MSIX, give the one vector only to the LAN VSI */
 	if (pf->flags & I40E_FLAG_MSIX_ENABLED)
@@ -7775,10 +7771,15 @@ static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
 	else
 		return -EINVAL;
 
+	current_cpu = cpumask_first(cpu_online_mask);
+
 	for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
-		err = i40e_vsi_alloc_q_vector(vsi, v_idx);
+		err = i40e_vsi_alloc_q_vector(vsi, v_idx, current_cpu);
 		if (err)
 			goto err_out;
+		current_cpu = cpumask_next(current_cpu, cpu_online_mask);
+		if (unlikely(current_cpu >= nr_cpu_ids))
+			current_cpu = cpumask_first(cpu_online_mask);
 	}
 
 	return 0;
@@ -9224,6 +9225,7 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi)
 static int i40e_add_vsi(struct i40e_vsi *vsi)
 {
 	int ret = -ENODEV;
+	i40e_status aq_ret = 0;
 	u8 laa_macaddr[ETH_ALEN];
 	bool found_laa_mac_filter = false;
 	struct i40e_pf *pf = vsi->back;
@@ -9413,6 +9415,18 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		vsi->seid = ctxt.seid;
 		vsi->id = ctxt.vsi_number;
 	}
+	/* Except FDIR VSI, for all othet VSI set the broadcast filter */
+	if (vsi->type != I40E_VSI_FDIR) {
+		aq_ret = i40e_aq_set_vsi_broadcast(hw, vsi->seid, true, NULL);
+		if (aq_ret) {
+			ret = i40e_aq_rc_to_posix(aq_ret,
+						  hw->aq.asq_last_status);
+			dev_info(&pf->pdev->dev,
+				 "set brdcast promisc failed, err %s, aq_err %s\n",
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+		}
+	}
 
 	spin_lock_bh(&vsi->mac_filter_list_lock);
 	/* If macvlan filters already exist, force them to get loaded */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 55f151f..a8868e1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1280,8 +1280,8 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    union i40e_rx_desc *rx_desc)
 {
 	struct i40e_rx_ptype_decoded decoded;
-	bool ipv4, ipv6, tunnel = false;
 	u32 rx_error, rx_status;
+	bool ipv4, ipv6;
 	u8 ptype;
 	u64 qword;
 
@@ -1336,19 +1336,23 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* The hardware supported by this driver does not validate outer
-	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
-	 * with it but the specification states that you "MAY validate", it
-	 * doesn't make it a hard requirement so if we have validated the
-	 * inner checksum report CHECKSUM_UNNECESSARY.
+	/* If there is an outer header present that might contain a checksum
+	 * we need to bump the checksum level by 1 to reflect the fact that
+	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP |
-				  I40E_RX_PTYPE_INNER_PROT_UDP |
-				  I40E_RX_PTYPE_INNER_PROT_SCTP))
-		tunnel = true;
-
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	skb->csum_level = tunnel ? 1 : 0;
+	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
+		skb->csum_level = 1;
+
+	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
+	switch (decoded.inner_prot) {
+	case I40E_RX_PTYPE_INNER_PROT_TCP:
+	case I40E_RX_PTYPE_INNER_PROT_UDP:
+	case I40E_RX_PTYPE_INNER_PROT_SCTP:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		/* fall though */
+	default:
+		break;
+	}
 
 	return;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index be99189..79d99cd 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -752,8 +752,8 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    union i40e_rx_desc *rx_desc)
 {
 	struct i40e_rx_ptype_decoded decoded;
-	bool ipv4, ipv6, tunnel = false;
 	u32 rx_error, rx_status;
+	bool ipv4, ipv6;
 	u8 ptype;
 	u64 qword;
 
@@ -808,19 +808,23 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* The hardware supported by this driver does not validate outer
-	 * checksums for tunneled VXLAN or GENEVE frames.  I don't agree
-	 * with it but the specification states that you "MAY validate", it
-	 * doesn't make it a hard requirement so if we have validated the
-	 * inner checksum report CHECKSUM_UNNECESSARY.
+	/* If there is an outer header present that might contain a checksum
+	 * we need to bump the checksum level by 1 to reflect the fact that
+	 * we are indicating we validated the inner checksum.
 	 */
-	if (decoded.inner_prot & (I40E_RX_PTYPE_INNER_PROT_TCP |
-				  I40E_RX_PTYPE_INNER_PROT_UDP |
-				  I40E_RX_PTYPE_INNER_PROT_SCTP))
-		tunnel = true;
-
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	skb->csum_level = tunnel ? 1 : 0;
+	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
+		skb->csum_level = 1;
+
+	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
+	switch (decoded.inner_prot) {
+	case I40E_RX_PTYPE_INNER_PROT_TCP:
+	case I40E_RX_PTYPE_INNER_PROT_UDP:
+	case I40E_RX_PTYPE_INNER_PROT_SCTP:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		/* fall though */
+	default:
+		break;
+	}
 
 	return;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 088c47c..8bebd86 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2887,7 +2887,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 	if (!test_bit(__IXGBE_DOWN, &adapter->state))
 		ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx));
 
-	return 0;
+	return min(work_done, budget - 1);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index 61a80da..2819abc 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -85,7 +85,7 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw)
 static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	if (!mbx->ops.read)
 		goto out;
@@ -111,7 +111,7 @@ out:
 static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	/* exit if either we can't write or there isn't a defined timeout */
 	if (!mbx->ops.write || !mbx->timeout)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a6d26d3..f92018b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -244,7 +244,7 @@
 /* Various constants */
 
 /* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS		1
+#define MVNETA_TXDONE_COAL_PKTS		0	/* interrupt per packet */
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
@@ -3458,6 +3458,8 @@ static int mvneta_open(struct net_device *dev)
 	return 0;
 
 err_free_irq:
+	unregister_cpu_notifier(&pp->cpu_notifier);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 4763252..d1cdc2d 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -481,20 +481,23 @@ static inline void mtk_rx_get_desc(struct mtk_rx_dma *rxd,
 /* the qdma core needs scratch memory to be setup */
 static int mtk_init_fq_dma(struct mtk_eth *eth)
 {
-	dma_addr_t phy_ring_head, phy_ring_tail;
+	dma_addr_t phy_ring_tail;
 	int cnt = MTK_DMA_SIZE;
 	dma_addr_t dma_addr;
 	int i;
 
 	eth->scratch_ring = dma_alloc_coherent(eth->dev,
 					       cnt * sizeof(struct mtk_tx_dma),
-					       &phy_ring_head,
+					       &eth->phy_scratch_ring,
 					       GFP_ATOMIC | __GFP_ZERO);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
 	eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE,
 				    GFP_KERNEL);
+	if (unlikely(!eth->scratch_head))
+		return -ENOMEM;
+
 	dma_addr = dma_map_single(eth->dev,
 				  eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE,
 				  DMA_FROM_DEVICE);
@@ -502,19 +505,19 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 		return -ENOMEM;
 
 	memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
-	phy_ring_tail = phy_ring_head +
+	phy_ring_tail = eth->phy_scratch_ring +
 			(sizeof(struct mtk_tx_dma) * (cnt - 1));
 
 	for (i = 0; i < cnt; i++) {
 		eth->scratch_ring[i].txd1 =
 					(dma_addr + (i * MTK_QDMA_PAGE_SIZE));
 		if (i < cnt - 1)
-			eth->scratch_ring[i].txd2 = (phy_ring_head +
+			eth->scratch_ring[i].txd2 = (eth->phy_scratch_ring +
 				((i + 1) * sizeof(struct mtk_tx_dma)));
 		eth->scratch_ring[i].txd3 = TX_DMA_SDL(MTK_QDMA_PAGE_SIZE);
 	}
 
-	mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD);
+	mtk_w32(eth, eth->phy_scratch_ring, MTK_QDMA_FQ_HEAD);
 	mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL);
 	mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT);
 	mtk_w32(eth, MTK_QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN);
@@ -671,7 +674,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 
 err_dma:
 	do {
-		tx_buf = mtk_desc_to_tx_buf(ring, txd);
+		tx_buf = mtk_desc_to_tx_buf(ring, itxd);
 
 		/* unmap dma */
 		mtk_tx_unmap(&dev->dev, tx_buf);
@@ -701,6 +704,20 @@ static inline int mtk_cal_txd_req(struct sk_buff *skb)
 	return nfrags;
 }
 
+static int mtk_queue_stopped(struct mtk_eth *eth)
+{
+	int i;
+
+	for (i = 0; i < MTK_MAC_COUNT; i++) {
+		if (!eth->netdev[i])
+			continue;
+		if (netif_queue_stopped(eth->netdev[i]))
+			return 1;
+	}
+
+	return 0;
+}
+
 static void mtk_wake_queue(struct mtk_eth *eth)
 {
 	int i;
@@ -766,12 +783,9 @@ static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (mtk_tx_map(skb, dev, tx_num, ring, gso) < 0)
 		goto drop;
 
-	if (unlikely(atomic_read(&ring->free_count) <= ring->thresh)) {
+	if (unlikely(atomic_read(&ring->free_count) <= ring->thresh))
 		mtk_stop_queue(eth);
-		if (unlikely(atomic_read(&ring->free_count) >
-			     ring->thresh))
-			mtk_wake_queue(eth);
-	}
+
 	spin_unlock_irqrestore(&eth->page_lock, flags);
 
 	return NETDEV_TX_OK;
@@ -826,6 +840,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 					  DMA_FROM_DEVICE);
 		if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
 			skb_free_frag(new_data);
+			netdev->stats.rx_dropped++;
 			goto release_desc;
 		}
 
@@ -833,6 +848,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		skb = build_skb(data, ring->frag_size);
 		if (unlikely(!skb)) {
 			put_page(virt_to_head_page(new_data));
+			netdev->stats.rx_dropped++;
 			goto release_desc;
 		}
 		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
@@ -921,7 +937,6 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
 		}
 		mtk_tx_unmap(eth->dev, tx_buf);
 
-		ring->last_free->txd2 = next_cpu;
 		ring->last_free = desc;
 		atomic_inc(&ring->free_count);
 
@@ -946,7 +961,8 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget, bool *tx_again)
 	if (!total)
 		return 0;
 
-	if (atomic_read(&ring->free_count) > ring->thresh)
+	if (mtk_queue_stopped(eth) &&
+	    (atomic_read(&ring->free_count) > ring->thresh))
 		mtk_wake_queue(eth);
 
 	return total;
@@ -1027,9 +1043,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 
 	atomic_set(&ring->free_count, MTK_DMA_SIZE - 2);
 	ring->next_free = &ring->dma[0];
-	ring->last_free = &ring->dma[MTK_DMA_SIZE - 2];
-	ring->thresh = max((unsigned long)MTK_DMA_SIZE >> 2,
-			      MAX_SKB_FRAGS);
+	ring->last_free = &ring->dma[MTK_DMA_SIZE - 1];
+	ring->thresh = MAX_SKB_FRAGS;
 
 	/* make sure that all changes to the dma ring are flushed before we
 	 * continue
@@ -1207,6 +1222,14 @@ static void mtk_dma_free(struct mtk_eth *eth)
 	for (i = 0; i < MTK_MAC_COUNT; i++)
 		if (eth->netdev[i])
 			netdev_reset_queue(eth->netdev[i]);
+	if (eth->scratch_ring) {
+		dma_free_coherent(eth->dev,
+				  MTK_DMA_SIZE * sizeof(struct mtk_tx_dma),
+				  eth->scratch_ring,
+				  eth->phy_scratch_ring);
+		eth->scratch_ring = NULL;
+		eth->phy_scratch_ring = 0;
+	}
 	mtk_tx_clean(eth);
 	mtk_rx_clean(eth);
 	kfree(eth->scratch_head);
@@ -1269,7 +1292,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 	mtk_w32(eth,
 		MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN |
 		MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS |
-		MTK_RX_BT_32DWORDS,
+		MTK_RX_BT_32DWORDS | MTK_NDP_CO_PRO,
 		MTK_QDMA_GLO_CFG);
 
 	return 0;
@@ -1383,7 +1406,7 @@ static int __init mtk_hw_init(struct mtk_eth *eth)
 
 	/* disable delay and normal interrupt */
 	mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
-	mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+	mtk_irq_disable(eth, ~0);
 	mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
 	mtk_w32(eth, 0, MTK_RST_GL);
 
@@ -1697,7 +1720,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
 
 	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
-	eth->netdev[id]->watchdog_timeo = HZ;
+	eth->netdev[id]->watchdog_timeo = 5 * HZ;
 	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
 	eth->netdev[id]->base_addr = (unsigned long)eth->base;
 	eth->netdev[id]->vlan_features = MTK_HW_FEATURES &
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index eed626d..a5eb7c6 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -91,6 +91,7 @@
 #define MTK_QDMA_GLO_CFG	0x1A04
 #define MTK_RX_2B_OFFSET	BIT(31)
 #define MTK_RX_BT_32DWORDS	(3 << 11)
+#define MTK_NDP_CO_PRO		BIT(10)
 #define MTK_TX_WB_DDONE		BIT(6)
 #define MTK_DMA_SIZE_16DWORDS	(2 << 4)
 #define MTK_RX_DMA_BUSY		BIT(3)
@@ -357,6 +358,7 @@ struct mtk_rx_ring {
  * @rx_ring:		Pointer to the memore holding info about the RX ring
  * @rx_napi:		The NAPI struct
  * @scratch_ring:	Newer SoCs need memory for a second HW managed TX ring
+ * @phy_scratch_ring:	physical address of scratch_ring
  * @scratch_head:	The scratch memory that scratch_ring points to.
  * @clk_ethif:		The ethif clock
  * @clk_esw:		The switch clock
@@ -384,6 +386,7 @@ struct mtk_eth {
 	struct mtk_rx_ring		rx_ring;
 	struct napi_struct		rx_napi;
 	struct mtk_tx_dma		*scratch_ring;
+	dma_addr_t			phy_scratch_ring;
 	void				*scratch_head;
 	struct clk			*clk_ethif;
 	struct clk			*clk_esw;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e94ca1c..f04a423 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2597,7 +2597,6 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	priv->cmd.free_head = 0;
 
 	sema_init(&priv->cmd.event_sem, priv->cmd.max_cmds);
-	spin_lock_init(&priv->cmd.context_lock);
 
 	for (priv->cmd.token_mask = 1;
 	     priv->cmd.token_mask < priv->cmd.max_cmds;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index fc95aff..44cf16d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1042,6 +1042,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	u32 rx_size, tx_size;
 	int port_up = 0;
 	int err = 0;
@@ -1061,22 +1063,25 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 	    tx_size == priv->tx_ring[0]->size)
 		return 0;
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	new_prof.tx_ring_size = tx_size;
+	new_prof.rx_ring_size = rx_size;
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
-	priv->prof->tx_ring_size = tx_size;
-	priv->prof->rx_ring_size = rx_size;
+	mlx4_en_safe_replace_resources(priv, tmp);
 
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
 		if (err)
@@ -1084,8 +1089,8 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 	}
 
 	err = mlx4_en_moderation_update(priv);
-
 out:
+	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
 	return err;
 }
@@ -1714,6 +1719,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	int port_up = 0;
 	int err = 0;
 
@@ -1723,23 +1730,26 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	    !channel->tx_count || !channel->rx_count)
 		return -EINVAL;
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	new_prof.num_tx_rings_p_up = channel->tx_count;
+	new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
+	new_prof.rx_ring_num = channel->rx_count;
+
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
-	priv->num_tx_rings_p_up = channel->tx_count;
-	priv->tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
-	priv->rx_ring_num = channel->rx_count;
-
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
+	mlx4_en_safe_replace_resources(priv, tmp);
 
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
@@ -1757,8 +1767,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	}
 
 	err = mlx4_en_moderation_update(priv);
-
 out:
+	kfree(tmp);
 	mutex_unlock(&mdev->state_lock);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 19ceced..8359e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -406,14 +406,18 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev,
 	mutex_lock(&mdev->state_lock);
 	if (mdev->device_up && priv->port_up) {
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
-		if (err)
+		if (err) {
 			en_err(priv, "Failed configuring VLAN filter\n");
+			goto out;
+		}
 	}
-	if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
-		en_dbg(HW, priv, "failed adding vlan %d\n", vid);
-	mutex_unlock(&mdev->state_lock);
+	err = mlx4_register_vlan(mdev->dev, priv->port, vid, &idx);
+	if (err)
+		en_dbg(HW, priv, "Failed adding vlan %d\n", vid);
 
-	return 0;
+out:
+	mutex_unlock(&mdev->state_lock);
+	return err;
 }
 
 static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
@@ -421,7 +425,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err;
+	int err = 0;
 
 	en_dbg(HW, priv, "Killing VID:%d\n", vid);
 
@@ -438,7 +442,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
 	}
 	mutex_unlock(&mdev->state_lock);
 
-	return 0;
+	return err;
 }
 
 static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
@@ -1950,7 +1954,7 @@ static int mlx4_en_close(struct net_device *dev)
 	return 0;
 }
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv)
+static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 {
 	int i;
 
@@ -1975,7 +1979,7 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 
 }
 
-int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
+static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
@@ -2032,11 +2036,91 @@ err:
 	return -ENOMEM;
 }
 
+static void mlx4_en_shutdown(struct net_device *dev)
+{
+	rtnl_lock();
+	netif_device_detach(dev);
+	mlx4_en_close(dev);
+	rtnl_unlock();
+}
+
+static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
+			     struct mlx4_en_priv *src,
+			     struct mlx4_en_port_profile *prof)
+{
+	memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config,
+	       sizeof(dst->hwtstamp_config));
+	dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up;
+	dst->tx_ring_num = prof->tx_ring_num;
+	dst->rx_ring_num = prof->rx_ring_num;
+	dst->flags = prof->flags;
+	dst->mdev = src->mdev;
+	dst->port = src->port;
+	dst->dev = src->dev;
+	dst->prof = prof;
+	dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
+					 DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
+
+	dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
+				GFP_KERNEL);
+	if (!dst->tx_ring)
+		return -ENOMEM;
+
+	dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
+			      GFP_KERNEL);
+	if (!dst->tx_cq) {
+		kfree(dst->tx_ring);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void mlx4_en_update_priv(struct mlx4_en_priv *dst,
+				struct mlx4_en_priv *src)
+{
+	memcpy(dst->rx_ring, src->rx_ring,
+	       sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num);
+	memcpy(dst->rx_cq, src->rx_cq,
+	       sizeof(struct mlx4_en_cq *) * src->rx_ring_num);
+	memcpy(&dst->hwtstamp_config, &src->hwtstamp_config,
+	       sizeof(dst->hwtstamp_config));
+	dst->tx_ring_num = src->tx_ring_num;
+	dst->rx_ring_num = src->rx_ring_num;
+	dst->tx_ring = src->tx_ring;
+	dst->tx_cq = src->tx_cq;
+	memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile));
+}
+
+int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
+				struct mlx4_en_priv *tmp,
+				struct mlx4_en_port_profile *prof)
+{
+	mlx4_en_copy_priv(tmp, priv, prof);
+
+	if (mlx4_en_alloc_resources(tmp)) {
+		en_warn(priv,
+			"%s: Resource allocation failed, using previous configuration\n",
+			__func__);
+		kfree(tmp->tx_ring);
+		kfree(tmp->tx_cq);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
+				    struct mlx4_en_priv *tmp)
+{
+	mlx4_en_free_resources(priv);
+	mlx4_en_update_priv(priv, tmp);
+}
 
 void mlx4_en_destroy_netdev(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	bool shutdown = mdev->dev->persist->interface_state &
+					    MLX4_INTERFACE_STATE_SHUTDOWN;
 
 	en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
 
@@ -2044,7 +2128,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	if (priv->registered) {
 		devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev,
 							      priv->port));
-		unregister_netdev(dev);
+		if (shutdown)
+			mlx4_en_shutdown(dev);
+		else
+			unregister_netdev(dev);
 	}
 
 	if (priv->allocated)
@@ -2064,12 +2151,17 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	mdev->upper[priv->port] = NULL;
 	mutex_unlock(&mdev->state_lock);
 
+#ifdef CONFIG_RFS_ACCEL
+	mlx4_en_cleanup_filters(priv);
+#endif
+
 	mlx4_en_free_resources(priv);
 
 	kfree(priv->tx_ring);
 	kfree(priv->tx_cq);
 
-	free_netdev(dev);
+	if (!shutdown)
+		free_netdev(dev);
 }
 
 static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
@@ -2447,9 +2539,14 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
 	 * strip that feature if this is an IPv6 encapsulated frame.
 	 */
 	if (skb->encapsulation &&
-	    (skb->ip_summed == CHECKSUM_PARTIAL) &&
-	    (ip_hdr(skb)->version != 4))
-		features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+	    (skb->ip_summed == CHECKSUM_PARTIAL)) {
+		struct mlx4_en_priv *priv = netdev_priv(dev);
+
+		if (!priv->vxlan_port ||
+		    (ip_hdr(skb)->version != 4) ||
+		    (udp_hdr(skb)->dest != priv->vxlan_port))
+			features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+	}
 
 	return features;
 }
@@ -3102,6 +3199,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_port_profile new_prof;
+	struct mlx4_en_priv *tmp;
 	int port_up = 0;
 	int err = 0;
 
@@ -3118,19 +3217,29 @@ int mlx4_en_reset_config(struct net_device *dev,
 		return -EINVAL;
 	}
 
+	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
 	mutex_lock(&mdev->state_lock);
+
+	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+	memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config));
+
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	if (err)
+		goto out;
+
 	if (priv->port_up) {
 		port_up = 1;
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	mlx4_en_free_resources(priv);
-
 	en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n",
-		ts_config.rx_filter, !!(features & NETIF_F_HW_VLAN_CTAG_RX));
+		ts_config.rx_filter,
+		!!(features & NETIF_F_HW_VLAN_CTAG_RX));
 
-	priv->hwtstamp_config.tx_type = ts_config.tx_type;
-	priv->hwtstamp_config.rx_filter = ts_config.rx_filter;
+	mlx4_en_safe_replace_resources(priv, tmp);
 
 	if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) {
 		if (features & NETIF_F_HW_VLAN_CTAG_RX)
@@ -3164,11 +3273,6 @@ int mlx4_en_reset_config(struct net_device *dev,
 		dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 	}
 
-	err = mlx4_en_alloc_resources(priv);
-	if (err) {
-		en_err(priv, "Failed reallocating port resources\n");
-		goto out;
-	}
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
 		if (err)
@@ -3177,6 +3281,8 @@ int mlx4_en_reset_config(struct net_device *dev,
 
 out:
 	mutex_unlock(&mdev->state_lock);
-	netdev_features_change(dev);
+	kfree(tmp);
+	if (!err)
+		netdev_features_change(dev);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index c1b3a9c..99b5407 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -514,9 +514,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	ring->rx_info = NULL;
 	kfree(ring);
 	*pring = NULL;
-#ifdef CONFIG_RFS_ACCEL
-	mlx4_en_cleanup_filters(priv);
-#endif
 }
 
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12c77a7..546fab0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3222,6 +3222,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
+	spin_lock_init(&priv->cmd.context_lock);
 
 	INIT_LIST_HEAD(&priv->bf_list);
 	mutex_init(&priv->bf_mutex);
@@ -4134,8 +4135,11 @@ static void mlx4_shutdown(struct pci_dev *pdev)
 
 	mlx4_info(persist->dev, "mlx4_shutdown was called\n");
 	mutex_lock(&persist->interface_state_mutex);
-	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
+	if (persist->interface_state & MLX4_INTERFACE_STATE_UP) {
+		/* Notify mlx4 clients that the kernel is being shut down */
+		persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN;
 		mlx4_unload_one(pdev);
+	}
 	mutex_unlock(&persist->interface_state_mutex);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 467d47e..13d297e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -353,12 +353,14 @@ struct mlx4_en_port_profile {
 	u32 rx_ring_num;
 	u32 tx_ring_size;
 	u32 rx_ring_size;
+	u8 num_tx_rings_p_up;
 	u8 rx_pause;
 	u8 rx_ppp;
 	u8 tx_pause;
 	u8 tx_ppp;
 	int rss_rings;
 	int inline_thold;
+	struct hwtstamp_config hwtstamp_config;
 };
 
 struct mlx4_en_profile {
@@ -623,8 +625,11 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
 			      u8 rx_ppp, u8 rx_pause,
 			      u8 tx_ppp, u8 tx_pause);
 
-void mlx4_en_free_resources(struct mlx4_en_priv *priv);
-int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
+int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
+				struct mlx4_en_priv *tmp,
+				struct mlx4_en_port_profile *prof);
+void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
+				    struct mlx4_en_priv *tmp);
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq,
 		      int entries, int ring, enum cq_type mode, int node);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index dcd2df6..d6e2a1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -295,6 +295,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_FLOW_GROUP:
 	case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_DEALLOC_FLOW_COUNTER:
+	case MLX5_CMD_OP_2ERR_QP:
+	case MLX5_CMD_OP_2RST_QP:
+	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
+	case MLX5_CMD_OP_MODIFY_FLOW_TABLE:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -321,8 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_RTR2RTS_QP:
 	case MLX5_CMD_OP_RTS2RTS_QP:
 	case MLX5_CMD_OP_SQERR2RTS_QP:
-	case MLX5_CMD_OP_2ERR_QP:
-	case MLX5_CMD_OP_2RST_QP:
 	case MLX5_CMD_OP_QUERY_QP:
 	case MLX5_CMD_OP_SQD_RTS_QP:
 	case MLX5_CMD_OP_INIT2INIT_QP:
@@ -342,7 +346,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT:
-	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_ROCE_ADDRESS:
 	case MLX5_CMD_OP_SET_ROCE_ADDRESS:
 	case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT:
@@ -390,11 +393,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_RQT:
 	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
+
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE:
 	case MLX5_CMD_OP_CREATE_FLOW_GROUP:
 	case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
@@ -545,6 +549,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_FLOW_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_FLOW_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_FLOW_COUNTER);
+	MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
 	default: return "unknown command opcode";
 	}
 }
@@ -601,11 +606,36 @@ static void dump_command(struct mlx5_core_dev *dev,
 		pr_debug("\n");
 }
 
+static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
+{
+	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
+
+	return be16_to_cpu(hdr->opcode);
+}
+
+static void cb_timeout_handler(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+						  work);
+	struct mlx5_cmd_work_ent *ent = container_of(dwork,
+						     struct mlx5_cmd_work_ent,
+						     cb_timeout_work);
+	struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
+						 cmd);
+
+	ent->ret = -ETIMEDOUT;
+	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
+		       mlx5_command_str(msg_to_opcode(ent->in)),
+		       msg_to_opcode(ent->in));
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
 	struct mlx5_cmd *cmd = ent->cmd;
 	struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
@@ -646,6 +676,9 @@ static void cmd_work_handler(struct work_struct *work)
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
 
+	if (ent->callback)
+		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -690,13 +723,6 @@ static const char *deliv_status_to_str(u8 status)
 	}
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
-
-	return be16_to_cpu(hdr->opcode);
-}
-
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -705,13 +731,13 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 
 	if (cmd->mode == CMD_MODE_POLLING) {
 		wait_for_completion(&ent->done);
-		err = ent->ret;
-	} else {
-		if (!wait_for_completion_timeout(&ent->done, timeout))
-			err = -ETIMEDOUT;
-		else
-			err = 0;
+	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
+		ent->ret = -ETIMEDOUT;
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
 	}
+
+	err = ent->ret;
+
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
@@ -760,6 +786,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (!callback)
 		init_completion(&ent->done);
 
+	INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler);
 	INIT_WORK(&ent->work, cmd_work_handler);
 	if (page_queue) {
 		cmd_work_handler(&ent->work);
@@ -769,28 +796,26 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		goto out_free;
 	}
 
-	if (!callback) {
-		err = wait_func(dev, ent);
-		if (err == -ETIMEDOUT)
-			goto out;
-
-		ds = ent->ts2 - ent->ts1;
-		op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
-		if (op < ARRAY_SIZE(cmd->stats)) {
-			stats = &cmd->stats[op];
-			spin_lock_irq(&stats->lock);
-			stats->sum += ds;
-			++stats->n;
-			spin_unlock_irq(&stats->lock);
-		}
-		mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
-				   "fw exec time for %s is %lld nsec\n",
-				   mlx5_command_str(op), ds);
-		*status = ent->status;
-		free_cmd(ent);
-	}
+	if (callback)
+		goto out;
 
-	return err;
+	err = wait_func(dev, ent);
+	if (err == -ETIMEDOUT)
+		goto out_free;
+
+	ds = ent->ts2 - ent->ts1;
+	op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
+	if (op < ARRAY_SIZE(cmd->stats)) {
+		stats = &cmd->stats[op];
+		spin_lock_irq(&stats->lock);
+		stats->sum += ds;
+		++stats->n;
+		spin_unlock_irq(&stats->lock);
+	}
+	mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
+			   "fw exec time for %s is %lld nsec\n",
+			   mlx5_command_str(op), ds);
+	*status = ent->status;
 
 out_free:
 	free_cmd(ent);
@@ -1180,41 +1205,30 @@ err_dbg:
 	return err;
 }
 
-void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
+static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		down(&cmd->sem);
-
 	down(&cmd->pages_sem);
 
-	flush_workqueue(cmd->wq);
-
-	cmd->mode = CMD_MODE_EVENTS;
+	cmd->mode = mode;
 
 	up(&cmd->pages_sem);
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		up(&cmd->sem);
 }
 
-void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd *cmd = &dev->cmd;
-	int i;
-
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-
-	down(&cmd->pages_sem);
-
-	flush_workqueue(cmd->wq);
-	cmd->mode = CMD_MODE_POLLING;
+	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
+}
 
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+{
+	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1250,6 +1264,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+			if (ent->callback)
+				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
 				sem = &cmd->pages_sem;
 			else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e8a6c33..943b1bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -145,7 +145,6 @@ struct mlx5e_umr_wqe {
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
-#define MLX5E_MIN_BW_ALLOC 1   /* Min percentage of BW allocation */
 #endif
 
 struct mlx5e_params {
@@ -191,6 +190,7 @@ struct mlx5e_tstamp {
 enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
+	MLX5E_RQ_STATE_FLUSH_TIMEOUT,
 };
 
 struct mlx5e_cq {
@@ -220,6 +220,8 @@ typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
 typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
 				  u16 ix);
 
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
@@ -241,6 +243,7 @@ struct mlx5e_rq {
 	struct mlx5e_cq        cq;
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_alloc_wqe     alloc_wqe;
+	mlx5e_fp_dealloc_wqe   dealloc_wqe;
 
 	unsigned long          state;
 	int                    ix;
@@ -305,6 +308,7 @@ struct mlx5e_sq_dma {
 enum {
 	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
 	MLX5E_SQ_STATE_BF_ENABLE,
+	MLX5E_SQ_STATE_TX_TIMEOUT,
 };
 
 struct mlx5e_ico_wqe_info {
@@ -401,7 +405,7 @@ enum mlx5e_traffic_types {
 };
 
 enum {
-	MLX5E_STATE_ASYNC_EVENTS_ENABLE,
+	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
@@ -538,6 +542,7 @@ struct mlx5e_priv {
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
+	struct work_struct         tx_timeout_work;
 	struct delayed_work        update_stats_work;
 
 	struct mlx5_core_dev      *mdev;
@@ -589,12 +594,16 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
 int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq);
 void mlx5e_complete_rx_linear_mpwqe(struct mlx5e_rq *rq,
 				    struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index b2db180..c585349 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -96,7 +96,7 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw,
 			tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
-			tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX5E_MIN_BW_ALLOC;
+			tc_tx_bw[i] = ets->tc_tx_bw[i];
 			break;
 		}
 	}
@@ -140,8 +140,12 @@ static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets)
 
 	/* Validate Bandwidth Sum */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
+			if (!ets->tc_tx_bw[i])
+				return -EINVAL;
+
 			bw_sum += ets->tc_tx_bw[i];
+		}
 	}
 
 	if (bw_sum != 0 && bw_sum != 100)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fc7dcc0..e667a87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -184,7 +184,9 @@ static unsigned long mlx5e_query_pfc_combined(struct mlx5e_priv *priv)
 #define MLX5E_NUM_SQ_STATS(priv) \
 	(NUM_SQ_STATS * priv->params.num_channels * priv->params.num_tc * \
 	 test_bit(MLX5E_STATE_OPENED, &priv->state))
-#define MLX5E_NUM_PFC_COUNTERS(priv) hweight8(mlx5e_query_pfc_combined(priv))
+#define MLX5E_NUM_PFC_COUNTERS(priv) \
+	(hweight8(mlx5e_query_pfc_combined(priv)) * \
+	 NUM_PPORT_PER_PRIO_PFC_COUNTERS)
 
 static int mlx5e_get_sset_count(struct net_device *dev, int sset)
 {
@@ -211,42 +213,41 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 
 	/* SW counters */
 	for (i = 0; i < NUM_SW_COUNTERS; i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].name);
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, sw_stats_desc[i].format);
 
 	/* Q counters */
 	for (i = 0; i < MLX5E_NUM_Q_CNTRS(priv); i++)
-		strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].name);
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format);
 
 	/* VPORT counters */
 	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       vport_stats_desc[i].name);
+		       vport_stats_desc[i].format);
 
 	/* PPORT counters */
 	for (i = 0; i < NUM_PPORT_802_3_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_802_3_stats_desc[i].name);
+		       pport_802_3_stats_desc[i].format);
 
 	for (i = 0; i < NUM_PPORT_2863_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_2863_stats_desc[i].name);
+		       pport_2863_stats_desc[i].format);
 
 	for (i = 0; i < NUM_PPORT_2819_COUNTERS; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
-		       pport_2819_stats_desc[i].name);
+		       pport_2819_stats_desc[i].format);
 
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s",
-				prio,
-				pport_per_prio_traffic_stats_desc[i].name);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_traffic_stats_desc[i].format, prio);
 	}
 
 	pfc_combined = mlx5e_query_pfc_combined(priv);
 	for_each_set_bit(prio, &pfc_combined, NUM_PPORT_PRIO) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, "prio%d_%s",
-				prio, pport_per_prio_pfc_stats_desc[i].name);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				pport_per_prio_pfc_stats_desc[i].format, prio);
 		}
 	}
 
@@ -256,16 +257,15 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 	/* per channel counters */
 	for (i = 0; i < priv->params.num_channels; i++)
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, "rx%d_%s", i,
-				rq_stats_desc[j].name);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_stats_desc[j].format, i);
 
 	for (tc = 0; tc < priv->params.num_tc; tc++)
 		for (i = 0; i < priv->params.num_channels; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				sprintf(data + (idx++) * ETH_GSTRING_LEN,
-					"tx%d_%s",
-					priv->channeltc_to_txq_map[i][tc],
-					sq_stats_desc[j].name);
+					sq_stats_desc[j].format,
+					priv->channeltc_to_txq_map[i][tc]);
 }
 
 static void mlx5e_get_strings(struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f5c8d5d..5a4d88c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,13 @@
 #include "eswitch.h"
 #include "vxlan.h"
 
+enum {
+	MLX5_EN_QP_FLUSH_TIMEOUT_MS	= 5000,
+	MLX5_EN_QP_FLUSH_MSLEEP_QUANT	= 20,
+	MLX5_EN_QP_FLUSH_MAX_ITER	= MLX5_EN_QP_FLUSH_TIMEOUT_MS /
+					  MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
+};
+
 struct mlx5e_rq_param {
 	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param       wq;
@@ -74,10 +81,13 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	port_state = mlx5_query_vport_state(mdev,
 		MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
 
-	if (port_state == VPORT_STATE_UP)
+	if (port_state == VPORT_STATE_UP) {
+		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
-	else
+	} else {
+		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);
+	}
 }
 
 static void mlx5e_update_carrier_work(struct work_struct *work)
@@ -91,6 +101,26 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
+static void mlx5e_tx_timeout_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       tx_timeout_work);
+	int err;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+	mlx5e_close_locked(priv->netdev);
+	err = mlx5e_open_locked(priv->netdev);
+	if (err)
+		netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   err);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+}
+
 static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
@@ -105,11 +135,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 
 		s->rx_packets	+= rq_stats->packets;
 		s->rx_bytes	+= rq_stats->bytes;
-		s->lro_packets	+= rq_stats->lro_packets;
-		s->lro_bytes	+= rq_stats->lro_bytes;
+		s->rx_lro_packets += rq_stats->lro_packets;
+		s->rx_lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
-		s->rx_csum_sw	+= rq_stats->csum_sw;
-		s->rx_csum_inner += rq_stats->csum_inner;
+		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
 		s->rx_mpwqe_frag   += rq_stats->mpwqe_frag;
@@ -122,24 +152,23 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
-			s->tso_packets		+= sq_stats->tso_packets;
-			s->tso_bytes		+= sq_stats->tso_bytes;
-			s->tso_inner_packets	+= sq_stats->tso_inner_packets;
-			s->tso_inner_bytes	+= sq_stats->tso_inner_bytes;
+			s->tx_tso_packets	+= sq_stats->tso_packets;
+			s->tx_tso_bytes		+= sq_stats->tso_bytes;
+			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
+			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
 			s->tx_queue_dropped	+= sq_stats->dropped;
-			s->tx_csum_inner	+= sq_stats->csum_offload_inner;
-			tx_offload_none		+= sq_stats->csum_offload_none;
+			s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
+			tx_offload_none		+= sq_stats->csum_none;
 		}
 	}
 
 	/* Update calculated offload counters */
-	s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner;
-	s->rx_csum_good    = s->rx_packets - s->rx_csum_none -
-			     s->rx_csum_sw;
+	s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner;
+	s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete;
 
-	s->link_down_events = MLX5_GET(ppcnt_reg,
+	s->link_down_events_phy = MLX5_GET(ppcnt_reg,
 				priv->stats.pport.phy_counters,
 				counter_set.phys_layer_cntrs.link_down_events);
 }
@@ -244,7 +273,7 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 {
 	struct mlx5e_priv *priv = vpriv;
 
-	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state))
+	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
 		return;
 
 	switch (event) {
@@ -260,12 +289,12 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 
 static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 {
-	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
 }
 
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
-	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
 	synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
 }
 
@@ -306,6 +335,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
 		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
 		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
@@ -321,6 +351,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
 		rq->wqe_sz = (priv->params.lro_en) ?
 				priv->params.lro_wqe_sz :
@@ -526,17 +557,25 @@ err_destroy_rq:
 
 static void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
+	int tout = 0;
+	int err;
+
 	clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
 
-	mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
-	while (!mlx5_wq_ll_is_empty(&rq->wq))
-		msleep(20);
+	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
+	while (!mlx5_wq_ll_is_empty(&rq->wq) && !err &&
+	       tout++ < MLX5_EN_QP_FLUSH_MAX_ITER)
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+
+	if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER)
+		set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state);
 
 	/* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
 	napi_synchronize(&rq->channel->napi);
 
 	mlx5e_disable_rq(rq);
+	mlx5e_free_rx_descs(rq);
 	mlx5e_destroy_rq(rq);
 }
 
@@ -580,7 +619,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c,
 	void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
 	int err;
 
-	err = mlx5_alloc_map_uar(mdev, &sq->uar, true);
+	err = mlx5_alloc_map_uar(mdev, &sq->uar, !!MLX5_CAP_GEN(mdev, bf));
 	if (err)
 		return err;
 
@@ -783,6 +822,9 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_close_sq(struct mlx5e_sq *sq)
 {
+	int tout = 0;
+	int err;
+
 	if (sq->txq) {
 		clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
 		/* prevent netif_tx_wake_queue */
@@ -793,15 +835,24 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
 		if (mlx5e_sq_has_room_for(sq, 1))
 			mlx5e_send_nop(sq, true);
 
-		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+		err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
+				      MLX5_SQC_STATE_ERR);
+		if (err)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
 	}
 
-	while (sq->cc != sq->pc) /* wait till sq is empty */
-		msleep(20);
+	/* wait till sq is empty, unless a TX timeout occurred on this SQ */
+	while (sq->cc != sq->pc &&
+	       !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+		if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+	}
 
 	/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
 	napi_synchronize(&sq->channel->napi);
 
+	mlx5e_free_tx_descs(sq);
 	mlx5e_disable_sq(sq);
 	mlx5e_destroy_sq(sq);
 }
@@ -1297,6 +1348,11 @@ static int mlx5e_open_channels(struct mlx5e_priv *priv)
 			goto err_close_channels;
 	}
 
+	/* FIXME: This is a W/A for tx timeout watch dog false alarm when
+	 * polling for inactive tx queues.
+	 */
+	netif_tx_start_all_queues(priv->netdev);
+
 	kfree(cparam);
 	return 0;
 
@@ -1316,6 +1372,12 @@ static void mlx5e_close_channels(struct mlx5e_priv *priv)
 {
 	int i;
 
+	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
+	 * polling for inactive tx queues.
+	 */
+	netif_tx_stop_all_queues(priv->netdev);
+	netif_tx_disable(priv->netdev);
+
 	for (i = 0; i < priv->params.num_channels; i++)
 		mlx5e_close_channel(priv->channel[i]);
 
@@ -1659,8 +1721,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 
 	netdev_set_num_tc(netdev, ntc);
 
+	/* Map netdev TCs to offset 0
+	 * We have our own UP to TXQ mapping for QoS
+	 */
 	for (tc = 0; tc < ntc; tc++)
-		netdev_set_tc_queue(netdev, tc, nch, tc * nch);
+		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
 int mlx5e_open_locked(struct net_device *netdev)
@@ -2591,6 +2656,29 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
+static void mlx5e_tx_timeout(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	bool sched_work = false;
+	int i;
+
+	netdev_err(dev, "TX timeout detected\n");
+
+	for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
+		struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+
+		if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
+			continue;
+		sched_work = true;
+		set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+		netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
+			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
+	}
+
+	if (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state))
+		schedule_work(&priv->tx_timeout_work);
+}
+
 static const struct net_device_ops mlx5e_netdev_ops_basic = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -2608,6 +2696,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_sriov = {
@@ -2637,6 +2726,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -2839,6 +2929,7 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 
 	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
 	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
+	INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
 	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index bd94770..9f2a16a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -212,6 +212,20 @@ err_free_skb:
 	return -ENOMEM;
 }
 
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct sk_buff *skb = rq->skb[ix];
+
+	if (skb) {
+		rq->skb[ix] = NULL;
+		dma_unmap_single(rq->pdev,
+				 *((dma_addr_t *)skb->cb),
+				 rq->wqe_sz,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb(skb);
+	}
+}
+
 static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
 {
 	return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
@@ -574,6 +588,30 @@ int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
 	return 0;
 }
 
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
+
+	wi->free_wqe(rq, wi);
+}
+
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5e_rx_wqe *wqe;
+	__be16 wqe_ix_be;
+	u16 wqe_ix;
+
+	while (!mlx5_wq_ll_is_empty(wq)) {
+		wqe_ix_be = *wq->tail_next;
+		wqe_ix    = be16_to_cpu(wqe_ix_be);
+		wqe       = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
+		rq->dealloc_wqe(rq, wqe_ix);
+		mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
+			       &wqe->next.next_wqe_index);
+	}
+}
+
 #define RQ_CANNOT_POST(rq) \
 		(!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \
 		 test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
@@ -689,7 +727,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 	if (is_first_ethertype_ip(skb)) {
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
-		rq->stats.csum_sw++;
+		rq->stats.csum_complete++;
 		return;
 	}
 
@@ -699,7 +737,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;
 			skb->encapsulation = 1;
-			rq->stats.csum_inner++;
+			rq->stats.csum_unnecessary_inner++;
 		}
 		return;
 	}
@@ -878,6 +916,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int work_done = 0;
 
+	if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state)))
+		return 0;
+
 	if (cq->decmprs_left)
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 83bc32b..fcd490c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -42,9 +42,11 @@
 	be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
 
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
+#define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
 
 struct counter_desc {
-	char		name[ETH_GSTRING_LEN];
+	char		format[ETH_GSTRING_LEN];
 	int		offset; /* Byte offset */
 };
 
@@ -53,18 +55,18 @@ struct mlx5e_sw_stats {
 	u64 rx_bytes;
 	u64 tx_packets;
 	u64 tx_bytes;
-	u64 tso_packets;
-	u64 tso_bytes;
-	u64 tso_inner_packets;
-	u64 tso_inner_bytes;
-	u64 lro_packets;
-	u64 lro_bytes;
-	u64 rx_csum_good;
+	u64 tx_tso_packets;
+	u64 tx_tso_bytes;
+	u64 tx_tso_inner_packets;
+	u64 tx_tso_inner_bytes;
+	u64 rx_lro_packets;
+	u64 rx_lro_bytes;
+	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
-	u64 rx_csum_sw;
-	u64 rx_csum_inner;
-	u64 tx_csum_offload;
-	u64 tx_csum_inner;
+	u64 rx_csum_complete;
+	u64 rx_csum_unnecessary_inner;
+	u64 tx_csum_partial;
+	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
 	u64 tx_queue_wake;
 	u64 tx_queue_dropped;
@@ -76,7 +78,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cqe_compress_pkts;
 
 	/* Special handling counters */
-	u64 link_down_events;
+	u64 link_down_events_phy;
 };
 
 static const struct counter_desc sw_stats_desc[] = {
@@ -84,18 +86,18 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tso_inner_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, lro_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_good) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_sw) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_offload) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
@@ -105,7 +107,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
 };
 
 struct mlx5e_qcounter_stats {
@@ -125,12 +127,6 @@ struct mlx5e_vport_stats {
 };
 
 static const struct counter_desc vport_stats_desc[] = {
-	{ "rx_vport_error_packets",
-		VPORT_COUNTER_OFF(received_errors.packets) },
-	{ "rx_vport_error_bytes", VPORT_COUNTER_OFF(received_errors.octets) },
-	{ "tx_vport_error_packets",
-		VPORT_COUNTER_OFF(transmit_errors.packets) },
-	{ "tx_vport_error_bytes", VPORT_COUNTER_OFF(transmit_errors.octets) },
 	{ "rx_vport_unicast_packets",
 		VPORT_COUNTER_OFF(received_eth_unicast.packets) },
 	{ "rx_vport_unicast_bytes",
@@ -192,94 +188,68 @@ struct mlx5e_pport_stats {
 };
 
 static const struct counter_desc pport_802_3_stats_desc[] = {
-	{ "frames_tx", PPORT_802_3_OFF(a_frames_transmitted_ok) },
-	{ "frames_rx", PPORT_802_3_OFF(a_frames_received_ok) },
-	{ "check_seq_err", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
-	{ "alignment_err", PPORT_802_3_OFF(a_alignment_errors) },
-	{ "octets_tx", PPORT_802_3_OFF(a_octets_transmitted_ok) },
-	{ "octets_received", PPORT_802_3_OFF(a_octets_received_ok) },
-	{ "multicast_xmitted", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
-	{ "broadcast_xmitted", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
-	{ "multicast_rx", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
-	{ "broadcast_rx", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
-	{ "in_range_len_errors", PPORT_802_3_OFF(a_in_range_length_errors) },
-	{ "out_of_range_len", PPORT_802_3_OFF(a_out_of_range_length_field) },
-	{ "too_long_errors", PPORT_802_3_OFF(a_frame_too_long_errors) },
-	{ "symbol_err", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
-	{ "mac_control_tx", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
-	{ "mac_control_rx", PPORT_802_3_OFF(a_mac_control_frames_received) },
-	{ "unsupported_op_rx",
-		PPORT_802_3_OFF(a_unsupported_opcodes_received) },
-	{ "pause_ctrl_rx", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
-	{ "pause_ctrl_tx",
-		PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
+	{ "tx_packets_phy", PPORT_802_3_OFF(a_frames_transmitted_ok) },
+	{ "rx_packets_phy", PPORT_802_3_OFF(a_frames_received_ok) },
+	{ "rx_crc_errors_phy", PPORT_802_3_OFF(a_frame_check_sequence_errors) },
+	{ "tx_bytes_phy", PPORT_802_3_OFF(a_octets_transmitted_ok) },
+	{ "rx_bytes_phy", PPORT_802_3_OFF(a_octets_received_ok) },
+	{ "tx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_xmitted_ok) },
+	{ "tx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_xmitted_ok) },
+	{ "rx_multicast_phy", PPORT_802_3_OFF(a_multicast_frames_received_ok) },
+	{ "rx_broadcast_phy", PPORT_802_3_OFF(a_broadcast_frames_received_ok) },
+	{ "rx_in_range_len_errors_phy", PPORT_802_3_OFF(a_in_range_length_errors) },
+	{ "rx_out_of_range_len_phy", PPORT_802_3_OFF(a_out_of_range_length_field) },
+	{ "rx_oversize_pkts_phy", PPORT_802_3_OFF(a_frame_too_long_errors) },
+	{ "rx_symbol_err_phy", PPORT_802_3_OFF(a_symbol_error_during_carrier) },
+	{ "tx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_transmitted) },
+	{ "rx_mac_control_phy", PPORT_802_3_OFF(a_mac_control_frames_received) },
+	{ "rx_unsupported_op_phy", PPORT_802_3_OFF(a_unsupported_opcodes_received) },
+	{ "rx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_received) },
+	{ "tx_pause_ctrl_phy", PPORT_802_3_OFF(a_pause_mac_ctrl_frames_transmitted) },
 };
 
 static const struct counter_desc pport_2863_stats_desc[] = {
-	{ "in_octets", PPORT_2863_OFF(if_in_octets) },
-	{ "in_ucast_pkts", PPORT_2863_OFF(if_in_ucast_pkts) },
-	{ "in_discards", PPORT_2863_OFF(if_in_discards) },
-	{ "in_errors", PPORT_2863_OFF(if_in_errors) },
-	{ "in_unknown_protos", PPORT_2863_OFF(if_in_unknown_protos) },
-	{ "out_octets", PPORT_2863_OFF(if_out_octets) },
-	{ "out_ucast_pkts", PPORT_2863_OFF(if_out_ucast_pkts) },
-	{ "out_discards", PPORT_2863_OFF(if_out_discards) },
-	{ "out_errors", PPORT_2863_OFF(if_out_errors) },
-	{ "in_multicast_pkts", PPORT_2863_OFF(if_in_multicast_pkts) },
-	{ "in_broadcast_pkts", PPORT_2863_OFF(if_in_broadcast_pkts) },
-	{ "out_multicast_pkts", PPORT_2863_OFF(if_out_multicast_pkts) },
-	{ "out_broadcast_pkts", PPORT_2863_OFF(if_out_broadcast_pkts) },
+	{ "rx_discards_phy", PPORT_2863_OFF(if_in_discards) },
+	{ "tx_discards_phy", PPORT_2863_OFF(if_out_discards) },
+	{ "tx_errors_phy", PPORT_2863_OFF(if_out_errors) },
 };
 
 static const struct counter_desc pport_2819_stats_desc[] = {
-	{ "drop_events", PPORT_2819_OFF(ether_stats_drop_events) },
-	{ "octets", PPORT_2819_OFF(ether_stats_octets) },
-	{ "pkts", PPORT_2819_OFF(ether_stats_pkts) },
-	{ "broadcast_pkts", PPORT_2819_OFF(ether_stats_broadcast_pkts) },
-	{ "multicast_pkts", PPORT_2819_OFF(ether_stats_multicast_pkts) },
-	{ "crc_align_errors", PPORT_2819_OFF(ether_stats_crc_align_errors) },
-	{ "undersize_pkts", PPORT_2819_OFF(ether_stats_undersize_pkts) },
-	{ "oversize_pkts", PPORT_2819_OFF(ether_stats_oversize_pkts) },
-	{ "fragments", PPORT_2819_OFF(ether_stats_fragments) },
-	{ "jabbers", PPORT_2819_OFF(ether_stats_jabbers) },
-	{ "collisions", PPORT_2819_OFF(ether_stats_collisions) },
-	{ "p64octets", PPORT_2819_OFF(ether_stats_pkts64octets) },
-	{ "p65to127octets", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
-	{ "p128to255octets", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
-	{ "p256to511octets", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
-	{ "p512to1023octets", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
-	{ "p1024to1518octets",
-		PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
-	{ "p1519to2047octets",
-		PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
-	{ "p2048to4095octets",
-		PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
-	{ "p4096to8191octets",
-		PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
-	{ "p8192to10239octets",
-		PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
+	{ "rx_undersize_pkts_phy", PPORT_2819_OFF(ether_stats_undersize_pkts) },
+	{ "rx_fragments_phy", PPORT_2819_OFF(ether_stats_fragments) },
+	{ "rx_jabbers_phy", PPORT_2819_OFF(ether_stats_jabbers) },
+	{ "rx_64_bytes_phy", PPORT_2819_OFF(ether_stats_pkts64octets) },
+	{ "rx_65_to_127_bytes_phy", PPORT_2819_OFF(ether_stats_pkts65to127octets) },
+	{ "rx_128_to_255_bytes_phy", PPORT_2819_OFF(ether_stats_pkts128to255octets) },
+	{ "rx_256_to_511_bytes_phy", PPORT_2819_OFF(ether_stats_pkts256to511octets) },
+	{ "rx_512_to_1023_bytes_phy", PPORT_2819_OFF(ether_stats_pkts512to1023octets) },
+	{ "rx_1024_to_1518_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1024to1518octets) },
+	{ "rx_1519_to_2047_bytes_phy", PPORT_2819_OFF(ether_stats_pkts1519to2047octets) },
+	{ "rx_2048_to_4095_bytes_phy", PPORT_2819_OFF(ether_stats_pkts2048to4095octets) },
+	{ "rx_4096_to_8191_bytes_phy", PPORT_2819_OFF(ether_stats_pkts4096to8191octets) },
+	{ "rx_8192_to_10239_bytes_phy", PPORT_2819_OFF(ether_stats_pkts8192to10239octets) },
 };
 
 static const struct counter_desc pport_per_prio_traffic_stats_desc[] = {
-	{ "rx_octets", PPORT_PER_PRIO_OFF(rx_octets) },
-	{ "rx_frames", PPORT_PER_PRIO_OFF(rx_frames) },
-	{ "tx_octets", PPORT_PER_PRIO_OFF(tx_octets) },
-	{ "tx_frames", PPORT_PER_PRIO_OFF(tx_frames) },
+	{ "rx_prio%d_bytes", PPORT_PER_PRIO_OFF(rx_octets) },
+	{ "rx_prio%d_packets", PPORT_PER_PRIO_OFF(rx_frames) },
+	{ "tx_prio%d_bytes", PPORT_PER_PRIO_OFF(tx_octets) },
+	{ "tx_prio%d_packets", PPORT_PER_PRIO_OFF(tx_frames) },
 };
 
 static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
-	{ "rx_pause", PPORT_PER_PRIO_OFF(rx_pause) },
-	{ "rx_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
-	{ "tx_pause", PPORT_PER_PRIO_OFF(tx_pause) },
-	{ "tx_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
-	{ "rx_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
+	{ "rx_prio%d_pause", PPORT_PER_PRIO_OFF(rx_pause) },
+	{ "rx_prio%d_pause_duration", PPORT_PER_PRIO_OFF(rx_pause_duration) },
+	{ "tx_prio%d_pause", PPORT_PER_PRIO_OFF(tx_pause) },
+	{ "tx_prio%d_pause_duration", PPORT_PER_PRIO_OFF(tx_pause_duration) },
+	{ "rx_prio%d_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
 };
 
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
-	u64 csum_sw;
-	u64 csum_inner;
+	u64 csum_complete;
+	u64 csum_unnecessary_inner;
 	u64 csum_none;
 	u64 lro_packets;
 	u64 lro_bytes;
@@ -292,19 +262,19 @@ struct mlx5e_rq_stats {
 };
 
 static const struct counter_desc rq_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_sw) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, csum_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, lro_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, mpwqe_frag) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_frag) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
 };
 
 struct mlx5e_sq_stats {
@@ -315,28 +285,28 @@ struct mlx5e_sq_stats {
 	u64 tso_bytes;
 	u64 tso_inner_packets;
 	u64 tso_inner_bytes;
-	u64 csum_offload_inner;
+	u64 csum_partial_inner;
 	u64 nop;
 	/* less likely accessed in data path */
-	u64 csum_offload_none;
+	u64 csum_none;
 	u64 stopped;
 	u64 wake;
 	u64 dropped;
 };
 
 static const struct counter_desc sq_stats_desc[] = {
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_inner) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, nop) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, csum_offload_none) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, stopped) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, wake) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sq_stats, dropped) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 };
 
 #define NUM_SW_COUNTERS			ARRAY_SIZE(sw_stats_desc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index b000ddc..5740b46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -110,8 +110,20 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
-	int up = (netdev_get_num_tc(dev) && skb_vlan_tag_present(skb)) ?
-		 skb->vlan_tci >> VLAN_PRIO_SHIFT : 0;
+	int up = 0;
+
+	if (!netdev_get_num_tc(dev))
+		return channel_ix;
+
+	if (skb_vlan_tag_present(skb))
+		up = skb->vlan_tci >> VLAN_PRIO_SHIFT;
+
+	/* channel_ix can be larger than num_channels since
+	 * dev->num_real_tx_queues = num_channels * num_tc
+	 */
+	if (channel_ix >= priv->params.num_channels)
+		channel_ix = reciprocal_scale(channel_ix,
+					      priv->params.num_channels);
 
 	return priv->channeltc_to_txq_map[channel_ix][up];
 }
@@ -123,7 +135,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 	 * headers and occur before the data gather.
 	 * Therefore these headers must be copied into the WQE
 	 */
-#define MLX5E_MIN_INLINE ETH_HLEN
+#define MLX5E_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 
 	if (bf) {
 		u16 ihs = skb_headlen(skb);
@@ -135,7 +147,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 			return skb_headlen(skb);
 	}
 
-	return MLX5E_MIN_INLINE;
+	return max(skb_network_offset(skb), MLX5E_MIN_INLINE);
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
@@ -192,12 +204,12 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		if (skb->encapsulation) {
 			eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM |
 					  MLX5_ETH_WQE_L4_INNER_CSUM;
-			sq->stats.csum_offload_inner++;
+			sq->stats.csum_partial_inner++;
 		} else {
 			eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
 		}
 	} else
-		sq->stats.csum_offload_none++;
+		sq->stats.csum_none++;
 
 	if (sq->cc != sq->prev_cc) {
 		sq->prev_cc = sq->cc;
@@ -341,6 +353,35 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return mlx5e_sq_xmit(sq, skb);
 }
 
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct sk_buff *skb;
+	u16 ci;
+	int i;
+
+	while (sq->cc != sq->pc) {
+		ci = sq->cc & sq->wq.sz_m1;
+		skb = sq->skb[ci];
+		wi = &sq->wqe_info[ci];
+
+		if (!skb) { /* nop */
+			sq->cc++;
+			continue;
+		}
+
+		for (i = 0; i < wi->num_dma; i++) {
+			struct mlx5e_sq_dma *dma =
+				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+			mlx5e_tx_dma_unmap(sq->pdev, dma);
+		}
+
+		dev_kfree_skb_any(skb);
+		sq->cc += wi->num_wqebbs;
+	}
+}
+
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq *sq;
@@ -352,6 +393,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
+	if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+		return false;
+
 	npkts = 0;
 	nbytes = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 42d16b9..96a5946 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -108,15 +108,21 @@ static int in_fatal(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev)
 {
+	mutex_lock(&dev->intf_state_mutex);
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		return;
+		goto unlock;
 
 	mlx5_core_err(dev, "start\n");
-	if (pci_channel_offline(dev->pdev) || in_fatal(dev))
+	if (pci_channel_offline(dev->pdev) || in_fatal(dev)) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		trigger_cmd_completions(dev);
+	}
 
 	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0);
 	mlx5_core_err(dev, "end\n");
+
+unlock:
+	mutex_unlock(&dev->intf_state_mutex);
 }
 
 static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
@@ -245,7 +251,6 @@ static void poll_health(unsigned long data)
 	u32 count;
 
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-		trigger_cmd_completions(dev);
 		mod_timer(&health->timer, get_next_poll_jiffies());
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a19b593..6695893 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1422,46 +1422,31 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 	mlx5_pci_err_detected(dev->pdev, 0);
 }
 
-/* wait for the device to show vital signs. For now we check
- * that we can read the device ID and that the health buffer
- * shows a non zero value which is different than 0xffffffff
+/* wait for the device to show vital signs by waiting
+ * for the health counter to start counting.
  */
-static void wait_vital(struct pci_dev *pdev)
+static int wait_vital(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	struct mlx5_core_health *health = &dev->priv.health;
 	const int niter = 100;
+	u32 last_count = 0;
 	u32 count;
-	u16 did;
 	int i;
 
-	/* Wait for firmware to be ready after reset */
-	msleep(1000);
-	for (i = 0; i < niter; i++) {
-		if (pci_read_config_word(pdev, 2, &did)) {
-			dev_warn(&pdev->dev, "failed reading config word\n");
-			break;
-		}
-		if (did == pdev->device) {
-			dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i);
-			break;
-		}
-		msleep(50);
-	}
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
-
 	for (i = 0; i < niter; i++) {
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
-			dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
-			break;
+			if (last_count && last_count != count) {
+				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				return 0;
+			}
+			last_count = count;
 		}
 		msleep(50);
 	}
 
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+	return -ETIMEDOUT;
 }
 
 static void mlx5_pci_resume(struct pci_dev *pdev)
@@ -1473,7 +1458,11 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 
 	pci_save_state(pdev);
-	wait_vital(pdev);
+	err = wait_vital(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		return;
+	}
 
 	err = mlx5_load_one(dev, priv);
 	if (err)
@@ -1508,8 +1497,9 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF},	/* ConnectX-4 VF */
 	{ PCI_VDEVICE(MELLANOX, 0x1015) },			/* ConnectX-4LX */
 	{ PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF},	/* ConnectX-4LX VF */
-	{ PCI_VDEVICE(MELLANOX, 0x1017) },			/* ConnectX-5 */
+	{ PCI_VDEVICE(MELLANOX, 0x1017) },			/* ConnectX-5, PCIe 3.0 */
 	{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 VF */
+	{ PCI_VDEVICE(MELLANOX, 0x1019) },			/* ConnectX-5, PCIe 4.0 */
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 9eeee05..32dea35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -345,7 +345,6 @@ retry:
 			       func_id, npages, err);
 		goto out_4k;
 	}
-	dev->priv.fw_pages += npages;
 
 	err = mlx5_cmd_status_to_err(&out.hdr);
 	if (err) {
@@ -373,6 +372,33 @@ out_free:
 	return err;
 }
 
+static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
+			     struct mlx5_manage_pages_inbox *in, int in_size,
+			     struct mlx5_manage_pages_outbox *out, int out_size)
+{
+	struct fw_page *fwp;
+	struct rb_node *p;
+	u32 npages;
+	u32 i = 0;
+
+	if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		return mlx5_cmd_exec_check_status(dev, (u32 *)in, in_size,
+						  (u32 *)out, out_size);
+
+	npages = be32_to_cpu(in->num_entries);
+
+	p = rb_first(&dev->priv.page_root);
+	while (p && i < npages) {
+		fwp = rb_entry(p, struct fw_page, rb_node);
+		out->pas[i] = cpu_to_be64(fwp->addr);
+		p = rb_next(p);
+		i++;
+	}
+
+	out->num_entries = cpu_to_be32(i);
+	return 0;
+}
+
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 			 int *nclaimed)
 {
@@ -398,15 +424,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	in.func_id = cpu_to_be16(func_id);
 	in.num_entries = cpu_to_be32(npages);
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
+	err = reclaim_pages_cmd(dev, &in, sizeof(in), out, outlen);
 	if (err) {
-		mlx5_core_err(dev, "failed reclaiming pages\n");
-		goto out_free;
-	}
-	dev->priv.fw_pages -= npages;
-
-	if (out->hdr.status) {
-		err = mlx5_cmd_status_to_err(&out->hdr);
+		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
 		goto out_free;
 	}
 
@@ -417,13 +437,15 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 		err = -EINVAL;
 		goto out_free;
 	}
-	if (nclaimed)
-		*nclaimed = num_claimed;
 
 	for (i = 0; i < num_claimed; i++) {
 		addr = be64_to_cpu(out->pas[i]);
 		free_4k(dev, addr);
 	}
+
+	if (nclaimed)
+		*nclaimed = num_claimed;
+
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
@@ -514,14 +536,10 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		p = rb_first(&dev->priv.page_root);
 		if (p) {
 			fwp = rb_entry(p, struct fw_page, rb_node);
-			if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-				free_4k(dev, fwp->addr);
-				nclaimed = 1;
-			} else {
-				err = reclaim_pages(dev, fwp->func_id,
-						    optimal_reclaimed_pages(),
-						    &nclaimed);
-			}
+			err = reclaim_pages(dev, fwp->func_id,
+					    optimal_reclaimed_pages(),
+					    &nclaimed);
+
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
 					       err);
@@ -536,6 +554,13 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		}
 	} while (p);
 
+	WARN(dev->priv.fw_pages,
+	     "FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.fw_pages);
+	WARN(dev->priv.vfs_pages,
+	     "VFs FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.vfs_pages);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index daf44cd..91846df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -513,7 +513,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
-	u8 *guid;
 	void *in;
 	int err;
 
@@ -535,8 +534,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
-	guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
-			    node_guid);
 	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
 
 	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index f2fd1ef..e25a73ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -72,8 +72,8 @@ static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)];
 	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)];
 
-	memset(&in, 0, sizeof(in));
-	memset(&out, 0, sizeof(out));
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
 
 	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
 		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
@@ -105,6 +105,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
+	if (mlx5e_vxlan_lookup_port(priv, port))
+		goto free_work;
+
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		goto free_work;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index ce21ee5..821a087 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -75,14 +75,14 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
 		return err;
 	}
 
 	err = mlx5_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq),
 				  &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
@@ -111,14 +111,14 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
 		return err;
 	}
 
 	err = mlx5_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq),
 				  &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
@@ -148,13 +148,14 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err);
 		return err;
 	}
 
-	err = mlx5_buf_alloc(mdev, mlx5_wq_ll_get_byte_size(wq), &wq_ctrl->buf);
+	err = mlx5_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq),
+				  &wq_ctrl->buf, param->buf_numa_node);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err);
 		goto err_db_free;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 1977e7a..57d48da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2718,7 +2718,7 @@ static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port,
  * Configures the switch priority to buffer table.
  */
 #define MLXSW_REG_PPTB_ID 0x500B
-#define MLXSW_REG_PPTB_LEN 0x0C
+#define MLXSW_REG_PPTB_LEN 0x10
 
 static const struct mlxsw_reg_info mlxsw_reg_pptb = {
 	.id = MLXSW_REG_PPTB_ID,
@@ -2784,6 +2784,13 @@ MLXSW_ITEM32(reg, pptb, pm_msb, 0x08, 24, 8);
  */
 MLXSW_ITEM32(reg, pptb, untagged_buff, 0x08, 0, 4);
 
+/* reg_pptb_prio_to_buff_msb
+ * Mapping of switch priority <i+8> to one of the allocated receive port
+ * buffers.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, pptb, prio_to_buff_msb, 0x0C, 0x04, 4);
+
 #define MLXSW_REG_PPTB_ALL_PRIO 0xFF
 
 static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port)
@@ -2792,6 +2799,14 @@ static inline void mlxsw_reg_pptb_pack(char *payload, u8 local_port)
 	mlxsw_reg_pptb_mm_set(payload, MLXSW_REG_PPTB_MM_UM);
 	mlxsw_reg_pptb_local_port_set(payload, local_port);
 	mlxsw_reg_pptb_pm_set(payload, MLXSW_REG_PPTB_ALL_PRIO);
+	mlxsw_reg_pptb_pm_msb_set(payload, MLXSW_REG_PPTB_ALL_PRIO);
+}
+
+static inline void mlxsw_reg_pptb_prio_to_buff_pack(char *payload, u8 prio,
+						    u8 buff)
+{
+	mlxsw_reg_pptb_prio_to_buff_set(payload, prio, buff);
+	mlxsw_reg_pptb_prio_to_buff_msb_set(payload, prio, buff);
 }
 
 /* PBMC - Port Buffer Management Control Register
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 6f9e3dd..3740800 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -171,23 +171,6 @@ static int mlxsw_sp_port_admin_status_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(paos), paos_pl);
 }
 
-static int mlxsw_sp_port_oper_status_get(struct mlxsw_sp_port *mlxsw_sp_port,
-					 bool *p_is_up)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char paos_pl[MLXSW_REG_PAOS_LEN];
-	u8 oper_status;
-	int err;
-
-	mlxsw_reg_paos_pack(paos_pl, mlxsw_sp_port->local_port, 0);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(paos), paos_pl);
-	if (err)
-		return err;
-	oper_status = mlxsw_reg_paos_oper_status_get(paos_pl);
-	*p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP ? true : false;
-	return 0;
-}
-
 static int mlxsw_sp_port_dev_addr_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				      unsigned char *addr)
 {
@@ -408,7 +391,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	}
 
 	mlxsw_sp_txhdr_construct(skb, &tx_info);
-	len = skb->len;
+	/* TX header is consumed by HW on the way so we shouldn't count its
+	 * bytes as being sent.
+	 */
+	len = skb->len - MLXSW_TXHDR_LEN;
+
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
@@ -1430,7 +1417,8 @@ static int mlxsw_sp_port_get_settings(struct net_device *dev,
 
 	cmd->supported = mlxsw_sp_from_ptys_supported_port(eth_proto_cap) |
 			 mlxsw_sp_from_ptys_supported_link(eth_proto_cap) |
-			 SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+			 SUPPORTED_Pause | SUPPORTED_Asym_Pause |
+			 SUPPORTED_Autoneg;
 	cmd->advertising = mlxsw_sp_from_ptys_advert_link(eth_proto_admin);
 	mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev),
 					eth_proto_oper, cmd);
@@ -1489,7 +1477,6 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
 	u32 eth_proto_new;
 	u32 eth_proto_cap;
 	u32 eth_proto_admin;
-	bool is_up;
 	int err;
 
 	speed = ethtool_cmd_speed(cmd);
@@ -1521,12 +1508,7 @@ static int mlxsw_sp_port_set_settings(struct net_device *dev,
 		return err;
 	}
 
-	err = mlxsw_sp_port_oper_status_get(mlxsw_sp_port, &is_up);
-	if (err) {
-		netdev_err(dev, "Failed to get oper status");
-		return err;
-	}
-	if (!is_up)
+	if (!netif_running(dev))
 		return 0;
 
 	err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index a3720a0..074cdda 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -194,7 +194,7 @@ static int mlxsw_sp_port_pb_prio_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 	mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port);
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		mlxsw_reg_pptb_prio_to_buff_set(pptb_pl, i, 0);
+		mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, 0);
 	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb),
 			       pptb_pl);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index 0b32366..01cfb75 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -103,7 +103,8 @@ static int mlxsw_sp_port_pg_prio_map(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	mlxsw_reg_pptb_pack(pptb_pl, mlxsw_sp_port->local_port);
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
-		mlxsw_reg_pptb_prio_to_buff_set(pptb_pl, i, prio_tc[i]);
+		mlxsw_reg_pptb_prio_to_buff_pack(pptb_pl, i, prio_tc[i]);
+
 	return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pptb),
 			       pptb_pl);
 }
@@ -249,6 +250,7 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev,
 		return err;
 
 	memcpy(mlxsw_sp_port->dcb.ets, ets, sizeof(*ets));
+	mlxsw_sp_port->dcb.ets->ets_cap = IEEE_8021QAZ_MAX_TCS;
 
 	return 0;
 }
@@ -351,7 +353,8 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev,
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	int err;
 
-	if (mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) {
+	if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) &&
+	    pfc->pfc_en) {
 		netdev_err(dev, "PAUSE frames already enabled on port\n");
 		return -EINVAL;
 	}
@@ -371,6 +374,7 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev,
 	}
 
 	memcpy(mlxsw_sp_port->dcb.pfc, pfc, sizeof(*pfc));
+	mlxsw_sp_port->dcb.pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 3842eab..25f658b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -316,7 +316,10 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 		}
 	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
-	len = skb->len;
+	/* TX header is consumed by HW on the way so we shouldn't count its
+	 * bytes as being sent.
+	 */
+	len = skb->len - MLXSW_TXHDR_LEN;
 	/* Due to a race we might fail here because of a full queue. In that
 	 * unlikely case we simply drop the packet.
 	 */
diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c
index 7066954..0a26b11 100644
--- a/drivers/net/ethernet/microchip/enc28j60.c
+++ b/drivers/net/ethernet/microchip/enc28j60.c
@@ -1151,7 +1151,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 			enc28j60_phy_read(priv, PHIR);
 		}
 		/* TX complete handler */
-		if ((intflags & EIR_TXIF) != 0) {
+		if (((intflags & EIR_TXIF) != 0) &&
+		    ((intflags & EIR_TXERIF) == 0)) {
 			bool err = false;
 			loop++;
 			if (netif_msg_intr(priv))
@@ -1203,7 +1204,7 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 					enc28j60_tx_clear(ndev, true);
 			} else
 				enc28j60_tx_clear(ndev, true);
-			locked_reg_bfclr(priv, EIR, EIR_TXERIF);
+			locked_reg_bfclr(priv, EIR, EIR_TXERIF | EIR_TXIF);
 		}
 		/* RX Error handler */
 		if ((intflags & EIR_RXERIF) != 0) {
@@ -1238,6 +1239,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
  */
 static void enc28j60_hw_tx(struct enc28j60_net *priv)
 {
+	BUG_ON(!priv->tx_skb);
+
 	if (netif_msg_tx_queued(priv))
 		printk(KERN_DEBUG DRV_NAME
 			": Tx Packet Len:%d\n", priv->tx_skb->len);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index fa47c14..ba26bb3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2015,7 +2015,7 @@ static void nfp_net_open_stack(struct nfp_net *nn)
 
 	netif_tx_wake_all_queues(nn->netdev);
 
-	enable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	enable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 	nfp_net_read_link_status(nn);
 }
 
@@ -2044,7 +2044,7 @@ static int nfp_net_netdev_open(struct net_device *netdev)
 				      NFP_NET_IRQ_LSC_IDX, nn->lsc_handler);
 	if (err)
 		goto err_free_exn;
-	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 
 	nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings),
 			       GFP_KERNEL);
@@ -2133,7 +2133,7 @@ static void nfp_net_close_stack(struct nfp_net *nn)
 {
 	unsigned int r;
 
-	disable_irq(nn->irq_entries[NFP_NET_CFG_LSC].vector);
+	disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
 	netif_carrier_off(nn->netdev);
 	nn->link_up = false;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 9afc15f..e29ed5a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -3700,6 +3700,7 @@ struct public_port {
 #define MEDIA_DA_TWINAX         0x3
 #define MEDIA_BASE_T            0x4
 #define MEDIA_SFP_1G_FIBER      0x5
+#define MEDIA_MODULE_FIBER      0x6
 #define MEDIA_KR                0xf0
 #define MEDIA_NOT_PRESENT       0xff
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 8fba87dd..aada4c7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -72,6 +72,7 @@ int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn,
 	p_ramrod->mtu			= cpu_to_le16(p_params->mtu);
 	p_ramrod->inner_vlan_removal_en	= p_params->remove_inner_vlan;
 	p_ramrod->drop_ttl0_en		= p_params->drop_ttl0;
+	p_ramrod->untagged		= p_params->only_untagged;
 
 	SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_UCAST_DROP_ALL, 1);
 	SET_FIELD(rx_mode, ETH_VPORT_RX_MODE_MCAST_DROP_ALL, 1);
@@ -247,10 +248,6 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn,
 		SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_DROP_ALL,
 			  !!(accept_filter & QED_ACCEPT_NONE));
 
-		SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL,
-			  (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) &&
-			   !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED)));
-
 		SET_FIELD(state, ETH_VPORT_TX_MODE_MCAST_DROP_ALL,
 			  !!(accept_filter & QED_ACCEPT_NONE));
 
@@ -1748,7 +1745,8 @@ static int qed_start_vport(struct qed_dev *cdev,
 			   start.vport_id, start.mtu);
 	}
 
-	qed_reset_vport_stats(cdev);
+	if (params->clear_stats)
+		qed_reset_vport_stats(cdev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 61cc686..c7e01b3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1085,6 +1085,7 @@ static int qed_get_port_type(u32 media_type)
 	case MEDIA_SFPP_10G_FIBER:
 	case MEDIA_SFP_1G_FIBER:
 	case MEDIA_XFP_FIBER:
+	case MEDIA_MODULE_FIBER:
 	case MEDIA_KR:
 		port_type = PORT_FIBRE;
 		break;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index acac662..b122f60 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -213,19 +213,15 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 	SET_FIELD(db.params, CORE_DB_DATA_AGG_VAL_SEL,
 		  DQ_XCM_CORE_SPQ_PROD_CMD);
 	db.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
-
-	/* validate producer is up to-date */
-	rmb();
-
 	db.spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
 
-	/* do not reorder */
-	barrier();
+	/* make sure the SPQE is updated before the doorbell */
+	wmb();
 
 	DOORBELL(p_hwfn, qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY), *(u32 *)&db);
 
 	/* make sure doorbell is rang */
-	mmiowb();
+	wmb();
 
 	DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
 		   "Doorbelled [0x%08x, CID 0x%08x] with Flags: %02x agg_params: %02x, prod: %04x\n",
@@ -614,7 +610,9 @@ qed_spq_add_entry(struct qed_hwfn *p_hwfn,
 
 			*p_en2 = *p_ent;
 
-			kfree(p_ent);
+			/* EBLOCK responsible to free the allocated p_ent */
+			if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK)
+				kfree(p_ent);
 
 			p_ent = p_en2;
 		}
@@ -749,6 +747,15 @@ int qed_spq_post(struct qed_hwfn *p_hwfn,
 		 * Thus, after gaining the answer perform the cleanup here.
 		 */
 		rc = qed_spq_block(p_hwfn, p_ent, fw_return_code);
+
+		if (p_ent->queue == &p_spq->unlimited_pending) {
+			/* This is an allocated p_ent which does not need to
+			 * return to pool.
+			 */
+			kfree(p_ent);
+			return rc;
+		}
+
 		if (rc)
 			goto spq_post_fail2;
 
@@ -844,8 +851,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 		found->comp_cb.function(p_hwfn, found->comp_cb.cookie, p_data,
 					fw_return_code);
 
-	if (found->comp_mode != QED_SPQ_MODE_EBLOCK)
-		/* EBLOCK is responsible for freeing its own entry */
+	if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) ||
+	    (found->queue == &p_spq->unlimited_pending))
+		/* EBLOCK  is responsible for returning its own entry into the
+		 * free list, unless it originally added the entry into the
+		 * unlimited pending list.
+		 */
 		qed_spq_return_entry(p_hwfn, found);
 
 	/* Attempt to post pending requests */
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 5733d18..f8e11f9 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -3231,7 +3231,7 @@ static int qede_stop_queues(struct qede_dev *edev)
 	return rc;
 }
 
-static int qede_start_queues(struct qede_dev *edev)
+static int qede_start_queues(struct qede_dev *edev, bool clear_stats)
 {
 	int rc, tc, i;
 	int vlan_removal_en = 1;
@@ -3462,6 +3462,7 @@ out:
 
 enum qede_load_mode {
 	QEDE_LOAD_NORMAL,
+	QEDE_LOAD_RELOAD,
 };
 
 static int qede_load(struct qede_dev *edev, enum qede_load_mode mode)
@@ -3500,7 +3501,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode)
 		goto err3;
 	DP_INFO(edev, "Setup IRQs succeeded\n");
 
-	rc = qede_start_queues(edev);
+	rc = qede_start_queues(edev, mode != QEDE_LOAD_RELOAD);
 	if (rc)
 		goto err4;
 	DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n");
@@ -3555,7 +3556,7 @@ void qede_reload(struct qede_dev *edev,
 	if (func)
 		func(edev, args);
 
-	qede_load(edev, QEDE_LOAD_NORMAL);
+	qede_load(edev, QEDE_LOAD_RELOAD);
 
 	mutex_lock(&edev->qede_lock);
 	qede_config_rx_mode(edev->ndev);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 7bd6f25..87c642d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -772,6 +772,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	tx_ring->tx_stats.tx_bytes += skb->len;
 	tx_ring->tx_stats.xmit_called++;
 
+	/* Ensure writes are complete before HW fetches Tx descriptors */
+	wmb();
 	qlcnic_update_cmd_producer(tx_ring);
 
 	return NETDEV_TX_OK;
@@ -2220,7 +2222,7 @@ void qlcnic_83xx_process_rcv_ring_diag(struct qlcnic_host_sds_ring *sds_ring)
 	if (!opcode)
 		return;
 
-	ring = QLCNIC_FETCH_RING_ID(qlcnic_83xx_hndl(sts_data[0]));
+	ring = QLCNIC_FETCH_RING_ID(sts_data[0]);
 	qlcnic_83xx_process_rcv_diag(adapter, ring, sts_data);
 	desc = &sds_ring->desc_head[consumer];
 	desc->status_desc_data[0] = cpu_to_le64(STATUS_OWNER_PHANTOM);
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 133e9e3..4c83739 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -104,7 +104,8 @@ int efx_farch_test_registers(struct efx_nic *efx,
 			     const struct efx_farch_register_test *regs,
 			     size_t n_regs)
 {
-	unsigned address = 0, i, j;
+	unsigned address = 0;
+	int i, j;
 	efx_oword_t mask, imask, original, reg, buf;
 
 	for (i = 0; i < n_regs; ++i) {
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 8af2556..b5ab5e1 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -116,7 +116,6 @@ struct smsc911x_data {
 
 	struct phy_device *phy_dev;
 	struct mii_bus *mii_bus;
-	int phy_irq[PHY_MAX_ADDR];
 	unsigned int using_extphy;
 	int last_duplex;
 	int last_carrier;
@@ -1073,7 +1072,6 @@ static int smsc911x_mii_init(struct platform_device *pdev,
 	pdata->mii_bus->priv = pdata;
 	pdata->mii_bus->read = smsc911x_mii_read;
 	pdata->mii_bus->write = smsc911x_mii_write;
-	memcpy(pdata->mii_bus->irq, pdata->phy_irq, sizeof(pdata->mii_bus));
 
 	pdata->mii_bus->parent = &pdev->dev;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a473c18..e407126 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2804,7 +2804,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
+			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
 				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
 							priv->rx_tail_addr,
 							STMMAC_CHAN0);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index e6bb0ec..5319089 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2505,8 +2505,6 @@ static int cpsw_probe(struct platform_device *pdev)
 clean_ale_ret:
 	cpsw_ale_destroy(priv->ale);
 clean_dma_ret:
-	cpdma_chan_destroy(priv->txch);
-	cpdma_chan_destroy(priv->rxch);
 	cpdma_ctlr_destroy(priv->dma);
 clean_runtime_disable_ret:
 	pm_runtime_disable(&pdev->dev);
@@ -2534,8 +2532,6 @@ static int cpsw_remove(struct platform_device *pdev)
 	unregister_netdev(ndev);
 
 	cpsw_ale_destroy(priv->ale);
-	cpdma_chan_destroy(priv->txch);
-	cpdma_chan_destroy(priv->rxch);
 	cpdma_ctlr_destroy(priv->dma);
 	pm_runtime_disable(&pdev->dev);
 	device_for_each_child(&pdev->dev, NULL, cpsw_remove_child_device);
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 0a15acc..11213a3 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -462,7 +462,7 @@ static void tile_tx_timestamp(struct sk_buff *skb, int instance)
 	if (unlikely((shtx->tx_flags & SKBTX_HW_TSTAMP) != 0)) {
 		struct mpipe_data *md = &mpipe_data[instance];
 		struct skb_shared_hwtstamps shhwtstamps;
-		struct timespec ts;
+		struct timespec64 ts;
 
 		shtx->tx_flags |= SKBTX_IN_PROGRESS;
 		gxio_mpipe_get_timestamp(&md->context, &ts);
@@ -886,9 +886,9 @@ static struct ptp_clock_info ptp_mpipe_caps = {
 /* Sync mPIPE's timestamp up with Linux system time and register PTP clock. */
 static void register_ptp_clock(struct net_device *dev, struct mpipe_data *md)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 
-	getnstimeofday(&ts);
+	ktime_get_ts64(&ts);
 	gxio_mpipe_set_timestamp(&md->context, &ts);
 
 	mutex_init(&md->ptp_lock);